Shengen Yan
10 papers · 2024–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (17) 💎 Century Club · Bronze ⚡ Prolific Year · Productive
📈
Trend Setter
Top co-authors
Research topics
Deep Learning
(6)
Machine Learning
(6)
Application Areas
(6)
Models
(5)
Artificial Intelligence
(4)
Architectures
(4)
Core AI
(4)
Computer Vision
(3)
Generation · Computer Vision
(3)
Optimization & Theory
(3)
Techniques
(2)
Natural Language Processing
(1)
Generation · Natural Language Processing
(1)
Learning Types
(1)
Keywords
diffusion transformer
(4)
post-training quantization
(3)
video generation
(3)
image generation
(2)
vision-language model
(2)
model compression
(2)
diffusion model
(2)
efficient computing
(2)
text-to-image generation
(1)
video understanding
(1)
feature similarity
(1)
computational efficiency
(1)
memory optimization
(1)
consistency model
(1)
kv cache quantization
(1)
evolutionary search
(1)
weight quantization
(1)
window attention
(1)
model merging
(1)
attention mechanism
(1)
Papers
DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers
ICCV 2025
DLFR-Gen: Diffusion-based Video Generation with Dynamic Latent Frame Rate
ICCV 2025
FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models
ICCV 2025
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
ICLR 2025
MBQ: Modality-Balanced Quantization for Large Vision-Language Models
CVPR 2025
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
ICLR 2025
ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction
NeurIPS 2024
DiTFastAttn: Attention Compression for Diffusion Transformer Models
NeurIPS 2024
Evaluating Quantized Large Language Models
ICML 2024
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
ECCV 2024