Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation Paper • 2608.17512 • Published 2 days ago • 44
SkillAligner: Treating Retrieved Skills as Adaptable Drafts at Execution Time Paper • 2608.06880 • Published 13 days ago • 1
AttriMem: Attribution-Guided Process Feedback for Agent Memory Learning Paper • 2607.21106 • Published 28 days ago • 2
Nemotron-Post-Training-v3 Collection Collection of datasets used in the post-training phase of Nemotron Nano, Super, and Ultra v3. • 50 items • Updated 8 days ago • 196
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts Paper • 2605.05974 • Published May 7 • 1
Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions Paper • 2602.05234 • Published Feb 5 • 1
Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions Paper • 2605.05983 • Published May 7 • 1