PaperHub

Song Han

~Song_Han5

26
论文总数
13.0
年均投稿
6.4
平均评分
接收情况20/26
会议分布
ICLR
16
NeurIPS
6
ICML
4

发表论文 (26 篇)

202520

6.1
4

XAttention: Block Sparse Attention with Antidiagonal Scoring

ICML 2025Poster
6.8
4

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search

NeurIPS 2025Poster
6.0
4

COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training

ICLR 2025Poster
6.8
5

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

ICLR 2025Poster
7.5
5

Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning

NeurIPS 2025Spotlight
5.5
4

SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity

ICML 2025Poster
6.3
6

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

ICLR 2025Poster
4.8
4

X-VILA: Cross-Modality Alignment for Large Language Models

ICLR 2025withdrawn
4.5
4

VILA^2: VLM Augmented VLM with Self-Improvement

ICLR 2025withdrawn
6.8
5

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

ICLR 2025Poster
7.3
6

SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models

ICLR 2025Spotlight
8.5
4

SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers

ICLR 2025Oral
6.5
4

VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

ICLR 2025Poster
7.3
4

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

NeurIPS 2025Spotlight
7.2
4

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

ICML 2025Poster
6.1
4

Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

ICML 2025Poster
7.3
4

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation

NeurIPS 2025Poster
6.8
4

Scaling RL to Long Videos

NeurIPS 2025Poster
6.7
3

LongVILA: Scaling Long-Context Visual Language Models for Long Videos

ICLR 2025Poster
4.8
4

Wolf: Accurate Video Captioning with a World Summarization Framework

ICLR 2025withdrawn