3 citations · 7 across the 14 of their papers we have counts for
15 papers
Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors
Yuchen Cai, Ding Cao, Qixiang Yin +10
Reinforcement learning (RL) has become a key paradigm for enhancing the reasoning of large language models, yet the high dimensionality of parameter updates makes its training dyna…
Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms
Siye Wu, Kai Yang, Yuchen Cai +8
Reinforcement learning with verifiable rewards (RLVR) improves specific capabilities of large language models, but covering multiple capabilities often involves training separate d…
GCPO: Diagnosing and Constraining Subspace Geometry in Rollout RL for LLMs
Kai Yang, Jingwei Xu, Wanyu Wang +4
On-policy rollout methods such as GRPO are central to post-training of large language models, yet they frequently suffer from training instabilities, cross-task capability degradat…
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
Yuchen Cai, Ding Cao, Liang Lin +9
On-policy distillation (OPD) has emerged as an efficient post-training paradigm for large language models. However, existing studies largely attribute this advantage to denser and…
Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
Yun Qu, Qi Wang, Yixiu Mao +11
Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for large language models (LLMs) post-training to incentivize reasoning capacity. Among existin…
Debiased Model-based Representations for Sample-efficient Continuous Control
Jiafei Lyu, Zichuan Lin, Scott Fujimoto +5
Model-based representations recently stand out as a promising framework that embeds latent dynamics information into the representations for downstream off-policy actor-critic lear…
C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving
Kefei Tian, Yuansheng Lian, Kai Yang +2
Safety-critical planning in complex environments, particularly at urban intersections, remains a fundamental challenge for autonomous driving. Existing methods, whether rule-based…
LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models
Boyang Shen, Kaixiang Yang, Hao Wang +4
Current Vision-Language-Action (VLA) models typically treat the deepest representation of a vision-language backbone as universally optimal for action prediction. However, robotic…
Exploration by Random Distribution Distillation
Zhirui Fang, Kai Yang, Jian Tao +4
Exploration remains a critical challenge in online reinforcement learning, as an agent must effectively explore unknown environments to achieve high returns. Currently, the main ex…
Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning
Yangkun Chen, Kai Yang, Jian Tao +1
Recently, deep Multi-Agent Reinforcement Learning (MARL) has demonstrated its potential to tackle complex cooperative tasks, pushing the boundaries of AI in collaborative environme…
A Two-stage Reinforcement Learning-based Approach for Multi-entity Task Allocation
Aicheng Gong, Kai Yang, Jiafei Lyu +1
Task allocation is a key combinatorial optimization problem, crucial for modern applications such as multi-robot cooperation and resource scheduling. Decision makers must allocate…
CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning
Zeyuan Liu, Kai Yang, Xiu Li
Distribution shift is a major obstacle in offline reinforcement learning, which necessitates minimizing the discrepancy between the learned policy and the behavior policy to avoid…
BATON: Aligning Text-to-Audio Model with Human Preference Feedback
Huan Liao, Haonan Han, Kai Yang +7
With the development of AI-Generated Content (AIGC), text-to-audio models are gaining widespread attention. However, it is challenging for these models to generate audio aligned wi…
Exploration and Anti-Exploration with Distributional Random Network Distillation
Kai Yang, Jian Tao, Jiafei Lyu +1
Exploration remains a critical issue in deep reinforcement learning for an agent to attain high returns in unknown environments. Although the prevailing exploration Random Network…
Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model
Kai Yang, Jian Tao, Jiafei Lyu +6
Using reinforcement learning with human feedback (RLHF) has shown significant promise in fine-tuning diffusion models. Previous methods start by training a reward model that aligns…