Michael Feldman

mfeldman143's activity

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

upvoted a paper about 1 hour ago

Behavior Knowledge Merge in Reinforced Agentic Models

Paper • 2601.13572 • Published 5 days ago • 21

upvoted a collection about 6 hours ago

Qwen3-TTS

Collection

7 items • Updated 2 days ago • 191

upvoted a paper about 16 hours ago

Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

Paper • 2601.16163 • Published 2 days ago • 9

liked 2 models 1 day ago

knowledgator/modern-gliner-bi-large-v1.0

Token Classification • Updated Feb 26, 2025 • 173 • 62

zai-org/GLM-4.7

Text Generation • 358B • Updated 17 days ago • 81.5k • • 1.79k

upvoted a collection 1 day ago

VibeVoice

Collection

Frontier Text-to-Speech Models https://microsoft.github.io/VibeVoice/ • 9 items • Updated 3 days ago • 197

upvoted a paper 1 day ago

VibeVoice Technical Report

Paper • 2508.19205 • Published Aug 26, 2025 • 143

liked 4 models 2 days ago

zai-org/GLM-4.7-Flash

Text Generation • 31B • Updated 4 days ago • 280k • • 1.11k

lightonai/LightOnOCR-2-1B

Image-Text-to-Text • 1B • Updated 3 days ago • 11.3k • 223

lightonai/LightOnOCR-2-1B-base

Image-Text-to-Text • 1B • Updated 3 days ago • 1.35k • 5

lightonai/LightOnOCR-0.9B-32k-1025

Updated 3 days ago • 461 • 17

upvoted a paper 2 days ago

LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR

Paper • 2601.14251 • Published 4 days ago • 21

liked 2 models 3 days ago

FlashLabs/Chroma-4B

Any-to-Any • 6B • Updated 3 days ago • 3.74k • 187

microsoft/VibeVoice-ASR

Automatic Speech Recognition • 9B • Updated 3 days ago • 6.97k • 418

upvoted a paper 3 days ago

Language of Thought Shapes Output Diversity in Large Language Models

Paper • 2601.11227 • Published 8 days ago • 7

liked a model 3 days ago

nvidia/bigvgan_v2_44khz_128band_512x

Audio-to-Audio • Updated Sep 5, 2024 • 492k • 66

liked a Space 3 days ago

Running

Featured

113

BigVGAN

🔊

113

Generate high-quality audio from input audio

upvoted a collection 3 days ago

BigVGAN

Collection

BigVGAN is a universal neural vocoder that generates audio waveform using mel spectrogram as input. • 11 items • Updated 4 days ago • 16

liked a dataset 3 days ago

nvidia/PhysicalAI-Autonomous-Vehicles

Updated 3 days ago • 167k • 713

liked a model 4 days ago

microsoft/OptiMind-SFT

Text Generation • 21B • Updated 9 days ago • 809 • 60