Richard Thompson

Orbit-Richard's activity

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

upvoted a paper about 11 hours ago

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

Paper • 2609.20715 • Published 3 days ago • 16

upvoted a paper 2 days ago

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

Paper • 2609.15810 • Published 6 days ago • 35

upvoted a paper 8 days ago

SenseNova-U1.5: Towards Native Unified Visual Intelligence

Paper • 2609.11929 • Published 10 days ago • 266

updated a dataset 9 days ago

Orbit-Richard/green-fact-0873d5

Viewer • Updated 9 days ago • 57 • 28

published a dataset 9 days ago

Orbit-Richard/green-fact-0873d5

Viewer • Updated 9 days ago • 57 • 28

upvoted a paper 9 days ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published 22 days ago • 464

liked a model 9 days ago

nex-agi/Nex-N2.5-mini

Text Generation • 35B • Updated 11 days ago • 8.24k • 838

upvoted a paper 10 days ago

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

Paper • 2609.05594 • Published 16 days ago • 36

liked a model 10 days ago

nex-agi/Nex-N2.5-Pro

Text Generation • 397B • Updated 3 days ago • 31.8k • 666

liked a model 15 days ago

XHToken/Spark-X2.5-4B

Text Generation • 4B • Updated 5 days ago • 30.2k • 1.28k

upvoted a paper 16 days ago

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

Paper • 2609.03796 • Published 17 days ago • 183

liked a model 29 days ago

0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF

Text Generation • 27B • Updated 30 days ago • 1.83M • 507

liked 2 models about 1 month ago

MiniMaxAI/MiniMax-H3

Image-Text-to-Video • 33B • Updated Aug 13 • 4.3M • • 5.48k

MiniMaxAI/MiniMax-Music3

Text-to-Audio • 2B • Updated Aug 14 • 13.6k • 1.4k

upvoted 3 papers about 1 month ago

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

Paper • 2608.10299 • Published Aug 10 • 136

CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks

Paper • 2608.06352 • Published Aug 6 • 24

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

Paper • 2608.05131 • Published Aug 6 • 15

liked a model about 2 months ago

DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

Image-Text-to-Text • 9B • Updated 3 days ago • 1.48M • 730

upvoted a paper about 2 months ago

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

Paper • 2608.04007 • Published Aug 4 • 20