arXiv (All)
open access
Aligning Thoughts with Answers: Probability Rewards to Tame Thinking Drift
This paper studies \textbf{thinking--answer consistency} in vision-language models. We focus on Visual Intention Grounding, where a model infers a target object based on a human intention query and predicts a bounding box. We reveal that previous IoU-based reinforcement learning (RL) frameworks suff
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models#1119117
- VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning#5993
- Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games#292667
- OODBench: Out-of-Distribution Benchmark for Large Vision-Language Models#614925
- OODBench: Out-of-Distribution Benchmark for Large Vision-Language Models#613958
Record · ID 1144150
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive