Tao Hongyuan

HongyuanTao's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 1 day ago

StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

Paper • 2609.26774 • Published 4 days ago • 30

upvoted 2 papers 7 days ago

Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation

Paper • 2609.20744 • Published 9 days ago • 50

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 9 days ago • 179

upvoted a paper 3 months ago

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

Paper • 2606.19195 • Published Jun 17 • 80

upvoted a paper 5 months ago

RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework

Paper • 2604.15308 • Published Apr 16 • 29

upvoted 2 papers 6 months ago

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Paper • 2604.05015 • Published Apr 6 • 232

UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving

Paper • 2604.02190 • Published Apr 2 • 26

upvoted a paper 7 months ago

Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning

Paper • 2602.21186 • Published Feb 24 • 5

upvoted 2 papers 9 months ago

DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

Paper • 2512.15713 • Published Dec 17, 2025 • 20

Towards Scalable Pre-training of Visual Tokenizers for Generation

Paper • 2512.13687 • Published Dec 15, 2025 • 108

upvoted a paper 10 months ago

InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models

Paper • 2512.08829 • Published Dec 9, 2025 • 23

upvoted 2 papers 12 months ago

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Paper • 2510.11696 • Published Oct 13, 2025 • 183

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Paper • 2508.18265 • Published Aug 25, 2025 • 222

upvoted a paper about 1 year ago

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning

Paper • 2507.13348 • Published Jul 17, 2025 • 80

upvoted 4 papers over 1 year ago

OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models

Paper • 2503.08686 • Published Mar 11, 2025 • 19

AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning

Paper • 2503.07608 • Published Mar 10, 2025 • 23

RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

Paper • 2502.13144 • Published Feb 18, 2025 • 38

Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation

Paper • 2502.13145 • Published Feb 18, 2025 • 38