Gibran Iqbal

Jibbscript's activity

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

upvoted an article 2 days ago

view article

Article

Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL

• 
• 
• +2

aminediroHF, qgallouedec, kashif, sergiopaniego

•

15 days ago

• 52

upvoted 2 collections 2 days ago

⛵ Vela 1.0

Collection

The model family for intelligent routing. • 16 items • Updated 2 days ago • 24

🎲 Decision 1.0

Collection

Open Decision Foundation Models • 7 items • Updated 2 days ago • 14

upvoted 2 papers 3 days ago

Hyper3-CLIP: Hierarchy-Conditioned Hyperbolic Vision-Language Training

Paper • 2608.29313 • Published 27 days ago • 3

EvoOntology: A Self-Evolving Ontology Layer for Data Agents

Paper • 2609.15779 • Published 11 days ago • 150

upvoted a paper 5 days ago

Self-Evolving Search Index

Paper • 2609.19656 • Published 8 days ago • 60

upvoted a collection 5 days ago

jina-ocr-v1

Collection

2 items • Updated 7 days ago • 5

upvoted a paper 5 days ago

Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards

Paper • 2609.03181 • Published 23 days ago • 11

upvoted a collection 6 days ago

Bonsai-2

Collection

4 items • Updated 7 days ago • 147

upvoted a paper 7 days ago

The Router Within: Eliciting Native Skill Routing from a Frozen LLM

Paper • 2609.15982 • Published 11 days ago • 8

upvoted an article 9 days ago

view article

Article

One sandbox per rollout, or how labs run RL for agents in 2026

• 

sergiopaniego

•

13 days ago

• 10

upvoted 5 papers 9 days ago

StepAudio 3 Gen Technical Report

Paper • 2609.12945 • Published 14 days ago • 100

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

Paper • 2609.11682 • Published 15 days ago • 46

Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models

Paper • 2609.08418 • Published 17 days ago • 135

Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training

Paper • 2609.15051 • Published 11 days ago • 14

Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work

Paper • 2609.11977 • Published 21 days ago • 116

upvoted a paper 12 days ago

NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference

Paper • 2609.01657 • Published 25 days ago • 34

upvoted a collection 12 days ago

NeoMME

Collection

Meet NeoMME: a family of 260M and 800M Multimodal-Native Multilingual Encoders • 12 items • Updated 21 days ago • 33

upvoted an article 12 days ago

view article

Article

NeoMME: an efficient Multimodal-native and Multilingual Encoder

• 

Hcompany

•

21 days ago

• 110

upvoted a collection 14 days ago

GLiNER2.5 Models

Collection

5 items • Updated 21 minutes ago • 33