Yongbin Li

Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity ACL 2026 Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions ACL 2026 EvoRoute: Experience-Driven Self-Routing LLM Agent Systems ACL 2026 Large Language Model Unlearning for Source Code AAAI 2026 MOA: Multi-Objective Alignment for Role-Playing Agents ACL 2026 RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization ACL 2026 RollArt: Disaggregated Multi-Task Agentic RL Training at Scale OSDI 2026 Selective Weak-to-Strong Generalization AAAI 2026 CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization EMNLP 2025 Debate Helps Weak-to-Strong Generalization AAAI 2025 DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking ACL 2025 DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling ACL 2025 EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models EMNLP 2025 EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning ACL 2025 ExploraCoder: Advancing Code Generation for Multiple Unseen APIs via Planning and Chained Exploration ACL 2025 IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization ACL 2025 MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct ACL 2025 OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction ACL 2025 On the Role of Attention Heads in Large Language Model Safety ICLR 2025 Reverse Preference Optimization for Complex Instruction Following ACL 2025 Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining ICLR 2025 SDPO: Segment-Level Direct Preference Optimization for Social Agents ACL 2025 StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization ICLR 2025 Supervised Optimism Correction: Be Confident When LLMs Are Sure ACL 2025 Transferable Post-training via Inverse Value Learning NAACL 2025 Aligning Logits Generatively for Principled Black-Box Knowledge Distillation CVPR 2024 DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories ACL 2024 Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning NAACL 2024 EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations NeurIPS 2024 Fine-Tuning Language Models with Reward Learning on Policy NAACL 2024 FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents EMNLP 2024 Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use ACL 2024 How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States EMNLP 2024 Improving Factual Consistency of News Summarization by Contrastive Preference Optimization EMNLP 2024 Iterative Forward Tuning Boosts In-Context Learning in Language Models ACL 2024 Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch ICML 2024 Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA EMNLP 2024 Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models ACL 2024 One-Shot Learning as Instruction Data Prospector for Large Language Models ACL 2024 Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts COLING 2024 Preference Ranking Optimization for Human Alignment AAAI 2024 Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment COLING 2024 Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models COLING 2024 Self-Retrieval: End-to-End Information Retrieval with One Large Language Model NeurIPS 2024 Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer CVPR 2024 SoFA: Shielded On-the-fly Alignment via Priority Rule Following ACL 2024 Tree-Instruct: A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment COLING 2024 UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt COLING 2024 API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs EMNLP 2023 Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs NeurIPS 2023 CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality ACL 2023 Causal Document-Grounded Dialogue Pre-training EMNLP 2023 Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue EMNLP 2023 Diversify Question Generation with Retrieval-Augmented Style Transfer EMNLP 2023 Domain Incremental Lifelong Learning in an Open World ACL 2023 Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection EMNLP 2023 Graphix-T5: Mixing Pre-trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing AAAI 2023 History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling ACL 2023 Improving Question Generation with Multi-level Content Planning EMNLP 2023 Long-Tailed Question Answering in an Open World ACL 2023 Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark ACL 2023 PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts ACL 2023 Plan-then-Seam: Towards Efficient Table-to-Text Generation EACL 2023 Sequence Parallelism: Long Sequence Training from System Perspective ACL 2023 Speech-Text Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment ACL 2023 SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents NeurIPS 2023 SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph AAAI 2023 Unified Language Representation for Question Answering over Text, Tables, and Images ACL 2023 Universal Information Extraction with Meta-Pretrained Self-Retrieval ACL 2023 A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots ACL 2022 CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation EMNLP 2022 Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddings EMNLP 2022 Doc2Bot: Accessing Heterogeneous Documents via Conversational Bots EMNLP 2022 Estimating Soft Labels for Out-of-Domain Intent Detection EMNLP 2022 GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-supervised Learning and Explicit Policy Injection AAAI 2022 Graph-to-Text Generation with Dynamic Structure Pruning COLING 2022 S2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers ACL 2022 Semi-Supervised Lifelong Language Learning EMNLP 2022 SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding COLING 2022 STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing EMNLP 2022 SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers COLING 2022 Towards Generalizable and Robust Text-to-SQL Parsing EMNLP 2022 Towards Generalized Open Information Extraction EMNLP 2022 UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition EMNLP 2022 Dynamic Hybrid Relation Exploration Network for Cross-Domain Context-Dependent Semantic Parsing AAAI 2021 Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking ACL 2021 Dynamic Memory Induction Networks for Few-Shot Text Classification ACL 2020 Learning Low-Resource End-To-End Goal-Oriented Dialog for Fast and Reliable System Deployment ACL 2020 Induction Networks for Few-Shot Text Classification EMNLP 2019 Lyb3b at SemEval-2018 Task 11: Machine Comprehension Task using Deep Learning Models SemEval 2018 Lyb3b at SemEval-2018 Task 12: Ensemble-based Deep Learning Models for Argument Reasoning Comprehension Task SemEval 2018 YNUDLG at IJCNLP-2017 Task 5: A CNN-LSTM Model with Attention for Multi-choice Question Answering in Examinations IJCNLP 2017