山下颯太

thomas-taylor's activity

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

liked a Space about 9 hours ago

Running on CPU Upgrade

1.47k

ProtectBirds

🏃

1.47k

Protect Birds

upvoted a paper about 18 hours ago

Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities

Paper • 2610.39301 • Published 3 days ago • 73

liked a model 3 days ago

tencent/Hy-SimulMT-30B-A3B-FP8

Translation • 30B • Updated 5 days ago • 1.14k • 458

liked a model 5 days ago

bytedance-research/Lance

Any-to-Any • Updated May 28 • 426 • 1.07k

upvoted a paper 9 days ago

Toward Recursive Self-Improvement in Physical AI

Paper • 2610.29677 • Published 11 days ago • 34

liked 7 models 9 days ago

nvidia/NVIDIA-Nemotron-Parse-v1.1

Image-Text-to-Text • 1.0B • Updated 11 days ago • 125k • 175

microsoft/xdoc-base-funsd

Token Classification • Updated Nov 16, 2022 • 109 • 8

facebook/mms-tts-bul

Text-to-Speech • 36.3M • Updated Sep 1, 2023 • 3.87k • 5

nvidia/Cosmos-Embed1-224p

1B • Updated Mar 12 • 230k • 22

microsoft/LLM2CLIP-Openai-L-14-224

Zero-Shot Classification • 0.6B • Updated Nov 19, 2024 • 166 • 10

google/tipsv2-b14

Zero-Shot Image Classification • 0.2B • Updated Aug 17 • 11.4k • 134

google/pegasus-arxiv

Summarization • Updated Jan 24, 2023 • 998 • 10

upvoted a paper 9 days ago

Jeva: System One Models from First Principles

Paper • 2610.18773 • Published 19 days ago • 376

liked 4 models 10 days ago

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16

Any-to-Any • 33B • Updated Aug 24 • 121k • 443

openai/whisper-large

Automatic Speech Recognition • 2B • Updated Feb 29, 2024 • 22.9k • 569

Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4

Text Generation • 33B • Updated Nov 18, 2024 • 1.27k • 32

Qwen/Qwen3-VL-2B-Thinking-FP8

Image-Text-to-Text • 2B • Updated Nov 26, 2025 • 1.08k • 38

upvoted 3 papers 13 days ago

FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

Paper • 2606.12087 • Published Jun 10 • 51

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Paper • 2607.06559 • Published Jul 7 • 46

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Paper • 2607.21461 • Published Jul 23 • 102