2 citations · 3 across the 8 of their papers we have counts for
9 papers
Geometric Self-Distillation for Reasoning Generalization
Josip Jukić, Ivan Titov
On-policy distillation provides dense teacher supervision on a language model's own trajectories. In self-distillation with privileged context, this supervision comes from the mode…
The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits
Tianhao Cheng, Zeyu Huang, Zihan Qiu +5
A commonly accepted explanation of critic-free RL for LLMs, based on sequence-level rewards, is that it reinforces successful rollouts with a positive advantage while penalizing fa…
A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training
Zihan Qiu, Zeyu Huang, Kaiyue Wen +16
We investigate the functional role of emergent outliers in large language models, specifically attention sinks (a few tokens that consistently receive large attention logits) and r…
Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them
Neel Rajani, Aryo Pradipta Gema, Seraphina Goldfarb-Tarrant +1
Training large language models (LLMs) for reasoning via maths and code datasets has become a major new focus in LLM post-training. Two particularly popular approaches are reinforce…
Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling
Zeyu Huang, Tianhao Cheng, Zihan Qiu +4
Existing LLMs-post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT). Each paradigm presents a distinct trade-off: (…
A Controllable Examination for Long-Context Language Models
Yijun Yang, Zeyu Huang, Wenhao Zhu +4
Existing frameworks for evaluating long-context language models (LCLM) can be broadly categorized into real-world applications (e.g, document summarization) and synthetic tasks (e.…
Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
Zihan Qiu, Zeyu Huang, Bo Zheng +7
This paper revisits the implementation of oad-alancing oss (LBL) when training Mixture-of-Experts (MoEs) models. Specifically, LBL for MoEs is d…
Post-hoc Reward Calibration: A Case Study on Length Bias
Zeyu Huang, Zihan Qiu, Zili Wang +2
Reinforcement Learning from Human Feedback aligns the outputs of Large Language Models with human values and preferences. Central to this process is the reward model (RM), which tr…
Layerwise Recurrent Router for Mixture-of-Experts
Zihan Qiu, Zeyu Huang, Shuang Cheng +4
The scaling of large language models (LLMs) has revolutionized their capabilities in various tasks, yet this growth must be matched with efficient computational strategies. The Mix…