影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
68.45/100
前 2.9%
全站排名 #1,865
发表论文17 篇
平均评分
年均产出5.7 篇/年
Jing Liu
研究方向
Efficient LLM · Efficient Learning · Network Quantization · Network Compression and Acceleration · Network Pruning
27
QVGen: Pushing the Limit of Quantized Video Generative Models
ICLR 2026Poster
三作17
Scaling Law for Quantization-Aware Training
ICLR 2026Rejected
三作20
Sparsity Forcing: Reinforcing Token Sparsity of MLLMs
ICLR 2026Poster
10
GatePro: Parameter-Free Expert Selection Optimization for Mixture-of-Experts Models
ICLR 2026Rejected
9
Balanced Actor Initialization: Stable RLHF Training of Distillation Reasoning Models
ICLR 2026Desk Rejected
5
HSA: Head-wise Sparse Attention for Efficient and Accurate Long-context Inference
ICLR 2026Withdrawn
一作-1
INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats
ICLR 2026Withdrawn
20
Model Merging in Pre-training of Large Language Models
NeurIPS 2025Poster
28
HarmoniCa: Harmonizing Training and Inference for Better Feature Cache in Diffusion Transformer Acceleration
ICLR 2025Rejected
19
Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher
ICLR 2025Poster
23
ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models
ICLR 2025Rejected
一作15
HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration
ICML 2025Poster
5
ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification and KV Cache Compression
ICLR 2025Withdrawn
三作