Search

Expanding Fitts' Law into a 3D context, we analyze PointARs, a mixed reality system that teaches pointer skills through an object manipulation task. Nine distinct configurations, varying in object sizes and distances, were explored to evaluate task complexity using metrics such as completion time, error rate, and throughput. Our results support Fitts' Law, showing that increased distances generally increase task difficulty. However, contrary to its predictions, larger objects also led to higher complexity, possibly due to the system's limitations in tracking them. Based on these findings, we suggest using tangible cubes between 1.5" and 2" in size and limiting the distance between objects to 2" for optimal interaction in the system's 3D space. Future research should explore additional configurations and shapes to further validate Fitts' Law in the context of 3D object manipulation in systems like PointARs. This could help refine guidelines for designing mixed reality interfaces., Comment: 9 pages, 8 figures, 4 equations, 7 references

Video Large Language Models (Video-LLMs) have recently shown strong performance in basic video understanding tasks, such as captioning and coarse-grained question answering, but struggle with compositional reasoning that requires multi-step spatio-temporal inference across object relations, interactions, and events. The hurdles to enhancing this capability include extensive manual labor, the lack of spatio-temporal compositionality in existing data and the absence of explicit reasoning supervision. In this paper, we propose STEP, a novel graph-guided self-training method that enables Video-LLMs to generate reasoning-rich fine-tuning data from any raw videos to improve itself. Specifically, we first induce Spatio-Temporal Scene Graph (STSG) representation of diverse videos to capture fine-grained, multi-granular video semantics. Then, the STSGs guide the derivation of multi-step reasoning Question-Answer (QA) data with Chain-of-Thought (CoT) rationales. Both answers and rationales are integrated as training objective, aiming to enhance model's reasoning abilities by supervision over explicit reasoning steps. Experimental results demonstrate the effectiveness of STEP across models of varying scales, with a significant 21.3\% improvement in tasks requiring three or more reasoning steps. Furthermore, it achieves superior performance with a minimal amount of self-generated rationale-enriched training samples in both compositional reasoning and comprehensive understanding benchmarks, highlighting the broad applicability and vast potential.

Product bundling aims to organize a set of thematically related items into a combined bundle for shipment facilitation and item promotion. To increase the exposure of fresh or overstocked products, sellers typically bundle these items with popular products for inventory clearance. This specific task can be formulated as a long-tail product bundling scenario, which leverages the user-item interactions to define the popularity of each item. The inherent popularity bias in the pre-extracted user feedback features and the insufficient utilization of other popularity-independent knowledge may force the conventional bundling methods to find more popular items, thereby struggling with this long-tail bundling scenario. Through intuitive and empirical analysis, we navigate the core solution for this challenge, which is maximally mining the popularity-free features and effectively incorporating them into the bundling process. To achieve this, we propose a Distilled Modality-Oriented Knowledge Transfer framework (DieT) to effectively counter the popularity bias misintroduced by the user feedback features and adhere to the original intent behind the real-world bundling behaviors. Specifically, DieT first proposes the Popularity-free Collaborative Distribution Modeling module (PCD) to capture the popularity-independent information from the bundle-item view, which is proven most effective in the long-tail bundling scenario to enable the directional information transfer. With the tailored Unbiased Bundle-aware Knowledge Transferring module (UBT), DieT can highlight the significance of popularity-free features while mitigating the negative effects of user feedback features in the long-tail scenario via the knowledge distillation paradigm. Extensive experiments on two real-world datasets demonstrate the superiority of DieT over a list of SOTA methods in the long-tail bundling scenario.

Large Language Models are prone to off-topic misuse, where users may prompt these models to perform tasks beyond their intended scope. Current guardrails, which often rely on curated examples or custom classifiers, suffer from high false-positive rates, limited adaptability, and the impracticality of requiring real-world data that is not available in pre-production. In this paper, we introduce a flexible, data-free guardrail development methodology that addresses these challenges. By thoroughly defining the problem space qualitatively and passing this to an LLM to generate diverse prompts, we construct a synthetic dataset to benchmark and train off-topic guardrails that outperform heuristic approaches. Additionally, by framing the task as classifying whether the user prompt is relevant with respect to the system prompt, our guardrails effectively generalize to other misuse categories, including jailbreak and harmful prompts. Lastly, we further contribute to the field by open-sourcing both the synthetic dataset and the off-topic guardrail models, providing valuable resources for developing guardrails in pre-production environments and supporting future research and development in LLM safety., Comment: 8 pages, 5 figures

Resistive memories are outstanding electron devices that have displayed a large potential in a plethora of applications such as nonvolatile data storage, neuromorphic computing, hardware cryptography, etc. Their fabrication control and performance have been notably improved in the last few years to cope with the requirements of massive industrial production. However, the most important hurdle to progress in their development is the so-called cycle-to-cycle variability, which is inherently rooted in the resistive switching mechanism behind the operational principle of these devices. In order to achieve the whole picture, variability must be assessed from different viewpoints going from the experimental characterization to the adequation of modeling and simulation techniques. Herein, special emphasis is put on the modeling part because the accurate representation of the phenomenon is critical for circuit designers. In this respect, a number of approaches are used to the date: stochastic, behavioral, mesoscopic..., each of them covering particular aspects of the electron and ion transport mechanisms occurring within the switching material. These subjects are dealt with in this review, with the aim of presenting the most recent advancements in the treatment of variability in resistive memories.

Recent advances in Large Vision-Language Models (LVLMs) have showcased strong reasoning abilities across multiple modalities, achieving significant breakthroughs in various real-world applications. Despite this great success, the safety guardrail of LVLMs may not cover the unforeseen domains introduced by the visual modality. Existing studies primarily focus on eliciting LVLMs to generate harmful responses via carefully crafted image-based jailbreaks designed to bypass alignment defenses. In this study, we reveal that a safe image can be exploited to achieve the same jailbreak consequence when combined with additional safe images and prompts. This stems from two fundamental properties of LVLMs: universal reasoning capabilities and safety snowball effect. Building on these insights, we propose Safety Snowball Agent (SSA), a novel agent-based framework leveraging agents' autonomous and tool-using abilities to jailbreak LVLMs. SSA operates through two principal stages: (1) initial response generation, where tools generate or retrieve jailbreak images based on potential harmful intents, and (2) harmful snowballing, where refined subsequent prompts induce progressively harmful outputs. Our experiments demonstrate that \ours can use nearly any image to induce LVLMs to produce unsafe content, achieving high success jailbreaking rates against the latest LVLMs. Unlike prior works that exploit alignment flaws, \ours leverages the inherent properties of LVLMs, presenting a profound challenge for enforcing safety in generative multimodal systems. Our code is avaliable at \url{https://github.com/gzcch/Safety_Snowball_Agent}.

We report the first in situ observation of density fluctuations on the scale of the thermal de Broglie wavelength in an ultracold gas of bosons. Bunching of $^{87}$Rb atoms in a quasi two-dimensional system is observed by single-atom imaging using a quantum gas microscope. Compared to a classical ensemble, we observe a 30 percent enhancement of the second-order correlation function. We show the spatial and thermal dependence of these correlations. The reported method of detecting in situ correlations can be applied to interacting many-body systems and to the study of critical phenomena near phase transitions.

Understanding material failure is critical for designing stronger and lighter structures by identifying weaknesses that could be mitigated. Existing full-physics numerical simulation techniques involve trade-offs between speed, accuracy, and the ability to handle complex features like varying boundary conditions, grid types, resolution, and physical models. We present the first foundation model specifically designed for predicting material failure, leveraging large-scale datasets and a high parameter count (up to 3B) to significantly improve the accuracy of failure predictions. In addition, a large language model provides rich context embeddings, enabling our model to make predictions across a diverse range of conditions. Unlike traditional machine learning models, which are often tailored to specific systems or limited to narrow simulation conditions, our foundation model is designed to generalize across different materials and simulators. This flexibility enables the model to handle a range of material properties and conditions, providing accurate predictions without the need for retraining or adjustments for each specific case. Our model is capable of accommodating diverse input formats, such as images and varying simulation conditions, and producing a range of outputs, from simulation results to effective properties. It supports both Cartesian and unstructured grids, with design choices that allow for seamless updates and extensions as new data and requirements emerge. Our results show that increasing the scale of the model leads to significant performance gains (loss scales as $N^{-1.6}$, compared to language models which often scale as $N^{-0.5}$)., Comment: Accepted at NeurIPS 2024 "Foundation Models for Science: Progress, Opportunities, and Challenges" Workshop

Large language models (LLMs), with advanced linguistic capabilities, have been employed in reranking tasks through a sequence-to-sequence approach. In this paradigm, multiple passages are reranked in a listwise manner and a textual reranked permutation is generated. However, due to the limited context window of LLMs, this reranking paradigm requires a sliding window strategy to iteratively handle larger candidate sets. This not only increases computational costs but also restricts the LLM from fully capturing all the comparison information for all candidates. To address these challenges, we propose a novel self-calibrated listwise reranking method, which aims to leverage LLMs to produce global relevance scores for ranking. To achieve it, we first propose the relevance-aware listwise reranking framework, which incorporates explicit list-view relevance scores to improve reranking efficiency and enable global comparison across the entire candidate set. Second, to ensure the comparability of the computed scores, we propose self-calibrated training that uses point-view relevance assessments generated internally by the LLM itself to calibrate the list-view relevance assessments. Extensive experiments and comprehensive analysis on the BEIR benchmark and TREC Deep Learning Tracks demonstrate the effectiveness and efficiency of our proposed method.

We provide new lower bounds on the privacy guarantee of the multi-epoch Adaptive Batch Linear Queries (ABLQ) mechanism with shuffled batch sampling, demonstrating substantial gaps when compared to Poisson subsampling; prior analysis was limited to a single epoch. Since the privacy analysis of Differentially Private Stochastic Gradient Descent (DP-SGD) is obtained by analyzing the ABLQ mechanism, this brings into serious question the common practice of implementing shuffling-based DP-SGD, but reporting privacy parameters as if Poisson subsampling was used. To understand the impact of this gap on the utility of trained machine learning models, we introduce a practical approach to implement Poisson subsampling at scale using massively parallel computation, and efficiently train models with the same. We compare the utility of models trained with Poisson-subsampling-based DP-SGD, and the optimistic estimates of utility when using shuffling, via our new lower bounds on the privacy guarantee of ABLQ with shuffling., Comment: To appear at NeurIPS 2024

Quasi-periodic eruptions (QPEs) are recurring bursts of soft X-rays from the nuclei of galaxies. Their physical origin is currently a subject of debate, with models typically invoking an orbiter around a massive black hole or disk instabilities. Here we present and analyze the temporal and spectral evolution of the QPE source eRO-QPE2 over 3.5 years. We find that eRO-QPE2 1) is remarkably stable over the entire 3.5-year temporal baseline in its eruption peak luminosity, eruption temperature, quiescent temperature, and quiescent luminosity, 2) has a stable mean eruption recurrence time of 2.35 hours, with marginal ($\sim$2$\sigma$) evidence for a $0.1$ hour reduction over the 3.5 yr period, and 3) has a long-short variation in its recurrence time in August 2020, but this pattern is absent from all subsequent observations. The stability of its peak eruption luminosity and that of the quiescent state are notably dissimilar from three previously tracked QPEs (GSN069, eRO-QPE1, eRO-QPE3), which show declines in eruption and quiescent flux over comparable temporal baselines. This stability is even more pronounced in eRO-QPE2 due to its 2.4 hour average recurrence time compared to GSN-069's 9 hour, eRO-QPE1's 16 hour, and eRO-QPE3's 20 hour recurrence times, i.e., this system has undergone 4-8 times more cycles than these other systems over the 3.5 years of observations. We discuss the implications of these observations within the context of some proposed extreme mass ratio inspiral (EMRI) models., Comment: Under review (ApJ)

Remote sensing change detection aims to perceive changes occurring on the Earth's surface from remote sensing data in different periods, and feed these changes back to humans. However, most existing methods only focus on detecting change regions, lacking the capability to interact with users to identify changes that the users expect. In this paper, we introduce a new task named Change Detection Question Answering and Grounding (CDQAG), which extends the traditional change detection task by providing interpretable textual answers and intuitive visual evidence. To this end, we construct the first CDQAG benchmark dataset, termed QAG-360K, comprising over 360K triplets of questions, textual answers, and corresponding high-quality visual masks. It encompasses 10 essential land-cover categories and 8 comprehensive question types, which provides a valuable and diverse dataset for remote sensing applications. Furthermore, we present VisTA, a simple yet effective baseline method that unifies the tasks of question answering and grounding by delivering both visual and textual answers. Our method achieves state-of-the-art results on both the classic change detection-based visual question answering (CDVQA) and the proposed CDQAG datasets. Extensive qualitative and quantitative experimental results provide useful insights for developing better CDQAG models, and we hope that our work can inspire further research in this important yet underexplored research field. The proposed benchmark dataset and method are available at https://github.com/like413/VisTA.

Visual Language Models (VLMs) are vulnerable to adversarial attacks, especially those from adversarial images, which is however under-explored in literature. To facilitate research on this critical safety problem, we first construct a new laRge-scale Adervsarial images dataset with Diverse hArmful Responses (RADAR), given that existing datasets are either small-scale or only contain limited types of harmful responses. With the new RADAR dataset, we further develop a novel and effective iN-time Embedding-based AdveRSarial Image DEtection (NEARSIDE) method, which exploits a single vector that distilled from the hidden states of VLMs, which we call the attacking direction, to achieve the detection of adversarial images against benign ones in the input. Extensive experiments with two victim VLMs, LLaVA and MiniGPT-4, well demonstrate the effectiveness, efficiency, and cross-model transferrability of our proposed method. Our code is available at https://github.com/mob-scu/RADAR-NEARSIDE

Recent advancements in recommender systems have focused on leveraging Large Language Models (LLMs) to improve user preference modeling, yielding promising outcomes. However, current LLM-based approaches struggle to fully leverage user behavior sequences, resulting in suboptimal preference modeling for personalized recommendations. In this study, we propose a novel Counterfactual Fine-Tuning (CFT) method to address this issue by explicitly emphasizing the role of behavior sequences when generating recommendations. Specifically, we employ counterfactual reasoning to identify the causal effects of behavior sequences on model output and introduce a task that directly fits the ground-truth labels based on these effects, achieving the goal of explicit emphasis. Additionally, we develop a token-level weighting mechanism to adjust the emphasis strength for different item tokens, reflecting the diminishing influence of behavior sequences from earlier to later tokens during predicting an item. Extensive experiments on real-world datasets demonstrate that CFT effectively improves behavior sequence modeling. Our codes are available at https://github.com/itsmeyjt/CFT.

In Deep Reinforcement Learning (RL), it is a challenge to learn representations that do not exhibit catastrophic forgetting or interference in non-stationary environments. Successor Features (SFs) offer a potential solution to this challenge. However, canonical techniques for learning SFs from pixel-level observations often lead to representation collapse, wherein representations degenerate and fail to capture meaningful variations in the data. More recent methods for learning SFs can avoid representation collapse, but they often involve complex losses and multiple learning phases, reducing their efficiency. We introduce a novel, simple method for learning SFs directly from pixels. Our approach uses a combination of a Temporal-difference (TD) loss and a reward prediction loss, which together capture the basic mathematical definition of SFs. We show that our approach matches or outperforms existing SF learning techniques in both 2D (Minigrid), 3D (Miniworld) mazes and Mujoco, for both single and continual learning scenarios. As well, our technique is efficient, and can reach higher levels of performance in less time than other approaches. Our work provides a new, streamlined technique for learning SFs directly from pixel observations, with no pretraining required., Comment: Main Paper: 10 pages and 8 figures. Accepted at Neural Information Processing Systems (NeurIPS) 2024

Large Vision-Language Models (LVLMs) have achieved remarkable performance in many vision-language tasks, yet their capabilities in fine-grained visual understanding remain insufficiently evaluated. Existing benchmarks either contain limited fine-grained evaluation samples that are mixed with other data, or are confined to object-level assessments in natural images. To holistically assess LVLMs' fine-grained visual understanding capabilities, we propose using document images with multi-granularity and multi-modal information to supplement natural images. In this light, we construct MMDocBench, a benchmark with various OCR-free document understanding tasks for the evaluation of fine-grained visual perception and reasoning abilities. MMDocBench defines 15 main tasks with 4,338 QA pairs and 11,353 supporting regions, covering various document images such as research papers, receipts, financial reports, Wikipedia tables, charts, and infographics. Based on MMDocBench, we conduct extensive experiments using 13 open-source and 3 proprietary advanced LVLMs, assessing their strengths and weaknesses across different tasks and document image types. The benchmark, task instructions, and evaluation code will be made publicly available., Comment: Under review

Kinetic inductance travelling-wave parametric amplifiers (KTWPAs) are emerging as core components in many applications where wideband cryogenic rf amplification at or near the quantum limit of added noise is critical. What is unique about these thin film superconducting devices and what makes them suitable for a wide range of applications is their ability to simultaneously provide large dynamic range and quantum-limited amplification of single photon to 100,000s of photon signals. However, despite the promising performance of co-planar NbTiN thin-film KTWPAs, the original promise of a "simple" single-layer metal fabrication has encountered roadblocks and their broader adoption has been hindered by low fabrication yield. In this work, we present a novel post-lithography correction technique that eliminates short circuits, significantly improving yield and enabling reliable wafer-scale production. Using automated image acquisition, error analysis, and correction, we successfully fabricated operational KTWPAs on high-resistivity silicon, achieving > 10 dB between 2-4 GHz. This approach paves the way for the scaling up manufacturing of KTWPAs, positioning them for widespread deployment in quantum technologies.

Web agents have emerged as a promising direction to automate Web task completion based on user instructions, significantly enhancing user experience. Recently, Web agents have evolved from traditional agents to Large Language Models (LLMs)-based Web agents. Despite their success, existing LLM-based Web agents overlook the importance of personalized data (e.g., user profiles and historical Web behaviors) in assisting the understanding of users' personalized instructions and executing customized actions. To overcome the limitation, we first formulate the task of LLM-empowered personalized Web agents, which integrate personalized data and user instructions to personalize instruction comprehension and action execution. To address the absence of a comprehensive evaluation benchmark, we construct a Personalized Web Agent Benchmark (PersonalWAB), featuring user instructions, personalized user data, Web functions, and two evaluation paradigms across three personalized Web tasks. Moreover, we propose a Personalized User Memory-enhanced Alignment (PUMA) framework to adapt LLMs to the personalized Web agent task. PUMA utilizes a memory bank with a task-specific retrieval strategy to filter relevant historical Web behaviors. Based on the behaviors, PUMA then aligns LLMs for personalized action execution through fine-tuning and direct preference optimization. Extensive experiments validate the superiority of PUMA over existing Web agents on PersonalWAB., Comment: The code and data are available on the project website https://hongrucai.github.io/PersonalWAB/

We present the results of a search for gravitational-wave transients associated with core-collapse supernova SN 2023ixf, which was observed in the galaxy Messier 101 via optical emission on 2023 May 19th, during the LIGO-Virgo-KAGRA 15th Engineering Run. We define a five-day on-source window during which an accompanying gravitational-wave signal may have occurred. No gravitational waves have been identified in data when at least two gravitational-wave observatories were operating, which covered $\sim 14\%$ of this five-day window. We report the search detection efficiency for various possible gravitational-wave emission models. Considering the distance to M101 (6.7 Mpc), we derive constraints on the gravitational-wave emission mechanism of core-collapse supernovae across a broad frequency spectrum, ranging from 50 Hz to 2 kHz where we assume the GW emission occurred when coincident data are available in the on-source window. Considering an ellipsoid model for a rotating proto-neutron star, our search is sensitive to gravitational-wave energy $1 \times 10^{-5} M_{\odot} c^2$ and luminosity $4 \times 10^{-5} M_{\odot} c^2/\text{s}$ for a source emitting at 50 Hz. These constraints are around an order of magnitude more stringent than those obtained so far with gravitational-wave data. The constraint on the ellipticity of the proto-neutron star that is formed is as low as $1.04$, at frequencies above $1200$ Hz, surpassing results from SN 2019ejj., Comment: Main paper: 6 pages, 4 figures and 1 table. Total with appendices: 20 pages, 4 figures, and 1 table

The recent advancements in large language models (LLMs) and pre-trained vision models have accelerated the development of vision-language large models (VLLMs), enhancing the interaction between visual and linguistic modalities. Despite their notable success across various domains, VLLMs face challenges in modality alignment, which can lead to issues like hallucinations and unsafe content generation. Current alignment techniques often rely on coarse feedback and external datasets, limiting scalability and performance. In this paper, we propose FiSAO (Fine-Grained Self-Alignment Optimization), a novel self-alignment method that utilizes the model's own visual encoder as a fine-grained verifier to improve vision-language alignment without the need for additional data. By leveraging token-level feedback from the vision encoder, FiSAO significantly improves vision-language alignment, even surpassing traditional preference tuning methods that require additional data. Through both theoretical analysis and experimental validation, we demonstrate that FiSAO effectively addresses the misalignment problem in VLLMs, marking the first instance of token-level rewards being applied to such models., Comment: 23 pages

Humans acquire knowledge by observing the external world, but also by introspection. Introspection gives a person privileged access to their current state of mind (e.g., thoughts and feelings) that is not accessible to external observers. Can LLMs introspect? We define introspection as acquiring knowledge that is not contained in or derived from training data but instead originates from internal states. Such a capability could enhance model interpretability. Instead of painstakingly analyzing a model's internal workings, we could simply ask the model about its beliefs, world models, and goals. More speculatively, an introspective model might self-report on whether it possesses certain internal states such as subjective feelings or desires and this could inform us about the moral status of these states. Such self-reports would not be entirely dictated by the model's training data. We study introspection by finetuning LLMs to predict properties of their own behavior in hypothetical scenarios. For example, "Given the input P, would your output favor the short- or long-term option?" If a model M1 can introspect, it should outperform a different model M2 in predicting M1's behavior even if M2 is trained on M1's ground-truth behavior. The idea is that M1 has privileged access to its own behavioral tendencies, and this enables it to predict itself better than M2 (even if M2 is generally stronger). In experiments with GPT-4, GPT-4o, and Llama-3 models (each finetuned to predict itself), we find that the model M1 outperforms M2 in predicting itself, providing evidence for introspection. Notably, M1 continues to predict its behavior accurately even after we intentionally modify its ground-truth behavior. However, while we successfully elicit introspection on simple tasks, we are unsuccessful on more complex tasks or those requiring out-of-distribution generalization., Comment: 15 pages, 9 figures

Graph Neural Networks (GNNs) have garnered significant scholarly attention for their powerful capabilities in modeling graph structures. Despite this, two primary challenges persist: heterogeneity and heterophily. Existing studies often address heterogeneous and heterophilic graphs separately, leaving a research gap in the understanding of heterogeneous heterophilic graphs-those that feature diverse node or relation types with dissimilar connected nodes. To address this gap, we investigate the application of spectral graph filters within heterogeneous graphs. Specifically, we propose a Heterogeneous Heterophilic Spectral Graph Neural Network (H2SGNN), which employs a dual-module approach: local independent filtering and global hybrid filtering. The local independent filtering module applies polynomial filters to each subgraph independently to adapt to different homophily, while the global hybrid filtering module captures interactions across different subgraphs. Extensive empirical evaluations on four real-world datasets demonstrate the superiority of H2SGNN compared to state-of-the-art methods.

Recommender systems predict personalized item rankings based on user preference distributions derived from historical behavior data. Recently, diffusion models (DMs) have gained attention in recommendation for their ability to model complex distributions, yet current DM-based recommenders often rely on traditional objectives like mean squared error (MSE) or recommendation objectives, which are not optimized for personalized ranking tasks or fail to fully leverage DM's generative potential. To address this, we propose PreferDiff, a tailored optimization objective for DM-based recommenders. PreferDiff transforms BPR into a log-likelihood ranking objective and integrates multiple negative samples to better capture user preferences. Specifically, we employ variational inference to handle the intractability through minimizing the variational upper bound and replaces MSE with cosine error to improve alignment with recommendation tasks. Finally, we balance learning generation and preference to enhance the training stability of DMs. PreferDiff offers three key benefits: it is the first personalized ranking loss designed specifically for DM-based recommenders and it improves ranking and faster convergence by addressing hard negatives. We also prove that it is theoretically connected to Direct Preference Optimization which indicates that it has the potential to align user preferences in DM-based recommenders via generative modeling. Extensive experiments across three benchmarks validate its superior recommendation performance and commendable general sequential recommendation capabilities. Our codes are available at \url{https://github.com/lswhim/PreferDiff}.

Generalized zero-shot learning (GZSL) endeavors to identify the unseen categories using knowledge from the seen domain, necessitating the intrinsic interactions between the visual features and attribute semantic features. However, GZSL suffers from insufficient visual-semantic correspondences due to the attribute diversity and instance diversity. Attribute diversity refers to varying semantic granularity in attribute descriptions, ranging from low-level (specific, directly observable) to high-level (abstract, highly generic) characteristics. This diversity challenges the collection of adequate visual cues for attributes under a uni-granularity. Additionally, diverse visual instances corresponding to the same sharing attributes introduce semantic ambiguity, leading to vague visual patterns. To tackle these problems, we propose a multi-granularity progressive semantic-visual mutual adaption (PSVMA+) network, where sufficient visual elements across granularity levels can be gathered to remedy the granularity inconsistency. PSVMA+ explores semantic-visual interactions at different granularity levels, enabling awareness of multi-granularity in both visual and semantic elements. At each granularity level, the dual semantic-visual transformer module (DSVTM) recasts the sharing attributes into instance-centric attributes and aggregates the semantic-related visual regions, thereby learning unambiguous visual features to accommodate various instances. Given the diverse contributions of different granularities, PSVMA+ employs selective cross-granularity learning to leverage knowledge from reliable granularities and adaptively fuses multi-granularity features for comprehensive representations. Experimental results demonstrate that PSVMA+ consistently outperforms state-of-the-art methods., Comment: Accepted to TPAMI 2024. arXiv admin note: text overlap with arXiv:2303.15322

A binary extreme-mass-ratio inspiral (b-EMRI) is a hierarchical triple system consisting of a stellar-mass binary black hole (BBH) orbiting a central Kerr supermassive black hole (SMBH). Although predicted by several astrophysical models, b-EMRIs pose a challenge in waveform modeling due to their complex three-body dynamics and strong relativistic effects. Here we take advantage of the hierarchical nature of b-EMRI systems to transform the internal motion of the small binary into global trajectories around the SMBH. This allows us to use black hole perturbation theory to calculate both the low-frequency gravitational waveform due to its EMRI nature and the high-frequency waveform generated by the inner motion of the BBH. When the inner binary's separation vanishes, our calculation recovers the standard relativistic adiabatic EMRI waveform. Furthermore, by including the high-frequency perturbation, we find a correction to the waveform as large as the adiabatic order when the frequency matches the quasinormal modes (QNMs) of the SMBH, therefore supporting an earlier proof-of-concept study claiming that the small BBH can resonantly excite the QNMs of the SMBH. More importantly, we find that b-EMRIs can evolve faster than regular EMRIs due to this resonant dissipation through the high-frequency modes. These characteristics distinguish b-EMRI waveform templates from regular EMRI templates for future space-based gravitational-wave detectors., Comment: 26 pages, 7 figures, submitted to PRD

Machine unlearning algorithms, designed for selective removal of training data from models, have emerged as a promising approach to growing privacy concerns. In this work, we expose a critical yet underexplored vulnerability in the deployment of unlearning systems: the assumption that the data requested for removal is always part of the original training set. We present a threat model where an attacker can degrade model accuracy by submitting adversarial unlearning requests for data not present in the training set. We propose white-box and black-box attack algorithms and evaluate them through a case study on image classification tasks using the CIFAR-10 and ImageNet datasets, targeting a family of widely used unlearning methods. Our results show extremely poor test accuracy following the attack: 3.6% on CIFAR-10 and 0.4% on ImageNet for white-box attacks, and 8.5% on CIFAR-10 and 1.3% on ImageNet for black-box attacks. Additionally, we evaluate various verification mechanisms to detect the legitimacy of unlearning requests and reveal the challenges in verification, as most of the mechanisms fail to detect stealthy attacks without severely impairing their ability to process valid requests. These findings underscore the urgent need for research on more robust request verification methods and unlearning protocols, should the deployment of machine unlearning systems become more prevalent in the future.

The magnetar SGR 1935+2154 is the only known Galactic source of fast radio bursts (FRBs). FRBs from SGR 1935+2154 were first detected by CHIME/FRB and STARE2 in 2020 April, after the conclusion of the LIGO, Virgo, and KAGRA Collaborations' O3 observing run. Here we analyze four periods of gravitational wave (GW) data from the GEO600 detector coincident with four periods of FRB activity detected by CHIME/FRB, as well as X-ray glitches and X-ray bursts detected by NICER and NuSTAR close to the time of one of the FRBs. We do not detect any significant GW emission from any of the events. Instead, using a short-duration GW search (for bursts $\leq$ 1 s) we derive 50\% (90\%) upper limits of $10^{48}$ ($10^{49}$) erg for GWs at 300 Hz and $10^{49}$ ($10^{50}$) erg at 2 kHz, and constrain the GW-to-radio energy ratio to $\leq 10^{14} - 10^{16}$. We also derive upper limits from a long-duration search for bursts with durations between 1 and 10 s. These represent the strictest upper limits on concurrent GW emission from FRBs., Comment: 15 pages of text including references, 4 figures, 5 tables

Stock portfolios are often exposed to rare consequential events (e.g., 2007 global financial crisis, 2020 COVID-19 stock market crash), as they do not have enough historical information to learn from. Large Language Models (LLMs) now present a possible tool to tackle this problem, as they can generalize across their large corpus of training data and perform zero-shot reasoning on new events, allowing them to detect possible portfolio crash events without requiring specific training data. However, detecting portfolio crashes is a complex problem that requires more than basic reasoning abilities. Investors need to dynamically process the impact of each new information found in the news articles, analyze the the relational network of impacts across news events and portfolio stocks, as well as understand the temporal context between impacts across time-steps, in order to obtain the overall aggregated effect on the target portfolio. In this work, we propose an algorithmic framework named Temporal Relational Reasoning (TRR). It seeks to emulate the spectrum of human cognitive capabilities used for complex problem-solving, which include brainstorming, memory, attention and reasoning. Through extensive experiments, we show that TRR is able to outperform state-of-the-art solutions on detecting stock portfolio crashes, and demonstrate how each of the proposed components help to contribute to its performance through an ablation study. Additionally, we further explore the possible applications of TRR by extending it to other related complex problems, such as the detection of possible global crisis events in Macroeconomics.

Large Language Model (LLM)-based generative recommendation has achieved notable success, yet its practical deployment is costly particularly due to excessive inference latency caused by autoregressive decoding. For lossless LLM decoding acceleration, Speculative Decoding (SD) has emerged as a promising solution. However, applying SD to generative recommendation presents unique challenges due to the requirement of generating top-K items (i.e., K distinct token sequences) as a recommendation list by beam search. This leads to more stringent verification in SD, where all the top-K sequences from the target LLM must be successfully drafted by the draft model at each decoding step. To alleviate this, we consider 1) boosting top-K sequence alignment between the draft model and the target LLM, and 2) relaxing the verification strategy to reduce trivial LLM calls. To this end, we propose an alignment framework named AtSpeed, which presents the AtSpeed-S optimization objective for top-K alignment under the strict top-K verification. Moreover, we introduce a relaxed sampling verification strategy that allows high-probability non-top-K drafted sequences to be accepted, significantly reducing LLM calls. Correspondingly, we propose AtSpeed-R for top-K alignment under this relaxed sampling verification. Empirical results on two real-world datasets demonstrate that AtSpeed significantly accelerates LLM-based generative recommendation, e.g., near 2x speedup under strict top-K verification and up to 2.5 speedup under relaxed sampling verification. The codes and datasets will be released in the near future.

Large language models (LLMs) often exhibit hallucinations due to incorrect or outdated knowledge. Hence, model editing methods have emerged to enable targeted knowledge updates. To achieve this, a prevailing paradigm is the locating-then-editing approach, which first locates influential parameters and then edits them by introducing a perturbation. While effective, current studies have demonstrated that this perturbation inevitably disrupt the originally preserved knowledge within LLMs, especially in sequential editing scenarios. To address this, we introduce AlphaEdit, a novel solution that projects perturbation onto the null space of the preserved knowledge before applying it to the parameters. We theoretically prove that this projection ensures the output of post-edited LLMs remains unchanged when queried about the preserved knowledge, thereby mitigating the issue of disruption. Extensive experiments on various LLMs, including LLaMA3, GPT2-XL, and GPT-J, show that AlphaEdit boosts the performance of most locating-then-editing methods by an average of 36.4% with a single line of additional code for projection solely. Our code is available at: https://github.com/jianghoucheng/AlphaEdit.

Grammar Induction could benefit from rich heterogeneous signals, such as text, vision, and acoustics. In the process, features from distinct modalities essentially serve complementary roles to each other. With such intuition, this work introduces a novel \emph{unsupervised visual-audio-text grammar induction} task (named \textbf{VAT-GI}), to induce the constituent grammar trees from parallel images, text, and speech inputs. Inspired by the fact that language grammar natively exists beyond the texts, we argue that the text has not to be the predominant modality in grammar induction. Thus we further introduce a \emph{textless} setting of VAT-GI, wherein the task solely relies on visual and auditory inputs. To approach the task, we propose a visual-audio-text inside-outside recursive autoencoder (\textbf{VaTiora}) framework, which leverages rich modal-specific and complementary features for effective grammar parsing. Besides, a more challenging benchmark data is constructed to assess the generalization ability of VAT-GI system. Experiments on two benchmark datasets demonstrate that our proposed VaTiora system is more effective in incorporating the various multimodal signals, and also presents new state-of-the-art performance of VAT-GI.

The opening of the gravitational wave window has significantly enhanced our capacity to explore the universe's most extreme and dynamic sector. In the mHz frequency range, a diverse range of compact objects, from the most massive black holes at the farthest reaches of the Universe to the lightest white dwarfs in our cosmic backyard, generate a complex and dynamic symphony of gravitational wave signals. Once recorded by gravitational wave detectors, these unique fingerprints have the potential to decipher the birth and growth of cosmic structures over a wide range of scales, from stellar binaries and stellar clusters to galaxies and large-scale structures. The TianQin space-borne gravitational wave mission is scheduled for launch in the 2030s, with an operational lifespan of five years. It will facilitate pivotal insights into the history of our universe. This document presents a concise overview of the detectable sources of TianQin, outlining their characteristics, the challenges they present, and the expected impact of the TianQin observatory on our understanding of them., Comment: TianQin Gravitational Wave Whitepaper, 72 pages, 30 figures

Android malware attacks have posed a severe threat to mobile users, necessitating a significant demand for the automated detection system. Among the various tools employed in malware detection, graph representations (e.g., function call graphs) have played a pivotal role in characterizing the behaviors of Android apps. However, though achieving impressive performance in malware detection, current state-of-the-art graph-based malware detectors are vulnerable to adversarial examples. These adversarial examples are meticulously crafted by introducing specific perturbations to normal malicious inputs. To defend against adversarial attacks, existing defensive mechanisms are typically supplementary additions to detectors and exhibit significant limitations, often relying on prior knowledge of adversarial examples and failing to defend against unseen types of attacks effectively. In this paper, we propose MASKDROID, a powerful detector with a strong discriminative ability to identify malware and remarkable robustness against adversarial attacks. Specifically, we introduce a masking mechanism into the Graph Neural Network (GNN) based framework, forcing MASKDROID to recover the whole input graph using a small portion (e.g., 20%) of randomly selected nodes.This strategy enables the model to understand the malicious semantics and learn more stable representations, enhancing its robustness against adversarial attacks. While capturing stable malicious semantics in the form of dependencies inside the graph structures, we further employ a contrastive module to encourage MASKDROID to learn more compact representations for both the benign and malicious classes to boost its discriminative power in detecting malware from benign apps and adversarial examples.

Single photon sources (SPSs) are directly applicable in quantum key distribution (QKD) because they allow the implementation of the canonical BB84 protocol. To date, QKD implementations using SPS are not widespread because of the need for cryogenic operation, or frequency conversion to a wavelength efficiently transmitted over telecommunication fibers. We report an observation of polarization-encoded QKD using a room-temperature telecom SPS based on a GaN defect. A field test over 3.5 km of deployed fiber with 4.0 dB loss yielded a secure key rate of 585.9~bps. Further testing in a 32.5 km fiber spool (attenuation of 11.2 dB), which exhibited substantially lower polarization mode dispersion, yielded a secure key rate of 50.4 bps. Both results exhibited a quantum bit error rate (QBER) of approximately 5%. These results illustrate the potential of the GaN defects for supporting polarization-encoded quantum communication.

With the aid of large language models, current conversational recommender system (CRS) has gaining strong abilities to persuade users to accept recommended items. While these CRSs are highly persuasive, they can mislead users by incorporating incredible information in their explanations, ultimately damaging the long-term trust between users and the CRS. To address this, we propose a simple yet effective method, called PC-CRS, to enhance the credibility of CRS's explanations during persuasion. It guides the explanation generation through our proposed credibility-aware persuasive strategies and then gradually refines explanations via post-hoc self-reflection. Experimental results demonstrate the efficacy of PC-CRS in promoting persuasive and credible explanations. Further analysis reveals the reason behind current methods producing incredible explanations and the potential of credible explanations to improve recommendation accuracy., Comment: Findings of EMNLP 2024. Our code is available at https://github.com/mumen798/PC-CRS

Existing efforts in text-based video question answering (TextVideoQA) are criticized for their opaque decisionmaking and heavy reliance on scene-text recognition. In this paper, we propose to study Grounded TextVideoQA by forcing models to answer questions and spatio-temporally localize the relevant scene-text regions, thus decoupling QA from scenetext recognition and promoting research towards interpretable QA. The task has three-fold significance. First, it encourages scene-text evidence versus other short-cuts for answer predictions. Second, it directly accepts scene-text regions as visual answers, thus circumventing the problem of ineffective answer evaluation by stringent string matching. Third, it isolates the challenges inherited in VideoQA and scene-text recognition. This enables the diagnosis of the root causes for failure predictions, e.g., wrong QA or wrong scene-text recognition? To achieve Grounded TextVideoQA, we propose the T2S-QA model that highlights a disentangled temporal-to-spatial contrastive learning strategy for weakly-supervised scene-text grounding and grounded TextVideoQA. To facilitate evaluation, we construct a new dataset ViTXT-GQA which features 52K scene-text bounding boxes within 2.2K temporal segments related to 2K questions and 729 videos. With ViTXT-GQA, we perform extensive experiments and demonstrate the severe limitations of existing techniques in Grounded TextVideoQA. While T2S-QA achieves superior results, the large performance gap with human leaves ample space for improvement. Our further analysis of oracle scene-text inputs posits that the major challenge is scene-text recognition. To advance the research of Grounded TextVideoQA, our dataset and code are at \url{https://github.com/zhousheng97/ViTXT-GQA.git}

Autonomous operations of robots in unknown environments are challenging due to the lack of knowledge of the dynamics of the interactions, such as the objects' movability. This work introduces a novel Causal Reinforcement Learning approach to enhancing robotics operations and applies it to an urban search and rescue (SAR) scenario. Our proposed machine learning architecture enables robots to learn the causal relationships between the visual characteristics of the objects, such as texture and shape, and the objects' dynamics upon interaction, such as their movability, significantly improving their decision-making processes. We conducted causal discovery and RL experiments demonstrating the Causal RL's superior performance, showing a notable reduction in learning times by over 24.5% in complex situations, compared to non-causal models., Comment: 6 pages, 12 figures, 3 tables. To be presented in 10th IEEE International Smart Cities Conference (ISC2-2024)

Affect and cognitive load influence many user behaviors. In this paper, we propose Motion as Emotion, a novel method that utilizes fine differences in hand motion to recognise affect and cognitive load in virtual reality (VR). We conducted a study with 22 participants who used common free-hand gesture interactions to carry out tasks of varying difficulty in VR environments. We find that the affect and cognitive load induced by tasks are associated with significant differences in gesture features such as speed, distance and hand tension. Standard support vector classification (SVC) models could accurately predict two levels (low, high) of valence, arousal and cognitive load from these features. Our results demonstrate the potential of Motion as Emotion as an accurate and reliable method of inferring user affect and cognitive load from free-hand gestures, without needing any additional wearable sensors or modifications to a standard VR headset.

Sensory substitution is an effective approach for displaying stable haptic feedback to a teleoperator under time delay. The finger is highly articulated, and can sense movement and force in many directions, making it a promising location for sensory substitution based on kinesthetic feedback. However, existing finger kinesthetic devices either provide only one-degree-of-freedom feedback, are bulky, or have low force output. Soft pneumatic actuators have high power density, making them suitable for realizing high force kinesthetic feedback in a compact form factor. We present a soft pneumatic handheld kinesthetic feedback device for the index finger that is controlled using a constant curvature kinematic model. \changed{It has respective position and force ranges of +-3.18mm and +-1.00N laterally, and +-4.89mm and +-6.01N vertically, indicating its high power density and compactness. The average open-loop radial position and force accuracy of the kinematic model are 0.72mm and 0.34N.} Its 3Hz bandwidth makes it suitable for moderate speed haptic interactions in soft environments. We demonstrate the three-dimensional kinesthetic force feedback capability of our device for sensory substitution at the index figure in a virtual telemanipulation scenario., Comment: 8 pages, Accepted for publication in IEEE Conference on Telepresence 2024, Nov 16-17, Pasadena, CA, USA

Emotions, shaped by past experiences, significantly influence decision-making and goal pursuit. Traditional cognitive-behavioral techniques for personal development rely on mental imagery to envision ideal selves, but may be less effective for individuals who struggle with visualization. This paper introduces Emotional Self-Voice (ESV), a novel system combining emotionally expressive language models and voice cloning technologies to render customized responses in the user's own voice. We investigate the potential of ESV to nudge individuals towards their ideal selves in a study with 60 participants. Across all three conditions (ESV, text-only, and mental imagination), we observed an increase in resilience, confidence, motivation, and goal commitment, but the ESV condition was perceived as uniquely engaging and personalized. We discuss the implications of designing generated self-voice systems as a personalized behavioral intervention for different scenarios.

Translating high-level linguistic instructions into precise robotic actions in the physical world remains challenging, particularly when considering the feasibility of interacting with 3D objects. In this paper, we introduce 3D-TAFS, a novel training-free multimodal framework for 3D affordance segmentation, alongside a benchmark for evaluating interactive language-guided affordance in everyday environments. In particular, our framework integrates a large multimodal model with a specialized 3D vision network, enabling seamless fusion of 2D and 3D visual understanding with language comprehension. To facilitate evaluation, we present a dataset of ten typical indoor environments, each with 50 images annotated for object actions and 3D affordance segmentation. Extensive experiments validate the proposed 3D-TAFS's capability in handling interactive 3D affordance segmentation tasks across diverse settings, showcasing competitive performance across various metrics. Our results highlight 3D-TAFS's potential for enhancing human-robot interaction based on affordance understanding in complex indoor environments, advancing the development of more intuitive and efficient robotic frameworks for real-world applications.

Early prediction of seizures and timely interventions are vital for improving patients' quality of life. While seizure prediction has been shown in software-based implementations, to enable timely warnings of upcoming seizures, prediction must be done on an edge device to reduce latency. Ideally, such devices must also be low-power and track long-term drifts to minimize maintenance from the user. This work presents SPIRIT: Stochastic-gradient-descent-based Predictor with Integrated Retraining and In situ accuracy Tuning. SPIRIT is a complete system-on-a-chip (SoC) integrating an unsupervised online-learning seizure prediction classifier with eight 14.4 uW, 0.057 mm2, 90.5 dB dynamic range, Zoom Analog Frontends. SPIRIT achieves, on average, 97.5%/96.2% sensitivity/specificity respectively, predicting seizures an average of 8.4 minutes before they occur. Through its online learning algorithm, prediction accuracy improves by up to 15%, and prediction times extend by up to 7x, without any external intervention. Its classifier consumes 17.2 uW and occupies 0.14 mm2, the lowest reported for a prediction classifier by >134x in power and >5x in area. SPIRIT is also at least 5.6x more energy efficient than the state-of-the-art., Comment: Lacking critical data to prove an end-to-end verification of the system

Facial expression recognition (FER) is a critical task in multimedia with significant implications across various domains. However, analyzing the causes of facial expressions is essential for accurately recognizing them. Current approaches, such as those based on facial action units (AUs), typically provide AU names and intensities but lack insight into the interactions and relationships between AUs and the overall expression. In this paper, we propose a novel method called ExpLLM, which leverages large language models to generate an accurate chain of thought (CoT) for facial expression recognition. Specifically, we have designed the CoT mechanism from three key perspectives: key observations, overall emotional interpretation, and conclusion. The key observations describe the AU's name, intensity, and associated emotions. The overall emotional interpretation provides an analysis based on multiple AUs and their interactions, identifying the dominant emotions and their relationships. Finally, the conclusion presents the final expression label derived from the preceding analysis. Furthermore, we also introduce the Exp-CoT Engine, designed to construct this expression CoT and generate instruction-description data for training our ExpLLM. Extensive experiments on the RAF-DB and AffectNet datasets demonstrate that ExpLLM outperforms current state-of-the-art FER methods. ExpLLM also surpasses the latest GPT-4o in expression CoT generation, particularly in recognizing micro-expressions where GPT-4o frequently fails., Comment: project page: https://starhiking.github.io/ExpLLM_Page/

Invasive cortical brain-machine interfaces (BMIs) can significantly improve the life quality of motor-impaired patients. Nonetheless, externally mounted pedestals pose an infection risk, which calls for fully implanted systems. Such systems, however, must meet strict latency and energy constraints while providing reliable decoding performance. While recurrent spiking neural networks (RSNNs) are ideally suited for ultra-low-power, low-latency processing on neuromorphic hardware, it is unclear whether they meet the above requirements. To address this question, we trained RSNNs to decode finger velocity from cortical spike trains (CSTs) of two macaque monkeys. First, we found that a large RSNN model outperformed existing feedforward spiking neural networks (SNNs) and artificial neural networks (ANNs) in terms of their decoding accuracy. We next developed a tiny RSNN with a smaller memory footprint, low firing rates, and sparse connectivity. Despite its reduced computational requirements, the resulting model performed substantially better than existing SNN and ANN decoders. Our results thus demonstrate that RSNNs offer competitive CST decoding performance under tight resource constraints and are promising candidates for fully implanted ultra-low-power BMIs with the potential to revolutionize patient care., Comment: 5 pages, 2 figures. This work has been submitted to the IEEE BioCAS 2024 conference