Junayed ahmed

tamim-korex's activity

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

upvoted 2 papers about 2 hours ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 3 days ago • 248

FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving

Paper • 2608.19758 • Published 3 days ago • 16

upvoted a paper about 4 hours ago

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

Paper • 2608.19799 • Published 3 days ago • 60

upvoted 2 papers 2 days ago

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published 9 days ago • 162

V-RAE: Rethinking Video Latent Spaces for Generation

Paper • 2608.13556 • Published 10 days ago • 28

upvoted a paper 4 days ago

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published 6 days ago • 148

upvoted 4 papers 9 days ago

PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives

Paper • 2608.13552 • Published 10 days ago • 45

From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection

Paper • 2608.11562 • Published 11 days ago • 10

SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure

Paper • 2608.11079 • Published 12 days ago • 17

Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence

Paper • 2608.12743 • Published 10 days ago • 43

upvoted 3 papers 10 days ago

Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution

Paper • 2608.07645 • Published 16 days ago • 26

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

Paper • 2608.08311 • Published 15 days ago • 90

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published 13 days ago • 111

upvoted 3 papers 13 days ago

YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family

Paper • 2608.07051 • Published 16 days ago • 20

Modular TTT: Rethinking Test-Time Training as Composable Modules

Paper • 2608.07110 • Published 16 days ago • 8

StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding

Paper • 2608.05703 • Published 17 days ago • 16

upvoted 4 papers 19 days ago

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Paper • 2607.28227 • Published 24 days ago • 307

Multi-Head Attention Residuals

Paper • 2607.27230 • Published Jul 22 • 11

Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers

Paper • 2607.28611 • Published 24 days ago • 22

CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents

Paper • 2607.25431 • Published 26 days ago • 113