Continuous Video Process: Modeling Videos as Continuous Multi-Dimensional Processes for Video Predictionby Gaurav Shrivastava, Abhinav…
Ltri-LLM: Streaming Long Context Inference for LLMs with Training-Free Dynamic Triangular Attention Patternby Hongyin Tang,…
DPGIIL: Dirichlet Process-Deep Generative Model-Integrated Incremental Learning for Clustering in Transmissibility-based Online Structural Anomaly Detectionby…
Slicing Vision Transformer for Flexible Inferenceby Yitian Zhang, Huseyin Coskun, Xu Ma, Huan Wang, Ke…
VisionZip: Longer is Better but Not Necessary in Vision Language Modelsby Senqiao Yang, Yukang Chen,…
Multi-Bin Batching for Increasing LLM Inference Throughputby Ozgur Guldogan, Jackson Kunde, Kangwook Lee, Ramtin PedarsaniFirst…
Solving High-dimensional Inverse Problems Using Amortized Likelihood-free Inference with Noisy and Incomplete Databy Jice Zeng,…
MultiTASC++: A Continuously Adaptive Scheduler for Edge-Based Multi-Device Cascade Inferenceby Sokratis Nikolaidis, Stylianos I. Venieris,…
Fixed-Mean Gaussian Processes for Post-hoc Bayesian Deep Learningby Luis A. Ortega, Simón Rodríguez-Santana, Daniel Hernández-LobatoFirst…
SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantizationby Runsheng Bai, Bo Liu, Qiang LiuFirst…