collaborators

6 papers

cs.CV2026

Distill What RGB Can Recover: Privileged 3D Evidence for RGB-Only Vision-Language Models

Yanbin Hu, Jin Cui, Jun Ye +4

3D scene understanding requires reasoning about entity existence, spatial layout, and object relations, yet RGB images alone often provide insufficient 3D cues. Existing 3D-VLMs co…

cs.CL2026

"The Whole Is Greater Than the Sum of Its Parts": A Compatibility-Aware Multi-Teacher CoT Distillation Framework

Jin Cui, Jiaqi Guo, Ruixuan Yang +6

Chain-of-Thought (CoT) reasoning empowers Large Language Models (LLMs) with remarkable capabilities but typically requires prohibitive parameter scales. CoT distillation has emerge…

cs.CL2026

MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation

Jin Cui, Jiaqi Guo, Jiepeng Zhou +6

While Large Language Models (LLMs) have emerged with remarkable capabilities in complex tasks through Chain-of-Thought reasoning, practical resource constraints have sparked intere…

cs.CL2025

SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs

Haiduo Huang, Jiangcheng Song, Yadong Zhang +1

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of tea…

cs.LG2025

FastEagle: Cascaded Drafting for Accelerating Speculative Decoding

Haiduo Huang, Jiangcheng Song, Wenzhe Zhao +1

Speculative decoding accelerates generation by drafting candidates and verifying them in parallel, yet state-of-the-art drafters (e.g., EAGLE) still require N sequential passes to…

cs.CV2025

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer

Haiduo Huang, Jiangcheng Song, Yadong Zhang +1

Recent advances in knowledge distillation have emphasized the importance of decoupling different knowledge components. While existing methods utilize momentum mechanisms to separat…