10 papers
MosaicQuant: Inlier-Outlier Disaggregation for Unified 4-Bit LLM Quantization
Yangjia Hu, Haodong Wang, Zicong Hong +8
4-bit quantization significantly reduces the memory footprint and accelerates the inference of large language models (LLMs). However, its limited bit-width representation struggles…
Director: Accelerating Distributed MoE Serving via Online Proactive Expert Placement
Qianli Liu, Kaibin Guo, Zicong Hong +5
Expert parallelism has become the prevailing paradigm to serve Mixture-of-Experts (MoE) models. Its efficiency depends on the communication and computation latencies of the GPUs, w…
TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization
Haodong Wang, Junjie Liu, Zicong Hong +4
4-bit quantization reduces the memory footprint and latency of large language model inference, but its aggressive precision reduction can severely degrade accuracy. Prior methods a…
PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence
Zile Wang, Qianli Liu, Kaibin Guo +4
Deploying large language model (LLM) on edge device enables personalized LLM agents for various users. The growing availability of diverse personalized agents presents a unique opp…
MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation
Changli Wu, Haodong Wang, Jiayi Ji +5
Most existing 3D referring expression segmentation (3DRES) methods rely on dense, high-quality point clouds, while real-world agents such as robots and mobile phones operate with o…
DocTalk: Scalable Graph-based Dialogue Synthesis for Enhancing LLM Conversational Capabilities
Jing Yang Lee, Hamed Bonab, Nasser Zalmout +6
Large Language Models (LLMs) are increasingly employed in multi-turn conversational tasks, yet their pre-training data predominantly consists of continuous prose, creating a potent…