John Giles III

maxnumbers's activity

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

liked a model about 13 hours ago

LatitudeGames/Hearthfire-24B

24B • Updated Dec 19, 2025 • 41 • 61

upvoted a paper 11 days ago

LLM-based Detection of Manipulative Political Narratives

Paper • 2605.14354 • Published 13 days ago • 5

upvoted 2 papers 12 days ago

When to Trust Imagination: Adaptive Action Execution for World Action Models

Paper • 2605.06222 • Published 20 days ago • 42

NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation

Paper • 2605.10813 • Published 16 days ago • 16

liked a model 13 days ago

ResembleAI/Dramabox

Text-to-Speech • Updated 13 days ago • 1.55k • 257

upvoted 2 papers 14 days ago

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

Paper • 2605.09063 • Published 18 days ago • 78

SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems

Paper • 2604.04514 • Published Apr 6 • 7

liked a model 21 days ago

poolside/Laguna-XS.2

Text Generation • 33B • Updated about 1 hour ago • 62k • 266

upvoted a paper 22 days ago

Map2World: Segment Map Conditioned Text to 3D World Generation

Paper • 2605.00781 • Published 26 days ago • 25

upvoted a paper 24 days ago

GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers

Paper • 2604.02648 • Published Apr 3 • 47

upvoted a paper 26 days ago

Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising

Paper • 2604.26694 • Published 28 days ago • 6

upvoted 2 papers 29 days ago

Building a Precise Video Language with Human-AI Oversight

Paper • 2604.21718 • Published Apr 22 • 17

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

Paper • 2604.22748 • Published Apr 24 • 227

upvoted 7 papers about 1 month ago

CreativeGame:Toward Mechanic-Aware Creative Game Generation

Paper • 2604.19926 • Published Apr 21 • 2

Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Paper • 2604.12374 • Published Apr 14 • 37

Toward Autonomous Long-Horizon Engineering for ML Research

Paper • 2604.13018 • Published Apr 14 • 34

ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents

Paper • 2604.11784 • Published Apr 13 • 143

SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding

Paper • 2604.09557 • Published Feb 10 • 11

Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs

Paper • 2604.10480 • Published Apr 12 • 20

On Semiotic-Grounded Interpretive Evaluation of Generative Art

Paper • 2604.08641 • Published Apr 9 • 4