Papers Visual Reasoning
“Visual Reasoning” 태그가 달린 논문 1,335편 · 필터 해제
ProAR: Learning Prospective Reasoning with Autoregressive Video Models
Autoregressive (AR) video models excel at causal generation, but their reliance on next-chunk prediction confines them to a short-sighted, reactive paradigm. This limitation is particularly consequential for reasoning-or…
Visual ReasoningVideo GenerationOmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning
We present OmniSeek, an agentic framework that transforms an Omni Large Language Model (Omni-LLM) into an active, multi-turn reasoning agent with native tool use. Rather than passively processing an entire audio-visual s…
Reinforcement LearningVisual ReasoningMoLE: Mixture of Latent Experts for Complementary Visual Reasoning
Latent visual reasoning equips vision--language models with continuous intermediate states that can process visual evidence without explicit textual reasoning traces or repeated image operations. However, existing method…
Visual ReasoningHob-VL: A Benchmark for Visually Grounded Boolean Reasoning
Reliable visual reasoning requires composing multiple visual observations and returning consistent answers to logically equivalent questions. We introduce Hob-VL, a benchmark for visually grounded Boolean reasoning. Hob-…
Visual ReasoningWorldAuditBench: Interactive 3D World Auditing with Multimodal Agents
As interactive 3D worlds are increasingly used to study intelligent behavior, it becomes important to develop efficient pipelines for identifying anomalies in these simulated environments, such as floating objects, trave…
Visual ReasoningLoopVL: Recurrent Visual Intelligence
We introduce LoopVL to study whether Loop Transformers can be effectively extended to vision- language models. LoopVL combines Module-Loop and Model-Loop computation to iteratively update a unified vision-language state …
Visual ReasoningRethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence
Latent visual reasoning (LVR) enables multimodal large language models (MLLMs) to perform intermediate computation in continuous latent tokens rather than expressing every reasoning step in words. However, unlike textual…
Visual ReasoningDIDO: Distilling Interaction-Centric Dynamics into One-Step Denoising for World Action Models
World Action Models (WAMs) use video generation models to predict future visual dynamics for robotic manipulation, but iterative denoising introduces additional latency for closed-loop control. We empirically find that v…
Video GenerationVisual ReasoningReasoning with Image Generation
Chain-of-thought reasoning has revolutionized natural language processing by enabling large language models (LLMs) to decompose problems into intermediate steps before answering. Yet confining reasoning to the textual do…
Spatial ReasoningImage GenerationDepth EstimationVisual ReasoningReason 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 ReasoningFrom Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making
Vision-Language Models are commonly evaluated through their final predictions, but understanding whether these decisions are grounded in visual evidence requires tracing how visual information contributes to language-bas…
Visual ReasoningPACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference
Vision-Language Models (VLMs) demonstrate exceptional visual reasoning capabilities, yet their inference costs escalate rapidly with the proliferation of visual tokens. Existing visual token pruning methods exhibit two f…
Visual ReasoningG2D: Generative-to-Discriminative Collaborative Inference for Zero-Shot Image Classification
Zero-shot classification needs efficient label retrieval and fine-grained visual reasoning, yet discriminative and generative vision-language models fail in complementary ways.When CLIP's top-1 prediction is wrong, the c…
Zero-Shot Image ClassificationVisual ReasoningVBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and videos) are not merely inputs to be understood or outputs to be rendered, but first-class substrates for …
Reinforcement LearningVideo GenerationVisual ReasoningInvestigating Relational Reasoning in VLMs
Vision-Language Models (VLMs) achieve strong performance in visual reasoning tasks, but it remains unclear whether they understand visual relations, or simply employ shortcuts such as language cues or priors. To investig…
Relational ReasoningVisual ReasoningVIALS: A Benchmark for Visual Interpretation of Artifacts in the Life Sciences
In professional life sciences workflows, scientists routinely interpret visual artifacts (gel blots, microscopy images, plasmid maps, flow cytometry plots, molecular structures, ...) to inform research decisions. We intr…
Visual ReasoningIs Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosis
Speculative decoding accelerates autoregressive generation by allowing a lightweight drafter to propose future tokens while a target model verifies them in parallel. Its lossless guarantee has motivated a line of work th…
Visual ReasoningImage CaptioningVGI-Bench: Probing Visual Intelligence in Video Generation Models
Recent studies suggest that video generation models can exhibit certain forms of zero-shot visual reasoning through generated frames. Yet reliable evaluation remains challenging: benchmarks should adopt inputs aligned wi…
Visual ReasoningVideo GenerationWhen Safety Overrides Vision: Exploring Dynamics between Vision Influence and Safety Alignment in Vision-Language Models
Aligned vision-language models (VLMs) are designed to balance grounded visual reasoning with safe generation behavior. However, we observe a striking phenomenon: under safety-constrained instruction, models frequently ab…
Visual ReasoningContinual Reasoning Gym: Diagnosing and Harnessing Shared Reasoning in Continual RLVR
Reinforcement learning with verifiable rewards (RLVR) commonly post-trains reasoning models on multiple tasks, while rerunning multitask RLVR (MTRL) as new tasks are added makes capability expansion costly. We therefore …
Reinforcement LearningVisual Reasoning