Scholarlink

We present an efficient method to distill reasoning capabilities into compact video-language models (VLMs) for video question answering (VideoQA). Our approach fine-tunes a 2B-parameter model using only \(\sim \) 900 uncertainty-selected examples, each augmented with synthetic chain-of-thought (CoT) rationales generated by a 4B teacher. Despite its minimal compute cost–under two hours on a single A100 GPU–our method enables the 2B model to outperform VLMs up to 4 \(\times \) larger, and generalize across CinePile, ActivityNet-QA, and MLVU, approaching the performance of its own 4B teacher. A key finding is that placing CoT rationales after the answer–contrary to standard prompting–substantially improves reasoning in compact models. This insight challenges prevailing CoT conventions and reveals new alignment strategies under limited model capacity. Our findings offer a practical blueprint for training deployable, reasoning-rich VLMs suited for mobile and edge applications.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Efficient Reasoning Distillation: Small Video-Language Models via Synthetic CoT and Difficulty-Aware Fine-Tuning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mantek Singh,
  • Jeshwanth Challagundla,
  • Siddharth Raina,
  • Jasmin Jarsania

摘要

We present an efficient method to distill reasoning capabilities into compact video-language models (VLMs) for video question answering (VideoQA). Our approach fine-tunes a 2B-parameter model using only \(\sim \) 900 uncertainty-selected examples, each augmented with synthetic chain-of-thought (CoT) rationales generated by a 4B teacher. Despite its minimal compute cost–under two hours on a single A100 GPU–our method enables the 2B model to outperform VLMs up to 4 \(\times \) larger, and generalize across CinePile, ActivityNet-QA, and MLVU, approaching the performance of its own 4B teacher. A key finding is that placing CoT rationales after the answer–contrary to standard prompting–substantially improves reasoning in compact models. This insight challenges prevailing CoT conventions and reveals new alignment strategies under limited model capacity. Our findings offer a practical blueprint for training deployable, reasoning-rich VLMs suited for mobile and edge applications.