From the 1 of 6 linked papers with an AI index.
6 papers
Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts
Jincheng Xie, Runheng Liu, Heyan Huang +4
The paper introduces EcoSpec, a cost-aware speculative decoding method that selects draft tokens to minimize expert activation overhead in large mixture-of-experts language models,…
AdaPLD: Adaptive Retrieval and Reuse for Efficient Model-Free Speculative Decoding
Runheng Liu, Jincheng Xie, Wen Hu +2
Speculative decoding accelerates generation by verifying multiple drafted tokens in a single target-model forward pass, reducing sequential decoding iterations. Model-free variants…
EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models
Jincheng Xie, Xingchen Xiao, Runheng Liu +3
Unified multimodal embedding spaces underpin practical applications such as cross-modal retrieval and zero-shot recognition. In many real deployments, however, supervision is avail…
SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference
Jincheng Xie, Yawen Ling, Qi Xiao +4
LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed: a few popular large models receive most requests, while many s…
MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
Xingchen Xiao, Heyan Huang, Runheng Liu +1
Large language models (LLMs) are widely used in retrieval-augmented generation (RAG) to incorporate external knowledge at inference time. However, when retrieved contexts are noisy…
Joint single-shot ToA and DoA estimation for VAA-based BLE ranging with phase ambiguity: A deep learning-based approach
Jincheng Xie, Yili Deng, Jiguang He +4
Conventional direction-of-arrival (DoA) estimation methods rely on multi-antenna arrays, which are costly to implement on size-constrained Bluetooth Low Energy (BLE) devices. Virtu…