Post-Training Sparse Attention with Double Sparsityby Shuo Yang, Ying Sheng, Joseph E. Gonzalez, Ion Stoica,…
SAMSA: Efficient Transformer for Many Data Modalitiesby Minh Lenhat, Viet Anh Nguyen, Khoa Nguyen, Duong…
Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollersby Moritz Scherer, Luka Macan,…
ZACK: Zero-Overhead LLM Inference Acceleration via Dimensionality Compression of the Key-Value Cacheby Zeyu Zhang, Haiying…
UniMoT: Unified Molecule-Text Language Model with Discrete Token Representationby Juzheng Zhang, Yatao Bian, Yongqiang Chen,…
Social Learning through Interactions with Other Agents: A Surveyby Dylan Hillier, Cheston Tan, Jing JiangFirst…
MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Trainingby…
Amelia: A Large Model and Dataset for Airport Surface Movement Forecastingby Ingrid Navarro, Pablo Ortega-Kral,…
Accelerating Large Language Model Inference with Self-Supervised Early Exitsby Florian ValadeFirst submitted to arxiv on:…
Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Modelsby Sanae Lotfi, Yilun…