2 papers
cs.CL2026
DistillLens: Symmetric Knowledge Distillation Through Logit Lens
Manish Dhakal, Uthman Jinadu, Anjila Budathoki +2
Standard Knowledge Distillation (KD) compresses Large Language Models (LLMs) by optimizing final outputs, yet it typically treats the teacher's intermediate layer's thought process…
cs.CV2025
GFT: Graph Feature Tuning for Efficient Point Cloud Analysis
Manish Dhakal, Venkat R. Dasari, Rajshekhar Sunderraman +1
Parameter-efficient fine-tuning (PEFT) significantly reduces computational and memory costs by updating only a small subset of the model's parameters, enabling faster adaptation to…