Gibran Iqbal

Jibbscript's activity

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

upvoted a paper 2 days ago

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Paper • 2605.30611 • Published 8 days ago • 188

upvoted a collection 2 days ago

GPU Forecasters

Collection

9 items • Updated 4 days ago • 1

upvoted 2 papers 4 days ago

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

Paper • 2605.31264 • Published 7 days ago • 104

Trust-Region Behavior Blending for On-Policy Distillation

Paper • 2605.31159 • Published 7 days ago • 64

upvoted 12 papers 8 days ago

JLT: Clean-Latent Prediction in Latent Diffusion Transformers

Paper • 2605.27102 • Published 10 days ago • 32

Macaron-A2UI: A Model for Generative UI in Personal Agents

Paper • 2605.24830 • Published 12 days ago • 80

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

Paper • 2605.21573 • Published 16 days ago • 108

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Paper • 2605.23904 • Published 14 days ago • 221

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

Paper • 2605.28816 • Published 9 days ago • 419

ResearchMath-14K: Scaling Research-Level Mathematics via Agents

Paper • 2605.28003 • Published 9 days ago • 49

EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation

Paper • 2605.23271 • Published 14 days ago • 79

Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling

Paper • 2605.27030 • Published 10 days ago • 31

Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration

Paper • 2605.17423 • Published 19 days ago • 33

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Paper • 2605.26494 • Published 10 days ago • 39

MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research

Paper • 2605.26114 • Published 11 days ago • 64

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

Paper • 2605.27365 • Published 10 days ago • 138

upvoted 4 papers 9 days ago

Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World

Paper • 2605.26086 • Published 11 days ago • 23

MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing

Paper • 2605.23986 • Published 20 days ago • 17

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills

Paper • 2605.23899 • Published 14 days ago • 29

DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning

Paper • 2605.25604 • Published 11 days ago • 134