John Giles III

maxnumbers's activity

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

upvoted 8 papers 2 days ago

Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching

Paper • 2609.01404 • Published 5 days ago • 26

Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement

Paper • 2609.01481 • Published 5 days ago • 16

The Mechanics of Democratic Dominance: A System Dynamics Paradigm for Dynamic Consent Engineering

Paper • 2608.27509 • Published 6 days ago • 6

Recursive Criticality of AI Self-Improvement

Paper • 2609.00137 • Published 6 days ago • 6

UI-Venus-2 Technical Report

Paper • 2609.00028 • Published 10 days ago • 60

Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence

Paper • 2608.31075 • Published 6 days ago • 28

Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities

Paper • 2608.28122 • Published 9 days ago • 65

LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering

Paper • 2608.28281 • Published 9 days ago • 101

upvoted 2 papers 3 days ago

SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers

Paper • 2609.01343 • Published 5 days ago • 93

Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

Paper • 2609.00111 • Published 6 days ago • 371

upvoted 6 papers 5 days ago

DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution

Paper • 2608.31106 • Published 6 days ago • 98

Sliding-window beats linear attention

Paper • 2608.28444 • Published 9 days ago • 16

UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City

Paper • 2608.27456 • Published 10 days ago • 112

CaRGo-T: Causal Reasoning Graph-of-Thought improves Multimodal Humor Comprehension

Paper • 2608.23172 • Published 13 days ago • 10

Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models

Paper • 2608.25518 • Published 11 days ago • 196

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

Paper • 2608.25593 • Published 11 days ago • 117

upvoted 4 papers 6 days ago

Procedura: Agentic 3D Modeling with Procedural Control

Paper • 2608.26238 • Published 11 days ago • 15

WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

Paper • 2608.27454 • Published 10 days ago • 29

What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents

Paper • 2608.27260 • Published 10 days ago • 72

GameWAM: A World Action Model for Video Games

Paper • 2608.26200 • Published 12 days ago • 47