3 citations · 4 across the 8 of their papers we have counts for
7 papers · 1 filter
ProtoFlow: Prototype-Guided Flow Matching for Multivariate Time Series Forecasting
Shibo Feng, Wanjin Feng, Yang Qiu +3
Generative modeling has shown strong promise for multivariate time mseries (MTS) forecasting, especially scale to high-dimensional settings. Diffusion-based methods achieve competi…
Distribution-Conditioned Task Routing for Class-Incremental Learning
Longhuan Xu, Zhipeng Zhou, Wei Ji +3
Parameter-efficient adaptation enables continual learners to acquire task-specific knowledge through compact model updates while maintaining strong within-task performance. However…
MedFlow: Class-Aware Multi-Scale Generation for Medical Time-Series Synthesis
Yanhao Huang, Shibo Feng, Wanjin Feng +2
Synthetic medical time-series generation can alleviate data scarcity and support the development of reliable clinical prediction models. However, existing methods mainly focus on m…
VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction
Zhifei Xie, Jiaqi Lang, Ze An +7
Conversational systems, such as duplex speech language models (SLMs), still lack a streaming, accurate, and empathetic memory system as their soul. We introduce VoiceMem, a simple…
PACT: Preserving Anchored Cores in Task-vectors for Model Merging
Ningyuan Shi, Zhipeng Zhou, Hao Wang +2
Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model. Most exi…
Delve into the Applicability of Advanced Optimizers for Multi-Task Learning
Zhipeng Zhou, Linxiao Cao, Pengcheng Wu +2
Multi-Task Learning (MTL) is a foundational machine learning problem that has seen extensive development over the past decade. Recently, various optimization-based MTL approaches h…
PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
Zhifei Xie, Zongzheng Hu, Fangda Ye +10
Proactivity is a core expectation for AGI. Prior work remains largely confined to laboratory settings, leaving a clear gap in real-world proactive agent: depth, complexity, ambigui…