arXiv (All)
open access
Token-Level Video Reinforcement Learning
Reinforcement learning (RL) for video generation usually assigns one scalar reward to an entire sampled video. Yet a video is not uniformly flawed: some visual tokens may already satisfy the prompt, whereas others require correction. A scalar reward cannot localize errors, causing optimization to pe
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
- Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning#1117430
- Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning#1118668
- Visual sensitivity is not claim retractability: persistence-aware credit assignment for multimodal reinforcement learning#1131773
- TTRSD: Test-Time Reinforcement Learning with Self-Distillation for Vision-Language Models#1118126
- Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Object Category-agnostic Temporal Localization#1048693
Record · ID 1157321
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