Basit mustafa

BasitMustafa's activity

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

upvoted a paper about 13 hours ago

Scaling Inherently Interpretable Language Models

Paper • 2608.07594 • Published 8 days ago • 18

upvoted a paper 2 days ago

Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution

Paper • 2608.08311 • Published 6 days ago • 83

upvoted a paper 6 days ago

Next-Latent Prediction Transformers Learn Compact World Models

Paper • 2511.05963 • Published Nov 8, 2025 • 4

upvoted a paper 8 days ago

OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents

Paper • 2608.05013 • Published 10 days ago • 35

upvoted an article 8 days ago

view article

Article

Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv

• 

sergiopaniego

•

8 days ago

• 25

upvoted a paper 9 days ago

Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency

Paper • 2604.04847 • Published Apr 6 • 2

upvoted a paper 10 days ago

Enhancing Rubric-based RL via Self-Distillation

Paper • 2607.18082 • Published 24 days ago • 25

upvoted a collection 16 days ago

ACM: Agentic Context Management for Long Horizon Tasks

Collection

10 items • Updated 25 days ago • 2

upvoted 2 papers 16 days ago

Video = World + Event Stream

Paper • 2607.15038 • Published 29 days ago • 24

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents

Paper • 2607.22798 • Published 21 days ago • 62

upvoted 2 papers 17 days ago

IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation

Paper • 2607.22375 • Published 21 days ago • 9

DataPrep-Bench: Benchmarking LLMs as Training Data Preparators

Paper • 2607.20465 • Published May 19 • 56

upvoted 2 papers 19 days ago

3rd Place at CVPR 2026 CASTLE Challenge: Agentic Multi-View Long-Context Video Understanding via Hierarchical Knowledge Graph Retrieval

Paper • 2606.01933 • Published Jun 1 • 1

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

Paper • 2607.20911 • Published 22 days ago • 26

upvoted a collection 20 days ago

JOSIE-2 4B Preview

Collection

A preview model of the new J.O.S.I.E. version 2 family of personality-driven language models trained entirely on Apple Silicon • 9 items • Updated 10 days ago • 5

upvoted 2 papers 22 days ago

Environment-free Synthetic Data Generation for API-Calling Agents

Paper • 2607.16900 • Published 27 days ago • 21

DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines

Paper • 2607.16617 • Published 27 days ago • 143

upvoted an article 23 days ago

view article

Article

Welcome Inkling by Thinking Machines

• 
• 
• +3

burtenshaw, merve, pcuenq, ariG23498, andito

•

30 days ago

• 163

upvoted a paper 23 days ago

S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation

Paper • 2607.15686 • Published 28 days ago • 16

upvoted a paper 27 days ago

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Paper • 2607.14952 • Published 29 days ago • 212