PaperHub

Yunhe Wang

~Yunhe_Wang1

24
论文总数
12.0
年均投稿
5.7
平均评分
接收情况14/24
会议分布
ICLR
14
NeurIPS
6
ICML
4

发表论文 (24 篇)

202514 篇

6.8
5

SlimLLM: Accurate Structured Pruning for Large Language Models

ICML 2025Poster
7.0
4

Linear Multistep Solver Distillation for Fast Sampling of Diffusion Models

ICLR 2025Poster
6.8
4

DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation

ICLR 2025Poster
7.2
4

Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning

ICML 2025Poster
6.8
4

U-REPA: Aligning Diffusion U-Nets to ViTs

NeurIPS 2025Poster
4.3
4

Weak-to-Strong Enhanced Vision Model

ICLR 2025withdrawn
5.5
4

LLM Data Selection and Utilization via Dynamic Bi-level Optimization

ICML 2025Poster
4.4
5

Prompt-guided Visual Perception for Efficient Training-free Video LLM

ICLR 2025withdrawn
7.2
4

Mixture of Lookup Experts

ICML 2025Oral
4.0
4

GenVidBench: A Challenging Benchmark for Detecting AI-Generated Video

ICLR 2025withdrawn
5.7
3

SAN-Diff: Structure-aware noise for super-resolution diffusion model

ICLR 2025Rejected
5.0
5

Empirical Study on Enhancing Efficiency in Masked Image Modeling Pre-training

ICLR 2025Rejected
6.0
4

Multi-Granularity Semantic Revision for Large Language Model Distillation

ICLR 2025Rejected
7.6
5

CBQ: Cross-Block Quantization for Large Language Models

ICLR 2025Spotlight

202410 篇

4.0
4

Revisiting Ternary Neural Networks towards Asymmetric Thresholds and Uniform Distribution

ICLR 2024Rejected
4.8
4

PPT: Token Pruning and Pooling for Efficient Vision Transformers

ICLR 2024withdrawn
4.3
4

Connectivity-based Token Condensation for Efficient Vision Transformer

ICLR 2024withdrawn
5.0
4

Double Rounding Quantization for Flexible Deep Neural Network Compression

ICLR 2024withdrawn
5.5
4

U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers

NeurIPS 2024Poster
5.6
5

Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting

NeurIPS 2024Poster
6.3
4

Enhancing Large Language Models through Adaptive Tokenizers

NeurIPS 2024Poster
6.5
4

Multiscale Positive-Unlabeled Detection of AI-Generated Texts

ICLR 2024Spotlight
5.8
4

Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning

NeurIPS 2024Poster
6.0
4

MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers

NeurIPS 2024Poster
合作者 (20)