5 papers
FOCUS: DLLMs Know How to Tame Their Compute Bound
Kaihua Liang, Xin Tan, An Zhong +2
Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high decoding cost. In this work, we identi…
PRISM: Parametrically Refactoring Inference for Speculative Sampling Draft Models
Xuliang Wang, Yuetao Chen, Maochan Zhen +5
Large Language Models (LLMs), constrained by their auto-regressive nature, suffer from slow decoding. Speculative decoding methods have emerged as a promising solution to accelerat…
Multimodal Learning for Fake News Detection in Short Videos Using Linguistically Verified Data and Heterogeneous Modality Fusion
Shanghong Li, Chiam Wen Qi Ruth, Hong Xu +1
The rapid proliferation of short video platforms has necessitated advanced methods for detecting fake news. This need arises from the widespread influence and ease of sharing misin…
MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs
Hongjun Xu, Junxi Xia, Weisi Yang +2
Deploying Mamba models on microcontrollers (MCUs) remains challenging due to limited memory, the lack of native operator support, and the absence of embedded-friendly toolchains. W…
Teola: Towards End-to-End Optimization of LLM-based Applications
Xin Tan, Yimin Jiang, Yitao Yang +1
Large language model (LLM)-based applications consist of both LLM and non-LLM components, each contributing to the end-to-end latency. Despite great efforts to optimize LLM inferen…