Sunishchal Dev

Researcher, Technology and Security Policy Center, RAND Corporation

Principal Researcher, Algoverse Coding Academy LLC

Joined

September 2024

Names

Sunishchal Dev (Preferred)

Emails

****@gmail.com (Confirmed)

****@algoverseairesearch.org (Confirmed)

****@rand.org (Confirmed)

Personal Links

Career & Education History

Researcher

Technology and Security Policy Center, RAND Corporation (rand.org)

2024 – Present

Principal Researcher

Algoverse Coding Academy LLC (algoversecodingacademy.com)

2024 – Present

Researcher

MATS (matsprogram.org)

2024 – 2024

Advisors, Relations & Conflicts

Coauthor

Marius Hobbhahn

2024 – 2024

Expertise

AI Safety

2024 – Present

Machine Learning

2024 – Present

AI Evaluations

2024 – Present

Publications

The science and practice of proportionality in AI risk evaluations
David Fernandez Llorca, Jose Hernandez-Orallo, Mario Fritz, Carlos Mougan, Lauritz Morlock, Jair Aguirre, jan brauner, james black, Simeon Campos, Sunishchal Dev, Alberto Franzin, Friederike Grosse Holz, Emilia Gomez, max hasin, Dan Lahav, Wout Schellaert, Vasilios Mavroudis, malcolm murray, Patricia Paskov, jaime raldua et al. (2 additional authors not shown)
- Science
- Readers: Everyone
CA-BED: Conversation-Aware Bayesian Experimental Design
Daniel Arnould, Rashad Aziz, Zixuan Kang, Tanav Changal, Kevin Zhu, Sunishchal Dev, Gabriel Grand, Shreyas Sunil Kulkarni
- Agentic AI in the Wild: From Hallucinations to Reliable Autonomy Poster
- Readers: Everyone
Judge Reliability Harness: Stress Testing the Reliability of LLM Judges
Sunishchal Dev, Andrew Sloan, Joshua Kavner, Nicholas Kong, Morgan Sandler
- ICLR 2026 AIWILD
- Readers: Everyone
One Model, Many Worlds: Cross-Lingual Fine-Tuning Can Improve Low-Resource Capabilities of Language Model
Tyler Slomianyj, Rudraansh Korlakunta, Victor He, Daniel Gao, Sunishchal Dev, Kevin Zhu, Aryan Shrivastava
- LM4UC@AAAI2026
- Readers: Everyone
SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
Shourya Batra, Pierce Tillman, Samarth Gaggar, Shashank Kesineni, Sunishchal Dev, Kevin Zhu, Ashwinee Panda, Vasu Sharma, Maheep Chaudhary
- ResponsibleFM @ NeurIPS 2025
- Readers: Everyone
Emergent Misalignment in Mixture-of-Experts Models
Daniel Doan, Andrew Y.S. Liao, Arnav Pallem, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Shreyas Sunil Kulkarni
- ResponsibleFM @ NeurIPS 2025
- Readers: Everyone
COMPASS: Context-Modulated PID Attention Steering System for Hallucination Mitigation
Kenji Sahay, Snigdha Pandya, Rohan Nagale, Anna Lin, Shikhar Shiromani, Kevin Zhu, Sunishchal Dev
- AIR-FM Poster
- Readers: Everyone
PALADIN: Self-Correcting Language Model Agents to Cure Tool-Failure Cases
Sri Vatsa Vuddanti, Aarav Shah, Satwik Kumar Chittiprolu, Tony Song, Sunishchal Dev, Kevin Zhu, Maheep Chaudhary
- LaMAS 2026 Oral
- Readers: Everyone
COMPASS: Context-Modulated PID Attention Steering System for Hallucination Mitigation
Kenji Sahay, Snigdha Pandya, Rohan Nagale, Anna Lin, Shikhar Shiromani, Kevin Zhu, Sunishchal Dev
- LaMAS 2026 Oral
- Readers: Everyone
Prompt-Adaptive Quantization: Adaptive Per-Prompt Routing for Efficient LLM Inference
Gabriel Jimenez, Vivann Khanna, Rishi Sastri, Raine Ma, Soham Chatterjee, Kevin Zhu, Sunishchal Dev
- AIR-FM Poster
- Readers: Everyone

View all 35 publications

Co-Authors

View all 148 co-authors