Papers Multimodal Reasoning
“Multimodal Reasoning” 태그가 달린 논문 1,043편 · 필터 해제
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities, yet whether they truly capture the physical consistency underlying real-world dynamics remains unclear. Existing benchmark paradigms ofte…
Multimodal ReasoningCan We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation
RLVR provides reliable trajectory-level credit, while OPSD offers dense supervision for token-level credit. This exposes a fundamental coupling when updating step-level credit direction and magnitude with teacher supervi…
Mathematical ReasoningMultimodal ReasoningNavHarness: Towards Lifelong Embodied Navigation
Frontier models can now perform well on individual embodied navigation tasks through multi-round multimodal reasoning with simple tools. Across successive tasks, however, an agent must also rely on an evolving map and ea…
Multimodal ReasoningWhat Do Hallucinations Reveal About Multimodal Reasoning? Diagnosing Visual Grounding Failures via Contrastive Decoding Probes
When strong multimodal models are widely available, progress requires new scientific methodologies beyond benchmark scores---using models as instruments for understanding behavior. We address this by asking: can we use l…
Multimodal ReasoningVisual GroundingReason Through the Latent! Making Latent Visual Reasoning Necessary
Latent visual reasoning aims to perform multimodal reasoning through hidden-state computation rather than explicit textual chains of thought. However, visual information being present in a latent state does not imply tha…
Multimodal ReasoningVisual ReasoningMobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control
Grounding natural-language instructions into reliable and executable actions remains a fundamental challenge for vision-language-action (VLA) systems on mobile robots, due to the persistent gap between high-level semanti…
Reinforcement LearningInstruction FollowingMultimodal ReasoningDecision MakingLearning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry
Multimodal geometry reasoning requires VLMs to extract precise visual relations and preserve them through multi-step deduction. Existing free-form traces obscure the decisions that determine the answer, and trajectory-le…
Reinforcement LearningMultimodal ReasoningReactivating Test-Time Scaling for Plane Geometry Problem Solving
Plane geometry problem (PGP) solving has become a critical benchmark for multimodal reasoning because it requires accurate visual perception and precise multi-step symbolic deduction. Although test-time scaling (TTS) has…
Mathematical ReasoningMultimodal ReasoningVisual GroundingTAKE 85: Testing Audiovisual filmmaKer's intEnt across 85 Hours of Film
Films communicate through deliberate creative choices, including lighting, color, composition, editing, dialogue, music, and sound. Humans naturally interpret these signals as directorial intent, yet current multimodal l…
Multimodal ReasoningCoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions
Chain-of-thought (CoT) reasoning has dramatically improved large language models (LLMs) by allowing them to decompose problems into intermediate steps. While CoT is widely effective for linguistic tasks, text-only CoT fo…
Multimodal ReasoningAphanta: Diagnosing Task-Aligned Image-Edited Intermediates for Multimodal Reasoning
Explicit visual intermediates can help multimodal large language models (MLLMs) externalize spatial evidence and updated visual states, but their utility depends on whether an image editor can faithfully realize the requ…
Multimodal ReasoningImage EditingOrder Matters: A Chinese Multi-Panel Meme Benchmark for Vision-Language Reasoning
Many multimodal tasks depend on how visual elements are ordered and composed, not only on recognizing them in isolation. Internet memes are a compact case of this problem: their punchline often depends on a constrained r…
Explanation GenerationMultimodal ReasoningMLLM-Assisted Audio VOS: A 3rd Place Report for the MeViS-Audio Track, 8th LSVOS Challenge
In this technical report, we present a training-free framework for audio-guided video object segmentation, which integrates Multimodal Large Language Models (MLLMs) with SAM-based segmentation models. We decompose the ta…
Video Object SegmentationMultimodal ReasoningVideo SegmentationPointing-VLA: Typed Spatial Grounding Interfaces for Vision-Language-Action Manipulation
Vision-language-action (VLA) models often expose spatial grounding through autoregressive text coordinates or opaque action tokens, creating brittle interfaces between multimodal reasoning and robot execution. We present…
Multimodal ReasoningVIG: Visual Information Gain as a Reward Signal for Multimodal Chain-of-Thought Compression
Multimodal large reasoning models often rely on long Chain-of-Thought (CoT) traces in which a substantial fraction of tokens, such as repeated visual descriptions, self-reflection, and other visually-disengaged filler, i…
Multimodal ReasoningIs Visual Prompting All You Need? Studying VLM Spatial Reasoning under Progressive Visual Scaffolds
Vision-language models (VLMs) have advanced rapidly in multimodal reasoning, yet recent work shows that their failures often reflect an interaction between visual grounding and downstream reasoning. What remains less cle…
Multimodal ReasoningSpatial ReasoningVisual GroundingObject DetectionRobust Incomplete Multimodal Sentiment Analysis via Iterative Proxy Correction
Multimodal sentiment analysis aims to infer affective states by integrating language, visual, and acoustic cues. However, real-world multimodal inputs are often incomplete or corrupted, which can weaken cross-modal compl…
Multimodal Sentiment AnalysisMultimodal ReasoningScaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning
Latent reasoning has advanced multimodal reasoning through a two-stage training paradigm: (1) a helper image is encoded into latent tokens to teach visual chain-of-thought during a supervised fine-tuning (SFT) stage, and…
Reinforcement LearningMultimodal ReasoningDeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigation
Existing agentic reasoning systems typically rely on centralized protocols. This design introduces routing bottlenecks and static role allocations that often fail when handling complex multimodal queries. We propose DeAR…
Multimodal ReasoningGLaQ: Grounding Latent Queries in Visual Evidence for Multimodal Reasoning
Chain-of-thought reasoning has substantially improved the problem-solving capabilities of multimodal large language models. Fine-grained visual evidence, however, remains difficult to preserve and reuse across text-based…
Reinforcement LearningMultimodal ReasoningAnswer Generation