Hao Zhang
~Hao_Zhang2
21
论文总数
10.5
年均投稿
平均评分
接收情况11/21
会议分布
ICLR
14
NeurIPS
5
ICML
1
COLM
1
发表论文 (21 篇)
202511 篇
5
In-context KV-Cache Eviction for LLMs via Attention-Gate
ICLR 2025Rejected
3
MPC-Minimized Secure LLM Inference
ICLR 2025Rejected
4
Cost-Effective Synthetic Data Generation for Post-Training using QWICK
ICLR 2025Rejected
4
Scaling Speculative Decoding with Lookahead Reasoning
NeurIPS 2025Poster
4
Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile
ICLR 2025Rejected
4
GameArena: Evaluating LLM Reasoning through Live Computer Games
ICLR 2025Poster
4
Scaling Long Context Training Data by Long-Distance Referrals
ICLR 2025Poster
4
Fast Video Generation with Sliding Tile Attention
ICML 2025Poster
5
MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
ICLR 2025Poster
3
Faster Video Diffusion with Trainable Sparse Attention
NeurIPS 2025Poster
3
Efficiently Scaling LLM Reasoning Programs with Certaindex
NeurIPS 2025Poster
202410 篇
4
Evaluating the Robustness of Text-to-image Diffusion Models against Real-world Attacks
ICLR 2024Rejected
4
Sapling: $\underline{S}$uccessive $\underline{A}$daptation and Com$\underline{p}$ression with $\underline{L}$ayer Dropp$\underline{ing}$ for LLMs
ICLR 2024Rejected
4
Neural Eigenfunctions Are Structured Representation Learners
ICLR 2024Rejected
3
Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model
ICLR 2024Rejected
4
Efficient LLM Scheduling by Learning to Rank
NeurIPS 2024Poster
4
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
NeurIPS 2024Poster
4
Online Speculative Decoding
ICLR 2024Rejected
4
DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training
COLM 2024Poster
4
LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers
ICLR 2024Rejected
4
LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset
ICLR 2024Spotlight