CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 9 Pith papers
-
DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning
DeFacto trains multimodal models using counterfactual image variants and reinforcement learning rewards to improve both answer accuracy and evidence-answer consistency.
-
VGR: Visual Grounded Reasoning
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.
-
Leveraging Latent Visual Reasoning in Silence
Latent visual reasoning improves multimodal models via training effects even without using latent tokens at inference, enabled by an attention-based RL reward that promotes interaction with text tokens.
-
Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Models
Foveated Reasoner integrates foveation as stateful actions inside the autoregressive decoding loop of vision-language models, trained via cold-start supervision then reinforcement learning to achieve higher accuracy a...
-
Video-ToC: Video Tree-of-Cue Reasoning
Video-ToC adds tree-guided cue localization, demand-based RL rewards, and automated datasets to video LLMs, reporting better results than prior methods on six understanding benchmarks plus a hallucination test.
-
DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning
DeFacto trains multimodal models with counterfactual image variants and GRPO reinforcement learning to enforce that correct answers are supported by correct visual evidence.
-
Semantic-Enriched Latent Visual Reasoning
SLVR enriches latent visual representations with fine-grained attribute semantics via supervised first-stage learning and multi-query alignment via M-GRPO, yielding improved robustness on region-level reasoning tasks.
-
Semantic-Enriched Latent Visual Reasoning
SLVR is a two-stage method that enriches region-centric latent representations with fine-grained attribute semantics and aligns them via M-GRPO across multiple queries on the same region, supported by new SLV-Set data...
-
Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence
A structured survey of multimodal code intelligence that formulates the field by code roles and organizes work into four domains while proposing verification-centered research directions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.