2 citations · 2 across the 5 of their papers we have counts for
7 papers
Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective
Han Cui, Jianhao Yan, Yun Luo +3
On-policy distillation (OPD) has become an important approach to language model post-training. However, despite its performance gains, OPD can also collapse into excessively long a…
FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation
Guangsheng Bao, Hongbo Zhang, Han Cui +4
Adapting pretrained models typically involves a trade-off between the high training costs of backpropagation and the heavy inference overhead of memory-based or in-context learning…
Detecting RLVR Training Data via Structural Convergence of Reasoning
Hongbo Zhang, Yue Yang, Jianhao Yan +2
Reinforcement learning with verifiable rewards (RLVR) is central to training modern reasoning models, but the undisclosed training data raises concerns about benchmark contaminatio…
Deep Literature Survey Automation with an Iterative Workflow
Hongbo Zhang, Han Cui, Yidong Wang +6
Automatic literature survey generation has attracted increasing attention, yet most existing systems follow a one-shot paradigm, where a large set of papers is retrieved at once an…
Correlation or Causation: Analyzing the Causal Structures of LLM and LRM Reasoning Process
Zhizhang FU, Guangsheng Bao, Hongbo Zhang +2
LLMs suffer from critical reasoning issues such as unfaithfulness, bias, and inconsistency, since they lack robust causal underpinnings and may rely on superficial correlations rat…
Constrain Alignment with Sparse Autoencoders
Qingyu Yin, Chak Tou Leong, Minjun Zhu +7
The alignment of large language models (LLMs) with human preferences remains a key challenge. While post-training techniques like Reinforcement Learning from Human Feedback (RLHF)…
CycleResearcher: Improving Automated Research via Automated Review
Yixuan Weng, Minjun Zhu, Guangsheng Bao +4
The automation of scientific discovery has been a long-standing goal within the research community, driven by the potential to accelerate knowledge creation. While significant prog…