Kulbir Singh PRO

kulbir97's activity

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

upvoted an article 4 days ago

view article

Article

NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI

• 

13 days ago

•

53

upvoted 4 papers 5 days ago

CoDA: Agentic Systems for Collaborative Data Visualization

Paper • 2510.03194 • Published Oct 3, 2025 • 29

Budget-Aware Tool-Use Enables Effective Agent Scaling

Paper • 2511.17006 • Published Nov 21, 2025 • 30

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

Paper • 2510.25992 • Published Oct 29, 2025 • 47

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning

Paper • 2512.20605 • Published 26 days ago • 60

updated a collection 6 days ago

RSS-2026

Collection

7 items • Updated 6 days ago

upvoted a paper 6 days ago

Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits

Paper • 2512.20578 • Published 26 days ago • 77

updated a collection 6 days ago

RSS-2026

Collection

7 items • Updated 6 days ago

upvoted a paper 6 days ago

4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation

Paper • 2512.17012 • Published about 1 month ago • 43

updated a collection 6 days ago

RSS-2026

Collection

7 items • Updated 6 days ago

upvoted a paper 6 days ago

Masking Teacher and Reinforcing Student for Distilling Vision-Language Models

Paper • 2512.22238 • Published 26 days ago • 25

upvoted a paper 7 days ago

DINOv3

Paper • 2508.10104 • Published Aug 13, 2025 • 292

upvoted a collection 7 days ago

DINOv3

Collection

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21, 2025 • 454

updated a collection 7 days ago

RSS-2026

Collection

7 items • Updated 6 days ago