12 papers
TRINE: A Token-Aware, Runtime-Adaptive FPGA Inference Engine for Multimodal AI
Hyunwoo Oh, Hanning Chen, Sanggeon Yun +5
Multimodal stacks that mix ViTs, CNNs, GNNs, and transformer NLP strain embedded platforms because their compute/memory patterns diverge and hard real-time targets leave little sla…
MERIT: Multi-domain Efficient RAW Image Translation
Wenjun Huang, Shenghao Fu, Yian Jin +10
RAW images captured by different camera sensors exhibit substantial domain shifts due to varying spectral responses, noise characteristics, and tone behaviors, complicating their d…
Cauchy-Schwarz Fairness Regularizer
Yezi Liu, Hanning Chen, Wenjun Huang +2
Group fairness in machine learning is often enforced by adding a regularizer that reduces the dependence between model predictions and sensitive attributes. However, existing regul…
Mitigating Bias in Graph Hyperdimensional Computing
Yezi Liu, William Youngwoo Chung, Yang Ni +2
Graph hyperdimensional computing (HDC) has emerged as a promising paradigm for cognitive tasks, emulating brain-like computation with high-dimensional vectors known as hypervectors…
LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples
Yezi Liu, Hanning Chen, Wenjun Huang +2
Large language models (LLMs) possess vast knowledge acquired from extensive training corpora, but they often cannot remove specific pieces of information when needed, which makes i…
Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearning
Yezi Liu, Hanning Chen, Wenjun Huang +2
Unlearning in large foundation models (e.g., LLMs) is essential for enabling dynamic knowledge updates, enforcing data deletion rights, and correcting model behavior. However, exis…