RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracyby Geonho Lee,…
R.I.P.: A Simple Black-box Attack on Continual Test-time Adaptationby Trung-Hieu Hoang, Duc Minh Vo, Minh…
Graph Community Augmentation with GMM-based Modeling in Latent Spaceby Shintaro Fukushima, Kenji YamanishiFirst submitted to…
Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendenceby Qianren Mao, Weifeng…
Leveraging Intermediate Neural Collapse with Simplex ETFs for Efficient Deep Neural Networksby Emily LiuFirst submitted…
A Deep Generative Model for the Design of Synthesizable Ionizable Lipidsby Yuxuan Ou, Jingyi Zhao,…
Bilinear Convolution Decomposition for Causal RL Interpretabilityby Narmeen Oozeer, Sinem Erisken, Alice RiggFirst submitted to…
Calibration through the Lens of Interpretabilityby Alireza Torabian, Ruth UrnerFirst submitted to arxiv on: 1…
STEVE-Audio: Expanding the Goal Conditioning Modalities of Embodied Agents in Minecraftby Nicholas Lenzen, Amogh Raut,…
Token Cropr: Faster ViTs for Quite a Few Tasksby Benjamin Bergner, Christoph Lippert, Aravindh MahendranFirst…