Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing
cs.AI
Submitted: 2026-05-06
Updated: 2026-09-25
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding
- A Survey on Evaluation of Large Language Models
- The Oscars of AI Theater: A Survey on Role-Playing with Language Models
- Progressive Supernet Training for Efficient Visual Autoregressive Modeling
- Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO
- VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
- VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
- CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards
- Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
- Video-R1: Reinforcing Video Reasoning in MLLMs
- S$^3$: Social-network Simulation System with Large Language Model-Empowered Agents
- Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
- Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning
- DeepStory: Video Story QA by Deep Embedded Memory Networks
- ChatHaruhi: Reviving Anime Character in Reality via Large Language Model
- Generative Agents: Interactive Simulacra of Human Behavior
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection