collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Geometric Self-Distillation for Reasoning Generalization

Josip Jukić, Ivan Titov

On-policy distillation is a practical post-training recipe for large language models, supplying dense teacher supervision on the student's own trajectories. In privileged-context s…

cs.LG2026

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: (…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

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…