5 papers
EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning
Can Xie, Yuyi Zhou, Wen Yang +5
Reinforcement learning with outcome-based objectives such as GRPO enables LLM-based agents to solve complex, long-horizon tasks, yet the reusable exploration patterns embedded in i…
DialectS2S: End-to-End Speech Dialogue Modeling for Low-Resource Chinese Dialects
Yi Shu, Tianyu Peng, Yingzhuo Deng +5
Current end-to-end speech dialogue models are primarily optimized for mainstream languages and remain limited in low-resource dialect scenarios due to the scarcity of dialect speec…
AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment
Zhenlin Wei, Pu Jian, Yingzhuo Deng +6
The alignment of Large Language Models (LLMs) for complex reasoning heavily relies on Reinforcement Learning with Verifiable Rewards (RLVR). However, standard algorithms like GRPO…
TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment
Chong Li, Yingzhuo Deng, Wen Yang +2
Tokenization is a foundational step in the text process of Large Language Models (LLMs). Texts must be first tokenized into token IDs, which are then input to LLMs. Inefficient tok…
Group then Scale: Dynamic Mixture-of-Experts Multilingual Language Model
Chong Li, Yingzhuo Deng, Jiajun Zhang +1
The curse of multilinguality phenomenon is a fundamental problem of multilingual Large Language Models (LLMs), where the competition between massive languages results in inferior p…