Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Modelsby Sathya Kamesh Bhethanabhotla, Omar Swelam,…
Nudging: Inference-time Alignment via Model Collaborationby Yu Fei, Yasaman Razeghi, Sameer SinghFirst submitted to arxiv…
Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensemblesby Buu Phan, Brandon…
nextlocllm: next location prediction using LLMsby Shuai Liu, Ning Cao, Yile Chen, Yue Jiang, Gao…
When Graph meets Multimodal: Benchmarking and Meditating on Multimodal Attributed Graphs Learningby Hao Yan, Chaozhuo…
Zero-Shot Offline Imitation Learning via Optimal Transportby Thomas Rupf, Marco Bagatella, Nico Gürtler, Jonas Frey,…
Retraining-Free Merging of Sparse MoE via Hierarchical Clusteringby I-Chun Chen, Hsu-Shen Liu, Wei-Fang Sun, Chen-Hao…
CSA: Data-efficient Mapping of Unimodal Features to Multimodal Featuresby Po-han Li, Sandeep P. Chinchali, Ufuk…
Parallel Digital Twin-driven Deep Reinforcement Learning for User Association and Load Balancing in Dynamic Wireless…
Zero-Shot Generalization of Vision-Based RL Without Data Augmentationby Sumeet Batra, Gaurav S. SukhatmeFirst submitted to…