John Giles III

maxnumbers's activity

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

upvoted 3 papers about 4 hours ago

MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation

Paper • 2603.16861 • Published 1 day ago • 2

Efficient Reasoning on the Edge

Paper • 2603.16867 • Published 1 day ago • 11

SegviGen: Repurposing 3D Generative Model for Part Segmentation

Paper • 2603.16869 • Published 1 day ago • 15

upvoted a paper about 19 hours ago

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs

Paper • 2603.05890 • Published 13 days ago • 88

upvoted 2 papers 1 day ago

Attention Residuals

Paper • 2603.15031 • Published 2 days ago • 89

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published 3 days ago • 230

upvoted 4 papers 2 days ago

CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges

Paper • 2603.11863 • Published 6 days ago • 5

Can Vision-Language Models Solve the Shell Game?

Paper • 2603.08436 • Published 9 days ago • 36

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Paper • 2603.12262 • Published 6 days ago • 28

HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios

Paper • 2603.11975 • Published 6 days ago • 10

upvoted a paper 3 days ago

The Trinity of Consistency as a Defining Principle for General World Models

Paper • 2602.23152 • Published 20 days ago • 198

upvoted a paper 4 days ago

Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents

Paper • 2602.16855 • Published Feb 15 • 50

upvoted 2 papers 5 days ago

DVD: Deterministic Video Depth Estimation with Generative Priors

Paper • 2603.12250 • Published 6 days ago • 26

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

Paper • 2603.12180 • Published 6 days ago • 60

liked a model 5 days ago

embedl/Cosmos-Reason2-2B-W4A16-Edge2

Image-Text-to-Text • 2B • Updated about 24 hours ago • 17.4k • 11

upvoted 4 papers 6 days ago

Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook

Paper • 2602.14299 • Published about 1 month ago • 27

Intelligent AI Delegation

Paper • 2602.11865 • Published Feb 12 • 16

Prism-Δ: Differential Subspace Steering for Prompt Highlighting in Large Language Models

Paper • 2603.10705 • Published 7 days ago • 11

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published 8 days ago • 119

upvoted a paper 8 days ago

Building AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned

Paper • 2603.05344 • Published 13 days ago • 6