EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL
cs.CV, cs.AI
Submitted: 2026-11-04
Updated: 2026-11-17
Code: https://github.com/Tencent-Hunyuan/EmoReward
Project page: https://emoreward-project.github.io
Terminology
Sources
- OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
- GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
- MemoGen: Can Past Experience Improve Future Text-to-Image Generation?
- Rethinking Agentic Reinforcement Learning In Large Language Models
- Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement
- Flow-OPD: On-Policy Distillation for Flow Matching Models
- Gen-Searcher: Reinforcing Agentic Search for Image Generation
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Camera Artist: A Multi-Agent Framework for Cinematic Language Storytelling Video Generation
- VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation
- D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
- VisionCreator: A Native Visual-Generation Agentic Model with Understanding, Thinking, Planning and Creation
- Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference
- Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models
- JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
- JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization
- RouteLLM: Learning to Route LLMs with Preference Data
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
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