Niranjani Prasad

Senior Researcher

Publications

View by:

- Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks
  
  Wasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth, Sushrut Karmalkar, Niranjani Prasad
  
  September 2026
  
  arXiv | September 2026
  
  Publication
- Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing
  
  Iskander Azangulov, Teodora Pandeva, Niranjani Prasad, Javier Zazo, Sushrut Karmalkar
  
  ICLR 2026 | April 2026
  
  DOI Publication
- Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task
  
  A. Curth, Rachel Lawrence, Sushrut Karmalkar, Niranjani Prasad
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- Deep learning for the prediction of clinical outcomes in internet-delivered CBT for depression and anxiety
  
  Niranjani Prasad, Isabel Chien, Tim Regan, Angel Enrique, Jorge Palacios, Dessie Kegan, Usman Munir, Ryutaro Tanno, Hannah Richardson (nee Murfet), Aditya Nori, Derek Richards, Gavin Doherty, Danielle Belgrave, Anja Thieme
  
  PLOS ONE | November 2023, Vol 18(11)
  
  PDF Publication DOI Project

- Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks
  
  Wasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth, Sushrut Karmalkar, Niranjani Prasad
  
  September 2026
  
  arXiv | September 2026
  
  Publication
- Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing
  
  Iskander Azangulov, Teodora Pandeva, Niranjani Prasad, Javier Zazo, Sushrut Karmalkar
  
  ICLR 2026 | April 2026
  
  DOI Publication
- Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task
  
  A. Curth, Rachel Lawrence, Sushrut Karmalkar, Niranjani Prasad
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- Deep learning for the prediction of clinical outcomes in internet-delivered CBT for depression and anxiety
  
  Niranjani Prasad, Isabel Chien, Tim Regan, Angel Enrique, Jorge Palacios, Dessie Kegan, Usman Munir, Ryutaro Tanno, Hannah Richardson (nee Murfet), Aditya Nori, Derek Richards, Gavin Doherty, Danielle Belgrave, Anja Thieme
  
  PLOS ONE | November 2023, Vol 18(11)
  
  PDF Publication DOI Project
- Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks
  
  Wasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth, Sushrut Karmalkar, Niranjani Prasad
  
  September 2026
  
  arXiv | September 2026
  
  Publication
- Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task
  
  A. Curth, Rachel Lawrence, Sushrut Karmalkar, Niranjani Prasad
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- Deep learning for the prediction of clinical outcomes in internet-delivered CBT for depression and anxiety
  
  Niranjani Prasad, Isabel Chien, Tim Regan, Angel Enrique, Jorge Palacios, Dessie Kegan, Usman Munir, Ryutaro Tanno, Hannah Richardson (nee Murfet), Aditya Nori, Derek Richards, Gavin Doherty, Danielle Belgrave, Anja Thieme
  
  PLOS ONE | November 2023, Vol 18(11)
  
  PDF Publication DOI Project

- Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks
  
  Wasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth, Sushrut Karmalkar, Niranjani Prasad
  
  September 2026
  
  arXiv | September 2026
  
  Publication
- Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task
  
  A. Curth, Rachel Lawrence, Sushrut Karmalkar, Niranjani Prasad
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing
  
  Iskander Azangulov, Teodora Pandeva, Niranjani Prasad, Javier Zazo, Sushrut Karmalkar
  
  ICLR 2026 | April 2026
  
  DOI Publication
- Deep learning for the prediction of clinical outcomes in internet-delivered CBT for depression and anxiety
  
  Niranjani Prasad, Isabel Chien, Tim Regan, Angel Enrique, Jorge Palacios, Dessie Kegan, Usman Munir, Ryutaro Tanno, Hannah Richardson (nee Murfet), Aditya Nori, Derek Richards, Gavin Doherty, Danielle Belgrave, Anja Thieme
  
  PLOS ONE | November 2023, Vol 18(11)
  
  PDF Publication DOI Project

Niranjani Prasad

Publications

Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks

Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing

Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task

Deep learning for the prediction of clinical outcomes in internet-delivered CBT for depression and anxiety

Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks

Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing

Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task

Deep learning for the prediction of clinical outcomes in internet-delivered CBT for depression and anxiety

Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks

Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task

Deep learning for the prediction of clinical outcomes in internet-delivered CBT for depression and anxiety

Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks

Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task

Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing

Deep learning for the prediction of clinical outcomes in internet-delivered CBT for depression and anxiety

Contact Niranjani Prasad

Microsoft Research Lab – Cambridge