EVAThink: Evidence Sufficiency-Guided Training for Adaptive Thinking in Video Understanding
cs.CV
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- Qwen3-VL Technical Report
- LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Video Evidence to Reasoning Efficient Video Understanding via Explicit Evidence Grounding
- Video-FLAIR: Not Whether to Reason, But How
- Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
- PhysBrain 1.0 Technical Report
- VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
- SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- AdaThinkV: Adaptive Thinking for Token-Efficient Video Reasoning
- AdapThink: Adaptive Thinking Preferences for Reasoning Language Model
- DynaSolidGeo: A Dynamic Benchmark for Genuine Spatial Mathematical Reasoning of VLMs in Solid Geometry
- ScalSelect: Scalable Training-Free Multimodal Data Selection for Efficient Visual Instruction Tuning
- REVEAL: A Rubric-Guided Agent for Explicit Evidence Sufficiency Verificationin Long-Video Question Answering
- When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
- LLaVA-Video: Video Instruction Tuning With Synthetic Data
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