8 papers
Physics-Guided Policy Optimization with Self-Distillation
Ke Wang, Yuning Wu, Haoran Liu +3
Self-distilled policy optimization (SDPO) has become a popular paradigm for LLM post-training, where a model learns from its own predictions conditioned on privileged information.…
CyberCorrect: A Cybernetic Framework for Closed-Loop Self-Correction in Large Language Models
Yuning Wu, Yingmin Liu, Yang Shu
Large language model (LLM) self-correction -- the ability to detect and fix errors in generated outputs -- remains largely ad hoc, relying on generic prompts such as "please recons…
Hindsight-Anchored Policy Optimization: Learning Through Hindsight with Thompson Sampling-Inspired Adaptive Gating
Yuning Wu, Ke Wang, Haoran Liu +3
Reinforcement Learning with Verifiable Rewards improves reasoning in large language models, yet on-policy learning often suffers from cold-start challenges in sparse-reward setting…
R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoning
Wanlong Liu, Bo Zhang, Chenliang Li +4
While deep reasoning with long chain-of-thought has dramatically improved large language models in verifiable domains like mathematics, its effectiveness for open-ended tasks such…
UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities
Xuenan Xu, Jiahao Mei, Zihao Zheng +9
Audio generation, including speech, music and sound effects, has advanced rapidly in recent years. These tasks can be divided into two categories: time-aligned (TA) tasks, where ea…
Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning
Xuanyu Lei, Chenliang Li, Yuning Wu +7
Recent advances in Large Language Models(LLMs) have enabled strong performance in long-form writing, but current training paradigms remain limited: Supervised Fine-Tuning (SFT) rem…
QwenLong-CPRS: Towards -LLMs with Dynamic Context Optimization
Weizhou Shen, Chenliang Li, Fanqi Wan +12
This technical report presents QwenLong-CPRS, a context compression framework designed for explicit long-context optimization, addressing prohibitive computation overhead during th…
State Space Paradox of Computational Research in Creativity
Ömer Akin, Yuning Wu
This paper explores the paradoxical nature of computational creativity, focusing on the inherent limitations of closed digital systems in emulating the open-ended, dynamic process…