Profiles2024-2026ORCID 0000-0001-6951-901X
Huan Wang
Westlake University
17Papers
10Last author
19Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers17
- OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language ModelsAuthor 6 of 6CVPR 2026 · 32 citations
- OBS-Diff: Accurate Pruning For Diffusion Models in One-ShotAuthor 5 of 5ICLR 2026 · 26 citations
- Autoregressive Image Generation with Randomized Parallel DecodingAuthor 4 of 4ICLR 2026 · 19 citations
- ReasonMap: Towards Fine-Grained Visual Reasoning from Transit MapsAuthor 7 of 8CVPR 2026 · 19 citations
- MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal UnderstandingAuthor 5 of 5ICLR 2026 · 14 citations
- Which Heads Matter for Reasoning? RL-Guided KV Cache CompressionAuthor 5 of 5ICML 2026 · 11 citations
- SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-ShotAuthor 2 of 2ICML 2026 · 6 citations
- QVGGT: Post-Training Quantized Visual Geometry Grounded TransformerAuthor 3 of 3CVPR 2026 · 2 citations
- Cross-Resolution Diffusion Models Via Network PruningAuthor 3 of 3CVPR Findings 2026
- Prism-MoE: Efficient Dense-to-MoE Conversion for Visual Autoregressive GenerationAuthor 6 of 6ICML 2026
- HoliTom: Holistic Token Merging for Fast Video Large Language ModelsAuthor 6 of 6NeurIPS 2025 · 72 citations
- Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian SplattingAuthor 7 of 8NeurIPS 2025 · 9 citations
- FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware GuidanceAuthor 3 of 5NeurIPS 2025 · 6 citations
- Individual Content and Motion Dynamics Preserved Pruning for Video Diffusion ModelsAuthor 3 of 6ACM MM 2025 · 2 citations
- On-Device Diffusion Transformer Policy for Efficient Robot ManipulationAuthor 2 of 6ICCV 2025 · 1 citation
- DyCoke: Dynamic Compression of Tokens for Fast Video Large Language ModelsAuthor 5 of 6CVPR 2025
- Towards Real-time Video Compressive Sensing on Mobile DevicesAuthor 3 of 5ACM MM 2024 · 4 citations
