14 citations · 31 across the 28 of their papers we have counts for
5 papers · 1 filter
PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition
Ziyan Gan, Fangxin Liu, Chenyang Guan +10
Mixture-of-Experts (MoE) architectures scale Large Language Model (LLM) capacity efficiently by activating a sparse subset of experts per token. However, modern MoE inference remai…
Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers
Hongzhan Lin, Zhiqi Bai, Xinmiao Zhang +10
Transformer decoders have achieved strong results across tasks, but the memory required for the KV cache becomes prohibitive at long sequence lengths. Although Cross-layer KV Cache…
Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
Yang Li, Zhichen Dong, Yuhan Sun +9
The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the dis…
DDK: Distilling Domain Knowledge for Efficient Large Language Models
Jiaheng Liu, Chenchen Zhang, Jinyang Guo +13
Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distil…
D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models
Haoran Que, Jiaheng Liu, Ge Zhang +13
Continual Pre-Training (CPT) on Large Language Models (LLMs) has been widely used to expand the model's fundamental understanding of specific downstream domains (e.g., math and cod…