collaborators

8 papers

cs.LG2026

Post-Trained MoE Can Skip Half Experts via Self-Distillation

Xingtai Lv, Li Sheng, Kaiyan Zhang +12

Mixture-of-Experts (MoE) scales language models efficiently through sparse expert activation, and its dynamic variant further reduces computation by adjusting the activated experts…

cs.CL2026

Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation

Bing Wang, Shaotian Yan, Chen Shen +7

Large language models (LLMs) have achieved remarkable success in complex reasoning tasks via long chain-of-thought (CoT), yet their immense computational overhead hinders real-worl…

cs.CL2026

Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection

Bing Wang, Rui Miao, Ximing Li +6

The rapid spread of misinformation on social media platforms has become a formidable challenge. To mitigate its proliferation, Misinformation Detection (MD) has emerged as a critic…

cs.CL2026

AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs

Wenxiang Lin, Juntao Huang, Luhan Zhang +5

Quantization is a key method for reducing the GPU memory requirement of training large language models (LLMs). Yet, current approaches are ineffective for 4-bit activations and 8-b…

cs.CL2026

UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification

Qihang Fan, Huaibo Huang, Zhiying Wu +2

As large language models (LLMs) continue to advance rapidly, they are becoming increasingly capable while simultaneously demanding ever-longer context lengths. To improve the infer…

cs.CL2026

FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling

Qihang Fan, Huaibo Huang, Zhiying Wu +3

Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-in…