collaborators

6 papers

cs.LG2026

Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation

Zhiwei Zhang, Zechen Sun, Fei Zhao +6

On-policy distillation (OPD) accelerates post-training by providing dense token-level supervision from a frozen teacher on the student's own rollouts. Vanilla OPD applies this supe…

cs.LG2026

D-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation

Zechen Sun, Zhiwei Zhang, Fei Zhao +7

Multi-teacher on-policy distillation (MOPD) distills several domain-expert teachers into a single student by minimizing per-domain reverse-KL divergence on the student's own rollou…

cs.CL2026

IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking

Zechen Sun, Yuyang Sun, Zecheng Tang +6

Generating coherent and controllable long-form content remains a persistent challenge for Large Language Models (LLMs). While reasoning-enhanced models have demonstrated success in…

cs.IR2026

QP-OneModel: A Unified Generative LLM for Multi-Task Query Understanding in Xiaohongshu Search

Jianzhao Huang, Xiaorui Huang, Fei Zhao +9

Query Processing (QP) bridges user intent and content supply in large-scale Social Network Service (SNS) search engines. Traditional QP systems rely on pipelines of isolated discri…

cs.CL2024

LOGO -- Long cOntext aliGnment via efficient preference Optimization

Zecheng Tang, Zechen Sun, Juntao Li +2

Long-context models(LCMs) have shown great potential in processing long input sequences(even more than 100M tokens) conveniently and effectively. With significant progress, recent…

cs.CL2024

OpenBA-V2: Reaching 77.3% High Compression Ratio with Fast Multi-Stage Pruning

Dan Qiao, Yi Su, Pinzheng Wang +18

Large Language Models (LLMs) have played an important role in many fields due to their powerful capabilities.However, their massive number of parameters leads to high deployment re…