Knowledge catalogue
arXiv:2604.10397v1 Announce Type: cross Abstract: Video-based human-object interaction (HOI) understanding requires both detecting ongoing interactions and anticipating their future evolution. However
arXiv:2604.10843v1 Announce Type: cross Abstract: Retinal Cysts are formed by leakage and accumulation of fluid in the retina due to the incompetence of retinal vasculature. These cystic spaces have s
arXiv:2604.11407v1 Announce Type: cross Abstract: We revisit retrieval-augmented generation (RAG) by embedding retrieval control directly into generation. Instead of treating retrieval as an external
arXiv:2604.09548v1 Announce Type: cross Abstract: Older adults commonly experience chronic conditions such as pain and sleep disturbances and may consider cannabidiol for symptom management. Safe use
arXiv:2604.11759v1 Announce Type: new Abstract: Organizational knowledge used by AI agents typically lacks epistemic structure: retrieval systems surface semantically relevant content without distingu
arXiv:2604.10695v1 Announce Type: new Abstract: Recent Audio-Visual Question Answering (AVQA) methods have advanced significantly. However, most AVQA methods lack effective mechanisms for handling mis
arXiv:2604.11496v1 Announce Type: cross Abstract: Dual-encoder Vision-Language Models (VLMs) such as CLIP are often characterized as bag-of-words systems due to their poor performance on compositional
arXiv:2505.24778v3 Announce Type: replace Abstract: As large language models (LLMs) are increasingly used in high-stakes domains, accurately assessing their confidence is crucial. Humans typically exp
arXiv:2604.09991v1 Announce Type: new Abstract: Infrared small target detection still faces two persistent challenges: training instability from non-monotonic scale loss functions, and inadequate spat
arXiv:2604.10916v1 Announce Type: cross Abstract: Ultrasound acquisition requires skilled probe manipulation and real-time adjustments. Vision-language models (VLMs) could enable autonomous ultrasound
arXiv:2604.10183v1 Announce Type: cross Abstract: Wireless sensing, traditionally relying on signal processing (SP) techniques, has recently shifted toward data-driven deep learning (DL) to achieve pe
arXiv:2604.07512v2 Announce Type: replace Abstract: We present Rhizome OS-1, a semi-autonomous operating system for small molecule drug discovery in which multi-modal AI agents operate as a full multi
arXiv:2601.08039v2 Announce Type: replace Abstract: In this paper, we study Riemannian zeroth-order optimization in settings where the underlying Riemannian metric g is geodesically incomplete, and th
arXiv:2509.21982v2 Announce Type: replace Abstract: E-commerce risk management requires aggregating diverse, deeply embedded web data through multi-step, stateful interactions, which traditional scrap
arXiv:2602.03402v3 Announce Type: replace Abstract: Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerabl
arXiv:2410.13987v3 Announce Type: replace Abstract: Answering complex real-world questions in the medical domain often requires accurate retrieval from medical Textual Knowledge Graphs (medical TKGs),
arXiv:2604.03768v2 Announce Type: replace Abstract: Unsustainable land-use practices in ecologically sensitive regions threaten biodiversity, water resources, and the livelihoods of millions. This pap
arXiv:2510.16333v2 Announce Type: replace Abstract: A dominant assumption in Multimodal Language Model (MLLM) research is that its performance is largely inherited from the LLM backbone, given its imm
arXiv:2604.10929v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) provide robots with contextual reasoning abilities to comprehend human instructions. Yet, current LLM-en
arXiv:2511.17441v3 Announce Type: replace Abstract: Despite the critical role of bimanual manipulation in endowing robots with human-like dexterity, large-scale and diverse datasets remain scarce due
arXiv:2604.09860v1 Announce Type: cross Abstract: The pursuit of general-purpose robotics has yielded impressive foundation models, yet simulation-based benchmarking remains a bottleneck due to rapid
arXiv:2603.12639v2 Announce Type: replace Abstract: Scalable Embodied AI faces fundamental constraints due to prohibitive costs and safety risks of real-world interaction. While Embodied World Models
arXiv:2604.10974v1 Announce Type: new Abstract: Reinforcement learning (RL) policies often fail under dynamics that differ from training, a gap not fully addressed by domain randomization or existing
arXiv:2604.09710v1 Announce Type: new Abstract: Automated diagnosis from chest CT has improved considerably with deep learning, but models trained on skewed datasets tend to perform unevenly across pa
arXiv:2508.21322v2 Announce Type: replace Abstract: Achieving both safety guarantees and real-time performance in cooperative vehicle coordination remains a fundamental challenge, particularly in dyna
arXiv:2604.09814v1 Announce Type: new Abstract: Medical image segmentation models built on Segment Anything Model (SAM) achieve strong performance on clean benchmarks, yet their reliability often degr
arXiv:2505.09368v2 Announce Type: replace Abstract: Standard benchmarks for optical flow, scene flow, and stereo vision algorithms generally focus on model accuracy rather than robustness to image cor
arXiv:2604.11655v1 Announce Type: cross Abstract: The rapid adoption of Large Language Models (LLMs) in interactive systems has enabled the creation of dynamic, open-ended Role-Playing Agents (RPAs).
arXiv:2604.11156v1 Announce Type: new Abstract: Unsupervised remote photoplethysmography (rPPG) promises to leverage unlabeled video data, but its potential is hindered by a critical challenge: traini
arXiv:2604.11037v1 Announce Type: cross Abstract: Multi-step agentic reinforcement learning benefits from fine-grained credit assignment, yet existing approaches offer limited options: critic-free met
arXiv:2604.11233v1 Announce Type: new Abstract: Lemmatization -- the task of mapping an inflected word form to its dictionary form -- is a crucial component of many NLP applications. In this paper, we
arXiv:2604.11315v1 Announce Type: cross Abstract: We introduce the Structured Sparsity Specification (S^3), an algebraic framework for defining, composing, and implementing structured sparse patterns.
arXiv:2503.05534v3 Announce Type: replace Abstract: Purpose: The Segment Anything Model (SAM) promises to ease the annotation bottleneck in medical segmentation, but overlapping anatomy and blurred bo
arXiv:2604.11803v1 Announce Type: new Abstract: Natural language processing (NLP) and speech technologies have made significant progress in recent years; however, they remain largely focused on standa
arXiv:2604.11447v1 Announce Type: new Abstract: Ensuring operational safety is critical for human-to-humanoid motion imitation. This paper presents a vision-based framework that enables a humanoid rob
arXiv:2508.11290v3 Announce Type: replace Abstract: LLMs increasingly exhibit over-refusal behavior, where safety mechanisms cause models to reject benign instructions that seemingly resemble harmful
arXiv:2604.10429v1 Announce Type: new Abstract: This paper considers the problem of zero-shot safety guarantees for cascade dynamical systems. These are systems where a subset of the states (the inner
arXiv:2604.11003v1 Announce Type: new Abstract: Agentic data science (ADS) pipelines have grown rapidly in both capability and adoption, with systems such as OpenAI Codex now able to directly analyze
arXiv:2505.13777v2 Announce Type: replace-cross Abstract: We present Sat2Sound, a unified multimodal framework for geospatial soundscape understanding, designed to predict and map the distribution of
arXiv:2604.10306v1 Announce Type: new Abstract: As Earth-observation workloads move toward onboard and edge processing, remote-sensing segmentation models must operate under tight latency and energy c
arXiv:2511.12022v2 Announce Type: replace Abstract: Autonomous robots operating in dynamic environments must balance global path optimality with real-time responsiveness to disturbances. This requires
arXiv:2512.19691v3 Announce Type: replace Abstract: Reference labels for machine-learning benchmarks are increasingly synthesized with LLM assistance, but their reliability remains underexamined. We a
arXiv:2512.12982v2 Announce Type: replace Abstract: The pursuit of a universal AI-generated image (AIGI) detector often relies on aggregating data from numerous generators to improve generalization. H
arXiv:2604.11402v1 Announce Type: new Abstract: Scene change detection (SCD) is crucial for urban monitoring and navigation but remains challenging in real-world environments due to lighting variation
arXiv:2511.18329v3 Announce Type: replace Abstract: Scientific posters play a vital role in academic communication by presenting ideas through visual summaries. Analyzing reading order and parent-chil
arXiv:2604.10718v1 Announce Type: new Abstract: Accelerating scientific discovery requires the identification of which experiments would yield the best outcomes before committing resources to costly p
arXiv:2307.01139v2 Announce Type: replace-cross Abstract: Instruction finetuning is a popular paradigm to align large language models (LLM) with human intent. Despite its popularity, this idea is less
arXiv:2604.05489v3 Announce Type: replace Abstract: Text-to-Video (T2V) generation has benefited from recent advances in diffusion models, yet current systems still struggle under complex scenarios, w
arXiv:2604.11625v1 Announce Type: cross Abstract: Neural operators have emerged as powerful surrogates for partial differential equation (PDE) solvers, yet they are typically trained as monolithic mod
arXiv:2512.12675v2 Announce Type: replace-cross Abstract: Subject-driven image generation has advanced from single- to multi-subject composition, while neglecting distinction, the ability to distingui
arXiv:2604.10688v1 Announce Type: cross Abstract: On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewa
arXiv:2604.10962v1 Announce Type: new Abstract: Flow Matching (FM) policies have emerged as an efficient backbone for robotic control, offering fast and expressive action generation that underpins rec
arXiv:2412.07469v3 Announce Type: replace-cross Abstract: Causal discovery is a crucial initial step in establishing causality from empirical data and background knowledge. Numerous algorithms have be
arXiv:2604.11244v1 Announce Type: new Abstract: Advances in Multimodal Large Language Models (MLLMs) are transforming video captioning from a descriptive endpoint into a semantic interface for both vi
arXiv:2604.09743v1 Announce Type: cross Abstract: Multi-modal image registration plays a critical role in precision medicine but faces challenges from non-linear intensity relationships and local opti
arXiv:2604.07791v2 Announce Type: replace Abstract: Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. Wit
arXiv:2509.22097v3 Announce Type: replace-cross Abstract: Large language model-powered code agents are rapidly transforming software engineering, yet the security risks of their generated code have be
arXiv:2604.09749v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) frequently hallucinate objects that are absent from the visual input, often because attention during decoding i
arXiv:2604.10299v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attack
arXiv:2505.15489v4 Announce Type: replace-cross Abstract: The impact of multimodal misinformation arises not only from factual inaccuracies but also from the misleading narratives that creators delibe