Joel Wang

joelhenwang's activity

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

upvoted 2 papers 1 day ago

An Empirical Study of Harness Design for Coding Agents

Paper • 2609.20804 • Published 3 days ago • 54

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published 3 days ago • 67

upvoted 14 papers 2 days ago

CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents

Paper • 2609.18779 • Published 4 days ago • 5

The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction

Paper • 2609.18063 • Published 4 days ago • 10

Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training

Paper • 2609.14306 • Published 7 days ago • 10

SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization

Paper • 2609.14320 • Published 7 days ago • 23

HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses

Paper • 2609.15938 • Published 6 days ago • 25

VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention

Paper • 2609.15810 • Published 6 days ago • 35

Agora: Git as Shared Memory for Collective AutoResearch

Paper • 2609.18094 • Published 4 days ago • 42

ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks

Paper • 2609.18805 • Published 4 days ago • 47

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

Paper • 2609.17488 • Published 5 days ago • 279

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published 6 days ago • 173

The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

Paper • 2609.11873 • Published 10 days ago • 89

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

Paper • 2609.17523 • Published 5 days ago • 26

AI for Games in the Foundation Model Era

Paper • 2609.16679 • Published 5 days ago • 124

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published 13 days ago • 331

upvoted 3 papers 5 days ago

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

Paper • 2609.11682 • Published 10 days ago • 40

Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation

Paper • 2609.11115 • Published 10 days ago • 166

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

Paper • 2609.13141 • Published 9 days ago • 62

upvoted a paper 6 days ago

HyQuant: Hybrid-Precision Quantization for LLM Attention

Paper • 2608.27875 • Published 23 days ago • 30