17 citations · 42 across the 27 of their papers we have counts for
12 papers · 1 filter
RAQ-MLA: Role-Aware Quantization for Multi-Head Latent Attention Caches
Tianqi Chen, Xunchao Li, Linchuan Xie +4
Multi-Head Latent Attention (MLA) has been adopted by recent frontier large language models. Instead of per-head keys and values, MLA caches a compressed KV latent that is up-proje…
NormTune: Norm-Guided Parameter-Efficient Fine-Tuning for Reasoning-Intensive Tasks
Zhangming Li, Qinghao Hu, Weifan Guan +3
Full fine-tuning has achieved remarkable success on reasoning-intensive tasks, but it often requires substantial GPU resource consumption. Parameter-efficient fine-tuning (PEFT) pr…
Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning
Yuanteng Chen, Zhilei Liu, Peisong Wang +7
Quantization-aware distillation (QAD) restores much of the short-form question-answering performance lost to sub-3-bit quantization, yet leaves mathematical and code reasoning subs…
You Only Need 2/3 of the Chosen Experts: An Empirical Study of Dynamic Expert Pruning in Fine-Grained MoE LLMs
Yuanteng Chen, Qiwei Lai, Chen Tianqi +7
Fine-grained mixture-of-experts (MoE) architectures have become a mainstream design for open-weight LLMs, with hundreds of experts and increasingly many selected per token. This sh…
From Splats to Silicon: Rethinking Computational Efficiency of 3DGS
Minnan Pei, Qiwei Dong, Yihan Zhou +7
3D Gaussian splatting (3DGS) represents scenes with explicit primitives and supports real-time novel-view synthesis, yet its system efficiency varies substantially across scenes, v…
BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression
Yuantian Shao, Peisong Wang, Zhilei Liu +6
Large language models (LLMs) are increasingly constrained by memory capacity, weight bandwidth, and checkpoint storage during deployment. Existing low-bit compression methods mainl…
MODE: Modality-Decomposed Expert-Level Mixed-Precision Quantization for MoE Multimodal LLMs
Yuanteng Chen, Nanxin Zeng, Peisong Wang +9
Mixture-of-Experts Multimodal Large Language Models (MoE-MLLMs) offer remarkable performance but incur prohibitive GPU memory costs, making compression essential. Among PTQ methods…
Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation
Changwang Mei, Peisong Wang, Zekun Li +7
Visual Autoregressive (VAR) models deliver high-quality image generation but suffer from significant inference latency at high resolutions. Recent acceleration approaches most rely…
SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration
Zekun Li, Ning Wang, Tongxin Bai +4
Visual AutoRegressive (VAR) modeling has garnered significant attention for its innovative next-scale prediction paradigm. However, mainstream VAR paradigms attend to all tokens ac…
DALI: A Workload-Aware Offloading Framework for Efficient MoE Inference on Local PCs
Zeyu Zhu, Gang Li, Peisong Wang +5
Mixture of Experts (MoE) architectures significantly enhance the capacity of LLMs without proportional increases in computation, but at the cost of a vast parameter size. Offloadin…
IntraSlice: Towards High-Performance Structural Pruning with Block-Intra PCA for LLMs
Meng Li, Peisong Wang, Yuantian Shao +5
Large Language Models (LLMs) achieve strong performance across diverse tasks but face deployment challenges due to their massive size. Structured pruning offers acceleration benefi…
Certain Head, Uncertain Tail: Expert-Sample for Test-Time Scaling in Fine-Grained MoE
Yuanteng Chen, Peisong Wang, Nanxin Zeng +5
Test-time scaling improves LLM performance by generating multiple candidate solutions, yet token-level sampling requires temperature tuning that trades off diversity against stabil…