Haofeng Huang

7 papers · 2024–2026 · 5 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 ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

ICML (3) AAAI (1) CVPR (1) ECCV (1) ICLR (1)

Top co-authors

Wenhan Yang (2) Jiaying Liu (2) Jintao Zhang (2) Jun Zhu (2) Jia wei (2) Jianfei Chen (2) Junxian Guo (1) Tianchen Zhao (1) Huazhong Yang (1) Li Yi (1)

Research topics

Deep Learning (6) Machine Learning (5) Computer Vision (4) Application Areas (4) Architectures (4) Generation (2) Learning Types · Deep Learning (2) Models (2) Processing (2) Artificial Intelligence (1) Core AI (1) Core Methods (1) Learning Types · Machine Learning (1)

Keywords

matrix multiplication (2) contrastive learning (1) image generation (1) domain adaptation (1) image restoration (1) video generation (1) video enhancement (1) self-supervised learning (1) sparsity (1) neural representation (1) memory optimization (1) vision foundation model (1) sparse attention (1) inference acceleration (1) video processing (1) diffusion transformer (1) model efficiency (1) block-sparse attention (1) low-light image enhancement (1) low-light video (1)

Papers

Towards Generalized Representations for Low-Light Understanding: When Signal Constancy Meets Semantic Enrichment CVPR 2026 SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization ICML 2025 SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference ICML 2025 ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation ICLR 2025 XAttention: Block Sparse Attention with Antidiagonal Scoring ICML 2025 FreeMotion: MoCap-Free Human Motion Synthesis with Multimodal Large Language Models ECCV 2024 Seeing Dark Videos via Self-Learned Bottleneck Neural Representation AAAI 2024