Vikas Chandra

Director, AI, Reality Labs, Meta

Joined

September 2020

Names

Vikas Chandra (Preferred)

Emails

****@fb.com (Confirmed)

****@meta.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Director, AI

Reality Labs, Meta (meta.com)

2018 – Present

Director, ML

R&D, Arm (arm.com)

2007 – 2018

PhD student

ECE, Carnegie Mellon University (cmu.edu)

2000 – 2004

Advisors, Relations & Conflicts

Coworker

Forrest Iandola

2022 – 2024

Coworker

Yunyang Xiong

2000 – 2024

Expertise

Computer Vision

2015 – 2024

Efficient Deep Learning

2015 – 2024

Publications

MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment
Hanxian Huang, Igor Fedorov, Andrey Gromov, Bernard Beckerman, Naveen Suda, David Eriksson, Maximilian Balandat, Rylan Conway, Patrick Huber, Chinnadhurai Sankar, Ayushi Dalmia, Zechun Liu, Lemeng Wu, Tarek Elgamal, Adithya Sagar, Vikas Chandra, Raghuraman Krishnamoorthi
- ACL 2026 Industry Track Oral
- Readers: Everyone
RPRA: Predicting an LLM-Judge for Efficient but Performant Inference
Dylan R. Ashley, Gael Le Lan, Changsheng Zhao, Naina Dhingra, Zhipeng Cai, Ernie Chang, Mingchen Zhuge, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber
- Agentic AI in the Wild: From Hallucinations to Reliable Autonomy Poster
- Readers: Everyone
RPRA: Predicting an LLM-Judge for Efficient but Performant Inference
Dylan R. Ashley, Gael Le Lan, Changsheng Zhao, Naina Dhingra, Zhipeng Cai, Ernie Chang, Mingchen Zhuge, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber
- MALGAI
- Readers: Everyone
Neural Computers
Mingchen Zhuge, Changsheng Zhao, Haozhe Liu, Zijian Zhou, Shuming Liu, Wenyi Wang, Ernie Chang, Gael Le Lan, Junjie Fei, Wenxuan Zhang, Yasheng SUN, Yunyang Xiong, Zechun Liu, Zhipeng Cai, Yining Yang, Yuandong Tian, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber
- ICLR 2026 Workshop World Models
- Readers: Everyone
AI with Recursive Self-Improvement
Mingchen Zhuge, Ailing Zeng, Deyao Zhu, Sherry Yang, Vikas Chandra, Jürgen Schmidhuber
- ICLR 2026 Workshop Proposals
- Readers: Everyone
Know When to Fold 'Em: Predicting an LLM-Judge for Efficient but Performant Inference
Dylan R. Ashley, Gael Le Lan, Changsheng Zhao, Naina Dhingra, Zhipeng Cai, Ernie Chang, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber
- Submitted to ICLR 2026
- Readers: Everyone
MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
Changsheng Zhao, Ernie Chang, Zechun Liu, Chia-Jung Chang, Wei Wen, Chen Lai, Sheng Cao, Yuandong Tian, Raghuraman Krishnamoorthi, Yangyang Shi, Vikas Chandra
- ICLR 2026 Poster
- Readers: Everyone
DepthLM: Metric Depth from Vision Language Models
Zhipeng Cai, Ching-Feng Yeh, Hu Xu, Zhuang Liu, Gregory P. Meyer, Xinjie Lei, Changsheng Zhao, Shang-Wen Li, Vikas Chandra, Yangyang Shi
- ICLR 2026 Oral
- Readers: Everyone
Streamlining Language Models via Semantic Basis Analysis
Yang Li, Daniel Agyei Asante, Changsheng Zhao, Ernie Chang, Yangyang Shi, Vikas Chandra
- Accepted by TMLR
- Readers: Everyone
ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
Zechun Liu, Changsheng Zhao, Hanxian Huang, Sijia Chen, Jing Zhang, Jiawei Zhao, Scott Roy, Lisa Jin, Yunyang Xiong, Yangyang Shi, Lin Xiao, Yuandong Tian, Bilge Soran, Raghuraman Krishnamoorthi, Tijmen Blankevoort, Vikas Chandra
- NeurIPS 2025 poster
- Readers: Everyone

View all 160 publications

Co-Authors

View all 339 co-authors