Michael Feldman

mfeldman143's activity

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

upvoted an article 2 days ago

view article

Article

Extremely Fast and Accurate Transcription with Granite Speech 5.0 Turbo CTC

• 

ibm-granite

•

Aug 25

• 38

upvoted a paper 3 days ago

SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model

Paper • 2610.11361 • Published 16 days ago • 47

upvoted a paper 4 days ago

Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning

Paper • 2610.23181 • Published 8 days ago • 54

upvoted an article 8 days ago

view article

Article

Welcome FLUX.3 Image Klein in Diffusers

• 
• 
• +1

ariG23498, sayakpaul, linoyts

•

9 days ago

• 49

upvoted a paper 12 days ago

Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute

Paper • 2610.10845 • Published 17 days ago • 11

upvoted a paper 18 days ago

When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models

Paper • 2610.05719 • Published 19 days ago • 35

upvoted a paper 23 days ago

LEGO-Anything: Coding Agents for 3D Scene Reconstruction

Paper • 2609.36380 • Published 26 days ago • 104

upvoted a collection 29 days ago

FLUX 3 Action

Collection

Open weights 7B world action model: base and shared encoders, SO-101 and DROID policies. Code: https://github.com/black-forest-labs/flux-action • 3 items • Updated 22 days ago • 46

upvoted an article 29 days ago

view article

Article

**Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization**

• 

nvidia

•

about 1 month ago

• 71

upvoted a collection about 1 month ago

Qwen-Scope

Collection

16 items • Updated May 14 • 80

upvoted a collection about 2 months ago

NeoMME

Collection

Meet NeoMME: a family of 260M and 800M Multimodal-Native Multilingual Encoders • 12 items • Updated 26 days ago • 33

upvoted an article about 2 months ago

view article

Article

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

• 
• 
• +1

iamleonie, burtenshaw, sergiopaniego

•

Sep 3

• 154

upvoted 2 papers about 2 months ago

Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling

Paper • 2608.30821 • Published Aug 31 • 119

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published Aug 20 • 221

upvoted an article 2 months ago

view article

Article

Up to 3.2x Faster Inference with LFM2.5-DSpark

• 

LiquidAI

•

Aug 20

• 62

upvoted 4 papers 2 months ago

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published Aug 10 • 122

PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives

Paper • 2608.13552 • Published Aug 13 • 49

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

Paper • 2504.18904 • Published Apr 26, 2025 • 10

RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies

Paper • 2604.09860 • Published Apr 14 • 9

upvoted a collection 2 months ago

Bonsai 27B

Collection

10 items • Updated Jul 15 • 253