10 citations · 20 across the 22 of their papers we have counts for
24 papers
TideKV: Delayed KV Eviction via Layer-Wise Chunked Prefill for Memory-Efficient Long-Context LLM Inference
Yu Wang, Zhu Wang, Ning Hu +4
Long-context large language model (LLM) inference is important for modern intelligent applications but remains constrained by peak memory during prompt prefill. Existing KV cache c…
Act2Intention: A Benchmark For Developing Active Mobile Agents Through Inferring User Intention from GUI Actions
Xiaokai Yan, Jingtao Ding, Yong Li +1
Mobile GUI Agents powered by multimodal large language models (MLLMs) show promise in human-computer intelligence. However, current research primarily focuses on reactive task exec…
Progressive: A Teacher-Student Progressive Co-Evolving Knowledge Distillation Method for Substantial Model Compression
Tiancong Cheng, Ying Zhang, Zhiwen Yu +2
Knowledge distillation (KD) is a widely utilized technique for transferring knowledge from a large model (the teacher) to a smaller model (the student). Owing to its flexibility an…
Think Thrice Before You Speak: Dual knowledge-enhanced Theory-of-Mind Reasoning for Persuasive Agents
Minghui Ma, Bin Guo, Runze Yang +7
Persuasive dialogue requires reasoning about others' latent mental states, a capability known as Theory of Mind (ToM). However, due to reliance on simple prompting strategies and i…
Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding
Ke Ma, Jiaqi Tang, Bin Guo +8
Proactive streaming video understanding requires Video-LLMs to decide when to respond as a video unfolds, a task where existing methods often fall short due to their implicit, quer…
Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents
Shijun Lei, Hongyu Wang, Yunji Liang +3
In-group favoritism refers to the phenomena of favoring members of one's in-group over out-group members and is widely observed in numerous social cooperative behaviors. Recently,…
Foundation Models Defining A New Era In Sensor-based Human Activity Recognition: A Survey And Outlook
Sizhen Bian, Mengxi Liu, Lala Shakti Swarup Ray +7
Sensor-based Human Activity Recognition (HAR) underpins many ubiquitous and wearable computing applications, yet current models remain limited by scarce labels, sensor heterogeneit…
AppFlow: Memory Scheduling for Cold Launch of Large Apps on Mobile and Vehicle Systems
Xiaochen Li, Sicong Liu, Bin Guo +4
GB-scale large apps like on-device LLMs and rich media editors are becoming the next-generation trend, but their heavy memory and I/O demands, especially during multitasking, cause…
Detecting Fake Reviewer Groups in Dynamic Networks: An Adaptive Graph Learning Method
Jing Zhang, Ke Huang, Yao Zhang +2
The proliferation of fake reviews, often produced by organized groups, undermines consumer trust and fair competition on online platforms. These groups employ sophisticated strateg…
MeCo: Enhancing LLM-Empowered Multi-Robot Collaboration via Similar Task Memoization
Baiqing Wang, Helei Cui, Bo Zhang +3
Multi-robot systems have been widely deployed in real-world applications, providing significant improvements in efficiency and reductions in labor costs. However, most existing mul…
VIL2C: Value-of-Information Aware Low-Latency Communication for Multi-Agent Reinforcement Learning
Qian Zhang, Zhuo Sun, Yao Zhang +3
Inter-agent communication serves as an effective mechanism for enhancing performance in collaborative multi-agent reinforcement learning(MARL) systems. However, the inherent commun…
Mitigating Sample-Level Imbalance via Probabilistic Separation for Adaptive Multimodal Fusion
Zhiwen Yu, Zhaocheng Liu, Xiaoqing Liu +2
Multimodal learning faces modality imbalance, where dominant modalities suppress weaker ones due to inconsistent convergence rates. Existing static or heuristic methods overlook sa…
MemoCue: Empowering LLM-Based Agents for Human Memory Recall via Strategy-Guided Querying
Qian Zhao, Zhuo Sun, Bin Guo +1
Agent-assisted memory recall is one critical research problem in the field of human-computer interaction. In conventional methods, the agent can retrieve information from its equip…
JointDistill: Adaptive Multi-Task Distillation for Joint Depth Estimation and Scene Segmentation
Tiancong Cheng, Ying Zhang, Yuxuan Liang +3
Depth estimation and scene segmentation are two important tasks in intelligent transportation systems. A joint modeling of these two tasks will reduce the requirement for both the…
SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity
Ke Ma, Jiaqi Tang, Bin Guo +8
Despite the growing integration of deep models into mobile terminals, the accuracy of these models declines significantly due to various deployment interferences. Test-time adaptat…
AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices
Yuzhan Wang, Sicong Liu, Bin Guo +6
Deep learning is reshaping mobile applications, with a growing trend of deploying deep neural networks (DNNs) directly to mobile and embedded devices to address real-time performan…
UbiHR: Resource-efficient Long-range Heart Rate Sensing on Ubiquitous Devices
Haoyu Bian, Bin Guo, Sicong Liu +3
Ubiquitous on-device heart rate sensing is vital for high-stress individuals and chronic patients. Non-contact sensing, compared to contact-based tools, allows for natural user mon…
AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments
Cheng Fang, Sicong Liu, Zimu Zhou +4
On-device adapting to continual, unpredictable domain shifts is essential for mobile applications like autonomous driving and augmented reality to deliver seamless user experiences…
AdaBridge: Dynamic Data and Computation Reuse for Efficient Multi-task DNN Co-evolution in Edge Systems
Lehao Wang, Zhiwen Yu, Sicong Liu +3
Running multi-task DNNs on mobiles is an emerging trend for various applications like autonomous driving and mobile NLP. Mobile DNNs are often compressed to fit the limited resourc…
Deep Learning Inference on Heterogeneous Mobile Processors: Potentials and Pitfalls
Sicong Liu, Wentao Zhou, Zimu Zhou +5
There is a growing demand to deploy computation-intensive deep learning (DL) models on resource-constrained mobile devices for real-time intelligent applications. Equipped with a v…
AdaOper: Energy-efficient and Responsive Concurrent DNN Inference on Mobile Devices
Zheng Lin, Bin Guo, Sicong Liu +4
Deep neural network (DNN) has driven extensive applications in mobile technology. However, for long-running mobile apps like voice assistants or video applications on smartphones,…
Joint Identifiability of Cross-Domain Recommendation via Hierarchical Subspace Disentanglement
Jing Du, Zesheng Ye, Bin Guo +2
Cross-Domain Recommendation (CDR) seeks to enable effective knowledge transfer across domains. Existing works rely on either representation alignment or transformation bridges, but…
The Future of Cognitive Strategy-enhanced Persuasive Dialogue Agents: New Perspectives and Trends
Mengqi Chen, Bin Guo, Hao Wang +6
Persuasion, as one of the crucial abilities in human communication, has garnered extensive attention from researchers within the field of intelligent dialogue systems. We humans te…
EchoPFL: Asynchronous Personalized Federated Learning on Mobile Devices with On-Demand Staleness Control
Xiaochen Li, Sicong Liu, Zimu Zhou +3
The rise of mobile devices with abundant sensory data and local computing capabilities has driven the trend of federated learning (FL) on these devices. And personalized FL (PFL) e…