6 papers
LiST: Local-Simplex Test-Time LoRA Fusion
Yihua Shao, Jia Li, Siyu Chen +12
Task-specific LoRA adapters offer a modular way to specialize large language and vision-language models. However, existing adapter composition methods are mostly static and cannot…
Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning
Xinyu Luo, Hui Liu, Yihua Shao +3
On-device in-context learning (ICL) relies on pre-inference retrieval to select demonstrations for useful context before downstream model inference. This retrieval must exploit tas…
A 33.6-136.2 TOPS/W Nonlinear Analog Computing-In-Memory Macro for Multi-bit LSTM Accelerator in 65 nm CMOS
Junyi Yang, Xinyu Luo, Ye Ke +7
The energy efficiency of analog computing-in-memory (ACIM) accelerator for recurrent neural networks, particularly long short-term memory (LSTM) network, is limited by the high pro…
Efficient Test-Time Adaptation through Latent Subspace Coefficients Search
Xinyu Luo, Jie Liu, Kecheng Chen +6
Real-world deployment often exposes vision models to distribution shifts, making test-time adaptation (TTA) important for reliable prediction. Existing TTA methods can be difficult…
SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks
Xinyu Luo, Kecheng Chen, Pao-Sheng Vincent Sun +3
Spiking Neural Networks (SNNs), as a biologically plausible alternative to Artificial Neural Networks (ANNs), have demonstrated advantages in terms of energy efficiency, temporal p…
Test-time Adaptation for Foundation Medical Segmentation Model without Parametric Updates
Kecheng Chen, Xinyu Luo, Tiexin Qin +5
Foundation medical segmentation models, with MedSAM being the most popular, have achieved promising performance across organs and lesions. However, MedSAM still suffers from compro…