Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Modelsby Anshuman Chhabra, Bo…
Sequence Compression Speeds Up Credit Assignment in Reinforcement Learningby Aditya A. Ramesh, Kenny Young, Louis…
Rethinking Data Shapley for Data Selection Tasks: Misleads and Meritsby Jiachen T. Wang, Tianji Yang,…
Out-of-Distribution Adaptation in Offline RL: Counterfactual Reasoning via Causal Normalizing Flowsby Minjae Cho, Jonathan P.…
Scalable Amortized GPLVMs for Single Cell Transcriptomics Databy Sarah Zhao, Aditya Ravuri, Vidhi Lalchand, Neil…
Transformer models as an efficient replacement for statistical test suites to evaluate the quality of…
MVDiff: Scalable and Flexible Multi-View Diffusion for 3D Object Reconstruction from Single-Viewby Emmanuelle Bourigault, Pauline…
Federated Graph Condensation with Information Bottleneck Principlesby Bo Yan, Sihao He, Cheng Yang, Shang Liu,…
Unlearning Backdoor Attacks through Gradient-Based Model Pruningby Kealan Dunnett, Reza Arablouei, Dimity Miller, Volkan Dedeoglu,…
KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantizationby…