Seeing Isn't Enough: Unlocking Visual Reasoning by Bridging the Reasoning-Access Gap with TIGER
cs.AI, cs.CV, cs.LG
Submitted: 2026-11-07
Updated: 2026-11-10
Code: https://github.com/minhngh/Tiger
Terminology
Sources
- LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Chain of Thought Prompt Tuning in Vision Language Models
- LLM Post-Training: A Deep Dive into Reasoning Large Language Models
- Silkie: Preference Distillation for Large Visual Language Models
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Gemma 4 Technical Report
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents