Ning Xu

Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization

Stepwise High-Level Semantic Alignment for Test-Time Adaptation

Towards Understanding Feature Learning in Parameter Transfer

Toward Fine-Grained Domain Knowledge: Curriculum Pseudo-Labeling for Online Test-Time Adaptation

Puzzle Everything: Benchmarking Knowledge Reasoning through Generalized Puzzle Solving

Enriching Knowledge Distillation with Intra-Class Contrastive Learning

LADA: Enabling Adaptation of Black-Box LLMs to Dynamic Domain Changes at Test Time

Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models

Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning

Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning

Progressively Label Enhancement for Large Language Model Alignment

Can Class-Priors Help Single-Positive Multi-Label Learning?

Selective Label Enhancement Learning for Test-Time Adaptation

Progressively Label Enhancement for Large Language Model Alignment

GenBen:A Genarative Benchmark for LLM-Aided Design

Enriching Knowledge Distillation with Intra-Class Contrastive Learning

Negative-Prompt-driven Alignment for Generative Language Model