EX
Enze Xie
cs.CVcs.AIcs.LGcs.CLcs.ROcs.GRAlgorithmscs.DCcs.NAeess.IV
On Valency
published · living versionsW_w39srt5b·v1 · currentpublished
PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data
with Kewei Zhang, Juncheng Ma, Guodong Lv, Duomin Wang +9
1 version
W_pf26rsgq·v1published
Preprints & journals
107 papers in the corpus · 2018–2026Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research2610.24944v1 · Yue Huang, Zhangchen Xu, Xiaonan Luo et al.2026 · 0 citationsarXivon Valency
Scaling Online Exploration for Robot Agents2610.22496v1 · Runhan Huang, Xiangcheng Zhang, Haoyu Chen et al.2026 · 0 citationsarXiv
SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video2609.37969v1 · Haozhe Liu, Tian Ye, Shuchen Xue et al.2026 · 0 citationsarXiv
Sol-H3: Recursive Self-Improvement for MiniMax-H3 Inference Acceleration on Sol-Engine across Cloud and Edge2609.35110v1 · Yitong Li, Jincheng Yu, Junsong Chen et al.2026 · 0 citationsarXiv
DraftAttention2: Fast Video Diffusion with Low-Resolution-Guided Mixed-Precision Attention2609.32628v1 · Rui Ding, Haopeng Li, Weize Ma et al.2026 · 0 citationsarXiv
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness2609.20519v1 · Haozhe Liu, Tian Ye, Sensen Gao et al.2026 · 0 citationsarXiv
Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification2607.24027v1 · Haopeng Li, Yitong Li, Junsong Chen et al.2026 · 0 citationsarXiv
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation2607.21553v1 · Junsong Chen, Jincheng Yu, Yitong Li et al.2026 · 0 citationsarXiv
Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding2607.05722v1 · Yonggan Fu, Lexington Whalen, Abhinav Garg et al.2026 · 0 citationsarXiv
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation2606.28128v1 · Peiwen Zhang, Yufan Deng, Shangkun Sun et al.2026 · 0 citationsarXiv
Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation2606.23743v2 · Yitong Li, Junsong Chen, Haopeng Li et al.2026 · 0 citationsarXiv
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining2606.20521v1 · Juncheng Ma, Jianxin Bi, Yufan Deng et al.2026 · 0 citationsarXiv
Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models2605.31158v3 · Jiacheng Lu, Haoyi Zhu, Sipei Yi et al.2026 · 0 citationsarXiv
SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer2605.30409v1 · Yuyang Zhao, Yicheng Pan, Qiyuan He et al.2026 · 0 citationsarXiv
Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving2605.23163v2 · Kewei Zhang, Jin Wang, Sensen Gao et al.2026 · 0 citationsarXiv
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation2605.18739v2 · Yukang Chen, Luozhou Wang, Wei Huang et al.2026 · 0 citationsarXiv
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer2605.15178v1 · Haoyi Zhu, Haozhe Liu, Yuyang Zhao et al.2026 · 0 citationsarXiv
Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM2604.06832v2 · Chengyue Wu, Shiyi Lan, Yonggan Fu et al.2026 · 0 citationsarXiv
FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling2604.06916v1 · Yitong Li, Junsong Chen, Shuchen Xue et al.2026 · 0 citationsarXiv
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head2601.07832v2 · Kewei Zhang, Ye Huang, Yufan Deng et al.2026 · 0 citationsarXiv
ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation2510.04290v2 · Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen et al.2025 · 0 citationsarXiv
Fast-dLLM v2: Efficient Block-Diffusion LLM2509.26328v1 · Chengyue Wu, Hao Zhang, Shuchen Xue et al.2025 · 0 citationsarXiv
DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space2509.25180v3 · Wenkun He, Yuchao Gu, Junyu Chen et al.2025 · 1 citationarXiv
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder2509.25182v1 · Junyu Chen, Wenkun He, Yuchao Gu et al.2025 · 0 citationsarXiv
LongLive: Real-time Interactive Long Video Generation2509.22622v2 · Shuai Yang, Wei Huang, Ruihang Chu et al.2025 · 0 citationsarXiv
DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space2508.00413v1 · Junyu Chen, Dongyun Zou, Wenkun He et al.2025 · 4 citationsarXiv
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer2507.04947v1 · Yecheng Wu, Junyu Chen, Zhuoyang Zhang et al.2025 · 1 citationarXiv
T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-Image Generation.40031217 · Huang, Kaiyi, Duan, Chengqi, Sun, Kaiyue et al.2025 · 63 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(5):3563-3579
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation2503.09641v4 · Junsong Chen, Shuchen Xue, Yuyang Zhao et al.2025 · 10 citationsarXiv
Magic 1-For-1: Generating One Minute Video Clips within One Minute2502.07701v3 · Hongwei Yi, Shitong Shao, Tian Ye et al.2025 · 0 citationsarXiv
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer2501.18427v4 · Enze Xie, Junsong Chen, Yuyang Zhao et al.2025 · 1 citationarXiv
Char-SAM: Turning Segment Anything Model into Scene Text Segmentation Annotator with Character-level Visual Prompts2412.19917v1 · Enze Xie, Jiaho Lyu, Daiqing Wu et al.2024 · 0 citationsarXiv
BEVFormer: Learning Bird's-Eye-View Representation From LiDAR-Camera Via Spatiotemporal Transformers.40030479 · Li, Zhiqi, Wang, Wenhai, Li, Hongyang et al.2025 · 300 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;PP
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models2411.05007v4 · Muyang Li, Yujun Lin, Zhekai Zhang et al.2024 · 3 citationsarXiv
Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline.38875097 · Li, Yangguang, Huang, Bin, Chen, Zeren et al.2024 · 93 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;46(12):8665-8679
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers2410.10629v3 · Enze Xie, Junsong Chen, Junyu Chen et al.2024 · 5 citationsarXiv
Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models2410.10733v8 · Junyu Chen, Han Cai, Junsong Chen et al.2024 · 3 citationsarXiv
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer2410.10812v1 · Haotian Tang, Yecheng Wu, Shang Yang et al.2024 · 1 citationarXiv
VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation2409.04429v3 · Yecheng Wu, Zhuoyang Zhang, Junyu Chen et al.2024 · 1 citationarXiv
Localization and recognition of human action in 3D using transformers.39227676 · Sun, Jiankai, Huang, Linjiang, Wang, Hongsong et al.2024 · 3 citationsCommunications engineering. 2024;3(1):125
Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Prompts2407.11382v2 · Jianhao Li, Tianyu Sun, Zhongdao Wang et al.2024 · 2 citationsarXiv
DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving2403.16996v1 · Tianqi Wang, Enze Xie, Ruihang Chu et al.2024 · 6 citationsarXiv
Editing Massive Concepts in Text-to-Image Diffusion Models2403.13807v1 · Tianwei Xiong, Yue Wu, Enze Xie et al.2024 · 0 citationsarXiv
PixArt-\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation2403.04692v2 · Junsong Chen, Chongjian Ge, Enze Xie et al.2024 · 113 citationsarXiv
Delving Into the Devils of Bird's-Eye-View Perception: A Review, Evaluation and Recipe.37976193 · Li, Hongyang, Sima, Chonghao, Dai, Jifeng et al.2024 · 175 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;46(4):2151-2170
Accelerating Diffusion Sampling with Optimized Time Steps2402.17376v3 · Shuchen Xue, Zhaoqiang Liu, Fei Chen et al.2024 · 28 citationsarXiv
AlgoFormer: An Efficient Transformer Framework with Algorithmic Structures2402.13572v2 · Yihang Gao, Chuanyang Zheng, Enze Xie et al.2024 · 0 citationsarXiv
Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation2401.15688v2 · Zhenyu Wang, Enze Xie, Aoxue Li et al.2024 · 2 citationsarXiv
PIXART-{\delta}: Fast and Controllable Image Generation with Latent Consistency Models2401.05252v1 · Junsong Chen, Yue Wu, Simian Luo et al.2024 · 3 citationsarXiv
SplatMesh: Interactive 3D Segmentation and Editing Using Mesh-Based Gaussian Splatting2312.15856v3 · Kaichen Zhou, Lanqing Hong, Xinhai Chang et al.2023 · 3 citationsarXiv
Career total: 122 works. 107 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.