Gibran Iqbal

Jibbscript's activity

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

upvoted a collection about 9 hours ago

AI2 Safety Toolkit

Collection

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

upvoted a paper about 9 hours ago

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

Paper • 2406.18495 • Published Jun 26, 2024 • 15

upvoted 13 papers 3 days ago

Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads

Paper • 2607.01002 • Published 6 days ago • 17

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

Paper • 2606.31825 • Published 7 days ago • 20

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

Paper • 2607.01874 • Published 5 days ago • 17

WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory

Paper • 2607.02517 • Published 5 days ago • 26

AgenticDataBench: A Comprehensive Benchmark for Data Agents

Paper • 2607.01647 • Published 5 days ago • 30

Morphing into Hybrid Attention Models

Paper • 2606.30562 • Published 8 days ago • 42

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

Paper • 2607.02440 • Published 5 days ago • 45

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

Paper • 2607.02255 • Published 5 days ago • 53

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

Paper • 2607.02512 • Published 5 days ago • 94

Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity

Paper • 2607.00248 • Published 7 days ago • 27

CausalMix: Data Mixture as Causal Inference for Language Model Training

Paper • 2607.01104 • Published 6 days ago • 18

ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving

Paper • 2607.00466 • Published 6 days ago • 26

MemSyco-Bench: Benchmarking Sycophancy in Agent Memory

Paper • 2607.01071 • Published 6 days ago • 25

upvoted 2 papers 4 days ago

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published 11 days ago • 106

Orca: The World is in Your Mind

Paper • 2606.30534 • Published 8 days ago • 234

upvoted 3 papers 10 days ago

LISA: Likelihood Score Alignment for Visual-condition Controllable Generation

Paper • 2606.27192 • Published 12 days ago • 13

Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments

Paper • 2606.14397 • Published 12 days ago • 18

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

Paper • 2606.26027 • Published 13 days ago • 18