GRIT: Gradient Masking for Visually Misgrounded Tokens in Text-Rich Reasoning
cs.CV, cs.AI, cs.CL
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: Accepted to WACV 2027
Code: https://github.com/chanseul01/GRIT
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen3-VL Technical Report
- SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning
- Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
- Self-Rewarding Vision-Language Model via Reasoning Decomposition
- A Survey on Hallucination in Large Vision-Language Models
- MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
- Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- OpenAI GPT-5 System Card
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models
- VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
- Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning
- Attention Heads of Large Language Models: A Survey
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