Aohan Zeng

Instruction-following is a fundamental ability of Large Language Models (LLMs), requiring their generated outputs to follow multiple constraints imposed in input instructions. Numerous studies have attempted to enhance this ability through preference optimization or reinforcement learning based o...

Data selection is a critical aspect of Reinforcement Learning with Verifiable Rewards (RLVR) for enhancing the reasoning capabilities of large language models (LLMs). Current data selection methods are largely heuristic-based, lacking theoretical guarantees and generalizability. This work propose...

Reinforcement learning (RL) is widely applied to boost the performance of pretrained models, yet its training efficiency is severely constrained by rollout generation. While speculative decoding based on multi-token prediction (MTP) offers a potential acceleration pathway, its widespread adoption...