EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the…
Best of Three Worlds: Adaptive Experimentation for Digital Marketing in Practiceby Tanner Fiez, Houssam Nassif,…
Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMsby Yeonhong Park, Jake Hyun, SangLyul Cho, Bonggeun…
CodaMal: Contrastive Domain Adaptation for Malaria Detection in Low-Cost Microscopesby Ishan Rajendrakumar Dave, Tristan de…
Interpretable Generative Adversarial Imitation Learningby Wenliang Liu, Danyang Li, Erfan Aasi, Roberto Tron, Calin BeltaFirst…
Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustmentby Rui Yang, Xiaoman Pan, Feng…
QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inferenceby Taesu Kim, Jongho Lee, Daehyun…
Accelerating Parallel Sampling of Diffusion Modelsby Zhiwei Tang, Jiasheng Tang, Hao Luo, Fan Wang, Tsung-Hui…
Fast Vocabulary Transfer for Language Model Compressionby Leonidas Gee, Andrea Zugarini, Leonardo Rigutini, Paolo TorroniFirst…
LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wildby Ziyu Zhao, Leilei…