Yu Sun

AttnPO: Attention-Guided Process Supervision for Efficient Reasoning ACL 2026 Blink: Dynamic Visual Token Resolution for Enhanced Multimodal Understanding CVPR 2026 Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models CVPR 2026 Uncertainty-Aware Routing for Principled Alignment with MoE Dynamics ACL 2026 BeamLoRA: Beam-Constraint Low-Rank Adaptation ACL 2025 Curiosity-Driven Reinforcement Learning from Human Feedback ACL 2025 HFT: Half Fine-Tuning for Large Language Models ACL 2025 Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking ACL 2025 MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions ICLR 2025 Mixture of Hidden-Dimensions: Not All Hidden-States’ Dimensions are Needed in Transformer ICML 2025 Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging ACL 2025 Autoregressive Pre-Training on Pixels and Texts EMNLP 2024 DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion NeurIPS 2024 LEMON: Reviving Stronger and Smaller LMs from Larger LMs with Linear Parameter Fusion ACL 2024 NACL: A General and Effective KV Cache Eviction Framework for LLM at Inference Time ACL 2024 On Training Data Influence of GPT Models EMNLP 2024 Tool-Augmented Reward Modeling ICLR 2024 ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages ACL 2023 ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Models IJCNLP 2023 ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model With Knowledge-Enhanced Mixture-of-Denoising-Experts CVPR 2023 Retrieval-Augmented Domain Adaptation of Language Models ACL 2023 Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards EMNLP 2022 ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding EMNLP 2022 Simple and Effective Relation-based Embedding Propagation for Knowledge Representation Learning IJCAI 2022 X-PuDu at SemEval-2022 Task 6: Multilingual Learning for English and Arabic Sarcasm Detection SemEval 2022 X-PuDu at SemEval-2022 Task 7: A Replaced Token Detection Task Pre-trained Model with Pattern-aware Ensembling for Identifying Plausible Clarifications SemEval 2022 Alpha at SemEval-2021 Task 6: Transformer Based Propaganda Classification SemEval 2021 Correcting Chinese Spelling Errors with Phonetic Pre-training ACL 2021 ERNIE-Doc: A Retrospective Long-Document Modeling Transformer ACL 2021 ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding NAACL 2021 ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora EMNLP 2021 ERNIE-ViL: Knowledge Enhanced Vision-Language Representations through Scene Graphs AAAI 2021 Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification IJCAI 2021 abcbpc at SemEval-2021 Task 7: ERNIE-based Multi-task Model for Detecting and Rating Humor and Offense SemEval 2021 ERNIE 2.0: A Continual Pre-Training Framework for Language Understanding AAAI 2020 ERNIE at SemEval-2020 Task 10: Learning Word Emphasis Selection by Pre-trained Language Model SemEval 2020 ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation IJCAI 2020 Galileo at SemEval-2020 Task 12: Multi-lingual Learning for Offensive Language Identification Using Pre-trained Language Models SemEval 2020 Kk2018 at SemEval-2020 Task 9: Adversarial Training for Code-Mixing Sentiment Classification SemEval 2020 PGL at TextGraphs 2020 Shared Task: Explanation Regeneration using Language and Graph Learning Methods COLING 2020 OleNet at SemEval-2019 Task 9: BERT based Multi-Perspective Models for Suggestion Mining SemEval 2019 RLTM: An Efficient Neural IR Framework for Long Documents IJCAI 2019