Yulun Zhang

Quantized reasoning models overthink more, negating efficiency gains, but a new method precisely targets and penalizes these "overthinking" tokens without retraining.

This paper proposes SWRouter, a Similarity-Contractive Window Router for multi-turn large language model routing that combines a similarity-based context segmentation mechanism for prompt construction with a dual-metric evaluation framework that decouples construction accuracy from router performance.

Achieving a 96% reduction in computation for RAW video restoration with minimal performance loss opens new avenues for efficient video processing in real-time applications.