Aurora Hill

aurorahi8's activity

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

upvoted a paper about 18 hours ago

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published 6 days ago • 142

upvoted a paper 1 day ago

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published 3 days ago • 143

upvoted a paper 3 days ago

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 6 days ago • 161

upvoted a paper 7 days ago

Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill

Paper • 2608.11924 • Published 8 days ago • 282

liked a Space 7 days ago

Running

Featured

697

Agent Memory Leaderboard

🧠

697

Unified memory evaluation · Results expected August 12.

upvoted a paper 8 days ago

Beyond Pixels: From Video Priors to 4D Worlds

Paper • 2608.10744 • Published 9 days ago • 179

liked a model 8 days ago

Qwen/Qwen2.5-VL-7B-Instruct

Image-Text-to-Text • 8B • Updated Apr 6, 2025 • 9.62M • • 1.68k

upvoted 2 papers 8 days ago

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 11 days ago • 213

SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

Paper • 2608.07468 • Published 13 days ago • 105

upvoted a paper 9 days ago

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Paper • 2608.09819 • Published 10 days ago • 335

upvoted a paper 13 days ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 13 days ago • 244

upvoted a paper 15 days ago

Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs

Paper • 2608.01755 • Published 17 days ago • 141

upvoted a paper 16 days ago

One Future, Every Robot: Label-Efficient Collective-State Prediction with Decentralized JEPA

Paper • 2607.28443 • Published 21 days ago • 9

upvoted a paper 17 days ago

TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting

Paper • 2607.28261 • Published 21 days ago • 116

upvoted 3 papers 20 days ago

Metis: Memory Foundation Model

Paper • 2607.26760 • Published 22 days ago • 271

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Paper • 2607.28227 • Published 21 days ago • 306

DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation

Paper • 2607.26811 • Published 22 days ago • 92

upvoted a paper 21 days ago

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

Paper • 2607.25659 • Published 23 days ago • 83

liked a model 21 days ago

sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

Sentence Similarity • 0.1B • Updated Jan 28 • 55.9M • • 1.35k

liked a Space 22 days ago

Running on Zero

MCP

110

ImageGen

🖼

110

Multi-task image generator with dynamic, chainable workflows