← Authors

Di He

76 papers · 2013–2026 · 16 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (4) πŸ—ΊοΈ Taxonomy Completionist (13) 🧭 Keyword Pioneer πŸƒ Academic Marathon (12) 🌍 Conference Polyglot (15) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🀝 Dynamic Duo (34) πŸ‘‘ Triple Crown 🧬 Topic Evolution πŸ† Grand Slam πŸ”¬ Deep Specialist (15) πŸ† Keyword Champion (2) πŸš€ Conference Pioneer ⚑ Prolific Year (7) πŸ”₯ Unstoppable (10) ❓ The Questioner (4) πŸ“ˆ Trend Setter πŸ’Ž Century Club (74) πŸ—ƒοΈ Keyword Collector (263)

Conferences

ICML (14) ICLR (13) NIPS (13) EMNLP (6) AAAI (5) ACL (4) INTERSPEECH (4) AISTATS (3) IJCAI (3) IJCNLP (3) CVPR (2) NAACL (2) COLING (1) COLT (1) EACL (1) ECCV (1)

Top co-authors

Tie-yan Liu (34) Liwei Wang (33) Tao Qin (24) Xu Tan (14) Shengjie Luo (12) Shuxin Zheng (9) Yingce Xia (9) Bohang Zhang (8) Guhao Feng (8) Guolin Ke (7)

Keywords

neural machine translation (13) neural network (6) machine translation (6) attention mechanism (5) non-autoregressive translation (4) transformer architecture (4) low-resource language (3) sequence generation (3) model compression (3) large language model (3) word embedding (3) adversarial example (3) relative positional encoding (3) adversarial training (3) graph neural network (3) certified robustness (3) representation learning (2) reinforcement learning (2) automatic speech recognition (2) autoregressive model (2)

Papers

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
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
Beyond Online Sampling: Bridging Offline-to-Online Alignment via Dynamic Data Transformation for LLMs EMNLP 2025
Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness ICLR 2024
Do Efficient Transformers Really Save Computation? ICML 2024
REST: Retrieval-Based Speculative Decoding NAACL 2024
Bridging Geometric States via Geometric Diffusion Bridge NIPS 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
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
Learning Physics-Informed Neural Networks without Stacked Back-propagation AISTATS 2023
A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests ICML 2023
One Transformer Can Understand Both 2D & 3D Molecular Data ICLR 2023
Denoising Masked Autoencoders Help Robust Classification ICLR 2023
Rethinking the Expressive Power of GNNs via Graph Biconnectivity ICLR 2023
Personalized Predictive ASR for Latency Reduction in Voice Assistants INTERSPEECH 2023
Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective NIPS 2023
Robustness-Aware Word Embedding Improves Certified Robustness to Adversarial Word Substitutions ACL 2023
DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets CVPR 2023
Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks AISTATS 2023
Finding the Dominant Winning Ticket in Pre-Trained Language Models ACL 2022
Your Transformer May Not be as Powerful as You Expect NIPS 2022
Is $L^2$ Physics Informed Loss Always Suitable for Training Physics Informed Neural Network? NIPS 2022
Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective NIPS 2022
Online Training Through Time for Spiking Neural Networks NIPS 2022
Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022
Boosting the Certified Robustness of L-infinity Distance Nets ICLR 2022
HousE: Knowledge Graph Embedding with Householder Parameterization ICML 2022
Do Transformers Really Perform Badly for Graph Representation? NIPS 2021
Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons ICML 2021
How could Neural Networks understand Programs? ICML 2021
Taking Notes on the Fly Helps Language Pre-Training ICLR 2021
Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder EMNLP 2021
wav2vec-C: A Self-Supervised Model for Speech Representation Learning INTERSPEECH 2021
Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding NIPS 2021
Rethinking Positional Encoding in Language Pre-training ICLR 2021
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training ICML 2021
MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius ICLR 2020
Invertible Image Rescaling ECCV 2020
On Layer Normalization in the Transformer Architecture ICML 2020
I4R: Promoting Deep Reinforcement Learning by the Indicator for Expressive Representations IJCAI 2020
Incorporating BERT into Neural Machine Translation ICLR 2020
Hint-Based Training for Non-Autoregressive Machine Translation EMNLP 2019
Multilingual Neural Machine Translation with Language Clustering EMNLP 2019
Representation Degeneration Problem in Training Natural Language Generation Models ICLR 2019
Multilingual Neural Machine Translation with Knowledge Distillation ICLR 2019
Microsoft Research Asia’s Systems for WMT19 ACL 2019
Efficient Training of BERT by Progressively Stacking ICML 2019
Towards a Deep and Unified Understanding of Deep Neural Models in NLP ICML 2019
Sentence-Wise Smooth Regularization for Sequence to Sequence Learning AAAI 2019
Tied Transformers: Neural Machine Translation with Shared Encoder and Decoder AAAI 2019
Non-Autoregressive Machine Translation with Auxiliary Regularization AAAI 2019
Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input AAAI 2019
Deliberation Learning for Image-to-Image Translation IJCAI 2019
Multilingual Neural Machine Translation with Language Clustering IJCNLP 2019
Machine Translation With Weakly Paired Documents IJCNLP 2019
Hint-Based Training for Non-Autoregressive Machine Translation IJCNLP 2019
Fast Structured Decoding for Sequence Models NIPS 2019
Machine Translation With Weakly Paired Documents EMNLP 2019
Improved ASR for Under-resourced Languages through Multi-task Learning with Acoustic Landmarks INTERSPEECH 2018
Double Path Networks for Sequence to Sequence Learning COLING 2018
Towards Binary-Valued Gates for Robust LSTM Training ICML 2018
Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation NIPS 2018
Dense Information Flow for Neural Machine Translation NAACL 2018
FRAGE: Frequency-Agnostic Word Representation NIPS 2018
Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter EMNLP 2018
Using Approximated Auditory Roughness as a Pre-Filtering Feature for Human Screaming and Affective Speech AED INTERSPEECH 2017
Decoding with Value Networks for Neural Machine Translation NIPS 2017
Dual Learning for Machine Translation NIPS 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