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.CL2026
Training-free Context-adaptive Attention for Efficient Long Context Modeling
Zeng You, Yaofo Chen, Shuhai Zhang +5
Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. These capabilities stem primarily from the self-att…
cs.CL2025
Curse of High Dimensionality Issue in Transformer for Long-context Modeling
Shuhai Zhang, Zeng You, Yaofo Chen +5
Transformer-based large language models (LLMs) excel in natural language processing tasks by capturing long-range dependencies through self-attention mechanisms. However, long-cont…