ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking Paper β’ 2601.06487 β’ Published Jan 10 β’ 53
ChARM: Character-based Act-adaptive Reward Modeling for Advanced Role-Playing Language Agents Paper β’ 2505.23923 β’ Published May 29, 2025 β’ 8
OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction Paper β’ 2505.20277 β’ Published May 26, 2025
Improving Transformer World Models for Data-Efficient RL Paper β’ 2502.01591 β’ Published Feb 3, 2025 β’ 10
OpenOmni: Large Language Models Pivot Zero-shot Omnimodal Alignment across Language with Real-time Self-Aware Emotional Speech Synthesis Paper β’ 2501.04561 β’ Published Jan 8, 2025 β’ 17
MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct Paper β’ 2409.05840 β’ Published Sep 9, 2024 β’ 49
Text-Video Retrieval with Global-Local Semantic Consistent Learning Paper β’ 2405.12710 β’ Published May 21, 2024
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Paper β’ 2406.18629 β’ Published Jun 26, 2024 β’ 42