Tab Bab

Tabbab321's activity

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

upvoted 2 papers 2 days ago

Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

Paper • 2605.16928 • Published 9 days ago • 87

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

Paper • 2605.20315 • Published 6 days ago • 28

liked a model 2 days ago

nvidia/Nemotron-Labs-Diffusion-8B

Text Generation • 8B • Updated 2 days ago • 27.3k • 24

upvoted 4 papers 2 days ago

Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention

Paper • 2605.22791 • Published 4 days ago • 22

Toto 2.0: Time Series Forecasting Enters the Scaling Era

Paper • 2605.20119 • Published 6 days ago • 36

TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation

Paper • 2605.22355 • Published 4 days ago • 169

DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards

Paper • 2605.21467 • Published 5 days ago • 196

liked 2 Spaces 2 days ago

Running on Zero

Agents

28

L2P - Z-Image 6B Pixel-Space

🎨

28

End-to-end pixel-space 6B diffusion via L2P

Running on Zero

Agents

11

Lens

🔍

11

Microsoft Lens & Lens-Turbo — 3.8B text-to-image

upvoted a paper 2 days ago

LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning

Paper • 2605.22012 • Published 4 days ago • 42

upvoted 3 papers 3 days ago

π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

Paper • 2605.14678 • Published 6 days ago • 92

HRM-Text: Efficient Pretraining Beyond Scaling

Paper • 2605.20613 • Published 5 days ago • 21

Stitched Value Model for Diffusion Alignment

Paper • 2605.19804 • Published 6 days ago • 11

liked a model 3 days ago

CohereLabs/command-a-plus-05-2026-w4a4

Image-Text-to-Text • 126B • Updated 3 days ago • 5.63k • • 190

upvoted an article 3 days ago

view article

Article

LeRobot Humanoid: An Open, Low-Cost, 3D-Printed Humanoid for Robot Learning

• 

VirgileBatto

•

4 days ago

• 33

upvoted 3 papers 3 days ago

UniT: Unified Geometry Learning with Group Autoregressive Transformer

Paper • 2605.21131 • Published 5 days ago • 7

Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation

Paper • 2605.19833 • Published 6 days ago • 127

IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools

Paper • 2605.20682 • Published 5 days ago • 81

upvoted 2 collections 3 days ago

MambaVision

Collection

MambaVision: A Hybrid Mamba-Transformer Vision Backbone. Includes both 1K and 21K pretrained models. • 12 items • Updated 5 days ago • 37

BigVGAN

Collection

BigVGAN is a universal neural vocoder that generates audio waveform using mel spectrogram as input. • 11 items • Updated 5 days ago • 19