Lijun Zhang

22

Papers

84

Total Citations

Papers (22)

CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition

Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs

NeurIPS 2025arXiv

Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors

Towards Unbiased Information Extraction and Adaptation in Cross-Domain Recommendation

Continuous Subspace Optimization for Continual Learning

Online Nonsubmodular Optimization with Delayed Feedback in the Bandit Setting

Deep Semantic Graph Transformer for Multi-View 3D Human Pose Estimation

Deep Homography Estimation for Visual Place Recognition

Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization

High-Probability Bound for Non-Smooth Non-Convex Stochastic Optimization with Heavy Tails

To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO

Non-stationary Online Convex Optimization with Arbitrary Delays

Small-loss Adaptive Regret for Online Convex Optimization

Generalization Bound and New Algorithm for Clean-Label Backdoor Attack

Efficient Stochastic Approximation of Minimax Excess Risk Optimization

Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning

Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond

Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding

External Knowledge Injection for CLIP-Based Class-Incremental Learning

Training Verification-Friendly Neural Networks via Neuron Behavior Consistency

Revisiting Projection-Free Online Learning with Time-Varying Constraints

Non-stationary Projection-Free Online Learning with Dynamic and Adaptive Regret Guarantees