collaborators

6 papers

cs.LG2026

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation

Yuki Ichihara, Naoto Iwase, Mohammad Atif Quamar +1

On-Policy Self-Distillation (OPSD) is commonly interpreted as the transfer of privileged information: a teacher observes the verified solution to the target problem and supervises…

stat.ML2026

Reliable Chain-of-Thought via Prefix Consistency

Naoto Iwase, Yuki Ichihara, Mohammad Atif Quamar +1

Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority voting (MV), a test-time techn…

cs.CL2026

STARS: Synchronous Token Alignment for Robust Supervision in Large Language Models

Mohammad Atif Quamar, Mohammad Areeb, Mikhail Kuznetsov +2

Aligning large language models (LLMs) with human values is crucial for safe deployment. Inference-time techniques offer granular control over generation; however, they rely on mode…

cs.AI2026

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

Yifei Shao, Kun Zhou, Ziming Xu +5

We study how to extend chain-of-thought (CoT) beyond language to better handle multimodal reasoning. While CoT helps LLMs and VLMs articulate intermediate steps, its text-only form…

cs.CL2025

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

Mohammad Atif Quamar, Mohammad Areeb

Chain-of-Thought (CoT) prompting is a key technique for enabling complex reasoning in large language models. However, generating full, fixed-length rationales is computationally wa…

cs.CL2025

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

Mohammad Atif Quamar, Mohammad Areeb, Nishant Sharma +5

LLM alignment remains a critical challenge. Inference-time methods provide a flexible alternative to fine-tuning, but their uniform computational effort often yields suboptimal ali…