Haotian Tang
14 papers · 2019–2025 · 4 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 ↓+3 more ↓ Show less ↑
🗺️ Taxonomy Completionist (26) 🌉 Interdisciplinary Bridge · Bronze 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🤝 Dynamic Duo (13)
👥
Mega-Team · Squad
⚡
Prolific Year · Productive
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Deep Learning
(9)
Architectures
(7)
Artificial Intelligence
(6)
Computer Vision
(6)
Machine Learning
(6)
Application Areas
(6)
Core AI · Artificial Intelligence
(6)
Models
(4)
Generation
(3)
Optimization & Theory
(3)
Analysis
(2)
Techniques
(2)
Natural Language Processing
(1)
Core AI · Computer Vision
(1)
Domain-Specific
(1)
Keywords
image generation
(4)
visual language model
(3)
computational efficiency
(2)
point cloud
(2)
model compression
(2)
attention mechanism
(2)
semantic segmentation
(2)
foundation model
(2)
window attention
(2)
diffusion model
(2)
object detection
(2)
efficient computing
(2)
neural network optimization
(1)
video understanding
(1)
sparse attention
(1)
trajectory prediction
(1)
inference efficiency
(1)
latent diffusion
(1)
parameter-efficient fine-tuning
(1)
autoregressive generation
(1)
Papers
Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
ICLR 2025
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
ICLR 2025
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
ICLR 2025
LongVILA: Scaling Long-Context Visual Language Models for Long Videos
ICLR 2025
NVILA: Efficient Frontier Visual Language Models
CVPR 2025
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers
ICLR 2025
VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
ICLR 2025
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
ICLR 2024
MoST: Multi-Modality Scene Tokenization for Motion Prediction
CVPR 2024
Sparse Refinement for Efficient High-Resolution Semantic Segmentation
ECCV 2024
FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
CVPR 2023
SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer
CVPR 2023
Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
ECCV 2020
Point-Voxel CNN for Efficient 3D Deep Learning
NeurIPS 2019