activity
20242026
collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation

Run Yang, Runpeng Dai, Jie Sun +5

Sampled-token on-policy distillation (OPD) efficiently transfers capabilities from teacher to student using student-generated tokens, requiring teacher probabilities only for sampl…

cs.CL2026

EasyOPD: An Easy-to-use On-Policy Distillation Framework for Large Language Models

Jie Sun, Mao Zheng, Mingyang Song +7

Conventional language-model distillation often relies on fixed teacher-generated data, which may not cover the states encountered by an evolving student policy. On-policy distillat…

cs.CL2026

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation

Jie Sun, Mao Zheng, Mingyang Song +6

On-policy distillation (OPD) is a standard tool for transferring teacher behavior to a smaller student, but it implicitly assumes that teacher and student predictions are comparabl…

cs.CL2026

SOD: Step-wise On-policy Distillation for Small Language Model Agents

Qiyong Zhong, Mao Zheng, Mingyang Song +5

Tool-integrated reasoning (TIR) is difficult to scale to small language models due to instability in long-horizon tool interactions and limited model capacity. While reinforcement…

cs.CL2026

SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs

Jie Sun, Yu Liu, Lu Han +9

While transformer-based Large Language Models (LLMs) theoretically support massive context windows, they suffer from severe performance degradation when processing long numerical s…

cs.CL2025

Robust Preference Optimization via Dynamic Target Margins

Jie Sun, Junkang Wu, Jiancan Wu +5

The alignment of Large Language Models (LLMs) is crucial for ensuring their safety and reliability in practical applications. Direct Preference Optimization (DPO) has emerged as an…