Get started
Author

Haocheng Xi

A benchmark of expert-level academic questions to assess AI capabilities
2026 · Long Phan, Alice Gatti, et al. · Nature · 185
PDF
NVILA: Efficient Frontier Visual Language Models
2025 · Zhijian Liu, Ligeng Zhu, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 73
PDF
Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
2025 · Xi, Haocheng, Yang, Shuo, et al. · arXiv (Cornell University) · 17
PDF
SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
2025 · Zhang, Jintao, Xiang, Chendong, et al. · arXiv (Cornell University) · 12
PDF
Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
2025 · Shuo Yang, Haocheng Xi, et al. · neural information processing systems · 7
Radial Attention: $\mathcal{O}(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation
2025 · XINGYANG LI, Muyang Li, et al. · neural information processing systems · 4
PDF
Oscillation-Reduced MXFP4 Training for Vision Transformers
2025 · Chen, Yuxiang, Xi, Haocheng, et al. · arXiv (Cornell University) · 3
PDF
Residual Context Diffusion Language Models
2026 · Hu, Yuezhou, Singh, Harman, et al. · arXiv (Cornell University) · 2
PDF
T-Rex: Text-assisted Retrosynthesis Prediction
2024 · Liu, Yifeng, Xu, Hanwen, et al. · arXiv (Cornell University) · 2
PDF
LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models
2026 · Xi, Haocheng, Singh, Harman, et al. · arXiv (Cornell University) · 1
PDF
SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
2026 · Zhang, Jintao, Jiang, Kai, et al. · arXiv (Cornell University) · 1
PDF
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
2026 · Xi, Haocheng, Yang, Shuo, et al. · arXiv (Cornell University) · 1
PDF
DC-Gen: Post-training Diffusion Acceleration with Deeply Compressed Latent Space
2026 · Wenkun He, Yuchao Gu, et al. · Lecture notes in computer science · 1
PDF
Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
2025 · Yuxian Gu, Qinghao Hu, et al. · neural information processing systems · 1
AWA-GCN: Enhancing Chinese sentiment analysis with a novel GCN model for Triplet and Quadruplet Extraction at SIGHAN 2024 dimABSA Task
2024 · Haocheng Xi, Yutong Wang, et al. · Applied and Computational Engineering · 1
Jet-QSparse: Accelerating Agentic LLM Inference with 4-Bit Sparse Attention
2026 · Tang, Haozhan, Kang, Hao, et al. · arXiv (Cornell University)
FrontierCS 2: A Benchmark for Computer Science R&D
2026 · Mang, Qiuyang, Chai, Wenhao, et al. · arXiv (Cornell University)
PDF
LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization
2026 · Pan, Yi, Xi, Haocheng, et al. · arXiv (Cornell University)
PDF
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
2026 · Xi, Haocheng, Xie, Yiming, et al. · arXiv (Cornell University)
PDF
VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention
2026 · Li, Xingyang, Zou, Dongyun, et al. · arXiv (Cornell University)
PDF
FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models
2026 · Xue, Bowen, Min, Zihan, et al. · arXiv (Cornell University)
PDF
Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow
2026 · Xi, Haocheng, Ruan, Charlie, et al. · arXiv (Cornell University)
PDF
SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing
2026 · Xuanyi Zhou, Qiuyang Mang, et al. · Lecture notes in computer science
PDF
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
2025 · Chen, Junyu, He, Wenkun, et al. · arXiv (Cornell University)
PDF
Works count: 25
Citation count: 314
H-index: 5
I10-index: 4
Year
Topic
Type