Knowledge catalogue
arXiv:2606.03540v1 Announce Type: new Abstract: Existing human attention (saliency) modeling methods persist as highly fragmented across modalities, scenes, and task formulations. Consequently, even w
arXiv:2606.02604v1 Announce Type: cross Abstract: ESG and climate risk data remain fragmented across heterogeneous Scope 1, Scope 2, and Scope 3 reporting environments, while conventional validation p
arXiv:2606.02775v1 Announce Type: new Abstract: The KV-cache is the right memory for datacenters but the wrong memory for robots. Datacenter inference batches many short requests and resets them, amor
arXiv:2606.02724v1 Announce Type: cross Abstract: Audio-visual speaker tracking aims to localize and track active speakers by leveraging auditory and visual cues, enabling fine-grained, human-centric
arXiv:2606.02679v1 Announce Type: new Abstract: Multimodal systems often benefit from combining information across language, sound, and visual streams, but this benefit is not guaranteed. A modality t
arXiv:2602.12221v2 Announce Type: replace Abstract: We propose UniDFlow, a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding an
arXiv:2509.14636v2 Announce Type: replace Abstract: Scale-consistent ego-motion estimation is fundamental for autonomous ground robots. Bird's-Eye-View (BEV) representation naturally addresses the sca
arXiv:2606.03879v1 Announce Type: cross Abstract: As foundation models scale toward fusing more heterogeneous visual streams, understanding how diverse encoders interact under joint training becomes a
arXiv:2606.03917v1 Announce Type: cross Abstract: As Moore's law reaches its limits, Ising machines offer a promising alternative computing approach for difficult optimization problems. However, many
arXiv:2606.03604v1 Announce Type: new Abstract: When asked what a meme or sarcastic post means, Large Vision Language Models (LVLMs) tend to describe what the image shows rather than what the author i
arXiv:2606.03628v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable progress in open-ended text generation, yet they remain prone to hallucinating incorrect or unsu
arXiv:2410.14573v2 Announce Type: replace-cross Abstract: Optimizing costly black-box functions within a constrained evaluation budget presents significant challenges in many real-world applications.
arXiv:2601.21683v2 Announce Type: replace Abstract: While end-to-end self-supervised learning with backpropagation (global BP-SSL) has become central for training modern AI systems, theories of local
arXiv:2606.03590v1 Announce Type: new Abstract: Kalman filter (KF)-based multi-object tracking (MOT) remains a strong baseline for autonomous driving due to its strong performance, computational effic
arXiv:2603.01372v2 Announce Type: replace-cross Abstract: Concept Bottleneck Models (CBMs) enhance the interpretability of end-to-end neural networks by introducing a layer of concepts and predicting
arXiv:2602.01483v2 Announce Type: replace-cross Abstract: We propose causal preference elicitation, a Bayesian framework for expert-in-the-loop causal discovery that actively queries local edge relati
arXiv:2606.02802v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong natural-language reasoning abilities for clinical decision support, but struggle to effectively model struct
arXiv:2604.17708v2 Announce Type: replace Abstract: Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows. Complex OR tas
arXiv:2606.03110v1 Announce Type: new Abstract: Aligning AI systems with diverse human values requires value specifications grounded in concrete examples, but generating such examples without extensiv
arXiv:2606.02655v1 Announce Type: cross Abstract: External regret certifies stability only against replacing one's behavior by a fixed alternative. In a quantum game, this misses a natural physical mo
arXiv:2606.03292v1 Announce Type: cross Abstract: Many systems used in real-world environments require adding new categories and incorporating new information without forgetting what was previously le
arXiv:2606.02742v1 Announce Type: new Abstract: Spatial reasoning is fundamental to robotics, autonomy, and embodied AI, yet modern vision-language models (VLMs) remain unreliable on metric distance q
arXiv:2606.03089v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to prov
arXiv:2606.03017v1 Announce Type: cross Abstract: Reward transfer in Inverse Reinforcement Learning (IRL) is unreliable when policies must generalize to unseen combinations of environment dynamics and
arXiv:2606.03888v1 Announce Type: new Abstract: Self-supervised learning has enabled large-scale pre-training on 2D natural images, producing general-purpose visual representations that transfer effec
arXiv:2606.02800v1 Announce Type: cross Abstract: We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences
arXiv:2606.02581v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) faces a fundamental three-way tension: deeper retrieval improves factual grounding but inflates token costs and e
arXiv:2606.02781v1 Announce Type: cross Abstract: Deep neural networks (DNNs) have achieved state-of-the-art performance across diverse domains. However, typical Von Neumann compute paradigms face sev
arXiv:2511.19995v2 Announce Type: replace Abstract: Creativity is a complex phenomenon. When it comes to representing and assessing creativity, treating it as a single undifferentiated quantity would
arXiv:2606.03210v1 Announce Type: cross Abstract: Automatic-differentiation-based inverse analysis methods, including physics-informed neural networks (PINNs) and differentiable programming, have rece
arXiv:2606.03618v1 Announce Type: new Abstract: AI-assisted coding agents are bottlenecked by input-token cost. Two pathologies of raw human input drive much of this overhead: tokenization inefficienc
arXiv:2606.02640v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to large language model (LLM) safety because they exploit feedback from auxiliary judge models to i
arXiv:2606.03128v1 Announce Type: cross Abstract: Smart contracts face critical security challenges that require thorough auditing in decentralized web services. While Large Language Models (LLMs) hav
arXiv:2606.03951v1 Announce Type: new Abstract: Human experience in digital environments offers a vast, underexplored resource of authentic, untrimmed interactions that contain rich procedural knowled
arXiv:2606.02789v1 Announce Type: new Abstract: Human-object interaction (HOI) recognition is critical for automatically analyzing student behavior in complex educational environments. Although state-
arXiv:2606.03142v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) show strong visualization interpretation, yet it is unclear whether their responses reflect genuine reasoning over
arXiv:2512.03019v2 Announce Type: replace-cross Abstract: Thinking Large Language Models (LLMs) used as judges for pairwise preferences remain noisy at the single-sample level, and common aggregation
arXiv:2606.03463v1 Announce Type: new Abstract: Conversational AI agents require memory systems that are both scalable and semantically coherent across long interaction horizons. Existing approaches r
arXiv:2606.02814v1 Announce Type: cross Abstract: Neural retrievers are trained to estimate query-document relevance from annotated query-document pairs. Yet annotation protocols may not purely reflec
arXiv:2606.02982v1 Announce Type: cross Abstract: The rapid growth of large language model (LLM) inference services has increased the demand for efficient multi-tenant GPU scheduling. While modern inf
arXiv:2606.03874v1 Announce Type: new Abstract: We present DyaPlex, a streaming, full-duplex speech-and-motion model designed for dyadic interaction. To capture the continuous and reciprocal nature of
arXiv:2606.03566v1 Announce Type: cross Abstract: Background: The lateral ventricle choroid plexus (LVCP) is gaining recognition as a key imaging biomarker for multiple sclerosis (MS) related to physi
arXiv:2606.02739v1 Announce Type: cross Abstract: Audio tokenizers serve as the discrete interface between continuous audio and Audio Language Models (ALMs), but existing tokenizers often struggle to
arXiv:2606.02939v1 Announce Type: new Abstract: Interpretable brain-computer interface classifiers that generalize across subjects without calibration remain an open challenge. We test whether prototy
arXiv:2602.07842v2 Announce Type: replace Abstract: Confidence calibration is essential for making large language models (LLMs) reliable, yet existing training-free methods have been primarily studied
arXiv:2606.03331v1 Announce Type: cross Abstract: Consumer device repair is an important but underexplored testbed for large language models (LLMs). Repair tasks require reasoning over incomplete prob
arXiv:2606.03678v1 Announce Type: new Abstract: Generating safety-critical scenarios is essential for validating and improving autonomous driving systems, yet it inherently requires maximizing adversa
arXiv:2606.03841v1 Announce Type: new Abstract: Recent progress in Large Language Model (LLM) agents has enabled promising advances in automated data science. However, existing approaches remain funda
arXiv:2606.03564v1 Announce Type: cross Abstract: Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning. Existing methods typically
arXiv:2606.03694v1 Announce Type: cross Abstract: To enable meaningful human-robot interaction (HRI), a robot must continuously assess engagement by consistently tracking users over time. State-of-the
arXiv:2606.03199v1 Announce Type: new Abstract: Organic crystal structure prediction (CSP) is a requirement for computational modelling of organic solids, but traditionally costs several CPU-years per
arXiv:2606.03927v1 Announce Type: cross Abstract: The Forward-Forward (FF) algorithm offers a computationally efficient and biologically plausible alternative to backpropagation (BP) by training neura
arXiv:2606.03919v1 Announce Type: cross Abstract: Understanding and anticipating scientific change requires models that distinguish between endogenous consolidation and exogenous diffusion of scientif
arXiv:2606.02764v1 Announce Type: new Abstract: Satellite-derived bathymetry (SDB) from multispectral imagery is cost-effective but scales poorly across regions, especially in optically complex coasta
arXiv:2606.03097v1 Announce Type: new Abstract: Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover
arXiv:2606.03304v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated in multilingual settings, yet their inference behavior in low-resource African languages remains
arXiv:2512.11213v2 Announce Type: replace Abstract: Scaling test-time computation has been shown to significantly improve large language model (LLM) performance without additional training. However, e
arXiv:2606.03307v1 Announce Type: cross Abstract: Graph foundation models (GFMs) emerged as a dominant paradigm in graph representation learning by leveraging large-scale pre-training for cross-domain
arXiv:2606.02607v1 Announce Type: cross Abstract: Tabular synthesis is critical for privacy-preserving sharing and augmentation, yet diffusion models rely on implicit mechanisms to capture inter-colum
arXiv:2606.03682v1 Announce Type: new Abstract: Embodied navigation connects intelligent agents with the physical world and is fundamental for general robotic intelligence. Limited availability and qu