activity
20232026
most citedSource-Free Object Detection with Detection Transformer

6 citations · 12 across the 27 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2025

Fast Quiet-STaR: Thinking Without Thought Tokens

Wei Huang, Yizhe Xiong, Xin Ye +4

Large Language Models (LLMs) have achieved impressive performance across a range of natural language processing tasks. However, recent advances demonstrate that further gains parti…

cs.CL2025

Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts

Leiyu Pan, Zhenpeng Su, Minxuan Lv +10

Large language models have demonstrated exceptional performance across a wide range of tasks. However, dense models usually suffer from sparse activation, where many activation val…

cs.CL2025

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs

Minxuan Lv, Zhenpeng Su, Leiyu Pan +10

As large language models continue to scale, computational costs and resource consumption have emerged as significant challenges. While existing sparsification methods like pruning…

cs.CL2025

UniAttn: Reducing Inference Costs via Softmax Unification for Post-Training LLMs

Yizhe Xiong, Wei Huang, Xin Ye +6

Post-training is essential for adapting Large Language Models (LLMs) to real-world applications. Deploying post-trained models faces significant challenges due to substantial memor…

cs.CL2024

Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models

Haoran Lian, Junmin Chen, Wei Huang +8

Recently, Large language models (LLMs) have revolutionized Natural Language Processing (NLP). Pretrained LLMs, due to limited training context size, struggle with handling long tok…

cs.CL2024

LBPE: Long-token-first Tokenization to Improve Large Language Models

Haoran Lian, Yizhe Xiong, Zijia Lin +5

The prevalent use of Byte Pair Encoding (BPE) in Large Language Models (LLMs) facilitates robust handling of subword units and avoids issues of out-of-vocabulary words. Despite its…