Di He

AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse ACL 2026 Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection Suppression AAAI 2026 Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning EACL 2026 Ted-Tok: Maintaining an Evolving Vocabulary for Lifelong Learning ACL 2026 Beyond Online Sampling: Bridging Offline-to-Online Alignment via Dynamic Data Transformation for LLMs EMNLP 2025 DPO Meets PPO: Reinforced Token Optimization for RLHF ICML 2025 How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs ACL 2025 Let the Code LLM Edit Itself When You Edit the Code ICLR 2025 On Retrieval of Long Audios with Complex Text Queries Interspeech 2025 Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness ICLR 2024 Bridging Geometric States via Geometric Diffusion Bridge NeurIPS 2024 Do Efficient Transformers Really Save Computation? ICML 2024 GeoMFormer: A General Architecture for Geometric Molecular Representation Learning ICML 2024 Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks ICLR 2024 Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers AISTATS 2024 REST: Retrieval-Based Speculative Decoding NAACL 2024 Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning ICML 2024 Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation ICML 2024 A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests ICML 2023 Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks AISTATS 2023 Denoising Masked Autoencoders Help Robust Classification ICLR 2023 DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets CVPR 2023 Learning Physics-Informed Neural Networks without Stacked Back-propagation AISTATS 2023 One Transformer Can Understand Both 2D & 3D Molecular Data ICLR 2023 Personalized Predictive ASR for Latency Reduction in Voice Assistants Interspeech 2023 Rethinking the Expressive Power of GNNs via Graph Biconnectivity ICLR 2023 Robustness-Aware Word Embedding Improves Certified Robustness to Adversarial Word Substitutions ACL 2023 Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective NeurIPS 2023 Boosting the Certified Robustness of L-infinity Distance Nets ICLR 2022 Finding the Dominant Winning Ticket in Pre-Trained Language Models ACL 2022 HousE: Knowledge Graph Embedding with Householder Parameterization ICML 2022 Is L^2 Physics Informed Loss Always Suitable for Training Physics Informed Neural Network? NeurIPS 2022 Online Training Through Time for Spiking Neural Networks NeurIPS 2022 Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective NeurIPS 2022 Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022 Your Transformer May Not be as Powerful as You Expect NeurIPS 2022 Do Transformers Really Perform Badly for Graph Representation? NeurIPS 2021 GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training ICML 2021 How could Neural Networks understand Programs? ICML 2021 Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder EMNLP 2021 Rethinking Positional Encoding in Language Pre-training ICLR 2021 Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding NeurIPS 2021 Taking Notes on the Fly Helps Language Pre-Training ICLR 2021 Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons ICML 2021 wav2vec-C: A Self-Supervised Model for Speech Representation Learning Interspeech 2021 I4R: Promoting Deep Reinforcement Learning by the Indicator for Expressive Representations IJCAI 2020 Incorporating BERT into Neural Machine Translation ICLR 2020 Invertible Image Rescaling ECCV 2020 MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius ICLR 2020 On Layer Normalization in the Transformer Architecture ICML 2020 Deliberation Learning for Image-to-Image Translation IJCAI 2019 Efficient Training of BERT by Progressively Stacking ICML 2019 Fast Structured Decoding for Sequence Models NeurIPS 2019 Hint-Based Training for Non-Autoregressive Machine Translation EMNLP 2019 Machine Translation With Weakly Paired Documents EMNLP 2019 Microsoft Research Asia’s Systems for WMT19 ACL 2019 Multilingual Neural Machine Translation with Knowledge Distillation ICLR 2019 Multilingual Neural Machine Translation with Language Clustering EMNLP 2019 Non-Autoregressive Machine Translation with Auxiliary Regularization AAAI 2019 Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input AAAI 2019 Representation Degeneration Problem in Training Natural Language Generation Models ICLR 2019 Sentence-Wise Smooth Regularization for Sequence to Sequence Learning AAAI 2019 Tied Transformers: Neural Machine Translation with Shared Encoder and Decoder AAAI 2019 Towards a Deep and Unified Understanding of Deep Neural Models in NLP ICML 2019 Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter EMNLP 2018 Dense Information Flow for Neural Machine Translation NAACL 2018 Double Path Networks for Sequence to Sequence Learning COLING 2018 FRAGE: Frequency-Agnostic Word Representation NeurIPS 2018 Improved ASR for Under-resourced Languages through Multi-task Learning with Acoustic Landmarks Interspeech 2018 Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation NeurIPS 2018 Towards Binary-Valued Gates for Robust LSTM Training ICML 2018 Decoding with Value Networks for Neural Machine Translation NeurIPS 2017 Using Approximated Auditory Roughness as a Pre-Filtering Feature for Human Screaming and Affective Speech AED Interspeech 2017 Dual Learning for Machine Translation NeurIPS 2016 A Game-Theoretic Machine Learning Approach for Revenue Maximization in Sponsored Search IJCAI 2013 A Theoretical Analysis of NDCG Type Ranking Measures COLT 2013