Tab Bab

Tabbab321

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

liked a Space 1 day ago

opendatalab/MinerU

upvoted a collection 1 day ago

View all activity

Organizations

None yet

upvoted a paper 1 day ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published 3 days ago • 82

liked a Space 1 day ago

MinerU Document Extraction Tools

Embedded MinerU document extraction demo

upvoted 2 collections 1 day ago

ACE

Ai2 Climate Emulator (ACE) is a family of fast ML models that simulate weather and climate variability over time scales from hours to centuries. • 14 items • Updated 1 day ago • 18

Papers I'm going to read

124 items • Updated 1 day ago • 8

upvoted a paper 1 day ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 3 days ago • 113

upvoted a collection 2 days ago

WeVisDoc

3 items • Updated 2 days ago • 9

liked 2 models 2 days ago

tencent/Hy-Embodied-VLM-1.0

Image-Text-to-Text • 31B • Updated Jul 15 • 616 • 26

yuhuili/EAGLE3-LLaMA3.1-Instruct-8B

Updated Sep 19, 2025 • 54.7k • 11

upvoted 2 articles 3 days ago

Article

ALTK‑Evolve: On‑the‑Job Learning for AI Agents

ibm-research

•

Apr 8

• 31

Article

Your Agent Aced the Task. Will It Do It Again?

ibm-research

•

5 days ago

• 83

upvoted a collection 3 days ago

MiniMax-H3-Lightx2v

5 items • Updated 25 days ago • 13

liked a model 3 days ago

lightx2v/Minimax-h3-Turbo

Image-to-Video • Updated 10 days ago • 1.54M • 969

liked a Space 3 days ago

MiniMax H3 Turbo LoRA

Video generation with a synchronized soundtrack

upvoted a paper 3 days ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published 13 days ago • 343

upvoted 2 collections 3 days ago

Knowledge

12 items • Updated 18 days ago • 3

Long context

65 items • Updated 4 days ago • 4

liked a Space 6 days ago

Qwen3-TTS Demo

Generate speech from text with voice design, cloning, or presets

liked a model 6 days ago

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4

Text Generation • 18B • Updated 10 days ago • 1.08M • 431

upvoted 2 collections 6 days ago

Switch-Transformers release

This release included various MoE (Mixture of expert) models, based on the T5 architecture . The base models use from 8 to 256 experts. • 9 items • Updated Jul 21 • 20

SEAHORSE release

The SEAHORSE metrics (as described in https://arxiv.org/abs/2305.13194). • 12 items • Updated Jul 21 • 22