8 papers
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…
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…
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…
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…
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…
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…