Basit mustafa

BasitMustafa's activity

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

upvoted a paper about 11 hours ago

VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails

Paper • 2610.12813 • Published 7 days ago • 1

upvoted a collection 2 days ago

QUEEN (Chess) models

Collection

Our models trained to play chess (4B) • 2 items • Updated 13 days ago • 2

upvoted 16 papers 3 days ago

Coding-Agent Benchmarks Should Match Their Users' Task Flows

Paper • 2610.09633 • Published 8 days ago • 12

Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution

Paper • 2609.37950 • Published 16 days ago • 16

Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding

Paper • 2610.12939 • Published 6 days ago • 17

From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning

Paper • 2609.39566 • Published 15 days ago • 17

DataVista: Diagnosing Multimodal LLMs on Data Video Understanding

Paper • 2610.11993 • Published 7 days ago • 17

GraphDecisionBench: Benchmarking System One Models on Graph Tasks

Paper • 2610.06354 • Published 6 days ago • 19

Recurrent Harness for Agentic Continual Learning

Paper • 2610.12668 • Published 7 days ago • 23

Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression

Paper • 2610.09788 • Published 7 days ago • 23

SWE-Duel: Towards a Self-Scaling Arena for Coding Agents

Paper • 2610.12569 • Published 7 days ago • 21

Contextual Correction of Parallel Drafts for Speculative Decoding

Paper • 2610.12570 • Published 7 days ago • 32

RSI-Anything: Unlocking Recursive Self-Improvement with World Models

Paper • 2610.13912 • Published 6 days ago • 45

Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction

Paper • 2610.12984 • Published 6 days ago • 51

SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model

Paper • 2610.11361 • Published 7 days ago • 45

ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents

Paper • 2610.13395 • Published 6 days ago • 54

Continually Post-training Small Models via Synthetic Self-distillation

Paper • 2610.13113 • Published 6 days ago • 45

General Agentic Memory Via Deep Research

Paper • 2511.18423 • Published Nov 23, 2025 • 174

upvoted an article 3 days ago

view article

Article

ColGrep-Agent: Cutting Frontier Coding Agents’ Tokens by a Third

• 

lightonai

•

3 days ago

• 19

upvoted a paper 4 days ago

RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations

Paper • 2610.01780 • Published 14 days ago • 287