REVIEW 20 cited by
Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large Language Models (LLMs) demonstrate enhanced capabilities and reliability by reasoning more, evolving from Chain-of-Thought prompting to product-level solutions like OpenAI o1. Despite various efforts to improve LLM reasoning, high-quality long-chain reasoning data and optimized training pipelines still remain inadequately explored in vision-language tasks. In this paper, we present Insight-V, an early effort to 1) scalably produce long and robust reasoning data for complex multi-modal tasks, and 2) an effective training pipeline to enhance the reasoning capabilities of multi-modal large language models (MLLMs). Specifically, to create long and structured reasoning data without human labor, we design a two-step pipeline with a progressive strategy to generate sufficiently long and diverse reasoning paths and a multi-granularity assessment method to ensure data quality. We observe that directly supervising MLLMs with such long and complex reasoning data will not yield ideal reasoning ability. To tackle this problem, we design a multi-agent system consisting of a reasoning agent dedicated to performing long-chain reasoning and a summary agent trained to judge and summarize reasoning results. We further incorporate an iterative DPO algorithm to enhance the reasoning agent's generation stability and quality. Based on the popular LLaVA-NeXT model and our stronger base MLLM, we demonstrate significant performance gains across challenging multi-modal benchmarks requiring visual reasoning. Benefiting from our multi-agent system, Insight-V can also easily maintain or improve performance on perception-focused multi-modal tasks.
Forward citations
Cited by 20 Pith papers
-
More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
Reasoning models trade visual grounding for language-based inference, and this paper measures that trade-off with a new metric and benchmark.
-
MIRROR: Learning from the Other View for Multi-Modal Reasoning
An RL method that selects the best-performing view of each geometry problem as an internal teacher and distills it into weaker views improves VLM reasoning accuracy and consistency.
-
InPhyRe Discovers: Large Multimodal Models Struggle in Inductive Physical Reasoning
Large multimodal models do far worse when collision videos violate familiar physics, and their small gains come from text exemplars, not the videos.
-
SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning
SyncLoop jointly evolves multimodal training data and model capability through alternating SFT and RL, selecting error-prone samples to improve geometry reasoning.
-
Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and Understanding
A new 1,000-video benchmark with adversarial question variants shows video LLMs remain far below human accuracy and robustness on short real-world videos.
-
VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
A vision-language model learns via reinforcement learning when to upscale a low-resolution image, cutting visual tokens roughly in half while preserving accuracy on most benchmarks.
-
HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context
Requiring omni-modal models to summarize context before reasoning, with LLM-judged context and logical rewards, improves human-intent reasoning benchmarks.
-
Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning
A 3B agent trained with supervised tool-use traces and reinforcement learning answers week-long egocentric video questions by dynamically selecting hierarchical retrieval, video-LLM, and VLM tools.
-
AD^2-Bench: A Hierarchical CoT Benchmark for MLLM in Autonomous Driving under Adverse Conditions
AD^2-Bench is a new adverse-weather driving benchmark with hierarchical chain-of-thought annotations and LLM-based quality metrics; 12 MLLMs all scored below 60%.
-
SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs
SparseMM shows that under 5% of attention heads carry visual understanding in MLLMs and uses OCR-derived head scores to allocate KV-cache budgets asymmetrically, preserving accuracy at low cache sizes.
-
UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
UniGen shows a 1.5B model trained on open data can beat larger systems on image understanding and generation once it verifies its own outputs with chain-of-thought and Best-of-N selection.
-
GenTune: Toward Traceable Prompts to Improve Controllability of Image Refinement in Environment Design
GenTune improves AI image refinement by tracing image regions back to prompt labels and allowing element-level, semantic-guided edits.
-
WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning
WeThink, a 120K-image QA dataset with AI-generated reasoning paths, combined with hybrid-reward reinforcement learning, improves a 7B vision-language model across 14 benchmarks.
-
MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning
MINT-CoT-7B interleaves fine-grained visual tokens into each math reasoning step and reports 73.70 on MathVista-Math, 64.72 on GeoQA, and 69.6 on MMStar-Math.
-
Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
Using a two-stage SFT-plus-GRPO pipeline, the authors train 3B and 7B multimodal models that beat prior open-source models on four math reasoning benchmarks, while showing that reflective 'aha moment' text is not a re...
-
MM-MovieDubber: Towards Multi-Modal Learning for Multi-Modal Movie Dubbing
A movie dubbing system that uses a vision-language model to extract scene type and speaker attributes from silent video, then feeds those attributes as extra conditions into a diffusion-based speech generator, support...
-
Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
On a PMC-VQA subset, GRPO-based RL fine-tuning of Qwen2-VL-2B-Instruct outperforms SFT in accuracy, but the study has no error bars and several prose claims conflict with its own table.
-
ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding
ChartSketcher has a multimodal LLM sketch intermediate reasoning steps directly on chart images and feed those sketches back as visual feedback, improving chart QA accuracy over its base model.
-
Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models
A survey-style position paper claims that reinforcement fine-tuning powers reasoning in multimodal LLMs, summarizing over a hundred recent works and proposing five future research directions.
-
Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization
A survey categorizing deep reinforcement learning and direct preference optimization methods for aligning large vision-language models, with tables of studies and datasets and no new experimental result.
Discussion (0). Sign in to comment.