Search

The current text-to-video (T2V) generation has made significant progress in synthesizing realistic general videos, but it is still under-explored in identity-specific human video generation with customized ID images. The key challenge lies in maintaining high ID fidelity consistently while preserving the original motion dynamic and semantic following after the identity injection. Current video identity customization methods mainly rely on reconstructing given identity images on text-to-image models, which have a divergent distribution with the T2V model. This process introduces a tuning-inference gap, leading to dynamic and semantic degradation. To tackle this problem, we propose a novel framework, dubbed \textbf{PersonalVideo}, that applies direct supervision on videos synthesized by the T2V model to bridge the gap. Specifically, we introduce a learnable Isolated Identity Adapter to customize the specific identity non-intrusively, which does not comprise the original T2V model's abilities (e.g., motion dynamic and semantic following). With the non-reconstructive identity loss, we further employ simulated prompt augmentation to reduce overfitting by supervising generated results in more semantic scenarios, gaining good robustness even with only a single reference image available. Extensive experiments demonstrate our method's superiority in delivering high identity faithfulness while preserving the inherent video generation qualities of the original T2V model, outshining prior approaches. Notably, our PersonalVideo seamlessly integrates with pre-trained SD components, such as ControlNet and style LoRA, requiring no extra tuning overhead.

The rapid evolution of multimodal foundation models has led to significant advancements in cross-modal understanding and generation across diverse modalities, including text, images, audio, and video. However, these models remain susceptible to jailbreak attacks, which can bypass built-in safety mechanisms and induce the production of potentially harmful content. Consequently, understanding the methods of jailbreak attacks and existing defense mechanisms is essential to ensure the safe deployment of multimodal generative models in real-world scenarios, particularly in security-sensitive applications. To provide comprehensive insight into this topic, this survey reviews jailbreak and defense in multimodal generative models. First, given the generalized lifecycle of multimodal jailbreak, we systematically explore attacks and corresponding defense strategies across four levels: input, encoder, generator, and output. Based on this analysis, we present a detailed taxonomy of attack methods, defense mechanisms, and evaluation frameworks specific to multimodal generative models. Additionally, we cover a wide range of input-output configurations, including modalities such as Any-to-Text, Any-to-Vision, and Any-to-Any within generative systems. Finally, we highlight current research challenges and propose potential directions for future research.The open-source repository corresponding to this work can be found at https://github.com/liuxuannan/Awesome-Multimodal-Jailbreak., Comment: ongoing work

Modeling long sequences is crucial for various large-scale models; however, extending existing architectures to handle longer sequences presents significant technical and resource challenges. In this paper, we propose an efficient and flexible attention architecture that enables the extension of context lengths in large language models with reduced computational resources and fine-tuning time compared to other excellent methods. Specifically, we introduce correlation-aware selection and merging mechanisms to facilitate efficient sparse attention. In addition, we also propose a novel data augmentation technique involving positional encodings to enhance generalization to unseen positions. The results are as follows: First, using a single A100, we achieve fine-tuning on Llama2-7B with a sequence length of 32K, which is more efficient than other methods that rely on subsets for regression. Second, we present a comprehensive method for extending context lengths across the pre-training, fine-tuning, and inference phases. During pre-training, our attention mechanism partially breaks translation invariance during token selection, so we apply positional encodings only to the selected tokens. This approach achieves relatively high performance and significant extrapolation capabilities. For fine-tuning, we introduce Cyclic, Randomly Truncated, and Dynamically Growing NTK Positional Embedding (CRD NTK). This design allows fine-tuning with a sequence length of only 16K, enabling models such as Llama2-7B and Mistral-7B to perform inference with context lengths of up to 1M or even arbitrary lengths. Our method achieves 100\% accuracy on the passkey task with a context length of 4M and maintains stable perplexity at a 1M context length. This represents at least a 64-fold reduction in resource requirements compared to traditional full-attention mechanisms, while still achieving competitive performance., Comment: 11 pages, 2 figures

Knowledge editing has been increasingly adopted to correct the false or outdated knowledge in Large Language Models (LLMs). Meanwhile, one critical but under-explored question is: can knowledge editing be used to inject harm into LLMs? In this paper, we propose to reformulate knowledge editing as a new type of safety threat for LLMs, namely Editing Attack, and conduct a systematic investigation with a newly constructed dataset EditAttack. Specifically, we focus on two typical safety risks of Editing Attack including Misinformation Injection and Bias Injection. For the risk of misinformation injection, we first categorize it into commonsense misinformation injection and long-tail misinformation injection. Then, we find that editing attacks can inject both types of misinformation into LLMs, and the effectiveness is particularly high for commonsense misinformation injection. For the risk of bias injection, we discover that not only can biased sentences be injected into LLMs with high effectiveness, but also one single biased sentence injection can cause a bias increase in general outputs of LLMs, which are even highly irrelevant to the injected sentence, indicating a catastrophic impact on the overall fairness of LLMs. Then, we further illustrate the high stealthiness of editing attacks, measured by their impact on the general knowledge and reasoning capacities of LLMs, and show the hardness of defending editing attacks with empirical evidence. Our discoveries demonstrate the emerging misuse risks of knowledge editing techniques on compromising the safety alignment of LLMs and the feasibility of disseminating misinformation or bias with LLMs as new channels., Comment: The first two authors contributed equally. 9 pages for main paper, 36 pages including appendix. The code, results, dataset for this paper and more resources are on the project website: https://llm-editing.github.io

Threshold cryptography is essential for many blockchain protocols. For example, many protocols rely on threshold common coin to implement asynchronous consensus, leader elections, and provide support for randomized applications. Similarly, threshold signature schemes are frequently used for protocol efficiency and state certification, and threshold decryption and threshold time-lock puzzles are often necessary for privacy. In this paper, we study the interplay between threshold cryptography and a class of blockchains that use Byzantine-fault tolerant (BFT) consensus protocols with a focus on latency. More specifically, we focus on blockchain-native threshold cryptosystem, where the blockchain validators seek to run a threshold cryptographic protocol once for every block with the block contents as an input to the threshold cryptographic protocol. All existing approaches for blockchain-native threshold cryptosystems introduce a latency overhead of at least one message delay for running the threshold cryptographic protocol. In this paper, we first propose a mechanism to eliminate this overhead for blockchain-native threshold cryptosystems with tight thresholds, i.e., in threshold cryptographic protocols where the secrecy and reconstruction thresholds are the same. However, many real-world proof-of-stake-based blockchain-native threshold cryptosystems rely on ramp thresholds, where reconstruction thresholds are strictly greater than secrecy thresholds. For these blockchains, we formally demonstrate that the additional delay is unavoidable. We then introduce a mechanism to minimize this delay in the optimistic case. We implement our optimistic protocol for the proof-of-stake distributed randomness scheme on the Aptos blockchain. Our measurements from the Aptos mainnet show that the optimistic approach reduces latency overhead by 71%.

The rapid development of Multimodal Large Language Models (MLLMs) is making AI-driven scientific assistants increasingly feasible, with interpreting scientific figures being a crucial task. However, existing datasets and benchmarks focus mainly on basic charts and limited science subjects, lacking comprehensive evaluations. To address this, we curated a multimodal, multidisciplinary dataset from peer-reviewed, open-access Nature Communications articles, spanning 72 scientific disciplines. This dataset includes figures such as schematic diagrams, simulated images, macroscopic/microscopic photos, and experimental visualizations (e.g., western blots), which often require graduate-level, discipline-specific expertise to interpret. We developed benchmarks for scientific figure captioning and multiple-choice questions, evaluating six proprietary and over ten open-source models across varied settings. The results highlight the high difficulty of these tasks and the significant performance gap among models. While many open-source models performed at chance level on the multiple-choice task, some matched the performance of proprietary models. However, the gap was more pronounced in the captioning task. Our dataset also provide valuable resource for training. Fine-tuning the Qwen2-VL-2B model with our task-specific multimodal training data improved its multiple-choice accuracy to a level comparable to GPT-4o, though captioning remains challenging. Continuous pre-training of MLLMs using our interleaved article and figure data enhanced their material generation capabilities, demonstrating potential for integrating scientific knowledge. The dataset and benchmarks will be released to support further research., Comment: Code and data are available at https://github.com/Leezekun/MMSci

We introduce MuirBench, a comprehensive benchmark that focuses on robust multi-image understanding capabilities of multimodal LLMs. MuirBench consists of 12 diverse multi-image tasks (e.g., scene understanding, ordering) that involve 10 categories of multi-image relations (e.g., multiview, temporal relations). Comprising 11,264 images and 2,600 multiple-choice questions, MuirBench is created in a pairwise manner, where each standard instance is paired with an unanswerable variant that has minimal semantic differences, in order for a reliable assessment. Evaluated upon 20 recent multi-modal LLMs, our results reveal that even the best-performing models like GPT-4o and Gemini Pro find it challenging to solve MuirBench, achieving 68.0% and 49.3% in accuracy. Open-source multimodal LLMs trained on single images can hardly generalize to multi-image questions, hovering below 33.3% in accuracy. These results highlight the importance of MuirBench in encouraging the community to develop multimodal LLMs that can look beyond a single image, suggesting potential pathways for future improvements., Comment: typos corrected, references added, Project Page: https://muirbench.github.io/

Current multimodal misinformation detection (MMD) methods often assume a single source and type of forgery for each sample, which is insufficient for real-world scenarios where multiple forgery sources coexist. The lack of a benchmark for mixed-source misinformation has hindered progress in this field. To address this, we introduce MMFakeBench, the first comprehensive benchmark for mixed-source MMD. MMFakeBench includes 3 critical sources: textual veracity distortion, visual veracity distortion, and cross-modal consistency distortion, along with 12 sub-categories of misinformation forgery types. We further conduct an extensive evaluation of 6 prevalent detection methods and 15 large vision-language models (LVLMs) on MMFakeBench under a zero-shot setting. The results indicate that current methods struggle under this challenging and realistic mixed-source MMD setting. Additionally, we propose an innovative unified framework, which integrates rationales, actions, and tool-use capabilities of LVLM agents, significantly enhancing accuracy and generalization. We believe this study will catalyze future research into more realistic mixed-source multimodal misinformation and provide a fair evaluation of misinformation detection methods., Comment: Project page: https://liuxuannan.github.io/MMFakeBench.github.io/

Flexible and accurate drag-based editing is a challenging task that has recently garnered significant attention. Current methods typically model this problem as automatically learning "how to drag" through point dragging and often produce one deterministic estimation, which presents two key limitations: 1) Overlooking the inherently ill-posed nature of drag-based editing, where multiple results may correspond to a given input, as illustrated in Fig.1; 2) Ignoring the constraint of image quality, which may lead to unexpected distortion. To alleviate this, we propose LucidDrag, which shifts the focus from "how to drag" to "what-then-how" paradigm. LucidDrag comprises an intention reasoner and a collaborative guidance sampling mechanism. The former infers several optimal editing strategies, identifying what content and what semantic direction to be edited. Based on the former, the latter addresses "how to drag" by collaboratively integrating existing editing guidance with the newly proposed semantic guidance and quality guidance. Specifically, semantic guidance is derived by establishing a semantic editing direction based on reasoned intentions, while quality guidance is achieved through classifier guidance using an image fidelity discriminator. Both qualitative and quantitative comparisons demonstrate the superiority of LucidDrag over previous methods., Comment: Accepted by NeurIPS 2024

Today's practical partially synchronous Byzantine Fault Tolerant (BFT) consensus protocols trade off low latency and high throughput. On the one end, traditional BFT protocols such as PBFT and its derivatives optimize for latency. They require, in fault-free executions, only 3 message exchanges to commit, the optimum for BFT consensus. However, this class of protocols typically relies on a single leader, hampering throughput scalability. On the other end, a new class of so-called DAG-BFT protocols demonstrates how to achieve highly scalable throughput by separating data dissemination from consensus, and using every replica as proposer. Unfortunately, existing DAG-BFT protocols pay a steep latency premium, requiring on average 10.5 message exchanges to commit a transactions. This work aims to soften this tension and proposes Shoal++, a novel DAG-based BFT consensus system that offers the throughput of DAGs while reducing commit latency to an average of 4.5 message exchanges. Our empirical findings are encouraging, showing that Shoal++ achieves throughput comparable to state-of-the-art DAG BFT solutions while reducing latency by up to 60%.

One of the main bottlenecks of blockchains is smart contract execution. To increase throughput, modern blockchains try to execute transactions in parallel. Unfortunately, however, common blockchain use cases introduce read-write conflicts between transactions, forcing sequentiality. We propose RapidLane, an extension for parallel execution engines that allows the engine to capture computations in conflicting parts of transactions and defer their execution until a later time, sometimes optimistically predicting execution results. This technique, coupled with support for a new construct for smart contract languages, allows one to turn certain sequential workloads into parallelizable ones. We integrated RapidLane into Block-STM, a state-of-the-art parallel execution engine used by several blockchains in production, and deployed it on the Aptos blockchain. Our evaluation shows that on commonly contended workloads, such as peer-to-peer transfers with a single fee payer and NFT minting, RapidLane yields up to $12\times$ more throughput.

SPECT can enable the quantification of activity uptake in lesions and at-risk organs in {\alpha}-particle-emitting radiopharmaceutical therapies ({\alpha}-RPTs). But this quantification is challenged by the low photon counts, complicated isotope physics, and the image-degrading effects in {\alpha}-RPT SPECT. Thus, strategies to optimize the SPECT system and protocol designs for the task of regional uptake quantification are needed. Objectively performing this task-based optimization requires a reliable (accurate and precise) regional uptake quantification method. Conventional reconstruction-based quantification (RBQ) methods have been observed to be erroneous for {\alpha}-RPT SPECT. Projection-domain quantification methods, which estimate regional uptake directly from SPECT projections, have demonstrated potential in providing reliable regional uptake estimates, but these methods assume constant uptake within the regions, an assumption that may not hold. To address these challenges, we propose WIN-PDQ, a Wiener-estimator-based projection-domain quantitative SPECT method. The method accounts for the heterogeneity within the regions of interest while estimating mean uptake. An early-stage evaluation of the method was conducted using 3D Monte Carlo-simulated SPECT of anthropomorphic phantoms with radium-223 uptake and lumpy-model-based intra-regional uptake heterogeneity. In this evaluation with phantoms of varying mean regional uptake and intra-regional uptake heterogeneity, the WIN-PDQ method yielded ensemble unbiased estimates and significantly outperformed both reconstruction-based and previously proposed projection-domain quantification methods. In conclusion, based on these preliminary findings, the proposed method is showing potential for estimating mean regional uptake in {\alpha}-RPTs and towards enabling the objective task-based optimization of SPECT system and protocol designs., Comment: The work has been accepted for publication in 2024 SPIE Medical Imaging conference proceedings

The massive generation of multimodal fake news involving both text and images exhibits substantial distribution discrepancies, prompting the need for generalized detectors. However, the insulated nature of training restricts the capability of classical detectors to obtain open-world facts. While Large Vision-Language Models (LVLMs) have encoded rich world knowledge, they are not inherently tailored for combating fake news and struggle to comprehend local forgery details. In this paper, we propose FKA-Owl, a novel framework that leverages forgery-specific knowledge to augment LVLMs, enabling them to reason about manipulations effectively. The augmented forgery-specific knowledge includes semantic correlation between text and images, and artifact trace in image manipulation. To inject these two kinds of knowledge into the LVLM, we design two specialized modules to establish their representations, respectively. The encoded knowledge embeddings are then incorporated into LVLMs. Extensive experiments on the public benchmark demonstrate that FKA-Owl achieves superior cross-domain performance compared to previous methods. Code is publicly available at https://liuxuannan.github.io/FKA_Owl.github.io/., Comment: Accepted by ACM MM 2024.Project page: https://liuxuannan.github.io/FKA_Owl.github.io/

Large language models (LLMs) are increasingly prevalent in conversational systems due to their advanced understanding and generative capabilities in general contexts. However, their effectiveness in task-oriented dialogues (TOD), which requires not only response generation but also effective dialogue state tracking (DST) within specific tasks and domains, remains less satisfying. In this work, we propose a novel approach FnCTOD for solving DST with LLMs through function calling. This method improves zero-shot DST, allowing adaptation to diverse domains without extensive data collection or model tuning. Our experimental results demonstrate that our approach achieves exceptional performance with both modestly sized open-source and also proprietary LLMs: with in-context prompting it enables various 7B or 13B parameter models to surpass the previous state-of-the-art (SOTA) achieved by ChatGPT, and improves ChatGPT's performance beating the SOTA by 5.6% average joint goal accuracy (JGA). Individual model results for GPT-3.5 and GPT-4 are boosted by 4.8% and 14%, respectively. We also show that by fine-tuning on a small collection of diverse task-oriented dialogues, we can equip modestly sized models, specifically a 13B parameter LLaMA2-Chat model, with function-calling capabilities and DST performance comparable to ChatGPT while maintaining their chat capabilities. We have made the code publicly available at https://github.com/facebookresearch/FnCTOD, Comment: ACL 2024 Main. Code available at: https://github.com/facebookresearch/FnCTOD

Understanding how we grasp objects with our hands has important applications in areas like robotics and mixed reality. However, this challenging problem requires accurate modeling of the contact between hands and objects. To capture grasps, existing methods use skeletons, meshes, or parametric models that does not represent hand shape accurately resulting in inaccurate contacts. We present MANUS, a method for Markerless Hand-Object Grasp Capture using Articulated 3D Gaussians. We build a novel articulated 3D Gaussians representation that extends 3D Gaussian splatting for high-fidelity representation of articulating hands. Since our representation uses Gaussian primitives, it enables us to efficiently and accurately estimate contacts between the hand and the object. For the most accurate results, our method requires tens of camera views that current datasets do not provide. We therefore build MANUS-Grasps, a new dataset that contains hand-object grasps viewed from 50+ cameras across 30+ scenes, 3 subjects, and comprising over 7M frames. In addition to extensive qualitative results, we also show that our method outperforms others on a quantitative contact evaluation method that uses paint transfer from the object to the hand., Comment: IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2024

We present Surf-D, a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies using Diffusion models. Previous methods explored shape generation with different representations and they suffer from limited topologies and poor geometry details. To generate high-quality surfaces of arbitrary topologies, we use the Unsigned Distance Field (UDF) as our surface representation to accommodate arbitrary topologies. Furthermore, we propose a new pipeline that employs a point-based AutoEncoder to learn a compact and continuous latent space for accurately encoding UDF and support high-resolution mesh extraction. We further show that our new pipeline significantly outperforms the prior approaches to learning the distance fields, such as the grid-based AutoEncoder, which is not scalable and incapable of learning accurate UDF. In addition, we adopt a curriculum learning strategy to efficiently embed various surfaces. With the pretrained shape latent space, we employ a latent diffusion model to acquire the distribution of various shapes. Extensive experiments are presented on using Surf-D for unconditional generation, category conditional generation, image conditional generation, and text-to-shape tasks. The experiments demonstrate the superior performance of Surf-D in shape generation across multiple modalities as conditions. Visit our project page at https://yzmblog.github.io/projects/SurfD/., Comment: Accepted to ECCV 2024. Project Page: https://yzmblog.github.io/projects/SurfD/

Stylized text-to-image generation focuses on creating images from textual descriptions while adhering to a style specified by a few reference images. However, subtle style variations within different reference images can hinder the model from accurately learning the target style. In this paper, we propose InstaStyle, a novel approach that excels in generating high-fidelity stylized images with only a single reference image. Our approach is based on the finding that the inversion noise from a stylized reference image inherently carries the style signal, as evidenced by their non-zero signal-to-noise ratio. We employ DDIM inversion to extract this noise from the reference image and leverage a diffusion model to generate new stylized images from the "style" noise. Additionally, the inherent ambiguity and bias of textual prompts impede the precise conveying of style. To address this, we introduce a learnable style token via prompt refinement, which enhances the accuracy of the style description for the reference image. Qualitative and quantitative experimental results demonstrate that InstaStyle achieves superior performance compared to current benchmarks. Furthermore, our approach also showcases its capability in the creative task of style combination with mixed inversion noise., Comment: Accepted by European Conference on Computer Vision (ECCV 2024). Project page: https://cuixing100876.github.io/instastyle.github.io/

Instruction-finetuning (IFT) has become crucial in aligning Large Language Models (LLMs) with diverse human needs and has shown great potential in medical applications. However, previous studies mainly fine-tune LLMs on biomedical datasets with limited diversity, which often rely on benchmarks or narrow task scopes, and hence significantly limit the effectiveness on their medical instruction-following ability and generalizability. To bridge this gap, we propose creating a diverse, machine-generated medical IFT dataset, MedInstruct-52k, using GPT-4 and ChatGPT with a high-quality expert-curated seed set. We then fine-tune LLaMA-series models on the dataset to develop AlpaCare. Despite using a smaller domain-specific dataset than previous medical LLMs, AlpaCare not only demonstrates superior performance on medical applications, with up to 38.1% absolute gain over best baselines in medical free-form instruction evaluations, but also achieves 6.7% absolute gains averaged over multiple general domain benchmarks. Human evaluation further shows that AlpaCare consistently outperforms best baselines in terms of both correctness and helpfulness. We offer public access to our data, model, and codebase in https://github.com/XZhang97666/AlpaCare.

Humans subconsciously engage in geospatial reasoning when reading articles. We recognize place names and their spatial relations in text and mentally associate them with their physical locations on Earth. Although pretrained language models can mimic this cognitive process using linguistic context, they do not utilize valuable geospatial information in large, widely available geographical databases, e.g., OpenStreetMap. This paper introduces GeoLM, a geospatially grounded language model that enhances the understanding of geo-entities in natural language. GeoLM leverages geo-entity mentions as anchors to connect linguistic information in text corpora with geospatial information extracted from geographical databases. GeoLM connects the two types of context through contrastive learning and masked language modeling. It also incorporates a spatial coordinate embedding mechanism to encode distance and direction relations to capture geospatial context. In the experiment, we demonstrate that GeoLM exhibits promising capabilities in supporting toponym recognition, toponym linking, relation extraction, and geo-entity typing, which bridge the gap between natural language processing and geospatial sciences. The code is publicly available at https://github.com/knowledge-computing/geolm., Comment: Accepted to EMNLP23 main

Recently, the development of large language models (LLMs) has been significantly enhanced the question answering and dialogue generation, and makes them become increasingly popular in current practical scenarios. While unlike the general dialogue system which emphasizes the semantic performance, the task-oriented dialogue (ToD) systems aim to achieve the dialogue goal efficiently and successfully in multiple turns. Unfortunately, existing LLM-induced ToD systems lack the direct reward toward the final goal and do not take account of the dialogue proactivity that can strengthen the dialogue efficiency. To fill these gaps, we introduce the ProToD (Proactively Goal-Driven LLM-Induced ToD) approach, which anticipates the future dialogue actions and incorporates the goal-oriented reward signal to enhance ToD systems. Additionally, we present a novel evaluation method that assesses ToD systems based on goal-driven dialogue simulations. This method allows us to gauge user satisfaction, system efficiency and successful rate while overcoming the limitations of current Information and Success metrics. Empirical experiments conducted on the MultiWoZ 2.1 dataset demonstrate that our model can achieve superior performance using only 10% of the data compared to previous end-to-end fully supervised models. This improvement is accompanied by enhanced user satisfaction and efficiency., Comment: 7 Pages

Semi-supervised learning (SSL) aims to leverage massive unlabeled data when labels are expensive to obtain. Unfortunately, in many real-world applications, the collected unlabeled data will inevitably contain unseen-class outliers not belonging to any of the labeled classes. To deal with the challenging open-set SSL task, the mainstream methods tend to first detect outliers and then filter them out. However, we observe a surprising fact that such approach could result in more severe performance degradation when labels are extremely scarce, as the unreliable outlier detector may wrongly exclude a considerable portion of valuable inliers. To tackle with this issue, we introduce a novel open-set SSL framework, IOMatch, which can jointly utilize inliers and outliers, even when it is difficult to distinguish exactly between them. Specifically, we propose to employ a multi-binary classifier in combination with the standard closed-set classifier for producing unified open-set classification targets, which regard all outliers as a single new class. By adopting these targets as open-set pseudo-labels, we optimize an open-set classifier with all unlabeled samples including both inliers and outliers. Extensive experiments have shown that IOMatch significantly outperforms the baseline methods across different benchmark datasets and different settings despite its remarkable simplicity. Our code and models are available at https://github.com/nukezil/IOMatch., Comment: Accepted by ICCV 2023, selected for an Oral presentation

Large Language Models (LLMs) have shown remarkable proficiency in following instructions, making them valuable in customer-facing applications. However, their impressive capabilities also raise concerns about the amplification of risks posed by adversarial instructions, which can be injected into the model input by third-party attackers to manipulate LLMs' original instructions and prompt unintended actions and content. Therefore, it is crucial to understand LLMs' ability to accurately discern which instructions to follow to ensure their safe deployment in real-world scenarios. In this paper, we propose a pioneering benchmark for automatically evaluating the robustness of instruction-following LLMs against adversarial instructions injected in the prompt. The objective of this benchmark is to quantify the extent to which LLMs are influenced by injected adversarial instructions and assess their ability to differentiate between these injected adversarial instructions and original user instructions. Through experiments conducted with state-of-the-art instruction-following LLMs, we uncover significant limitations in their robustness against adversarial instruction injection attacks. Furthermore, our findings indicate that prevalent instruction-tuned models are prone to being ``overfitted'' to follow any instruction phrase in the prompt without truly understanding which instructions should be followed. This highlights the need to address the challenge of training models to comprehend prompts instead of merely following instruction phrases and completing the text. The data and code can be found at \url{https://github.com/Leezekun/Adv-Instruct-Eval}., Comment: The data and code can be found at https://github.com/Leezekun/Adv-Instruct-Eval

Scanned historical maps in libraries and archives are valuable repositories of geographic data that often do not exist elsewhere. Despite the potential of machine learning tools like the Google Vision APIs for automatically transcribing text from these maps into machine-readable formats, they do not work well with large-sized images (e.g., high-resolution scanned documents), cannot infer the relation between the recognized text and other datasets, and are challenging to integrate with post-processing tools. This paper introduces the mapKurator system, an end-to-end system integrating machine learning models with a comprehensive data processing pipeline. mapKurator empowers automated extraction, post-processing, and linkage of text labels from large numbers of large-dimension historical map scans. The output data, comprising bounding polygons and recognized text, is in the standard GeoJSON format, making it easily modifiable within Geographic Information Systems (GIS). The proposed system allows users to quickly generate valuable data from large numbers of historical maps for in-depth analysis of the map content and, in turn, encourages map findability, accessibility, interoperability, and reusability (FAIR principles). We deployed the mapKurator system and enabled the processing of over 60,000 maps and over 100 million text/place names in the David Rumsey Historical Map collection. We also demonstrated a seamless integration of mapKurator with a collaborative web platform to enable accessing automated approaches for extracting and linking text labels from historical map scans and collective work to improve the results., Comment: 4 pages, 4 figures

The Narwhal system is a state-of-the-art Byzantine fault-tolerant scalable architecture that involves constructing a directed acyclic graph (DAG) of messages among a set of validators in a Blockchain network. Bullshark is a zero-overhead consensus protocol on top of the Narwhal's DAG that can order over 100k transactions per second. Unfortunately, the high throughput of Bullshark comes with a latency price due to the DAG construction, increasing the latency compared to the state-of-the-art leader-based BFT consensus protocols. We introduce Shoal, a protocol-agnostic framework for enhancing Narwhal-based consensus. By incorporating leader reputation and pipelining support for the first time, Shoal significantly reduces latency. Moreover, the combination of properties of the DAG construction and the leader reputation mechanism enables the elimination of timeouts in all but extremely uncommon scenarios in practice, a property we name Prevalent Responsiveness" (it strictly subsumes the established and often desired Optimistic Responsiveness property for BFT protocols). We integrated Shoal instantiated with Bullshark, the fastest existing Narwhal-based consensus protocol, in an open-source Blockchain project and provide experimental evaluations demonstrating up to 40% latency reduction in the failure-free executions, and up-to 80% reduction in executions with failures against the vanilla Bullshark implementation.

Thorium-227-based alpha-particle radiopharmaceutical therapies ({\alpha}-RPTs) are being investigated in several clinical and pre-clinical studies. After administration, Thorium-227 decays to Radium-223, another alpha-particle-emitting isotope, which redistributes within the patient. Reliable dose quantification of both Thorium-227 and Radium-223 is clinically important, and SPECT may perform this quantification as these isotopes also emit X- and gamma-ray photons. However, reliable quantification is challenged by the orders-of-magnitude lower activity compared to conventional SPECT, resulting in a very low number of detected counts, the presence of multiple photopeaks, substantial overlap in the emission spectra of these isotopes, and the image-degrading effects in SPECT. To address these issues, we propose a multiple-energy-window projection-domain quantification (MEW-PDQ) method that jointly estimates the regional activity uptake of both Thorium-227 and Radium-223 directly using the SPECT projection from multiple energy windows. We evaluated the method with realistic simulation studies using anthropomorphic digital phantoms, in the context of imaging patients with bone metastases of prostate cancer and treated with Thorium-227-based {\alpha}-RPTs. The proposed method yielded reliable (accurate and precise) regional uptake estimates of both isotopes and outperformed state-of-the-art methods across different lesion sizes and contrasts, in a virtual imaging trial, as well as with moderate levels of intra-regional heterogeneous uptake and with moderate inaccuracies in the definitions of the support of various regions. Additionally, we demonstrated the effectiveness of using multiple energy windows and the variance of the estimated uptake using the proposed method approached the Cram\'er-Rao-lower-bound-defined theoretical limit.

SPECT provides a mechanism to perform absorbed-dose quantification tasks for $\alpha$-particle radiopharmaceutical therapies ($\alpha$-RPTs). However, quantitative SPECT for $\alpha$-RPT is challenging due to the low number of detected counts, the complex emission spectrum, and other image-degrading artifacts. Towards addressing these challenges, we propose a low-count quantitative SPECT reconstruction method for isotopes with multiple emission peaks. Given the low-count setting, it is important that the reconstruction method extract the maximal possible information from each detected photon. Processing data over multiple energy windows and in list-mode (LM) format provide mechanisms to achieve that objective. Towards this goal, we propose a list-mode multi-energy window (LM-MEW) OSEM-based SPECT reconstruction method that uses data from multiple energy windows in LM format, and includes the energy attribute of each detected photon. For computational efficiency, we developed a multi-GPU-based implementation of this method. The method was evaluated using 2-D SPECT simulation studies in a single-scatter setting conducted in the context of imaging [$^{223}$Ra]RaCl${_2}$. The proposed method yielded improved performance on the task of estimating activity uptake within known regions of interest in comparison to approaches that use a single energy window or use binned data. The improved performance was observed in terms of both accuracy and precision and for different sizes of the region of interest. Results of our studies show that the use of multiple energy windows and processing data in LM format with the proposed LM-MEW method led to improved quantification performance in low-count SPECT of isotopes with multiple emission peaks. These results motivate further development and validation of the LM-MEW method for such imaging applications, including for $\alpha$-RPT SPECT.

This paper proposes an anchor-based deformation model, namely AnchorDEF, to predict 3D garment animation from a body motion sequence. It deforms a garment mesh template by a mixture of rigid transformations with extra nonlinear displacements. A set of anchors around the mesh surface is introduced to guide the learning of rigid transformation matrices. Once the anchor transformations are found, per-vertex nonlinear displacements of the garment template can be regressed in a canonical space, which reduces the complexity of deformation space learning. By explicitly constraining the transformed anchors to satisfy the consistencies of position, normal and direction, the physical meaning of learned anchor transformations in space is guaranteed for better generalization. Furthermore, an adaptive anchor updating is proposed to optimize the anchor position by being aware of local mesh topology for learning representative anchor transformations. Qualitative and quantitative experiments on different types of garments demonstrate that AnchorDEF achieves the state-of-the-art performance on 3D garment deformation prediction in motion, especially for loose-fitting garments., Comment: Accepted to CVPR 2023. Project page: https://semanticdh.github.io/AnchorDEF

This paper explores interactive facial image editing via dialogue and introduces the ChatEdit benchmark dataset for evaluating image editing and conversation abilities in this context. ChatEdit is constructed from the CelebA-HQ dataset, incorporating annotated multi-turn dialogues corresponding to user edit requests on the images. The dataset is challenging, as it requires the system to dynamically track user requests, edit images, and generate appropriate responses. Accordingly, we propose three benchmark tasks: (i) user edit request tracking, (ii) image editing, and (iii) response generation. We present a novel baseline framework that integrates a dialogue module for both tracking user requests and generating responses and an image editing module for image editing. Unlike previous approaches, our framework directly tracks user edit requests from the entire dialogue history up to the current turn and modifies the original image rather than adjusting the previous turn's output, thereby reducing error accumulation and preventing attribute forgetfulness. Extensive experiments on the ChatEdit dataset underline our framework's superior performance against prior models, while also highlighting potential room for further research. We will release the code and data publicly to facilitate advancements in complex interactive facial image editing., Comment: Accepted to EMNLP 2023 (Main Conference)

Irregularly sampled time series are increasingly prevalent, particularly in medical domains. While various specialized methods have been developed to handle these irregularities, effectively modeling their complex dynamics and pronounced sparsity remains a challenge. This paper introduces a novel perspective by converting irregularly sampled time series into line graph images, then utilizing powerful pre-trained vision transformers for time series classification in the same way as image classification. This method not only largely simplifies specialized algorithm designs but also presents the potential to serve as a universal framework for time series modeling. Remarkably, despite its simplicity, our approach outperforms state-of-the-art specialized algorithms on several popular healthcare and human activity datasets. Especially in the rigorous leave-sensors-out setting where a portion of variables is omitted during testing, our method exhibits strong robustness against varying degrees of missing observations, achieving an impressive improvement of 42.8% in absolute F1 score points over leading specialized baselines even with half the variables masked. Code and data are available at https://github.com/Leezekun/ViTST, Comment: Accepted to NeurIPS2023. Code and data are available at: https://github.com/Leezekun/ViTST

We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model (e.g., T5) to generate an auxiliary directional stimulus prompt for each input instance. These directional stimulus prompts act as nuanced, instance-specific hints and clues to guide LLMs in generating desired outcomes, such as including specific keywords in the generated summary. Our approach sidesteps the challenges of direct LLM tuning by optimizing the policy model to explore directional stimulus prompts that align LLMs with desired behaviors. The policy model can be optimized through 1) supervised fine-tuning using labeled data and 2) reinforcement learning from offline or online rewards based on the LLM's output. We assess our method across summarization, dialogue response generation, and chain-of-thought reasoning tasks. Our experiments demonstrate that the framework consistently improves LLMs' (e.g., ChatGPT, Codex, InstructGPT) performance on these supervised tasks using minimal labeled data. Notably, using just 80 dialogues on the MultiWOZ dataset, our approach enhances ChatGPT's performance by an impressive 41.4%, matching or surpassing some fully supervised start-of-the-art models. Additionally, the instance-specific chain-of-thought prompt generated by our approach improves InstructGPT's reasoning accuracy compared to human-crafted or automatically generated prompts. The code and data are publicly available at \url{https://github.com/Leezekun/Directional-Stimulus-Prompting}., Comment: Accepted by NeurIPS2023. The code and data are available at https://github.com/Leezekun/Directional-Stimulus-Prompting

Named geographic entities (geo-entities for short) are the building blocks of many geographic datasets. Characterizing geo-entities is integral to various application domains, such as geo-intelligence and map comprehension, while a key challenge is to capture the spatial-varying context of an entity. We hypothesize that we shall know the characteristics of a geo-entity by its surrounding entities, similar to knowing word meanings by their linguistic context. Accordingly, we propose a novel spatial language model, SpaBERT, which provides a general-purpose geo-entity representation based on neighboring entities in geospatial data. SpaBERT extends BERT to capture linearized spatial context, while incorporating a spatial coordinate embedding mechanism to preserve spatial relations of entities in the 2-dimensional space. SpaBERT is pretrained with masked language modeling and masked entity prediction tasks to learn spatial dependencies. We apply SpaBERT to two downstream tasks: geo-entity typing and geo-entity linking. Compared with the existing language models that do not use spatial context, SpaBERT shows significant performance improvement on both tasks. We also analyze the entity representation from SpaBERT in various settings and the effect of spatial coordinate embedding., Comment: Accepted by EMNLP 2022

Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations. In this paper, we consider the problem of leveraging the explanations generated by LLM to improve the training of small reasoners, which are more favorable in real-production deployment due to their low cost. We systematically explore three explanation generation approaches from LLM and utilize a multi-task learning framework to facilitate small models to acquire strong reasoning power together with explanation generation capabilities. Experiments on multiple reasoning tasks show that our method can consistently and significantly outperform finetuning baselines across different settings, and even perform better than finetuning/prompting a 60x larger GPT-3 (175B) model by up to 9.5% in accuracy. As a side benefit, human evaluation further shows that our method can generate high-quality explanations to justify its predictions, moving towards the goal of explainable AI.

Building dialogue systems requires a large corpus of annotated dialogues. Such datasets are usually created via crowdsourcing, which is expensive and time-consuming. In this paper, we propose \textsc{Dialogic}, a novel dialogue simulation method based on large language model in-context learning to automate dataset creation. Seeded with a few annotated dialogues, \textsc{Dialogic} automatically selects in-context examples for demonstration and prompts GPT-3 to generate new dialogues and annotations in a controllable way. Our method can rapidly expand a small set of dialogue data with minimum or zero \textit{human involvement} and \textit{parameter update} and is thus much more cost-efficient and time-saving than crowdsourcing. Experimental results on the MultiWOZ dataset demonstrate that training a model on the simulated dialogues leads to even better performance than using the same amount of human-generated dialogues under the challenging low-resource settings, with as few as 85 dialogues as a seed. When enough data is available, our method can still serve as an effective data augmentation method. Human evaluation results also show that our simulated dialogues have near-human fluency and annotation accuracy. The code and data are available at \textbf{\url{https://github.com/Leezekun/dialogic}}., Comment: EMNLP 2022 Findings, code and data are available at https://github.com/Leezekun/dialogic

Recent work has shown that large pretrained Language Models (LMs) can not only perform remarkably well on a range of Natural Language Processing (NLP) tasks but also start improving on reasoning tasks such as arithmetic induction, symbolic manipulation, and commonsense reasoning with increasing size of models. However, it is still unclear what the underlying capabilities of these LMs are. Surprisingly, we find that these models have limitations on certain basic symbolic manipulation tasks such as copy, reverse, and addition. When the total number of symbols or repeating symbols increases, the model performance drops quickly. We investigate the potential causes behind this phenomenon and examine a set of possible methods, including explicit positional markers, fine-grained computation steps, and LMs with callable programs. Experimental results show that none of these techniques can solve the simplest addition induction problem completely. In the end, we introduce LMs with tutor, which demonstrates every single step of teaching. LMs with tutor is able to deliver 100% accuracy in situations of OOD and repeating symbols, shedding new insights on the boundary of large LMs in induction.

Sample assignment plays a prominent part in modern object detection approaches. However, most existing methods rely on manual design to assign positive / negative samples, which do not explicitly establish the relationships between sample assignment and object detection performance. In this work, we propose a novel dynamic sample assignment scheme based on hyper-parameter search. We first define the number of positive samples assigned to each ground truth as the hyper-parameters and employ a surrogate optimization algorithm to derive the optimal choices. Then, we design a dynamic sample assignment procedure to dynamically select the optimal number of positives at each training iteration. Experiments demonstrate that the resulting HPS-Det brings improved performance over different object detection baselines. Moreover, We analyze the hyper-parameter reusability when transferring between different datasets and between different backbones for object detection, which exhibits the superiority and versatility of our method.