airlsyn

airlsyn's activity

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

upvoted a paper about 17 hours ago

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published 2 days ago • 64

liked a dataset about 21 hours ago

orbit-ai/orbit-20k

Viewer • Updated 5 days ago • 20.1k • 80 • 5

upvoted a paper 3 days ago

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

Paper • 2604.02190 • Published 6 days ago • 22

liked a dataset 8 days ago

nvidia/Privasis-Zero

Viewer • Updated 9 days ago • 1.3M • 217 • 7

liked a model 13 days ago

mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-NVFP4

Text Generation • 22B • Updated 19 days ago • 24.2k • 41

liked a dataset 14 days ago

UniParser/OmniScience

Viewer • Updated Mar 5 • 1.53M • 8.91k • 120

upvoted 2 papers 15 days ago

DFlash: Block Diffusion for Flash Speculative Decoding

Paper • 2602.06036 • Published Feb 5 • 45

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Paper • 2603.17024 • Published 21 days ago • 107

liked a model 15 days ago

JANGQ-AI/Mistral-Small-4-119B-A6B-JANG_2L

Text Generation • 12B • Updated 14 days ago • 1.42k • 5

liked a dataset 16 days ago

OpenSQZ/AutoMathText-V2

Viewer • Updated 6 days ago • 15.2B • 366k • 72

upvoted a paper 20 days ago

On Surprising Effectiveness of Masking Updates in Adaptive Optimizers

Paper • 2602.15322 • Published Feb 17 • 10

upvoted an article 28 days ago

view article

Article

Introducing Storage Buckets on the Hugging Face Hub

• 
• 
• +10

29 days ago

•

189

upvoted a paper 29 days ago

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

Paper • 2603.06569 • Published Mar 6 • 118

liked a dataset 30 days ago

TianHongZXY/CHIMERA

Viewer • Updated 28 days ago • 18.5k • 1.18k • 20

upvoted a paper 30 days ago

CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning

Paper • 2603.00889 • Published Mar 1 • 56

liked a model about 1 month ago

Qwen/Qwen3.5-2B-Base

Image-Text-to-Text • 2B • Updated Mar 2 • 77.4k • 64

liked a Space about 1 month ago

Running on Zero

32

Qwen 3.5 HF Demo

🤗

32

Demo of the Qwen 3.5 Multimodal Model

upvoted a paper about 1 month ago

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Paper • 2602.10604 • Published Feb 11 • 194

New activity in openbmb/MiniCPM-o-4_5 about 1 month ago

Seems like `chat(stream=True)` is broken — requires `do_sample=True` + `num_beams=1`, then crashes with `AttributeError: 'dict' object has no attribute 'sequences'`

3

#13 opened about 2 months ago by

Volotat

fix: stream in chat not return early

#16 opened about 1 month ago by

airlsyn