Visual Reasoning
12개 벤치마크 · 논문 1,335편 · 이 태스크의 논문 보기 →
Benchmarks
Winoground
NLVR2 Dev
NLVR2 Test
CLEVRER
Bongard-OpenWorld
WinoGAViL
VSR
PHYRE-1B-Cross
PHYRE-1B-Within
VASR
NLVR
Most implemented
Learning Transferable Visual Models From Natural Language Supervision
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
Visual Instruction Tuning
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
VisualBERT: A Simple and Performant Baseline for Vision and Language
Compositional Attention Networks for Machine Reasoning
Papers
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 Reasoning