Richard Thompson

Orbit-Richard's activity

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

upvoted a paper 2 days ago

Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL

Paper • 2609.20715 • Published 4 days ago • 28

upvoted a paper 4 days ago

VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention

Paper • 2609.15810 • Published 7 days ago • 42

upvoted a paper 9 days ago

SenseNova-U1.5: Towards Native Unified Visual Intelligence

Paper • 2609.11929 • Published 11 days ago • 272

upvoted a paper 10 days ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published 23 days ago • 471

upvoted a paper 12 days ago

SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution

Paper • 2609.05594 • Published 17 days ago • 36

upvoted a paper 17 days ago

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Paper • 2609.03796 • Published 18 days ago • 186

upvoted 2 papers about 1 month ago

Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design

Paper • 2608.10299 • Published Aug 10 • 137

CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks

Paper • 2608.06352 • Published Aug 6 • 24

upvoted 2 papers about 2 months ago

OPD-V: Visual On-Policy Self-Distillation with Modality Balance

Paper • 2608.05131 • Published Aug 6 • 15

TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning

Paper • 2608.04007 • Published Aug 4 • 20