Jie Zhang

Latest

Causally Motivated Sycophancy Mitigation for Large Language Models
Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View
Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing
SFP: Spurious Feature-Targeted Pruning for Out-of-Distribution Generalization
Collaborative Neural Architecture Search for Personalized Federated Learning
Model Decomposition and Reassembly for Purified Knowledge Transfer in Personalized Federated Learning
ParsNets: A Parsimonious Composition of Orthogonal and Low-Rank Linear Networks for Zero-Shot Learning
Amend to Alignment: Decoupled Prompt Tuning for Mitigating Spurious Correlation in Vision-Language Models
Causally Motivated Personalized Federated Invariant Learning with Shortcut-Averse Information-Theoretic Regularization
Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring
DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning
OTAS: An Elastic Transformer Serving System via Token Adaptation
Learning Personalized Causally Invariant Representations for Heterogeneous Federated Clients
Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learning
Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators
On the Robustness of Neural-enhanced Video Streaming Against Adversarial Attacks
SwapPrompt: Test-Time Prompt Adaptation for Vision-Language Models
Towards Unbiased Training in Federated Open-world Semi-supervised Learning
PROPHET: Conflict-Free Sharding Blockchain via Byzantine-Tolerant Deterministic Ordering
From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization
RuleDRL: Reliability-Aware SFC Provisioning with Bounded Approximations in Dynamic Environments
Towards Data-independent Knowledge Transfer in Model-heterogeneous Federated Learning
Hierarchical Channel-spatial Encoding for Communication-efficient Collaborative Learning
Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression
Layer-wised Model Aggregation for Personalized Federated Learning
Adaptive Vertical Federated Learning on Unbalanced Features
Parameterized Knowledge Transfer for Personalized Federated Learning
Adaptive Federated Learning on Non-IID Data with Resource Constraint
Dual-view Attention Networks for Single Image Super-Resolution
Stochastic Scheduling Towards Cost Efficient Network Function Virtualization in Edge Cloud
Take Renewable Energy into CRAN toward Green Wireless Access Networks