Atif Quamar

Atif Quamar

23, New Delhi

About

Currently working on diffusion language models at Virginia University. Previously, at UC San Diego, I worked on introducing a new paradigm for reasoning in vision language models, and at Purdue University, my work was focused on inference-time alignment of language models. I also founded Insituate, where we shipped agentic systems to banks and judiciary. I earned my bachelors degree in Computer Science and Biosciences from IIIT Delhi in 2024.

My research focuses on advancing the reasoning capabilities of language models and developing trustworthy AI systems that are aligned with human values. While LLMs are a primary focus, I am also open to exploring other areas that can meaningfully expand the capabilities of intelligent systems.

I am currently looking for research opportunities in both academia (PhD) and industry for a 2026 start.

Interests
  • Reasoning in Language Models
  • Trustworthiness in AI Systems
  • Agentic System Capabilities
  • Reinforcement Learning
Education

  • B.Tech in Computer Science and Biosciences, 2020-2024

    IIIT - Delhi

Publications

Quickly discover relevant content by filtering publications.
M. Atif Quamar, M. Areeb, N. Sharma, A. Shreekumar, J. Rosenthal, M. Kuznetsov, M. Ozgur Ozmen, Z. Berkay Celik (2025). Adaptive Blockwise Search: Inference-Time Alignment for Large Language Models.

Project arXiv

Y. Shao, K. Zhou, M. Atif Quamar, Z. Xu, S. Hao, Z. Wang, Z. Hu, B. Huang (2025). Learning Modal-Mixed Chain-of-Thought Reasoning with Latent Embeddings. Under review at The 14th International Conference of Learning Representations (ICLR 2026).

Project OpenReview

M. Atif Quamar, M. Areeb, M. Kuznetsov, M. Ozgur Ozmen, Z. Berkay Celik (2025). STARS: Segment-level Token Alignment via Rejection Sampling in Large Language Models. Accepted at the Frontiers in Probabilistic Inference: Sampling Meets Learning workshop at NeurIPS 2025.

Project arXiv

M. Atif Quamar, M. Areeb (2025). Logit–Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning. Accepted at The Efficient Reasoning workshop at NeurIPS 2025.

OpenReview

N. Sharma, M. Atif Quamar, P. Xie (2025). Decoding Histone Modification Signatures of Non-Coding RNAs via Foundation Models. Accepted at the Multi-modal Foundation Models and Large Language Models for Life Sciences workshop at NeurIPS 2025.

OpenReview

Experience

 
 
 
 
 
University of Virginia
Research Intern
University of Virginia
Oct 2025 – Present Charlottesville, Virginia, United States
Working on improving masked diffusion language models by designing masking curricula and principled unmasking policies to improve non-autoregressive decoding efficiency and accuracy.
 
 
 
 
 
University of California - San Diego
Research Intern
University of California - San Diego
Jul 2025 – Oct 2025 San Diego, California, United States
Working on multimodal reasoning - interleaving text and visuals within the chain-of-thought, enabling models to “think” with sketches, diagrams, and images. This work bridges language and vision to solve complex problems with richer, more interpretable reasoning.
 
 
 
 
 
Purdue University
Research Intern
Purdue University
Feb 2025 – Jul 2025 West Lafayette, Indiana, United States
Worked on inference-time alignment method that outperforms Best-of-N decoding by over 30%, while reducing reward model calls by 20%. Aligned LLMs in reducing harmlessness, improved reasoning and positive sentiment generation.
 
 
 
 
 
Insituate
Founder & CTO
Insituate
Sep 2023 – Feb 2025 New Delhi, India

Built agentic software for the Supreme Court of India, Mizuho Bank, PNC Bank and Indian High Courts.

Insituate is a no-code platform that enables companies to make custom AI agents for industry-specific needs, and allowing them to productionize these copilots 10x faster securely on their data.

 
 
 
 
 
Tweek Labs
Software Engineering Intern
Tweek Labs
May 2023 – Jul 2020 New Delhi, India
Engineered the company’s android’s application. Worked on Jetpack-Compose library for developing. Developed multiple features currently running in production.
 
 
 
 
 
Singapore University of Technology & Design
Research Intern
Singapore University of Technology & Design
Sep 2022 – Dec 2021 Singapore
Designed an edge-friendly Stream Processing Engine (SPE) with a congestion-aware scheduler, optimizing task-to-resource allocation using graph-based optimization.

Projects

Adaptive Blockwise Search : Inference-Time Alignment for Large Language Models
M. Atif Quamar 1 , M. Areeb , N. Sharma , A. Shreekumar , J. Rosenthal , M. Kuznetsov , M. Ozgur Ozmen , Z. Berkay Celik
Adaptively focuses computation on the most critical early tokens during LLM decoding, boosting alignment performance across multiple tasks compared to Best-of-N and fine-tuning.
Adaptive Blockwise Search : Inference-Time Alignment for Large Language Models
Learning Modal-Mixed Chain-of-Thought Reasoning with Latent Embeddings
Y. Shao , K. Zhou , M. Atif Quamar , Z. Xu , S. Hao , Z. Wang , Z. Hu , B. Huang
Modal-mixed chain-of-thought lets a VLM interleave text with compact latent visual “sketches”, using a diffusion-based latent decoder with SFT+RL training to boost vision-intensive reasoning while adding only modest inference overhead.
Learning Modal-Mixed Chain-of-Thought Reasoning with Latent Embeddings
STARS - Segment-level Token Alignment via Rejection Sampling in Large Language Models
M. Atif Quamar 1 , M. Areeb , M. Kuznetsov , M. Ozgur Ozmen , Z. Berkay Celik
Decoding method that aligns large language models with human preferences at inference time by accepting only high-reward text segments, boosting quality without retraining.
STARS - Segment-level Token Alignment via Rejection Sampling in Large Language Models

Contact