Profiles2023-2026
Jin Wang
Yunnan University
15Papers
0Last author
20Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers15
- LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language ModelsAuthor 3 of 7AAAI 2026 · 2 citations
- SAPO: Self-Adaptive Process Optimization Makes Small Reasoners StrongerAuthor 3 of 5AAAI 2026 · 1 citation
- Step-GRPO: Enhancing Reasoning Quality and Efficiency via Structured PRM-Based Reinforcement LearningAuthor 2 of 4AAAI 2026 · 1 citation
- DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language ModelsAuthor 2 of 3ACL Findings 2026
- Vision-aware Multimodal Prompt Tuning for Uploadable Multi-source Few-shot Domain AdaptationAuthor 2 of 5AAAI 2025 · 4 citations
- Sample-aware Adaptive Structured Pruning for Large Language ModelsAuthor 3 of 4AAAI 2025 · 1 citation
- Data-Free Black-Box Federated Learning via Zeroth-Order Gradient EstimationAuthor 2 of 3AAAI 2025
- Multi-Attribute Multi-Grained Adaptation of Pre-Trained Language Models for Text Understanding from Bayesian PerspectiveAuthor 2 of 5AAAI 2025
- Instruction Tuning with Retrieval-based Examples Ranking for Aspect-based Sentiment AnalysisAuthor 2 of 4ACL Findings 2024 · 25 citations
- Personalized LoRA for Human-Centered Text UnderstandingAuthor 2 of 5AAAI 2024 · 22 citations
- Zero-Shot Cross-Domain Dialogue State Tracking via Dual Low-Rank AdaptationAuthor 3 of 4ACL 2024 · 5 citations
- Joint Multimodal Entity-Relation Extraction Based on Edge-Enhanced Graph Alignment Network and Word-Pair Relation TaggingAuthor 3 of 4AAAI 2023 · 89 citations
- Learning to Memorize Entailment and Discourse Relations for Persona-Consistent DialoguesAuthor 2 of 4AAAI 2023 · 32 citations
- FedID: Federated Interactive Distillation for Large-Scale Pretraining Language ModelsAuthor 3 of 4EMNLP 2023 · 7 citations
- Domain Generalization via Switch Knowledge Distillation for Robust Review RepresentationAuthor 2 of 5ACL Findings 2023 · 2 citations
