3 papers
cs.CV2026
Anti-Shortcut Distillation via Temporal Negative Knowledge Transfer
Syed Muhammad Raza, Omer Tariq, Jeongbae Son
Knowledge distillation (KD) trains a compact student by attracting it towards a converged teacher. It is silent about which directions the teacher itself learned to suppress: repul…
cs.LG2026
SAD-LoRA: Spectral Alignment for Low-Rank Knowledge Distillation
Omer Tariq, Syed Muhammad Raza, Jeongbae Son
Distilling a fine-tuned teacher into a LoRA-adapted student is a standard recipe for parameter-efficient compression, but output-level KD does not explicitly control which rank-…
cs.CV2026
Uncertainty-Aware and Decoder-Aligned Learning for Video Summarization
Omer Tariq, Syed Muhammad Raza, Jeongbae Son
Video summarization aims to produce a compact representation of a long video by selecting a subset of temporally important segments that best reflect human preferences. This task i…