8 papers
How Does Local Landscape Geometry Evolve in Language Model Pre-Training?
Zhanpeng Zhou, Yuhan Sun, Bingrui Li +4
The scale and expense of pre-training language models make efficient hyperparameter tuning essential, yet a principled guidance is still missing. In this work, we analyze language…
Visual sensitivity is not claim retractability: persistence-aware credit assignment for multimodal reinforcement learning
Zhongan Bi, Kepeng Lin, Xuanang Gao +2
Reinforcement Learning with Verifiable Rewards (RLVR) has been extended to Large Vision-Language Models (LVLMs), and perception-aware methods further encourage policies to rely on…
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs
Zhichen Dong, Yang Li, Yuhan Sun +9
Token-level credit assignment remains a key obstacle for reinforcement learning (RL) in large language models (LLMs), where RL recipes typically treat all tokens equally, failing t…
A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms
Kejin Yu, Yuhan Sun, Taiqiang Wu +5
The development of high-level autonomous driving (AD) is shifting from perception-centric limitations to a more fundamental bottleneck, namely, a deficit in robust and generalizabl…
LiveThinking: Enabling Real-Time Efficient Reasoning for AI-Powered Livestreaming via Reinforcement Learning
Yuhan Sun, Zhiwei Huang, Wanqing Cui +4
In AI-powered e-commerce livestreaming, digital avatars require real-time responses to drive engagement, a task for which high-latency Large Reasoning Models (LRMs) are ill-suited.…
Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
Yang Li, Zhichen Dong, Yuhan Sun +9
The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the dis…
Technical Report of TeleChat2, TeleChat2.5 and T1
Zihan Wang, Xinzhang Liu, Yitong Yao +35
We introduce the latest series of TeleChat models: \textbf{TeleChat2}, \textbf{TeleChat2.5}, and \textbf{T1}, offering a significant upgrade over their predecessor, TeleChat. Despi…
To be or not to be? an exploration of continuously controllable prompt engineering
Yuhan Sun, Mukai Li, Yixin Cao +4
As the use of large language models becomes more widespread, techniques like parameter-efficient fine-tuning and other methods for controlled generation are gaining traction for cu…