sshell

sshell's activity

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

upvoted a paper about 21 hours ago

BrickBench: Evaluating Agentic Brick Design

Paper • 2610.12452 • Published 21 days ago • 15

upvoted 16 papers 1 day ago

Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps

Paper • 2610.02740 • Published 27 days ago • 13

Evaluating LLM Creativity through Long-Tail Performance

Paper • 2610.12998 • Published 20 days ago • 15

Scaling Agentic Data for Long-Horizon Terminal Intelligence

Paper • 2610.13166 • Published 20 days ago • 149

Thinking Inertia: LLMs Keep Thinking When Told Not To

Paper • 2610.11765 • Published 21 days ago • 246

Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents

Paper • 2610.18614 • Published 16 days ago • 6

AutoEnvScaling: Automating the Data Flywheel with Terminal Agents

Paper • 2610.14163 • Published 20 days ago • 13

Jeva: System One Models from First Principles

Paper • 2610.18773 • Published 16 days ago • 443

Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes

Paper • 2610.18356 • Published 16 days ago • 135

Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching

Paper • 2610.19636 • Published 15 days ago • 8

Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models

Paper • 2610.22428 • Published 14 days ago • 21

OfficeTown: Generative Organizations for Evolving Agent Intelligence

Paper • 2610.23194 • Published 13 days ago • 23

S-Agent 2.0: Spatial Reasoning with a General Coding Agent

Paper • 2610.28354 • Published 9 days ago • 109

Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents

Paper • 2610.11942 • Published 21 days ago • 190

Spectral-Spatial Interpretation

Paper • 2610.21114 • Published 14 days ago • 758

DirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model

Paper • 2610.31734 • Published 7 days ago • 32

Building Auditable AI Text Detectors with Sparse Autoencoders

Paper • 2610.30006 • Published 8 days ago • 16

upvoted 3 papers 7 months ago

CutClaw: Agentic Hours-Long Video Editing via Music Synchronization

Paper • 2603.29664 • Published Mar 31 • 50

VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward

Paper • 2603.26599 • Published Mar 27 • 65

All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models

Paper • 2604.00479 • Published Apr 1 • 37