Aligning Thoughts with Answers: Probability Rewards to Tame Thinking Drift
cs.CV
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- GPT-4 Technical Report
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- Qwen2.5-VL Technical Report
- UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning
- Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning
- MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
- OpenAI o1 System Card
- Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
- One RL to See Them All: Visual Triple Unified Reinforcement Learning
- VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
- RLPR: Extrapolating RLVR to General Domains without Verifiers
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models