Search: “reasoning”

arXiv:2605.21973v1 Announce Type: new Abstract: Current Video-LLM approaches for Video Temporal Grounding (VTG) typically rely on direct timestamp generation from an unstructured visual-token stream,

arXiv:2605.20176v1 Announce Type: new Abstract: Large language models (LLMs) and agentic systems have shown promise for clinical decision support, but existing works largely assume that evidence has a

arXiv:2605.19634v1 Announce Type: cross Abstract: Vision-and-language navigation (VLN) requires an embodied agent to ground natural-language instructions into executable navigation actions in unseen e

arXiv:2605.19382v1 Announce Type: new Abstract: Programmatic video generation through code offers geometric precision and temporal coherence beyond pixel-level diffusion models, yet rigorously evaluat

arXiv:2605.19491v1 Announce Type: new Abstract: Traditional whole slide image (WSI) analysis methods typically rely on the multiple instance learning (MIL) paradigm, which extracts patch-level feature

Agentmw is an open-source middleware framework designed to enhance AI agent reliability and efficiency across different models and frameworks. It addresses key operational challenges including mid-run

arXiv:2605.17262v1 Announce Type: new Abstract: Despite extensive efforts on egocentric video datasets and benchmarks, understanding users' internal states, which is crucial for enabling seamless AI a

arXiv:2605.16899v1 Announce Type: new Abstract: A fundamental challenge in embodied AI is verifying if agents build internal models of spatial structure or merely learn to mimic task-specific expert t

arXiv:2605.16409v1 Announce Type: cross Abstract: Optical character recognition (OCR) and multilingual text understanding remain major failure modes of multimodal large language models (MLLMs), partic

arXiv:2605.16727v1 Announce Type: new Abstract: We introduce PopuLoRA, a population-based asymmetric self-play framework for reinforcement learning with verifiable rewards (RLVR) post-training of LLMs

arXiv:2605.18570v1 Announce Type: new Abstract: Cross-domain knowledge alignment is essential for integrating heterogeneous medical systems, yet existing approaches typically treat entity alignment as

arXiv:2602.12633v2 Announce Type: replace Abstract: Reconstructing physically valid 3D scenes from single-view observations is a prerequisite for bridging the gap between visual perception and robotic

arXiv:2601.09413v2 Announce Type: replace-cross Abstract: We introduce a voice-agentic framework that learns one critical omni-understanding skill: knowing when to trust itself versus when to consult

arXiv:2605.15203v1 Announce Type: cross Abstract: We introduce Agent4POI, the first POI recommendation framework that generates context-conditioned multimodal representations at recommendation time, r

arXiv:2605.15978v1 Announce Type: cross Abstract: Law enforcement reports contain structured fields and written narratives. However, many incident facts that are needed for review, police training, an

arXiv:2605.14857v1 Announce Type: new Abstract: Harmonized System (HS) tariff classification is a high-stakes, expert-level task in which a free-form product description must be mapped to a specific s

arXiv:2510.02837v2 Announce Type: replace Abstract: Although recent tool-augmented benchmarks involve complex requests, evaluation remains limited to answer matching, neglecting critical trajectory as

arXiv:2601.21174v2 Announce Type: replace Abstract: Entity alignment (EA) is critical for knowledge graph (KG) fusion. Existing EA models lack transferability and are incapable of aligning unseen KGs

arXiv:2605.13854v1 Announce Type: new Abstract: Multi-person 3D reconstruction is pivotal for real-world interaction analysis, yet remains challenging due to severe occlusions and depth ambiguity. Cur

arXiv:2605.14403v1 Announce Type: new Abstract: Dermatological diagnosis requires integrating fine-grained visual perception with expert clinical knowledge. Although Multimodal Large Language Models (

arXiv:2605.15071v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly applied to cultural heritage materials, from digital archives to educational platforms. This work ident

arXiv:2605.14040v1 Announce Type: new Abstract: We audit the multimodal-physics evaluation pipeline end-to-end and document three undetected construction practices that distort how the field measures

arXiv:2605.13077v1 Announce Type: cross Abstract: Responsibility allocation -- determining the extent to which agents are accountable for outcomes -- is a fundamental challenge in the design and analy

arXiv:2605.12542v1 Announce Type: cross Abstract: Large foundation models (FMs) are transforming Earth science by integrating heterogeneous multimodal data, such as multi-platform imagery, gridded rea

arXiv:2605.13321v1 Announce Type: new Abstract: VLN has achieved remarkable progress by scaling data and model capacity. However, the assumption of a static environment breaks down in real-world indoo

arXiv:2605.11258v1 Announce Type: cross Abstract: Autonomous science promises to augment scientific discovery, particularly in complex fields like biomedicine. However, this requires AI systems that c

arXiv:2605.09153v1 Announce Type: cross Abstract: Closed-loop traffic simulation requires agents that are both scalable and behaviorally realistic. Recent self-play reinforcement learning approaches d

arXiv:2605.08404v1 Announce Type: cross Abstract: This work investigates the use of large language models (LLMs) for tasks in smart cities. The core idea is to leverage remote sensing imagery to chara

arXiv:2605.10410v1 Announce Type: new Abstract: Large language models can score well on named game-theory benchmarks while failing on the same strategic computation once semantic cues are removed. We

arXiv:2605.09419v1 Announce Type: new Abstract: While experience replay is essential for data efficiency in reinforcement learning (RL), standard methods treat the replay buffer as a passive memory sy

arXiv:2605.10806v1 Announce Type: cross Abstract: Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern re

arXiv:2605.09343v1 Announce Type: new Abstract: Decision making in large-scale complaint handling systems increasingly relies on heterogeneous evidence, including complaint narratives, screenshots, or

arXiv:2605.10247v1 Announce Type: new Abstract: Using Large Language Models (LLMs) to process graph-structured data is an active research area, yet current state-of-the-art approaches typically rely o

arXiv:2605.09900v1 Announce Type: new Abstract: A vision-language model can look at a knot diagram and report what it sees, yet fail to act on that structure. KnotBench pairs an 858,318-image corpus f

arXiv:2605.07103v1 Announce Type: new Abstract: Reaction feasibility prediction, as a fundamental problem in computational chemistry, has benefited from diverse tools enabled by recent advances in art

arXiv:2510.01569v3 Announce Type: replace Abstract: We present InvThink, a training and prompting framework that requires the model to enumerate, analyze, and constrain potential failures before gener

arXiv:2605.01566v1 Announce Type: new Abstract: Advances in inference methods have enabled language models to improve their predictions without additional training. These methods often prioritize raw

arXiv:2605.03609v1 Announce Type: cross Abstract: Large language models often display heterogeneous moral preferences across settings. We study inference-time steering toward a desired ethical framewo

arXiv:2605.01345v1 Announce Type: new Abstract: Visual perception in modern Vision-Language Models (VLMs) is constrained by a fundamental perceptual bandwidth bottleneck: a broad field of view inevita

arXiv:2605.02475v1 Announce Type: cross Abstract: Stories hold a reader's attention because they have causes, secrets, and consequences. Shadow-Loom is an experimental open-source framework that turns

arXiv:2605.00270v1 Announce Type: new Abstract: Standard methods for aggregating natural language judgments, such as majority voting, often fail to produce logically consistent results when applied to

arXiv:2605.00438v1 Announce Type: cross Abstract: Long-horizon robotic manipulation requires plans that are both logically coherent and geometrically grounded. Existing Vision-Language-Action policies

arXiv:2604.27576v1 Announce Type: cross Abstract: We present BAss (BDD-based ADF symbolic solver), a novel analysis tool for Abstract Dialectical Frameworks (ADFs) based on Binary Decision Diagrams (B

arXiv:2501.19143v2 Announce Type: replace Abstract: As the cornerstone of artificial intelligence, machine perception confronts a fundamental threat posed by adversarial illusions. These adversarial a

arXiv:2604.27713v1 Announce Type: new Abstract: The risks posed by AI features are increasing as they are rapidly integrated into software applications. In response, regulations and standards for safe

arXiv:2602.01297v3 Announce Type: replace Abstract: Electronic medical records (EMRs), particularly in neurology, are inherently heterogeneous, sparse, and noisy, which poses significant challenges fo