Gibran Iqbal

Jibbscript's activity

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

upvoted 3 papers 3 days ago

Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation

Paper • 2607.05382 • Published 10 days ago • 83

SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding

Paper • 2607.10400 • Published 8 days ago • 69

Unified Audio Intelligence Without Regressing on Text Intelligence

Paper • 2607.05196 • Published 13 days ago • 21

upvoted a paper 4 days ago

ABot-OCR Technical Report

Paper • 2605.27978 • Published May 27 • 2

upvoted a collection 4 days ago

Bonsai 27B

Collection

10 items • Updated 4 days ago • 164

upvoted a paper 4 days ago

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published 11 days ago • 128

upvoted a collection 4 days ago

gliner2 family

Collection

GLiNER2 extends the original GLiNER architecture to support multi-task information extraction with a schema-driven interface. • 9 items • Updated 5 days ago • 56

upvoted 2 articles 6 days ago

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego

•

Mar 10

• 173

view article

Article

After the party comes the free lunch: regularizing ColBERT models to enhance pooling capabilities and reduce index footprint

• 

lightonai

•

12 days ago

• 13

upvoted a paper 9 days ago

RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules

Paper • 2607.01293 • Published 18 days ago • 3

upvoted an article 10 days ago

view article

Article

Native-speed vLLM transformers modeling backend

• 
• 

hmellor, lysandre

•

11 days ago

• 54

upvoted a collection 13 days ago

AI2 Safety Toolkit

Collection

Safety data, moderation tools and safe LLMs. • 6 items • Updated Dec 23, 2025 • 11

upvoted a paper 13 days ago

WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Paper • 2406.18495 • Published Jun 26, 2024 • 15

upvoted 7 papers 15 days ago

Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads

Paper • 2607.01002 • Published 18 days ago • 19

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

Paper • 2606.31825 • Published 19 days ago • 29

SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use

Paper • 2607.01874 • Published 17 days ago • 22

WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory

Paper • 2607.02517 • Published 17 days ago • 33

AgenticDataBench: A Comprehensive Benchmark for Data Agents

Paper • 2607.01647 • Published 17 days ago • 37

Morphing into Hybrid Attention Models

Paper • 2606.30562 • Published 20 days ago • 51

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

Paper • 2607.02440 • Published 17 days ago • 51