collaborators

6 papers

cs.CL2025

Power-Law Decay Loss for Large Language Model Finetuning: A Theory Perspective

Jintian Shao

During the finetuning stage of text generation tasks, standard cross-entropy loss treats all tokens equally. This can lead models to overemphasize high-frequency, low-information t…

cs.CL2025

Towards Analyzing and Understanding the Limitations of VAPO: A Theoretical Perspective

Jintian Shao, Yiming Cheng

Reinforcement learning (RL) enhances large language models (LLMs) in complex, long-chain-of-thought (long-CoT) reasoning. The advanced VAPO framework, despite sophisticated mechani…

cs.CL2025

CoT is Not True Reasoning, It Is Just a Tight Constraint to Imitate: A Theory Perspective

Jintian Shao, Yiming Cheng

Chain-of-Thought (CoT) prompting has demonstrably enhanced the performance of Large Language Models on tasks requiring multi-step inference. This success has led to widespread clai…

cs.LG2025

Towards Analyzing and Understanding the Limitations of VAPO: A Theoretical Perspective

Jintian Shao, Yiming Cheng, Hongyi Huang +4

The VAPO framework has demonstrated significant empirical success in enhancing the efficiency and reliability of reinforcement learning for long chain-of-thought (CoT) reasoning ta…

cs.LG2025

ComplexFormer: Disruptively Advancing Transformer Inference Ability via Head-Specific Complex Vector Attention

Jintian Shao, Hongyi Huang, Jiayi Wu +4

Transformer models rely on self-attention to capture token dependencies but face challenges in effectively integrating positional information while allowing multi-head attention (M…

cs.CL2025

VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits

Jintian Shao, Hongyi Huang, Jiayi Wu +4

Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their extensive output vocabularies. The…