Publications d'Nilaksh

• 

  Nilaksh

  Co-superviseur: Caglar Gulcehre
  Domaines de recherche: Apprentissage par renforcement, IA incarnée

Activité

• Étudiant au doctorat: sept. 2025 - maintenant

Articles de conférence et de revue

2026

3. Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
   Nilaksh*, Saurav Jha*, Artem Zholus* et Sarath Chandar
   Conference on Neural Information Processing Systems (NeurIPS) Evaluations and Datasets Track, 2026.
   #DL, #Other
   [openreview], [arXiv], [code]

4. Squeezing More from the Stream: Learning Representation Online for Streaming Reinforcement Learning
   Nilaksh*, Antoine Clavaud*, Mathieu Reymond, François Rivest et Sarath Chandar
   International Conference on Machine Learning (ICML), 2026.
   #RL, #DL
   [openreview], [arXiv], [code]

5. BRIDGE: Predicting Human Task Completion Time From Model Performance
   Fengyuan Liu*, Jay Gala*, Nilaksh, Dzmitry Bahdanau, Siva Reddy et Hugo Larochelle
   International Conference on Machine Learning (ICML), 2026.
   #NLP
   [openreview], [arXiv], [code]