Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models
cs.CV, cs.AI, cs.LG
Submitted: 2026-05-12
Updated: 2026-11-11
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
- GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning
- Visual Enhanced Depth Scaling for Multimodal Latent Reasoning
- Training Large Language Models to Reason in a Continuous Latent Space
- Vision-aligned Latent Reasoning for Multi-modal Large Language Model
- Latent Visual Reasoning
- Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
- Latent Implicit Visual Reasoning
- SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm
- Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
- Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
- OpenAI GPT-5 System Card
- Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers
- Gemma 3 Technical Report
- Attention Residuals
- Monet: Reasoning in Latent Visual Space Beyond Images and Language
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs