Wangxinchao
Wangxinchao on Hugging Face Daily Papers: 19 papers, 5 in the top 3 of their day, 474 upvotes.
- Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps 23 upvotes, #15 of 2025-05-27
- Thinkless: LLM Learns When to Think 46 upvotes, #5 of 2025-05-20
- PE3R: Perception-Efficient 3D Reconstruction 8 upvotes, #23 of 2025-03-11
- Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling 4 upvotes, #21 of 2025-02-28
- Introducing Visual Perception Token into Multimodal Large Language Model 14 upvotes, #9 of 2025-02-26
- CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up 18 upvotes, #3 of 2024-12-23
- TinyFusion: Diffusion Transformers Learned Shallow 13 upvotes, #12 of 2024-12-03
- OminiControl: Minimal and Universal Control for Diffusion Transformer 41 upvotes, #2 of 2024-11-25
- MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models 43 upvotes, #1 of 2024-09-27
- Vista3D: Unravel the 3D Darkside of a Single Image 8 upvotes, #10 of 2024-09-19
- Kolmogorov-Arnold Transformer 34 upvotes, #2 of 2024-09-17
- IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation 14 upvotes, #5 of 2024-09-13
- FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally 8 upvotes, #9 of 2024-09-13
- MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities 10 upvotes, #7 of 2024-08-02
- KAN or MLP: A Fairer Comparison 36 upvotes, #2 of 2024-07-24
- Compositional Video Generation as Flow Equalization 12 upvotes, #7 of 2024-07-09
- Video-Infinity: Distributed Long Video Generation 25 upvotes, #5 of 2024-06-25
- AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising 10 upvotes, #10 of 2024-06-12
- DeepCache: Accelerating Diffusion Models for Free 23 upvotes, #4 of 2023-12-05
Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.