Search

Commit Message Generation (CMG) approaches aim to automatically generate commit messages based on given code diffs, which facilitate collaboration among developers and play a critical role in Open-Source Software (OSS). Very recently, Large Language Models (LLMs) have demonstrated extensive applicability in diverse code-related task. But few studies systematically explored their effectiveness using LLMs. This paper conducts the first comprehensive experiment to investigate how far we have been in applying LLM to generate high-quality commit messages. Motivated by a pilot analysis, we first clean the most widely-used CMG dataset following practitioners' criteria. Afterward, we re-evaluate diverse state-of-the-art CMG approaches and make comparisons with LLMs, demonstrating the superior performance of LLMs against state-of-the-art CMG approaches. Then, we further propose four manual metrics following the practice of OSS, including Accuracy, Integrity, Applicability, and Readability, and assess various LLMs accordingly. Results reveal that GPT-3.5 performs best overall, but different LLMs carry different advantages. To further boost LLMs' performance in the CMG task, we propose an Efficient Retrieval-based In-Context Learning (ICL) framework, namely ERICommiter, which leverages a two-step filtering to accelerate the retrieval efficiency and introduces semantic/lexical-based retrieval algorithm to construct the ICL examples. Extensive experiments demonstrate the substantial performance improvement of ERICommiter on various LLMs for code diffs of different programming languages. Meanwhile, ERICommiter also significantly reduces the retrieval time while keeping almost the same performance. Our research contributes to the understanding of LLMs' capabilities in the CMG field and provides valuable insights for practitioners seeking to leverage these tools in their workflows.

Enhancing the performance of quantum key distribution is crucial, driving the exploration of various key distillation techniques to increase the key rate and tolerable error rate. It is imperative to develop a comprehensive framework to encapsulate and enhance the existing methods. In this work, we propose an advantage distillation framework for quantum key distribution. Building on the entanglement distillation protocol, our framework integrates all the existing key distillation methods and offers better generalization and performance. Using classical linear codes, our framework can achieve higher key rates, particularly without one-time pad encryption for postprocessing. Our approach provides insights into existing protocols and offers a systematic way for future enhancements of quantum key distribution protocols., Comment: 24 pages, 14 figures, comments are welcome

The recent 3D Gaussian Splatting (GS) exhibits high-quality and real-time synthesis of novel views in 3D scenes. Currently, it primarily focuses on geometry and appearance modeling, while lacking the semantic understanding of scenes. To bridge this gap, we present CLIP-GS, which integrates semantics from Contrastive Language-Image Pre-Training (CLIP) into Gaussian Splatting to efficiently comprehend 3D environments without annotated semantic data. In specific, rather than straightforwardly learning and rendering high-dimensional semantic features of 3D Gaussians, which significantly diminishes the efficiency, we propose a Semantic Attribute Compactness (SAC) approach. SAC exploits the inherent unified semantics within objects to learn compact yet effective semantic representations of 3D Gaussians, enabling highly efficient rendering (>100 FPS). Additionally, to address the semantic ambiguity, caused by utilizing view-inconsistent 2D CLIP semantics to supervise Gaussians, we introduce a 3D Coherent Self-training (3DCS) strategy, resorting to the multi-view consistency originated from the 3D model. 3DCS imposes cross-view semantic consistency constraints by leveraging refined, self-predicted pseudo-labels derived from the trained 3D Gaussian model, thereby enhancing precise and view-consistent segmentation results. Extensive experiments demonstrate that our method remarkably outperforms existing state-of-the-art approaches, achieving improvements of 17.29% and 20.81% in mIoU metric on Replica and ScanNet datasets, respectively, while maintaining real-time rendering speed. Furthermore, our approach exhibits superior performance even with sparse input data, verifying the robustness of our method., Comment: https://github.com/gbliao/CLIP-GS

We present the design and characterization of the first full chain precision timing prototype ASIC, named ETL Readout Chip version 1 (ETROC1) for the CMS MTD endcap timing layer (ETL) upgrade. The ETL utilizes Low Gain Avalanche Diode (LGAD) sensors to detect charged particles, with the goal to achieve a time resolution of 40 - 50 ps per hit, and 30 - 40 ps per track with hits from two detector layers. The ETROC1 is composed of a 5 x 5 pixel array and peripheral circuits. The pixel array includes a 4 x 4 active pixel array with an H-tree shaped network delivering clock and charge injection signals. Each active pixel is composed of various components, including a bump pad, a charge injection circuit, a pre-amplifier, a discriminator, a digital-to-analog converter, and a time-to-digital converter. These components play essential roles as the front-end link in processing LGAD signals and measuring timing-related information. The peripheral circuits provide clock signals and readout functionalities. The size of the ETROC1 chip is 7 mm x 9 mm. ETROC1 has been fabricated in a 65 nm CMOS process, and extensively tested under stimuli of charge injection, infrared laser, and proton beam. The time resolution of bump-bonded ETROC1 + LGAD chipsets reaches 42 - 46 ps per hit in the beam test., Comment: 14 pages, 15 figures

Quantum computing is of great potential for chemical system simulations. In this study, we propose an efficient protocol of quantum computer based simulation of chemical systems which enables accurate chemical reaction modeling on noisy intermediate-scale quantum (NISQ) devices. In this protocol, we combine an correlation energy-based active orbital selection, an effective Hamiltonian from the driven similarity renormalization group (DSRG) method, and a noise-resilient wavefunction ansatz. Such a combination gives a quantum resource-efficient way to accurately simulate chemical systems. The power of this protocol is demonstrated by numerical results for systems with up to tens of atoms. Modeling of a Diels-Alder (DA) reaction is also performed on a cloud-based superconducting quantum computer. These results represent an important step forward in realizing quantum utility in the NISQ era.

TLS is extensively utilized for secure data transmission over networks. However, with the advent of quantum computers, the security of TLS based on traditional public-key cryptography is under threat. To counter quantum threats, it is imperative to integrate post-quantum algorithms into TLS. Most PQ-TLS research focuses on integration and evaluation, but few studies address the improvement of PQ-TLS performance by optimizing PQC implementation. For the TLS protocol, handshake performance is crucial, and for post-quantum TLS (PQ-TLS) the performance of post-quantum key encapsulation mechanisms (KEMs) directly impacts handshake performance. In this work, we explore the impact of post-quantum KEMs on PQ-TLS performance. We explore how to improve ML-KEM performance using the latest Intel's Advanced Vector Extensions instruction set AVX-512. We detail a spectrum of techniques devised to parallelize polynomial multiplication, modular reduction, and other computationally intensive modules within ML-KEM. Our optimized ML-KEM implementation achieves up to 1.64x speedup compared to the latest AVX2 implementation. Furthermore, we introduce a novel batch key generation method for ML-KEM that can seamlessly integrate into the TLS protocols. The batch method accelerates the key generation procedure by 3.5x to 4.9x. We integrate the optimized AVX-512 implementation of ML-KEM into TLS 1.3, and assess handshake performance under both PQ-only and hybrid modes. The assessment demonstrates that our faster ML-KEM implementation results in a higher number of TLS 1.3 handshakes per second under both modes. Additionally, we revisit two IND-1-CCA KEM constructions discussed in Eurocrypt22 and Asiacrypt23. Besides, we implement them based on ML-KEM and integrate the one of better performance into TLS 1.3 with benchmarks., Comment: update the title

Recently,smart roadside infrastructure (SRI) has demonstrated the potential of achieving fully autonomous driving systems. To explore the potential of infrastructure-assisted autonomous driving, this paper presents the design and deployment of Soar, the first end-to-end SRI system specifically designed to support autonomous driving systems. Soar consists of both software and hardware components carefully designed to overcome various system and physical challenges. Soar can leverage the existing operational infrastructure like street lampposts for a lower barrier of adoption. Soar adopts a new communication architecture that comprises a bi-directional multi-hop I2I network and a downlink I2V broadcast service, which are designed based on off-the-shelf 802.11ac interfaces in an integrated manner. Soar also features a hierarchical DL task management framework to achieve desirable load balancing among nodes and enable them to collaborate efficiently to run multiple data-intensive autonomous driving applications. We deployed a total of 18 Soar nodes on existing lampposts on campus, which have been operational for over two years. Our real-world evaluation shows that Soar can support a diverse set of autonomous driving applications and achieve desirable real-time performance and high communication reliability. Our findings and experiences in this work offer key insights into the development and deployment of next-generation smart roadside infrastructure and autonomous driving systems.

With the rapid development of underwater communication, sensing, automation, robot technologies, autonomous underwater vehicle (AUV) swarms are gradually becoming popular and have been widely promoted in ocean exploration and underwater tracking or surveillance, etc. However, the complex underwater environment poses significant challenges for AUV swarm-based accurate tracking for the underwater moving targets. In this paper, we aim at proposing a multi-AUV cooperative underwater multi-target tracking algorithm especially when the real underwater factors are taken into account.We first give normally modelling approach for the underwater sonar-based detection and the ocean current interference on the target tracking process.Then, we regard the AUV swarm as a underwater ad-hoc network and propose a novel Multi-Agent Reinforcement Learning (MARL) architecture towards the AUV swarm based on Software-Defined Networking (SDN).It enhances the flexibility and scalability of the AUV swarm through centralized management and distributed operations.Based on the proposed MARL architecture, we propose the "dynamic-attention switching" and "dynamic-resampling switching" mechanisms, to enhance the efficiency and accuracy of AUV swarm cooperation during task execution.Finally, based on a proposed AUV classification method, we propose an efficient cooperative tracking algorithm called ASMA.Evaluation results demonstrate that our proposed tracking algorithm can perform precise underwater multi-target tracking, comparing with many of recent research products in terms of convergence speed and tracking accuracy.

Large Language Models (LLMs) have exhibited an impressive ability to perform In-Context Learning (ICL) from only a few examples. Recent works have indicated that the functions learned by ICL can be represented through compressed vectors derived from the transformer. However, the working mechanisms and optimization of these vectors are yet to be thoroughly explored. In this paper, we address this gap by presenting a comprehensive analysis of these compressed vectors, drawing parallels to the parameters trained with gradient descent, and introduce the concept of state vector. Inspired by the works on model soup and momentum-based gradient descent, we propose inner and momentum optimization methods that are applied to refine the state vector progressively as test-time adaptation. Moreover, we simulate state vector aggregation in the multiple example setting, where demonstrations comprising numerous examples are usually too lengthy for regular ICL, and further propose a divide-and-conquer aggregation method to address this challenge. We conduct extensive experiments using Llama-2 and GPT-J in both zero-shot setting and few-shot setting. The experimental results show that our optimization method effectively enhances the state vector and achieves the state-of-the-art performance on diverse tasks. Code is available at https://github.com/HITsz-TMG/ICL-State-Vector, Comment: 17 pages, 7 figures, 5 tables

We introduce VASA, a framework for generating lifelike talking faces with appealing visual affective skills (VAS) given a single static image and a speech audio clip. Our premiere model, VASA-1, is capable of not only producing lip movements that are exquisitely synchronized with the audio, but also capturing a large spectrum of facial nuances and natural head motions that contribute to the perception of authenticity and liveliness. The core innovations include a holistic facial dynamics and head movement generation model that works in a face latent space, and the development of such an expressive and disentangled face latent space using videos. Through extensive experiments including evaluation on a set of new metrics, we show that our method significantly outperforms previous methods along various dimensions comprehensively. Our method not only delivers high video quality with realistic facial and head dynamics but also supports the online generation of 512x512 videos at up to 40 FPS with negligible starting latency. It paves the way for real-time engagements with lifelike avatars that emulate human conversational behaviors., Comment: Tech Report. Project webpage: https://www.microsoft.com/en-us/research/project/vasa-1/

The diagnosis and prognosis of cancer are typically based on multi-modal clinical data, including histology images and genomic data, due to the complex pathogenesis and high heterogeneity. Despite the advancements in digital pathology and high-throughput genome sequencing, establishing effective multi-modal fusion models for survival prediction and revealing the potential association between histopathology and transcriptomics remains challenging. In this paper, we propose Pathology-Genome Heterogeneous Graph (PGHG) that integrates whole slide images (WSI) and bulk RNA-Seq expression data with heterogeneous graph neural network for cancer survival analysis. The PGHG consists of biological knowledge-guided representation learning network and pathology-genome heterogeneous graph. The representation learning network utilizes the biological prior knowledge of intra-modal and inter-modal data associations to guide the feature extraction. The node features of each modality are updated through attention-based graph learning strategy. Unimodal features and bi-modal fused features are extracted via attention pooling module and then used for survival prediction. We evaluate the model on low-grade gliomas, glioblastoma, and kidney renal papillary cell carcinoma datasets from the Cancer Genome Atlas (TCGA) and the First Affiliated Hospital of Zhengzhou University (FAHZU). Extensive experimental results demonstrate that the proposed method outperforms both unimodal and other multi-modal fusion models. For demonstrating the model interpretability, we also visualize the attention heatmap of pathological images and utilize integrated gradient algorithm to identify important tissue structure, biological pathways and key genes.

For segmented telescopes, achieving fine co-focus adjustment is essential for realizing co-phase adjustment and maintenance, which involves adjusting the millimeter-scale piston between segments to fall within the capture range of the co-phase detection system. CGST proposes using a SHWFS for piston detection during the co-focus adjustment stage. However, the residual piston after adjustment exceeds the capture range of the broadband PSF phasing algorithm$(\pm 30 \mu m) $, and the multi-wavelength PSF algorithm requires even higher precision in co-focus adjustment. To improve the co-focus adjustment accuracy of CGST, a fine co-focus adjustment based on cross-calibration is proposed. This method utilizes a high-precision detector to calibrate and fit the measurements from the SHWFS, thereby reducing the impact of atmospheric turbulence and systematic errors on piston measurement accuracy during co-focus adjustment. Simulation results using CGST demonstrate that the proposed method significantly enhances adjustment accuracy compared to the SHWFS detection method. Additionally, the residual piston after fine co-focus adjustment using this method falls within the capture range of the multi-wavelength PSF algorithm. To verify the feasibility of this method, experiments were conducted on an 800mm ring segmented mirror system, successfully achieving fine co-focus adjustment where the remaining piston of all segments fell within $\pm 15 \mu m$.

The Multi-channel Photometric Survey Telescope (Mephisto) is a real-time, three-color photometric system designed to capture the color evolution of stars and transients accurately. This telescope system can be crucial in cosmological distance measurements of low-redshift (low-$z$, $z$ $\lesssim 0.1$) Type Ia supernovae (SNe Ia). To optimize the capabilities of this instrument, we perform a comprehensive simulation study before its official operation is scheduled to start. By considering the impact of atmospheric extinction, weather conditions, and the lunar phase at the observing site involving the instrumental features, we simulate the light curves of SNe Ia obtained by the Mephisto. The best strategy in the case of SN Ia cosmology is to take the image at an exposure time of 130 s with a cadence of 3 days. In this condition, Mephisto can obtain hundreds of high-quality SNe Ia to achieve a distance measurement better than $4.5\%$. Given the on-time spectral classification and monitoring of the Lijiang 2.4 m Telescope at the same observatory, Mephisto, in the whole operation, can significantly enrich the well-calibrated sample of supernovae at low-$z$ and improve the calibration accuracy of high-$z$ SNe Ia., Comment: 15 pages, 7 figures

Existing semi-supervised video object segmentation methods either focus on temporal feature matching or spatial-temporal feature modeling. However, they do not address the issues of sufficient target interaction and efficient parallel processing simultaneously, thereby constraining the learning of dynamic, target-aware features. To tackle these limitations, this paper proposes a spatial-temporal multi-level association framework, which jointly associates reference frame, test frame, and object features to achieve sufficient interaction and parallel target ID association with a spatial-temporal memory bank for efficient video object segmentation. Specifically, we construct a spatial-temporal multi-level feature association module to learn better target-aware features, which formulates feature extraction and interaction as the efficient operations of object self-attention, reference object enhancement, and test reference correlation. In addition, we propose a spatial-temporal memory to assist feature association and temporal ID assignment and correlation. We evaluate the proposed method by conducting extensive experiments on numerous video object segmentation datasets, including DAVIS 2016/2017 val, DAVIS 2017 test-dev, and YouTube-VOS 2018/2019 val. The favorable performance against the state-of-the-art methods demonstrates the effectiveness of our approach. All source code and trained models will be made publicly available.

One of the most critical factors in achieving sharp Novel View Synthesis (NVS) using neural field methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) is the quality of the training images. However, Conventional RGB cameras are susceptible to motion blur. In contrast, neuromorphic cameras like event and spike cameras inherently capture more comprehensive temporal information, which can provide a sharp representation of the scene as additional training data. Recent methods have explored the integration of event cameras to improve the quality of NVS. The event-RGB approaches have some limitations, such as high training costs and the inability to work effectively in the background. Instead, our study introduces a new method that uses the spike camera to overcome these limitations. By considering texture reconstruction from spike streams as ground truth, we design the Texture from Spike (TfS) loss. Since the spike camera relies on temporal integration instead of temporal differentiation used by event cameras, our proposed TfS loss maintains manageable training costs. It handles foreground objects with backgrounds simultaneously. We also provide a real-world dataset captured with our spike-RGB camera system to facilitate future research endeavors. We conduct extensive experiments using synthetic and real-world datasets to demonstrate that our design can enhance novel view synthesis across NeRF and 3DGS. The code and dataset will be made available for public access.

We present VoiceShop, a novel speech-to-speech framework that can modify multiple attributes of speech, such as age, gender, accent, and speech style, in a single forward pass while preserving the input speaker's timbre. Previous works have been constrained to specialized models that can only edit these attributes individually and suffer from the following pitfalls: the magnitude of the conversion effect is weak, there is no zero-shot capability for out-of-distribution speakers, or the synthesized outputs exhibit undesirable timbre leakage. Our work proposes solutions for each of these issues in a simple modular framework based on a conditional diffusion backbone model with optional normalizing flow-based and sequence-to-sequence speaker attribute-editing modules, whose components can be combined or removed during inference to meet a wide array of tasks without additional model finetuning. Audio samples are available at \url{https://voiceshopai.github.io}.

Large language models (LLMs) have shown excellent mastering of human language, but still struggle in real-world applications that require mathematical problem-solving. While many strategies and datasets to enhance LLMs' mathematics are developed, it remains a challenge to simultaneously maintain and improve both language and mathematical capabilities in deployed LLM systems.In this work, we tailor the Self-Critique pipeline, which addresses the challenge in the feedback learning stage of LLM alignment. We first train a general Math-Critique model from the LLM itself to provide feedback signals. Then, we sequentially employ rejective fine-tuning and direct preference optimization over the LLM's own generations for data collection. Based on ChatGLM3-32B, we conduct a series of experiments on both academic and our newly created challenging dataset, MathUserEval. Results show that our pipeline significantly enhances the LLM's mathematical problem-solving while still improving its language ability, outperforming LLMs that could be two times larger. Related techniques have been deployed to ChatGLM\footnote{\url{https://chatglm.cn}}, an online serving LLM. Related evaluation dataset and scripts are released at \url{https://github.com/THUDM/ChatGLM-Math}.

Individuals with visual impairments, encompassing both partial and total difficulties in visual perception, are referred to as visually impaired (VI) people. An estimated 2.2 billion individuals worldwide are affected by visual impairments. Recent advancements in multi-modal large language models (MLLMs) have showcased their extraordinary capabilities across various domains. It is desirable to help VI individuals with MLLMs' great capabilities of visual understanding and reasoning. However, it is challenging for VI people to use MLLMs due to the difficulties in capturing the desirable images to fulfill their daily requests. For example, the target object is not fully or partially placed in the image. This paper explores how to leverage MLLMs for VI individuals to provide visual-question answers. VIAssist can identify undesired images and provide detailed actions. Finally, VIAssist can provide reliable answers to users' queries based on the images. Our results show that VIAssist provides +0.21 and +0.31 higher BERTScore and ROUGE scores than the baseline, respectively., Comment: Accepted to IEEE International Workshop on Foundation Models for Cyber-Physical Systems & Internet of Things (FMSys 2024)

Blind super-resolution methods based on stable diffusion showcase formidable generative capabilities in reconstructing clear high-resolution images with intricate details from low-resolution inputs. However, their practical applicability is often hampered by poor efficiency, stemming from the requirement of thousands or hundreds of sampling steps. Inspired by the efficient adversarial diffusion distillation (ADD), we design~\name~to address this issue by incorporating the ideas of both distillation and ControlNet. Specifically, we first propose a prediction-based self-refinement strategy to provide high-frequency information in the student model output with marginal additional time cost. Furthermore, we refine the training process by employing HR images, rather than LR images, to regulate the teacher model, providing a more robust constraint for distillation. Second, we introduce a timestep-adaptive ADD to address the perception-distortion imbalance problem introduced by original ADD. Extensive experiments demonstrate our~\name~generates better restoration results, while achieving faster speed than previous SD-based state-of-the-art models (e.g., $7$$\times$ faster than SeeSR).

Evolutionary multiobjective optimization has witnessed remarkable progress during the past decades. However, existing algorithms often encounter computational challenges in large-scale scenarios, primarily attributed to the absence of hardware acceleration. In response, we introduce a Tensorized Reference Vector Guided Evolutionary Algorithm (TensorRVEA) for harnessing the advancements of GPU acceleration. In TensorRVEA, the key data structures and operators are fully transformed into tensor forms for leveraging GPU-based parallel computing. In numerical benchmark tests involving large-scale populations and problem dimensions, TensorRVEA consistently demonstrates high computational performance, achieving up to over 1000$\times$ speedups. Then, we applied TensorRVEA to the domain of multiobjective neuroevolution for addressing complex challenges in robotic control tasks. Furthermore, we assessed TensorRVEA's extensibility by altering several tensorized reproduction operators. Experimental results demonstrate promising scalability and robustness of TensorRVEA. Source codes are available at \url{https://github.com/EMI-Group/tensorrvea}., Comment: Genetic and Evolutionary Computation Conference (GECCO '24)

ChatGLM is a free-to-use AI service powered by the ChatGLM family of large language models (LLMs). In this paper, we present the ChatGLM-RLHF pipeline -- a reinforcement learning from human feedback (RLHF) system -- designed to enhance ChatGLM's alignment with human preferences. ChatGLM-RLHF encompasses three major components: the collection of human preference data, the training of the reward model, and the optimization of policies. Throughout the process of integrating ChatGLM-RLHF into production, we encountered and addressed several unprecedented challenges. We introduce the strategies to mitigate reward variance for stabilized large-scale training, implement model parallelism with fused gradient-descent, and design regularization constraints to avoid catastrophic forgetting in LLMs. Experiments show that ChatGLM-RLHF brings significant improvements in alignment tasks compared to the supervised fine-tuned (SFT) version of ChatGLM. For instance, it achieves on average 15\% more wins against ChatGLM-SFT in Chinese alignment tasks. The work presents our practices of aligning LLMs with human preferences, offering insights into the challenges and solutions in RLHF implementations.

We propose MonoBox, an innovative box-supervised segmentation method constrained by monotonicity to liberate its training from the user-unfriendly box-tightness assumption. In contrast to conventional box-supervised segmentation, where the box edges must precisely touch the target boundaries, MonoBox leverages imprecisely-annotated boxes to achieve robust pixel-wise segmentation. The 'linchpin' is that, within the noisy zones around box edges, MonoBox discards the traditional misguiding multiple-instance learning loss, and instead optimizes a carefully-designed objective, termed monotonicity constraint. Along directions transitioning from the foreground to background, this new constraint steers responses to adhere to a trend of monotonically decreasing values. Consequently, the originally unreliable learning within the noisy zones is transformed into a correct and effective monotonicity optimization. Moreover, an adaptive label correction is introduced, enabling MonoBox to enhance the tightness of box annotations using predicted masks from the previous epoch and dynamically shrink the noisy zones as training progresses. We verify MonoBox in the box-supervised segmentation task of polyps, where satisfying box-tightness is challenging due to the vague boundaries between the polyp and normal tissues. Experiments on both public synthetic and in-house real noisy datasets demonstrate that MonoBox exceeds other anti-noise state-of-the-arts by improving Dice by at least 5.5% and 3.3%, respectively. Codes are at https://github.com/Huster-Hq/MonoBox.

Handling graph data is one of the most difficult tasks. Traditional techniques, such as those based on geometry and matrix factorization, rely on assumptions about the data relations that become inadequate when handling large and complex graph data. On the other hand, deep learning approaches demonstrate promising results in handling large graph data, but they often fall short of providing interpretable explanations. To equip the graph processing with both high accuracy and explainability, we introduce a novel approach that harnesses the power of a large language model (LLM), enhanced by an uncertainty-aware module to provide a confidence score on the generated answer. We experiment with our approach on two graph processing tasks: few-shot knowledge graph completion and graph classification. Our results demonstrate that through parameter efficient fine-tuning, the LLM surpasses state-of-the-art algorithms by a substantial margin across ten diverse benchmark datasets. Moreover, to address the challenge of explainability, we propose an uncertainty estimation based on perturbation, along with a calibration scheme to quantify the confidence scores of the generated answers. Our confidence measure achieves an AUC of 0.8 or higher on seven out of the ten datasets in predicting the correctness of the answer generated by LLM., Comment: Because my organization does not allow members to privately upload papers to arXiv, I am requesting a withdrawal of my submission

Existing tracking methods mainly focus on learning better target representation or developing more robust prediction models to improve tracking performance. While tracking performance has significantly improved, the target loss issue occurs frequently due to tracking failures, complete occlusion, or out-of-view situations. However, considerably less attention is paid to the self-recovery issue of tracking methods, which is crucial for practical applications. To this end, we propose a recoverable tracking framework, RTracker, that uses a tree-structured memory to dynamically associate a tracker and a detector to enable self-recovery ability. Specifically, we propose a Positive-Negative Tree-structured memory to chronologically store and maintain positive and negative target samples. Upon the PN tree memory, we develop corresponding walking rules for determining the state of the target and define a set of control flows to unite the tracker and the detector in different tracking scenarios. Our core idea is to use the support samples of positive and negative target categories to establish a relative distance-based criterion for a reliable assessment of target loss. The favorable performance in comparison against the state-of-the-art methods on numerous challenging benchmarks demonstrates the effectiveness of the proposed algorithm., Comment: accepted by CVPR 2024

In the current state of 3D object detection research, the severe scarcity of annotated 3D data, substantial disparities across different data modalities, and the absence of a unified architecture, have impeded the progress towards the goal of universality. In this paper, we propose \textbf{OV-Uni3DETR}, a unified open-vocabulary 3D detector via cycle-modality propagation. Compared with existing 3D detectors, OV-Uni3DETR offers distinct advantages: 1) Open-vocabulary 3D detection: During training, it leverages various accessible data, especially extensive 2D detection images, to boost training diversity. During inference, it can detect both seen and unseen classes. 2) Modality unifying: It seamlessly accommodates input data from any given modality, effectively addressing scenarios involving disparate modalities or missing sensor information, thereby supporting test-time modality switching. 3) Scene unifying: It provides a unified multi-modal model architecture for diverse scenes collected by distinct sensors. Specifically, we propose the cycle-modality propagation, aimed at propagating knowledge bridging 2D and 3D modalities, to support the aforementioned functionalities. 2D semantic knowledge from large-vocabulary learning guides novel class discovery in the 3D domain, and 3D geometric knowledge provides localization supervision for 2D detection images. OV-Uni3DETR achieves the state-of-the-art performance on various scenarios, surpassing existing methods by more than 6\% on average. Its performance using only RGB images is on par with or even surpasses that of previous point cloud based methods. Code and pre-trained models will be released later., Comment: Accepted by ECCV2024

Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content. Recent works aim to reduce misinformation and hallucinations by resorting to attribution as a means to provide evidence (i.e., citations). However, current attribution methods usually focus on the retrieval stage and automatic evaluation that neglect mirroring the citation mechanisms in human scholarly writing to bolster credibility. In this paper, we address these challenges by modelling the attribution task as preference learning and introducing an Automatic Preference Optimization (APO) framework. First, we create a curated collection for post-training with 6,330 examples by collecting and filtering from existing datasets. Second, considering the high cost of labelling preference data, we further propose an automatic method to synthesize attribution preference data resulting in 95,263 pairs. Moreover, inspired by the human citation process, we further propose a progressive preference optimization method by leveraging fine-grained information. Extensive experiments on three datasets (i.e., ASQA, StrategyQA, and ELI5) demonstrate that APO achieves state-of-the-art citation F1 with higher answer quality., Comment: 23 pages, 15 tables, 2 figures

Deepfake is a technology dedicated to creating highly realistic facial images and videos under specific conditions, which has significant application potential in fields such as entertainment, movie production, digital human creation, to name a few. With the advancements in deep learning, techniques primarily represented by Variational Autoencoders and Generative Adversarial Networks have achieved impressive generation results. More recently, the emergence of diffusion models with powerful generation capabilities has sparked a renewed wave of research. In addition to deepfake generation, corresponding detection technologies continuously evolve to regulate the potential misuse of deepfakes, such as for privacy invasion and phishing attacks. This survey comprehensively reviews the latest developments in deepfake generation and detection, summarizing and analyzing current state-of-the-arts in this rapidly evolving field. We first unify task definitions, comprehensively introduce datasets and metrics, and discuss developing technologies. Then, we discuss the development of several related sub-fields and focus on researching four representative deepfake fields: face swapping, face reenactment, talking face generation, and facial attribute editing, as well as forgery detection. Subsequently, we comprehensively benchmark representative methods on popular datasets for each field, fully evaluating the latest and influential published works. Finally, we analyze challenges and future research directions of the discussed fields., Comment: We closely follow the latest developments in https://github.com/flyingby/Awesome-Deepfake-Generation-and-Detection

We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for general visual recognition. The recent Mamba model has shown how SSMs can be highly competitive with other architectures on sequential data and initial attempts have been made to apply it to images. In this paper, we further adapt the selective scanning process of Mamba to the visual domain, enhancing its ability to learn features from two-dimensional images by (i) a continuous 2D scanning process that improves spatial continuity by ensuring adjacency of tokens in the scanning sequence, and (ii) direction-aware updating which enables the model to discern the spatial relations of tokens by encoding directional information. Our architecture is designed to be easy to use and easy to scale, formed by stacking identical PlainMamba blocks, resulting in a model with constant width throughout all layers. The architecture is further simplified by removing the need for special tokens. We evaluate PlainMamba on a variety of visual recognition tasks, achieving performance gains over previous non-hierarchical models and is competitive with hierarchical alternatives. For tasks requiring high-resolution inputs, in particular, PlainMamba requires much less computing while maintaining high performance. Code and models are available at: https://github.com/ChenhongyiYang/PlainMamba ., Comment: Accepted to BMVC 2024

We present a Chain-of-Action (CoA) framework for multimodal and retrieval-augmented Question-Answering (QA). Compared to the literature, CoA overcomes two major challenges of current QA applications: (i) unfaithful hallucination that is inconsistent with real-time or domain facts and (ii) weak reasoning performance over compositional information. Our key contribution is a novel reasoning-retrieval mechanism that decomposes a complex question into a reasoning chain via systematic prompting and pre-designed actions. Methodologically, we propose three types of domain-adaptable `Plug-and-Play' actions for retrieving real-time information from heterogeneous sources. We also propose a multi-reference faith score (MRFS) to verify and resolve conflicts in the answers. Empirically, we exploit both public benchmarks and a Web3 case study to demonstrate the capability of CoA over other methods.

While deep neural networks (NN) significantly advance image compressed sensing (CS) by improving reconstruction quality, the necessity of training current CS NNs from scratch constrains their effectiveness and hampers rapid deployment. Although recent methods utilize pre-trained diffusion models for image reconstruction, they struggle with slow inference and restricted adaptability to CS. To tackle these challenges, this paper proposes Invertible Diffusion Models (IDM), a novel efficient, end-to-end diffusion-based CS method. IDM repurposes a large-scale diffusion sampling process as a reconstruction model, and finetunes it end-to-end to recover original images directly from CS measurements, moving beyond the traditional paradigm of one-step noise estimation learning. To enable such memory-intensive end-to-end finetuning, we propose a novel two-level invertible design to transform both (1) the multi-step sampling process and (2) the noise estimation U-Net in each step into invertible networks. As a result, most intermediate features are cleared during training to reduce up to 93.8% GPU memory. In addition, we develop a set of lightweight modules to inject measurements into noise estimator to further facilitate reconstruction. Experiments demonstrate that IDM outperforms existing state-of-the-art CS networks by up to 2.64dB in PSNR. Compared to the recent diffusion model-based approach DDNM, our IDM achieves up to 10.09dB PSNR gain and 14.54 times faster inference.

Recently, a quaternion tensor product named Qt-product was proposed, and then the singular value decomposition and the rank of a third-order quaternion tensor were given. From a more applicable perspective, we extend the Qt-product and propose a novel multiplication principle for third-order quaternion tensor named gQt-product. With the gQt-product, we introduce a brand-new singular value decomposition for third-order quaternion tensors named gQt-SVD and then define gQt-rank and multi-gQt-rank. We prove that the optimal low-rank approximation of a third-order quaternion tensor exists and some numerical experiments demonstrate the low-rankness of color videos. So, we apply the low-rank quaternion tensor completion to color video inpainting problems and present alternating least-square algorithms to solve the proposed low gQt-rank and multi-gQt-rank quaternion tensor completion models. The convergence analyses of the proposed algorithms are established and some numerical experiments on various color video datasets show the high recovery accuracy and computational efficiency of our methods.

Influenced by ChatGPT, artificial intelligence (AI) large models have witnessed a global upsurge in large model research and development. As people enjoy the convenience by this AI large model, more and more large models in subdivided fields are gradually being proposed, especially large models in radiology imaging field. This article first introduces the development history of large models, technical details, workflow, working principles of multimodal large models and working principles of video generation large models. Secondly, we summarize the latest research progress of AI large models in radiology education, radiology report generation, applications of unimodal and multimodal radiology. Finally, this paper also summarizes some of the challenges of large AI models in radiology, with the aim of better promoting the rapid revolution in the field of radiography.

The capabilities of AI for biomedicine span a wide spectrum, from the atomic level, where it solves partial differential equations for quantum systems, to the molecular level, predicting chemical or protein structures, and further extending to societal predictions like infectious disease outbreaks. Recent advancements in large language models, exemplified by models like ChatGPT, have showcased significant prowess in natural language tasks, such as translating languages, constructing chatbots, and answering questions. When we consider biomedical data, we observe a resemblance to natural language in terms of sequences: biomedical literature and health records presented as text, biological sequences or sequencing data arranged in sequences, or sensor data like brain signals as time series. The question arises: Can we harness the potential of recent large language models to drive biomedical knowledge discoveries? In this survey, we will explore the application of large language models to three crucial categories of biomedical data: 1) textual data, 2) biological sequences, and 3) brain signals. Furthermore, we will delve into large language model challenges in biomedical research, including ensuring trustworthiness, achieving personalization, and adapting to multi-modal data representation, Comment: 8 pages, 3 figures

Depth completion is a vital task for autonomous driving, as it involves reconstructing the precise 3D geometry of a scene from sparse and noisy depth measurements. However, most existing methods either rely only on 2D depth representations or directly incorporate raw 3D point clouds for compensation, which are still insufficient to capture the fine-grained 3D geometry of the scene. To address this challenge, we introduce Tri-Perspective view Decomposition (TPVD), a novel framework that can explicitly model 3D geometry. In particular, (1) TPVD ingeniously decomposes the original point cloud into three 2D views, one of which corresponds to the sparse depth input. (2) We design TPV Fusion to update the 2D TPV features through recurrent 2D-3D-2D aggregation, where a Distance-Aware Spherical Convolution (DASC) is applied. (3) By adaptively choosing TPV affinitive neighbors, the newly proposed Geometric Spatial Propagation Network (GSPN) further improves the geometric consistency. As a result, our TPVD outperforms existing methods on KITTI, NYUv2, and SUN RGBD. Furthermore, we build a novel depth completion dataset named TOFDC, which is acquired by the time-of-flight (TOF) sensor and the color camera on smartphones. Project page: https://yanzq95.github.io/projectpage/TOFDC/index.html, Comment: Accepted to CVPR 2024

Classical convergence analyses for optimization algorithms rely on the widely-adopted uniform smoothness assumption. However, recent experimental studies have demonstrated that many machine learning problems exhibit non-uniform smoothness, meaning the smoothness factor is a function of the model parameter instead of a universal constant. In particular, it has been observed that the smoothness grows with respect to the gradient norm along the training trajectory. Motivated by this phenomenon, the recently introduced $(L_0, L_1)$-smoothness is a more general notion, compared to traditional $L$-smoothness, that captures such positive relationship between smoothness and gradient norm. Under this type of non-uniform smoothness, existing literature has designed stochastic first-order algorithms by utilizing gradient clipping techniques to obtain the optimal $\mathcal{O}(\epsilon^{-3})$ sample complexity for finding an $\epsilon$-approximate first-order stationary solution. Nevertheless, the studies of quasi-Newton methods are still lacking. Considering higher accuracy and more robustness for quasi-Newton methods, in this paper we propose a fast stochastic quasi-Newton method when there exists non-uniformity in smoothness. Leveraging gradient clipping and variance reduction, our algorithm can achieve the best-known $\mathcal{O}(\epsilon^{-3})$ sample complexity and enjoys convergence speedup with simple hyperparameter tuning. Our numerical experiments show that our proposed algorithm outperforms the state-of-the-art approaches., Comment: Paper accepted by CDC 2024

Recent advancements in large language models (LLMs) have highlighted the potential for vulnerability detection, a crucial component of software quality assurance. Despite this progress, most studies have been limited to the perspective of a single role, usually testers, lacking diverse viewpoints from different roles in a typical software development life-cycle, including both developers and testers. To this end, this paper introduces a multi-role approach to employ LLMs to act as different roles simulating a real-life code review process and engaging in discussions toward a consensus on the existence and classification of vulnerabilities in the code. Preliminary evaluation of this approach indicates a 13.48% increase in the precision rate, an 18.25% increase in the recall rate, and a 16.13% increase in the F1 score.

Choreographers determine what the dances look like, while cameramen determine the final presentation of dances. Recently, various methods and datasets have showcased the feasibility of dance synthesis. However, camera movement synthesis with music and dance remains an unsolved challenging problem due to the scarcity of paired data. Thus, we present DCM, a new multi-modal 3D dataset, which for the first time combines camera movement with dance motion and music audio. This dataset encompasses 108 dance sequences (3.2 hours) of paired dance-camera-music data from the anime community, covering 4 music genres. With this dataset, we uncover that dance camera movement is multifaceted and human-centric, and possesses multiple influencing factors, making dance camera synthesis a more challenging task compared to camera or dance synthesis alone. To overcome these difficulties, we propose DanceCamera3D, a transformer-based diffusion model that incorporates a novel body attention loss and a condition separation strategy. For evaluation, we devise new metrics measuring camera movement quality, diversity, and dancer fidelity. Utilizing these metrics, we conduct extensive experiments on our DCM dataset, providing both quantitative and qualitative evidence showcasing the effectiveness of our DanceCamera3D model. Code and video demos are available at https://github.com/Carmenw1203/DanceCamera3D-Official., Comment: Accept to CVPR 2024

Accurate identification of End-Diastolic (ED) and End-Systolic (ES) frames is key for cardiac function assessment through echocardiography. However, traditional methods face several limitations: they require extensive amounts of data, extensive annotations by medical experts, significant training resources, and often lack robustness. Addressing these challenges, we proposed an unsupervised and training-free method, our novel approach leverages unsupervised segmentation to enhance fault tolerance against segmentation inaccuracies. By identifying anchor points and analyzing directional deformation, we effectively reduce dependence on the accuracy of initial segmentation images and enhance fault tolerance, all while improving robustness. Tested on Echo-dynamic and CAMUS datasets, our method achieves comparable accuracy to learning-based models without their associated drawbacks. The code is available at https://github.com/MRUIL/DDSB

Math word problem (MWP) solving requires generating a reasoning path based on a given problem description that often contains irrelevant conditions. Existing chain-of-thought (CoT) prompting methods elicited multi-step reasoning abilities of large language models (LLMs) to solve MWPs. However, they were seriously confused by the irrelevant conditions, resulting in low accuracy. In this paper, we propose a novel approach named I$^3$C that instructs LLMs to identify and ignore irrelevant conditions. It identifies a set of irrelevant condition candidates that have a weak semantic relevance with the question. Then it prompts LLMs to verify the irrelevant conditions. Lastly it instructs the LLMs with the verification on relevant and irrelevant conditions to avoid confusion and improve reasoning paths. Moreover, we propose to select (problem, reasoning paths) pairs as demonstrations to enhance I$^3$C with few-shot reasoning. We develop I$^3$C-Select that selects the most confusing problems based on the semantic relevance measurement. We conduct extensive experiments on eight MWP datasets. I$^3$C can be combined with any CoT prompting methods to improve the performance of solving MWPs. Notably, with GPT-3.5-Turbo and I$^3$C-Select, we achieve an accuracy of 96.0 and 94.1 on GSM-IC2-1K and GSM-ICM-1K, respectively, significantly outperforming the state-of-the-art few-shot prompting method Complex-CoT by +11.7 and +11.1. Our implementation is made publicly available at https://wzy6642.github.io/I3C.github.io/., Comment: NAACL 2024 - Camera Ready

The task of financial analysis primarily encompasses two key areas: stock trend prediction and the corresponding financial question answering. Currently, machine learning and deep learning algorithms (ML&DL) have been widely applied for stock trend predictions, leading to significant progress. However, these methods fail to provide reasons for predictions, lacking interpretability and reasoning processes. Also, they can not integrate textual information such as financial news or reports. Meanwhile, large language models (LLMs) have remarkable textual understanding and generation ability. But due to the scarcity of financial training datasets and limited integration with real-time knowledge, LLMs still suffer from hallucinations and are unable to keep up with the latest information. To tackle these challenges, we first release AlphaFin datasets, combining traditional research datasets, real-time financial data, and handwritten chain-of-thought (CoT) data. It has a positive impact on training LLMs for completing financial analysis. We then use AlphaFin datasets to benchmark a state-of-the-art method, called Stock-Chain, for effectively tackling the financial analysis task, which integrates retrieval-augmented generation (RAG) techniques. Extensive experiments are conducted to demonstrate the effectiveness of our framework on financial analysis., Comment: COLING 2024. The first three authors contributed equally. Project website: https://github.com/AlphaFin-proj/AlphaFin

Multi-scale deformable attention (MSDeformAttn) has emerged as a key mechanism in various vision tasks, demonstrating explicit superiority attributed to multi-scale grid-sampling. However, this newly introduced operator incurs irregular data access and enormous memory requirement, leading to severe PE underutilization. Meanwhile, existing approaches for attention acceleration cannot be directly applied to MSDeformAttn due to lack of support for this distinct procedure. Therefore, we propose a dedicated algorithm-architecture co-design dubbed DEFA, the first-of-its-kind method for MSDeformAttn acceleration. At the algorithm level, DEFA adopts frequency-weighted pruning and probability-aware pruning for feature maps and sampling points respectively, alleviating the memory footprint by over 80%. At the architecture level, it explores the multi-scale parallelism to boost the throughput significantly and further reduces the memory access via fine-grained layer fusion and feature map reusing. Extensively evaluated on representative benchmarks, DEFA achieves 10.1-31.9x speedup and 20.3-37.7x energy efficiency boost compared to powerful GPUs. It also rivals the related accelerators by 2.2-3.7x energy efficiency improvement while providing pioneering support for MSDeformAttn., Comment: Accepted to DAC 2024

Recent advances in deep learning generative models (GMs) have created high capabilities in accessing and assessing complex high-dimensional data, allowing superior efficiency in navigating vast material configuration space in search of viable structures. Coupling such capabilities with physically significant data to construct trained models for materials discovery is crucial to moving this emerging field forward. Here, we present a universal GM for crystal structure prediction (CSP) via a conditional crystal diffusion variational autoencoder (Cond-CDVAE) approach, which is tailored to allow user-defined material and physical parameters such as composition and pressure. This model is trained on an expansive dataset containing over 670,000 local minimum structures, including a rich spectrum of high-pressure structures, along with ambient-pressure structures in Materials Project database. We demonstrate that the Cond-CDVAE model can generate physically plausible structures with high fidelity under diverse pressure conditions without necessitating local optimization, accurately predicting 59.3% of the 3,547 unseen ambient-pressure experimental structures within 800 structure samplings, with the accuracy rate climbing to 83.2% for structures comprising fewer than 20 atoms per unit cell. These results meet or exceed those achieved via conventional CSP methods based on global optimization. The present findings showcase substantial potential of GMs in the realm of CSP.

Quadrupedal robots exhibit a wide range of viable gaits, but generating specific footfall sequences often requires laborious expert tuning of numerous variables, such as touch-down and lift-off events and holonomic constraints for each leg. This paper presents a unified reinforcement learning framework for generating versatile quadrupedal gaits by leveraging the intrinsic symmetries of dynamic legged systems. We propose a symmetry-guided reward function design that incorporates temporal, morphological, and time-reversal symmetries, streamlining gait design, accelerating learning, and enhancing robot agility. By focusing on preserved symmetries and natural dynamics, our approach eliminates the need for predefined trajectories or footfall sequences, enabling smooth transitions between diverse locomotion patterns such as trotting, bounding, half-bounding, and galloping. Implemented on the Petoi Bittle robot, our method demonstrates robust performance across a range of speeds in both simulations and hardware tests, significantly improving gait adaptability without extensive reward tuning or explicit foot placement control. This work provides insights into dynamic locomotion strategies and underscores the crucial role of symmetries in robotic gait design.

Federated learning is designed to enhance data security and privacy, but faces challenges when dealing with heterogeneous data in long-tailed and non-IID distributions. This paper explores an overlooked scenario where tail classes are sparsely distributed over a few clients, causing the models trained with these classes to have a lower probability of being selected during client aggregation, leading to slower convergence rates and poorer model performance. To address this issue, we propose a two-stage Decoupled Federated learning framework using Feature Statistics (DFL-FS). In the first stage, the server estimates the client's class coverage distributions through masked local feature statistics clustering to select models for aggregation to accelerate convergence and enhance feature learning without privacy leakage. In the second stage, DFL-FS employs federated feature regeneration based on global feature statistics and utilizes resampling and weighted covariance to calibrate the global classifier to enhance the model's adaptability to long-tailed data distributions. We conducted experiments on CIFAR10-LT and CIFAR100-LT datasets with various long-tailed rates. The results demonstrate that our method outperforms state-of-the-art methods in both accuracy and convergence rate.

The random batch method (RBM) proposed in [Jin et al., J. Comput. Phys., 400(2020), 108877] for large interacting particle systems is an efficient with linear complexity in particle numbers and highly scalable algorithm for $N$-particle interacting systems and their mean-field limits when $N$ is large. We consider in this work the quantitative error estimate of RBM toward its mean-field limit, the Fokker-Planck equation. Under mild assumptions, we obtain a uniform-in-time $O(\tau^2 + 1/N)$ bound on the scaled relative entropy between the joint law of the random batch particles and the tensorized law at the mean-field limit, where $\tau$ is the time step size and $N$ is the number of particles. Therefore, we improve the existing rate in discretization step size from $O(\sqrt{\tau})$ to $O(\tau)$ in terms of the Wasserstein distance.

We present Envision3D, a novel method for efficiently generating high-quality 3D content from a single image. Recent methods that extract 3D content from multi-view images generated by diffusion models show great potential. However, it is still challenging for diffusion models to generate dense multi-view consistent images, which is crucial for the quality of 3D content extraction. To address this issue, we propose a novel cascade diffusion framework, which decomposes the challenging dense views generation task into two tractable stages, namely anchor views generation and anchor views interpolation. In the first stage, we train the image diffusion model to generate global consistent anchor views conditioning on image-normal pairs. Subsequently, leveraging our video diffusion model fine-tuned on consecutive multi-view images, we conduct interpolation on the previous anchor views to generate extra dense views. This framework yields dense, multi-view consistent images, providing comprehensive 3D information. To further enhance the overall generation quality, we introduce a coarse-to-fine sampling strategy for the reconstruction algorithm to robustly extract textured meshes from the generated dense images. Extensive experiments demonstrate that our method is capable of generating high-quality 3D content in terms of texture and geometry, surpassing previous image-to-3D baseline methods., Comment: GitHub repository: https://github.com/PKU-YuanGroup/Envision3D

Traditional deep learning methods struggle to simultaneously segment, recognize, and forecast human activities from sensor data. This limits their usefulness in many fields such as healthcare and assisted living, where real-time understanding of ongoing and upcoming activities is crucial. This paper introduces P2LHAP, a novel Patch-to-Label Seq2Seq framework that tackles all three tasks in a efficient single-task model. P2LHAP divides sensor data streams into a sequence of "patches", served as input tokens, and outputs a sequence of patch-level activity labels including the predicted future activities. A unique smoothing technique based on surrounding patch labels, is proposed to identify activity boundaries accurately. Additionally, P2LHAP learns patch-level representation by sensor signal channel-independent Transformer encoders and decoders. All channels share embedding and Transformer weights across all sequences. Evaluated on three public datasets, P2LHAP significantly outperforms the state-of-the-art in all three tasks, demonstrating its effectiveness and potential for real-world applications.

Incorporating first-order QED effects, we explore the shadows of Kerr-Newman black holes with a magnetic charge through the numerical backward ray-tracing method. Our investigation accounts for both the direct influence of the electromagnetic field on light rays and the distortion of the background spacetime metric due to QED corrections. We notice that the area of the shadow increases with the QED effect, mainly due to the fact that the photons move more slowly in the effective medium and become easier to be trapped by the black hole., Comment: 14 pages, 8 figures; v2: references added and minor revisions

The Agent and AIGC (Artificial Intelligence Generated Content) technologies have recently made significant progress. We propose AesopAgent, an Agent-driven Evolutionary System on Story-to-Video Production. AesopAgent is a practical application of agent technology for multimodal content generation. The system integrates multiple generative capabilities within a unified framework, so that individual users can leverage these modules easily. This innovative system would convert user story proposals into scripts, images, and audio, and then integrate these multimodal contents into videos. Additionally, the animating units (e.g., Gen-2 and Sora) could make the videos more infectious. The AesopAgent system could orchestrate task workflow for video generation, ensuring that the generated video is both rich in content and coherent. This system mainly contains two layers, i.e., the Horizontal Layer and the Utility Layer. In the Horizontal Layer, we introduce a novel RAG-based evolutionary system that optimizes the whole video generation workflow and the steps within the workflow. It continuously evolves and iteratively optimizes workflow by accumulating expert experience and professional knowledge, including optimizing the LLM prompts and utilities usage. The Utility Layer provides multiple utilities, leading to consistent image generation that is visually coherent in terms of composition, characters, and style. Meanwhile, it provides audio and special effects, integrating them into expressive and logically arranged videos. Overall, our AesopAgent achieves state-of-the-art performance compared with many previous works in visual storytelling. Our AesopAgent is designed for convenient service for individual users, which is available on the following page: https://aesopai.github.io/., Comment: 22 pages, 13 figures

We introduce the Yi model family, a series of language and multimodal models that demonstrate strong multi-dimensional capabilities. The Yi model family is based on 6B and 34B pretrained language models, then we extend them to chat models, 200K long context models, depth-upscaled models, and vision-language models. Our base models achieve strong performance on a wide range of benchmarks like MMLU, and our finetuned chat models deliver strong human preference rate on major evaluation platforms like AlpacaEval and Chatbot Arena. Building upon our scalable super-computing infrastructure and the classical transformer architecture, we attribute the performance of Yi models primarily to its data quality resulting from our data-engineering efforts. For pretraining, we construct 3.1 trillion tokens of English and Chinese corpora using a cascaded data deduplication and quality filtering pipeline. For finetuning, we polish a small scale (less than 10K) instruction dataset over multiple iterations such that every single instance has been verified directly by our machine learning engineers. For vision-language, we combine the chat language model with a vision transformer encoder and train the model to align visual representations to the semantic space of the language model. We further extend the context length to 200K through lightweight continual pretraining and demonstrate strong needle-in-a-haystack retrieval performance. We show that extending the depth of the pretrained checkpoint through continual pretraining further improves performance. We believe that given our current results, continuing to scale up model parameters using thoroughly optimized data will lead to even stronger frontier models.