Gibran Iqbal

Jibbscript's activity

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

upvoted 13 papers 1 day ago

Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads

Paper • 2607.01002 • Published 4 days ago • 14

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

Paper • 2606.31825 • Published 5 days ago • 19

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

Paper • 2607.01874 • Published 3 days ago • 14

WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory

Paper • 2607.02517 • Published 3 days ago • 21

AgenticDataBench: A Comprehensive Benchmark for Data Agents

Paper • 2607.01647 • Published 3 days ago • 26

Morphing into Hybrid Attention Models

Paper • 2606.30562 • Published 6 days ago • 37

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

Paper • 2607.02440 • Published 3 days ago • 43

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

Paper • 2607.02255 • Published 3 days ago • 45

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

Paper • 2607.02512 • Published 3 days ago • 74

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

Paper • 2607.00248 • Published 5 days ago • 23

CausalMix: Data Mixture as Causal Inference for Language Model Training

Paper • 2607.01104 • Published 4 days ago • 17

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

Paper • 2607.00466 • Published 4 days ago • 24

MemSyco-Bench: Benchmarking Sycophancy in Agent Memory

Paper • 2607.01071 • Published 4 days ago • 22

upvoted 2 papers 3 days ago

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published 9 days ago • 103

Orca: The World is in Your Mind

Paper • 2606.30534 • Published 6 days ago • 231

upvoted 5 papers 8 days ago

LISA: Likelihood Score Alignment for Visual-condition Controllable Generation

Paper • 2606.27192 • Published 10 days ago • 13

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

Paper • 2606.14397 • Published 10 days ago • 18

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

Paper • 2606.26027 • Published 11 days ago • 18

GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents

Paper • 2606.24551 • Published 13 days ago • 28

Fast LeWorldModel

Paper • 2606.26217 • Published 11 days ago • 27