PPaperPicks

Zhangyang Wang

University of Texas at Austin, Cockrell School of Engineering, TX, USA

84 papers at tracked venues · 74 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-2050-5693 ↗Google Scholar ↗Homepage ↗

Venues

CVPR ×17ICLR ×17ICML ×17NeurIPS ×16ACL ×3ECCV ×3AAAI ×2MLSys ×2WACV ×2AISTATS ×1EMNLP ×1IROS ×1VLDB ×1WWW ×1

Frequent coauthors

Peihao Wang
DBLP profile ↗ORCID search ↗
×5
Ruisi Cai
DBLP profile ↗ORCID search ↗
×4
Shijie Zhou
DBLP profile ↗ORCID search ↗
×3
Zhiwen Fan
DBLP profile ↗ORCID search ↗
×3
Yan Zheng
DBLP profile ↗ORCID search ↗
×2
Renjie Li
DBLP profile ↗ORCID search ↗
×2
Ajay Kumar Jaiswal
DBLP profile ↗ORCID search ↗
×2
Zhenyu Zhang
DBLP profile ↗ORCID search ↗
×2
Zhangheng Li
DBLP profile ↗ORCID search ↗
×2
Hongru Yang
DBLP profile ↗ORCID search ↗
×2
Junyuan Hong
DBLP profile ↗ORCID search ↗
×2
Lu Yin
DBLP profile ↗ORCID search ↗
×2

Papers

  1. FlowMorph: Revealing an Optimizable Flow Latent Space for Controlled Image Morphing
    WACV 2026 ·
    Yan Zheng
    DBLP profile ↗ORCID search ↗
  2. Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration
    ACL 2026 ·
    Jucheng Shen
    DBLP profile ↗ORCID search ↗
  3. Oscillation Inversion: Training-Free Image and Video Enhancement Through Oscillated Latents in Large Flow Models
    AAAI 2026 ·
    Yan Zheng
    DBLP profile ↗ORCID search ↗
  4. 4K4DGen: Panoramic 4D Generation at 4K Resolution
    ICLR 2025 ·
    Renjie Li
    DBLP profile ↗ORCID search ↗
  5. A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
    CVPR 2025 ·
    Wangbo Zhao
    DBLP profile ↗ORCID search ↗
  6. APOLLO: SGD-like Memory, AdamW-level Performance
    MLSys 2025 ·
    Hanqing Zhu
    DBLP profile ↗ORCID search ↗
  7. Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention
    ICML 2025 ·
    Dejia Xu
    DBLP profile ↗ORCID search ↗
  8. Copy or Not? Reference-Based Face Image Restoration with Fine Details
    WACV 2025 ·
    Min Jin Chong
    DBLP profile ↗ORCID search ↗
  9. Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
    NeurIPS 2025 ·
    Zhiyuan Liang
    DBLP profile ↗ORCID search ↗
  10. Efficient Image Generation with Variadic Attention Heads
    CVPR 2025 ·
    Steven Walton
    DBLP profile ↗ORCID search ↗
  11. Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields
    CVPR 2025 ·
    Shijie Zhou
    DBLP profile ↗ORCID search ↗
  12. FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting
    CVPR 2025 ·
    Hengyu Liu
    DBLP profile ↗ORCID search ↗
  13. From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications
    ICML 2025 ·
    Ajay Kumar Jaiswal
    DBLP profile ↗ORCID search ↗
  14. Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models
    NeurIPS 2025 ·
    Haoyu Wang
    DBLP profile ↗ORCID search ↗
  15. HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training
    ICML 2025 ·
    Geon-Woo Kim
    DBLP profile ↗ORCID search ↗
  16. HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models
    ICLR 2025 ·
    Hayk Manukyan
    DBLP profile ↗ORCID search ↗
  17. Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework
    MLSys 2025 ·
    Neel P. Bhatt
    DBLP profile ↗ORCID search ↗
  18. LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing
    ICLR 2025 ·
    Ruisi Cai
    DBLP profile ↗ORCID search ↗
  19. Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions
    NeurIPS 2025 ·
    Longfei Li
    DBLP profile ↗ORCID search ↗
  20. MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models
    EMNLP 2025 ·
    Shrey Pandit
    DBLP profile ↗ORCID search ↗
  21. On the Provable Separation of Scales in Maximal Update Parameterization
    ICML 2025 ·
    Letong Hong
    DBLP profile ↗ORCID search ↗
  22. On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving
    ICML 2025 ·
    Yeonju Ro
    DBLP profile ↗ORCID search ↗
  23. One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
    NeurIPS 2025 ·
    Mohan Zhang
    DBLP profile ↗ORCID search ↗
  24. PIPA: Preference Alignment as Prior-Informed Statistical Estimation
    ICML 2025 ·
    Junbo Li
    DBLP profile ↗ORCID search ↗
  25. R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
    ICLR 2025 ·
    Zhenyu Zhang
    DBLP profile ↗ORCID search ↗
  26. REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
    NeurIPS 2025 ·
    Ziqiao Wang
    DBLP profile ↗ORCID search ↗
  27. Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding
    ICML 2025 ·
    Jiajun Zhu
    DBLP profile ↗ORCID search ↗
  28. SAS: Simulated Attention Score
    NeurIPS 2025 ·
    Chuanyang Zheng
    DBLP profile ↗ORCID search ↗
  29. SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
    ICLR 2025 ·
    Tianjin Huang
    DBLP profile ↗ORCID search ↗
  30. Scaling Up Parameter Generation: A Recurrent Diffusion Approach
    NeurIPS 2025 ·
    Kai Wang
    DBLP profile ↗ORCID search ↗
  31. Sparse Transfer Learning Accelerates and Enhances Certified Robustness: A Comprehensive Study
    AAAI 2025 ·
    Zhangheng Li
    DBLP profile ↗ORCID search ↗
  32. Steepest Descent Density Control for Compact 3D Gaussian Splatting
    CVPR 2025 ·
    Peihao Wang
    DBLP profile ↗ORCID search ↗
  33. SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity
    AISTATS 2025 ·
    Peihao Wang
    DBLP profile ↗ORCID search ↗
  34. StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
    CVPR 2025 ·
    Roberto Henschel
    DBLP profile ↗ORCID search ↗
  35. Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement
    ACL 2025 ·
    Yaxuan Kong
    DBLP profile ↗ORCID search ↗
  36. Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow
    ICLR 2025 ·
    Hongru Yang
    DBLP profile ↗ORCID search ↗
  37. Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing
    ICLR 2025 ·
    Peihao Wang
    DBLP profile ↗ORCID search ↗
  38. AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
    NeurIPS 2024 ·
    Haiquan Lu
    DBLP profile ↗ORCID search ↗
  39. Compressing LLMs: The Truth is Rarely Pure and Never Simple
    ICLR 2024 ·
    Ajay Kumar Jaiswal
    DBLP profile ↗ORCID search ↗
  40. DGBD: Depth Guided Branched Diffusion for Comprehensive Controllability in Multi-View Generation
    CVPR 2024 ·
    Hovhannes Margaryan
    DBLP profile ↗ORCID search ↗
  41. DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
    ICLR 2024 ·
    Junyuan Hong
    DBLP profile ↗ORCID search ↗
  42. Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality
    ICLR 2024 ·
    Xuxi Chen
    DBLP profile ↗ORCID search ↗
  43. Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
    ICML 2024 ·
    Junyuan Hong
    DBLP profile ↗ORCID search ↗
  44. Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models
    NeurIPS 2024 ·
    Hanwen Liang
    DBLP profile ↗ORCID search ↗
  45. Doubly Robust Instance-Reweighted Adversarial Training
    ICLR 2024 ·
    Daouda Sow
    DBLP profile ↗ORCID search ↗
  46. DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting
    ECCV 2024 ·
    Shijie Zhou
    DBLP profile ↗ORCID search ↗
  47. Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day
    ICLR 2024 ·
    Yifan Jiang
    DBLP profile ↗ORCID search ↗
  48. Expressive Gaussian Human Avatars from Monocular RGB Video
    NeurIPS 2024 ·
    Hezhen Hu
    DBLP profile ↗ORCID search ↗
  49. FSGS: Real-Time Few-Shot View Synthesis Using Gaussian Splatting
    ECCV 2024 ·
    Zehao Zhu
    DBLP profile ↗ORCID search ↗
  50. Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
    CVPR 2024 ·
    Shijie Zhou
    DBLP profile ↗ORCID search ↗
  51. Flextron: Many-in-One Flexible Large Language Model
    ICML 2024 ·
    Ruisi Cai
    DBLP profile ↗ORCID search ↗
  52. Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models
    CVPR 2024 ·
    Gong Zhang
    DBLP profile ↗ORCID search ↗
  53. Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
    NeurIPS 2024 ·
    Zhenyu Zhang
    DBLP profile ↗ORCID search ↗
  54. GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
    ICML 2024 ·
    Jiawei Zhao
    DBLP profile ↗ORCID search ↗
  55. Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
    ICML 2024 ·
    Harry Dong
    DBLP profile ↗ORCID search ↗
  56. Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs "Difficult" Downstream Tasks in LLMs
    ICML 2024 ·
    Lu Yin
    DBLP profile ↗ORCID search ↗
  57. LLM-PBE: Assessing Data Privacy in Large Language Models
    VLDB 2024 ·
    Qinbin Li
    DBLP profile ↗ORCID search ↗
  58. LLaGA: Large Language and Graph Assistant
    ICML 2024 ·
    Runjin Chen
    DBLP profile ↗ORCID search ↗
  59. Large Spatial Model: End-to-end Unposed Images to Semantic 3D
    NeurIPS 2024 ·
    Zhiwen Fan
    DBLP profile ↗ORCID search ↗
  60. Latent 3D Graph Diffusion
    ICLR 2024 ·
    Yuning You
    DBLP profile ↗ORCID search ↗
  61. Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D
    CVPR 2024 ·
    Mukund Varma T.
    DBLP profile ↗ORCID search ↗
  62. LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
    NeurIPS 2024 ·
    Zhiwen Fan
    DBLP profile ↗ORCID search ↗
  63. LoCoCo: Dropping In Convolutions for Long Context Compression
    ICML 2024 ·
    Ruisi Cai
    DBLP profile ↗ORCID search ↗
  64. MM3DGS SLAM: Multi-modal 3D Gaussian Splatting for SLAM Using Vision, Depth, and Inertial Measurements
    IROS 2024 ·
    Lisong C. Sun
    DBLP profile ↗ORCID search ↗
  65. Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild
    NeurIPS 2024 ·
    Xinyu Zhao
    DBLP profile ↗ORCID search ↗
  66. NeRF as Pretraining at Scale: Generalizable 3D-Aware Semantic Representation Learning from View Prediction
    CVPR 2024 ·
    Wenyan Cong
    DBLP profile ↗ORCID search ↗
  67. OpenBias: Open-Set Bias Detection in Text-to-Image Generative Models
    CVPR 2024 ·
    Moreno D'Incà
    DBLP profile ↗ORCID search ↗
  68. Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
    ICML 2024 ·
    Lu Yin
    DBLP profile ↗ORCID search ↗
  69. PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor
    CVPR 2024 ·
    Vidit Goel
    DBLP profile ↗ORCID search ↗
  70. POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference
    CVPR 2024 ·
    Zhiwen Fan
    DBLP profile ↗ORCID search ↗
  71. Polynomial Width is Sufficient for Set Representation with High-dimensional Features
    ICLR 2024 ·
    Peihao Wang
    DBLP profile ↗ORCID search ↗
  72. Principled Architecture-aware Scaling of Hyperparameters
    ICLR 2024 ·
    Wuyang Chen
    DBLP profile ↗ORCID search ↗
  73. Prompt-Free Diffusion: Taking "Text" Out of Text-to-Image Diffusion Models
    CVPR 2024 ·
    Xingqian Xu
    DBLP profile ↗ORCID search ↗
  74. RankMean: Module-Level Importance Score for Merging Fine-tuned LLM Models
    ACL 2024 ·
    Gabriel J. Perin
    DBLP profile ↗ORCID search ↗
  75. Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
    NeurIPS 2024 ·
    Ruisi Cai
    DBLP profile ↗ORCID search ↗
  76. Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
    ICML 2024 ·
    Yihua Zhang
    DBLP profile ↗ORCID search ↗
  77. Safe and Robust Watermark Injection with a Single OoD Image
    ICLR 2024 ·
    Shuyang Yu
    DBLP profile ↗ORCID search ↗
  78. Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community
    ICLR 2024 ·
    Arman Isajanyan
    DBLP profile ↗ORCID search ↗
  79. Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once
    ICML 2024 ·
    Zhangheng Li
    DBLP profile ↗ORCID search ↗
  80. Taming Mode Collapse in Score Distillation for Text-to-3D Generation
    CVPR 2024 ·
    Peihao Wang
    DBLP profile ↗ORCID search ↗
  81. Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
    NeurIPS 2024 ·
    Hongru Yang
    DBLP profile ↗ORCID search ↗
  82. Turning A Curse into A Blessing: Data-Aware Memory-Efficient Training of Graph Neural Networks by Dynamic Exiting
    WWW 2024 ·
    Yan Han
    DBLP profile ↗ORCID search ↗
  83. VersatileGaussian: Real-Time Neural Rendering for Versatile Tasks Using Gaussian Splatting
    ECCV 2024 ·
    Renjie Li
    DBLP profile ↗ORCID search ↗
  84. Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis
    CVPR 2024 ·
    Marianna Ohanyan
    DBLP profile ↗ORCID search ↗