Joel Wang

joelhenwang's activity

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

liked a model about 17 hours ago

Baekpica/Qwen3.8-Flash-Next-Mixed-Quant-SSD-PLE-GGUF

Image-Text-to-Text • 129B • Updated about 10 hours ago • 9.38k • 20

liked a model about 22 hours ago

FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree

Text-to-Video • 35B • Updated 2 days ago • 177

upvoted 18 papers 2 days ago

Memory for Large Language Models

Paper • 2607.25380 • Published Jul 28 • 16

Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions

Paper • 2607.20891 • Published Jul 23 • 5

Multi-Head Attention Residuals

Paper • 2607.27230 • Published Jul 22 • 12

Self-Evolving Coding Agents

Paper • 2608.03392 • Published 27 days ago • 9

What AI Red-Team Evaluations Can and Cannot Prove

Paper • 2607.21735 • Published Jul 23 • 6

Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming

Paper • 2608.05108 • Published 26 days ago • 9

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

Paper • 2608.15089 • Published 16 days ago • 445

Personalized Auto-Research: Towards a True AI Co-Scientist

Paper • 2608.14881 • Published 17 days ago • 6

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

Paper • 2608.14036 • Published 17 days ago • 169

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

Paper • 2608.16157 • Published 14 days ago • 102

Looped Language Models Improve Compositional Tool Calling

Paper • 2608.18171 • Published 14 days ago • 18

Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses

Paper • 2608.08466 • Published 22 days ago • 12

4DAnyone: Create Anyone in 4D from a Casual Monocular Video

Paper • 2608.20335 • Published 11 days ago • 81

AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale

Paper • 2608.20634 • Published 10 days ago • 12

Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs

Paper • 2608.21134 • Published 10 days ago • 8

Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference

Paper • 2608.20210 • Published 11 days ago • 8

Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence

Paper • 2608.21156 • Published 10 days ago • 60

Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation

Paper • 2608.15062 • Published 5 days ago • 10