1 citations · 1 across the 10 of their papers we have counts for
12 papers
OMP-MoE: Efficient Expert Pruning for Mixture-of-Experts LLMs via Orthogonal Matching Pursuit
Dezhi Li, Lujun Li, Qiyuan Zhu +4
Mixture-of-Experts (MoE) models enable efficient scaling of large language models but face critical deployment challenges due to massive memory requirements. Existing pruning metho…
Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning
Qiyuan Zhu, Dezhi Li, Pengyu Cheng +8
Large Reasoning Models (LRMs) excel on complex tasks through long chain-of-thought (CoT) reasoning, but their lengthy intermediate steps cause severe overthinking that inflates inf…
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Xiang Hu, Xinyu Wei, Hao Gu +10
Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention. Chunk-wise sparse atten…
AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization
Haoran Gu, Handing Wang, Yi Mei +1
Expensive optimization tasks are ubiquitous in real-world applications, demanding highly specialized solvers. While LLM-driven automated solver generation shows promise, current pa…
IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference
Xintong Yang, Hao Gu, Binxing Xu +6
Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, qui…
Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs
Binxing Xu, Hao Gu, Lujun Li +8
Training LLMs at ultra-low precision remains a formidable challenge. Direct low-bit QAT often suffers from convergence instability and substantial training costs, exacerbated by qu…
QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch
Hao Gu, Hao Wang, Jiacheng Liu +9
Large language model (LLM) reinforcement learning (RL) pipelines are often bottlenecked by rollout generation, making end-to-end training slow. Recent work mitigates this by runnin…
Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models
Hao Wang, Hao Gu, Hongming Piao +6
The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while…
Discovering Transformer Circuits via a Hybrid Attribution and Pruning Framework
Hao Gu, Vibhas Nair, Amrithaa Ashok Kumar +2
Interpreting language models often involves circuit analysis, which aims to identify sparse subnetworks, or circuits, that accomplish specific tasks. Existing circuit discovery alg…
Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging
Lujun Li, Zhu Qiyuan, Jiacheng Wang +4
Mixture of Experts (MoE) LLMs face significant obstacles due to their massive parameter scale, which imposes memory, storage, and deployment challenges. Although recent expert merg…
BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook
Hao Gu, Lujun Li, Hao Wang +7
Binary quantization represents the most extreme form of compression, reducing weights to +/-1 for maximal memory and computational efficiency. While recent sparsity-aware binarizat…
Delta Decompression for MoE-based LLMs Compression
Hao Gu, Wei Li, Lujun Li +5
Mixture-of-Experts (MoE) architectures in large language models (LLMs) achieve exceptional performance, but face prohibitive storage and memory requirements. To address these chall…