OmniCoT is a new panoramic reasoning benchmark with 6.7K eval, 1K real, and 14.3K training examples plus a two-stage SFT+GRPO training method to enforce global 360-degree consistency.
Mme-cot: Benchmarking chain-of-thought in large multimodal models for reasoning quality, robustness, and efficiency
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 10representative citing papers
ATLAS uses a single functional token to unify agentic and latent visual reasoning without image generation or external execution.
VGR introduces a visual-grounded reasoning MLLM that detects and replays image regions during inference, achieving gains on visual benchmarks with 30% fewer image tokens than the LLaVA-NeXT-7B baseline.
Introduces CausalPhys benchmark with causal graphs and CRFT fine-tuning to improve VLMs' causal physical reasoning accuracy and interpretability.
AutoTool uses dual-mode RL to let MLLMs adaptively choose tool use or text-only reasoning, reporting 21.8% accuracy gain on V* and 44.9% efficiency gain on POPE versus baselines.
Video-MME-v2 is a new benchmark that applies progressive visual-to-reasoning levels and non-linear group scoring to expose gaps in video MLLM capabilities.
Longer textual reasoning chains degrade MLLM accuracy on fine-grained visual tasks; a new normalization and constrained-reward training framework mitigates the effect and sets new SOTA numbers.
AgroCoT is a new Chain-of-Thought VQA benchmark with 4759 samples to evaluate reasoning capabilities of vision-language models in agriculture.
NoisyGRPO is an RL framework that perturbs visual inputs with Gaussian noise for exploration and computes trajectory advantages via Bayesian posterior fusion of noise prior and reward likelihood to improve multimodal CoT generalization.
The paper provides the first comprehensive survey of multimodal chain-of-thought reasoning, including foundational concepts, a taxonomy of methodologies, application analyses, challenges, and future directions.
citing papers explorer
No citing papers match the current filters.