Kalender

Towards safe, aligned, and efficient reinforcement learning from human feedback

5 jun

Disputationer

Datalogi

torsdag 2025-06-05, 15.00

Plats: Q2, Malvinas väg 10, Stockholm

Respondent: Daniel Marta , Robotik, perception och lärande, RPL

2025-06-05T15:00:00.000+02:00 2025-06-05T15:00:00.000+02:00 Towards safe, aligned, and efficient reinforcement learning from human feedback (Disputationer) Q2, Malvinas väg 10, Stockholm (KTH, Stockholm, Sweden)Towards safe, aligned, and efficient reinforcement learning from human feedback (Disputationer)

Approach-constrained Grasp Synthesis and Interactive Perception for Rigid and Deformable Objects

10 jun

Disputationer

Datalogi

tisdag 2025-06-10, 14.30

Plats: D3, Lindstedtvägen 9

Videolänk: https://kth-se.zoom.us/j/68663108750

Respondent: Zehang Weng , Robotik, perception och lärande, RPL

2025-06-10T14:30:00.000+02:00 2025-06-10T14:30:00.000+02:00 Approach-constrained Grasp Synthesis and Interactive Perception for Rigid and Deformable Objects (Disputationer) D3, Lindstedtvägen 9 (KTH, Stockholm, Sweden)Approach-constrained Grasp Synthesis and Interactive Perception for Rigid and Deformable Objects (Disputationer)