Publications

Adaptive Blockwise Search: Inference-Time Alignment for Large Language Models

LLM alignment remains a critical challenge. Inference-time methods provide a flexible alternative to fine-tuning, but their uniform …

M. Atif Quamar, M. Areeb, N. Sharma, A. Shreekumar, J. Rosenthal, M. Kuznetsov, M. Ozgur Ozmen, Z. Berkay Celik

Learning Modal-Mixed Chain-of-Thought Reasoning with Latent Embeddings

We study how to extend chain-of-thought (CoT) beyond language to better handle multimodal reasoning. While CoT helps LLMs and VLMs …

Y. Shao, K. Zhou, M. Atif Quamar, Z. Xu, S. Hao, Z. Wang, Z. Hu, B. Huang

STARS: Segment-level Token Alignment via Rejection Sampling in Large Language Models

Aligning large language models (LLMs) with human values is critical for their safe deployment, but existing methods like fine-tuning …

M. Atif Quamar, M. Areeb, M. Kuznetsov, M. Ozgur Ozmen, Z. Berkay Celik

Logit–Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning

Chain-of-thought (CoT) decoding improves reasoning in LLMs, yet fixed-length rationales and vote-heavy schemes waste tokens and inflate …

M. Atif Quamar, M. Areeb

Decoding Histone Modification Signatures of Non-Coding RNAs via Foundation Models

N. Sharma, M. Atif Quamar, P. Xie