Publications by Nilaksh

• 

  Nilaksh

  Co-supervisor: Caglar Gulcehre
  Research Areas: Reinforcement Learning, Embodied AI

Activity

• PhD Student: Aug 2025 - now

Preprints

• Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
  Nilkash*, Saurav Jha*, Artem Zholus*, and Sarath Chandar
  In ArXiv, 2026.
  #DL, #RL
  [arXiv]

Conference and Journal Papers

2026

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

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