Junxian He

How Can Synthetic Data Improve Multilingual Language Model Pretraining? A Data Quality Perspective ACL 2026 Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging ICML 2025 B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners ICLR 2025 CodeIO: Condensing Reasoning Patterns via Code Input-Output Prediction ICML 2025 Diving into Self-Evolving Training for Multimodal Reasoning ICML 2025 Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning ACL 2025 High-Dimensional Interlingual Representations of Large Language Models ACL 2025 Non-myopic Generation of Language Models for Reasoning and Planning ICLR 2025 On the Perception Bottleneck of VLMs for Chart Understanding EMNLP 2025 OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis ACL 2025 Predictive Data Selection: The Data That Predicts Is the Data That Teaches ICML 2025 Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies ACL 2025 Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas ICML 2025 AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents NeurIPS 2024 Belief Revision: The Adaptability of Large Language Models Reasoning EMNLP 2024 Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs ICLR 2024 DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving NeurIPS 2024 In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation ICML 2024 InstructCoder: Instruction Tuning Large Language Models for Code Editing ACL 2024 IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce EMNLP 2024 On the Universal Truthfulness Hyperplane Inside LLMs EMNLP 2024 Prompt Optimization via Adversarial In-Context Learning ACL 2024 Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in LLMs NeurIPS 2024 What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning ICLR 2024 Automatic Model Selection with Large Language Models for Reasoning EMNLP 2023 C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models NeurIPS 2023 Composing Parameter-Efficient Modules with Arithmetic Operation NeurIPS 2023 Contrastive Learning of Sentence Embeddings from Scratch EMNLP 2023 FELM: Benchmarking Factuality Evaluation of Large Language Models NeurIPS 2023 Mega: Moving Average Equipped Gated Attention ICLR 2023 Self-Evaluation Guided Beam Search for Reasoning NeurIPS 2023 Simple Temporal Adaptation to Changing Label Sets: Hashtag Prediction via Dense KNN EMNLP 2023 Capturing Structural Locality in Non-parametric Language Models ICLR 2022 CTRLsum: Towards Generic Controllable Text Summarization EMNLP 2022 Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval ICML 2022 Prompt Consistency for Zero-Shot Task Generalization EMNLP 2022 Towards a Unified View of Parameter-Efficient Transfer Learning ICLR 2022 Dependency Induction Through the Lens of Visual Perception CoNLL 2021 Efficient Nearest Neighbor Language Models EMNLP 2021 The Source-Target Domain Mismatch Problem in Machine Translation EACL 2021 A Probabilistic Formulation of Unsupervised Text Style Transfer ICLR 2020 Learning Sparse Prototypes for Text Generation NeurIPS 2020 On the Sentence Embeddings from Pre-trained Language Models EMNLP 2020 Revisiting Self-Training for Neural Sequence Generation ICLR 2020 A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text EMNLP 2019 Choosing Transfer Languages for Cross-Lingual Learning ACL 2019 Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections ACL 2019 Lagging Inference Networks and Posterior Collapse in Variational Autoencoders ICLR 2019 Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation ACL 2019 StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing ACL 2018 Texar: A Modularized, Versatile, and Extensible Toolbox for Text Generation ACL 2018 Unsupervised Learning of Syntactic Structure with Invertible Neural Projections EMNLP 2018