REVIEW 6 cited by
CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning
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
Vision-Language Models (VLMs) have demonstrated their broad effectiveness thanks to extensive training in aligning visual instructions to responses. However, such training of conclusive alignment leads models to ignore essential visual reasoning, further resulting in failures in meticulous visual problems and unfaithful responses. Drawing inspiration from human cognition in solving visual problems (e.g., marking, zoom in), this paper introduces Chain of Manipulations, a mechanism that enables VLMs to solve problems step-by-step with evidence. After training, models can solve various visual problems by eliciting intrinsic manipulations (e.g., grounding, zoom in) with results (e.g., boxes, image) actively without involving external tools, while also allowing users to trace error causes. We study the roadmap to implement this mechanism, including (1) a flexible design of manipulations upon extensive analysis, (2) an efficient automated data generation pipeline, (3) a compatible VLM architecture capable of multi-turn multi-image, and (4) a model training process for versatile capabilities. With the design, we also manually annotate 6K high-quality samples for the challenging graphical mathematical problems. Our trained model, \textbf{CogCoM}, equipped with this mechanism with 17B parameters achieves state-of-the-art performance across 9 benchmarks from 4 categories, demonstrating the effectiveness while preserving the interpretability. Our code, model weights, and collected data are publicly available at https://github.com/THUDM/CogCoM.
Forward citations
Cited by 6 Pith papers
-
Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO
A recalibrated GRPO reinforcement learning method lets multimodal LLMs say 'None' for nonexistent referring expressions without sacrificing localization accuracy on objects that do exist.
-
Beyond Zooming: Learning Multi-Tool Visual Reasoning for Ultra-High-Resolution Remote Sensing
Training on multi-tool visual reasoning trajectories (zoom, grounding, lines) with an attention-focused RL objective improves UHR remote-sensing VQA accuracy over single-tool zoom-in and larger base models.
-
BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception
BVS combines early-stop attention rollout priors with a scale-aware non-stationary kernel and GP-UCB to locate tiny objects in UHR images more accurately and with fewer MLLM queries than prior visual-search methods.
-
LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance
LIRA improves referring segmentation and reduces hallucination in multimodal LLMs by fusing semantic and pixel features and interleaving local image regions with text descriptions.
-
VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning
Fine-tuning Qwen2.5-VL on VisReason, a 489K-example multi-round visual chain-of-thought dataset (165K with pseudo-depth), modestly improves LLM-judged visual reasoning scores, with caveats about self-referential 3D ev...
-
Reinforced Visual Perception with Tools
ReVPT uses GRPO reinforcement learning with a cold-start SFT phase to make Qwen2.5-VL models call visual tools, improving perception benchmarks over SFT and text-only RL baselines.
Discussion (0). Sign in to comment.