Profiles2021-2026
Peihao Wang
The University of Texas at Austin
22Papers
0Last author
51Unique co-authors
10First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers22
- ∇-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent SpaceAuthor 1 of 7ICLR 2026 · 5 citations
- Beyond Test-Time Memory: State-Space Optimal Control for LLM ReasoningAuthor 1 of 12ICML 2026
- CryoFastAR: Fast Cryo-EM AB Initio Reconstruction Made EasyAuthor 5 of 10ICCV 2025 · 2 citations
- Steepest Descent Density Control for Compact 3D Gaussian SplattingAuthor 1 of 12CVPR 2025
- Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothingAuthor 1 of 7ICLR 2025
- Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-DesignAuthor 4 of 7NeurIPS 2024 · 21 citations
- Polynomial Width is Sufficient for Set Representation with High-dimensional FeaturesAuthor 1 of 5ICLR 2024 · 9 citations
- Taming Mode Collapse in Score Distillation for Text-to-3D GenerationAuthor 1 of 11CVPR 2024 · 8 citations
- Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3DAuthor 2 of 7CVPR 2024 · 3 citations
- Vision HGNN: An Image is More than a Graph of NodesAuthor 2 of 5ICCV 2023 · 86 citations
- Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-ExpertsAuthor 3 of 8ICCV 2023 · 36 citations
- PINAT: A Permutation INvariance Augmented Transformer for NAS PredictorAuthor 3 of 8AAAI 2023 · 31 citations
- Data Efficient Neural Scaling Law via Model ReusingAuthor 1 of 3ICML 2023 · 18 citations
- Learning to Grow Pretrained Models for Efficient Transformer TrainingAuthor 1 of 9ICLR 2023 · 13 citations
- Equivariant Hypergraph Diffusion Neural OperatorsAuthor 1 of 5ICLR 2023 · 6 citations
- Is Attention All That NeRF Needs?Author 2 of 6ICLR 2023 · 6 citations
- Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to PracticeAuthor 1 of 4ICLR 2022 · 212 citations
- Signal Processing for Implicit Neural RepresentationsAuthor 2 of 4NeurIPS 2022 · 62 citations
- Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded AugmentationsAuthor 2 of 4CVPR 2022 · 32 citations
- CADTransformer: Panoptic Symbol Spotting Transformer for CAD DrawingsAuthor 3 of 4CVPR 2022 · 19 citations
- Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great AgainAuthor 2 of 6NeurIPS 2022 · 17 citations
- Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical SystemsAuthor 4 of 5NeurIPS 2021 · 13 citations
