LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?
Paper • 2605.08985 • Published • 21
airlsyn
airlsyn
AI & ML interests
AI & RL
Recent Activity
liked a dataset 1 day ago
GD-ML/TransitLM liked a dataset 4 days ago
zhifeixie/Voices-in-the-Wild-2M liked a dataset 4 days ago
witcheer/local-agentic-coding-bench-8gb-vram-2026-05Organizations
upvoted a paper 13 days ago
upvoted 2
papers 14 days ago
upvoted a paper 23 days ago
upvoted a paper 25 days ago
upvoted 2
papers about 1 month ago
upvoted an article about 1 month ago
Article
You could have designed state of the art positional encoding
FL33TW00D-HF
• • 481 upvoted 2
papers about 2 months ago
upvoted 3
papers 2 months ago
DFlash: Block Diffusion for Flash Speculative Decoding
Paper • 2602.06036 • Published • 81
HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
Paper • 2603.17024 • Published • 110
On Surprising Effectiveness of Masking Updates in Adaptive Optimizers
Paper • 2602.15322 • Published • 11
upvoted an article 3 months ago
Article
Introducing Storage Buckets on the Hugging Face Hub
- +10
Wauplin, coyotte508, XciD, victor, julien-c, lhoestq, pierric, Sylvestre, hlarcher, rajatarya, seanses, assafvayner
• • 194 upvoted 4
papers 3 months ago
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
Paper • 2603.06569 • Published • 120
CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning
Paper • 2603.00889 • Published • 56
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Paper • 2602.10604 • Published • 199
DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning
Paper • 2602.16742 • Published • 12
upvoted a collection 3 months ago
upvoted a paper 3 months ago