Joel Wang

joelhenwang's activity

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

upvoted 2 papers about 19 hours ago

Block Sparse Attention with Log-Linear Complexity

Paper • 2609.31093 • Published 4 days ago • 20

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 4 days ago • 118

upvoted 4 papers 3 days ago

Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures

Paper • 2609.29429 • Published 5 days ago • 14

AgentKernel: The Trust-Native Agentic Operating System

Paper • 2609.29647 • Published Aug 29 • 10

Rufus-Air: An Open LLM Post-Training Recipe

Paper • 2609.29421 • Published 5 days ago • 22

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

Paper • 2609.29845 • Published 5 days ago • 82

upvoted 14 papers 4 days ago

OpenGame: Open Agentic Coding for Games

Paper • 2604.18394 • Published Apr 20 • 88

Hunyuan-Game: Industrial-grade Intelligent Game Creation Model

Paper • 2505.14135 • Published May 20, 2025 • 17

Sprite Sheet Diffusion: Generate Game Character for Animation

Paper • 2412.03685 • Published Dec 4, 2024 • 2

GameGPT: Multi-agent Collaborative Framework for Game Development

Paper • 2310.08067 • Published Sep 7, 2025 • 1

GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills

Paper • 2609.21749 • Published 11 days ago • 19

EvoOntology: A Self-Evolving Ontology Layer for Data Agents

Paper • 2609.15779 • Published 15 days ago • 157

Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations

Paper • 2609.22255 • Published 23 days ago • 22

Harness-Zero: Harness Distillation via Agent-as-Harness

Paper • 2609.24974 • Published 8 days ago • 37

GameASG-Bench: Benchmarking Autonomous Software Generation for Game Development

Paper • 2609.21293 • Published 11 days ago • 1

GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?

Paper • 2608.21833 • Published Aug 22 • 18

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay

Paper • 2609.25001 • Published 8 days ago • 130

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 8 days ago • 212

Recursive self-improvement of AI research agents

Paper • 2609.26457 • Published 7 days ago • 27

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

Paper • 2609.25804 • Published 7 days ago • 160