conftrace_

Kazuki Irie

23 papers · 2016–2025 · 6 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+13 more ↓ 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) 🌉 Interdisciplinary Bridge 🌈 Renaissance Researcher (5) 🏃 Academic Marathon (9)
🏃 Academic Marathon (9) 🐝 Cross-Pollinator (8) 🗺️ Taxonomy Completionist (43) 🤝 Dynamic Duo (13) 👑 Triple Crown 🏆 Keyword Champion (2) 🧬 Topic Evolution 🔥 Unstoppable (5) 🗃️ Keyword Collector (94) Prolific Year (5) The Questioner 💎 Century Club (23) 🚀 Conference Pioneer

Conferences

INTERSPEECH (6) NIPS (6) EMNLP (4) ICLR (3) ICML (3) ACL (1)

Research topics

Papers

Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? A Petroglyph Revisited ACL 2025 SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention NIPS 2024 Exploring the Promise and Limits of Real-Time Recurrent Learning ICLR 2024 MoEUT: Mixture-of-Experts Universal Transformers NIPS 2024 Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers NIPS 2024 Contrastive Training of Complex-Valued Autoencoders for Object Discovery NIPS 2023 Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions EMNLP 2023 Approximating Two-Layer Feedforward Networks for Efficient Transformers EMNLP 2023 Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules ICLR 2023 The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization ICLR 2022 The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention ICML 2022 A Modern Self-Referential Weight Matrix That Learns to Modify Itself ICML 2022 Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules NIPS 2022 CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations EMNLP 2022 Going Beyond Linear Transformers with Recurrent Fast Weight Programmers NIPS 2021 The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers EMNLP 2021 Linear Transformers Are Secretly Fast Weight Programmers ICML 2021 RWTH ASR Systems for LibriSpeech: Hybrid vs Attention INTERSPEECH 2019 On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition INTERSPEECH 2019 Language Modeling with Deep Transformers INTERSPEECH 2019 Improved Training of End-to-end Attention Models for Speech Recognition INTERSPEECH 2018 Investigation on Estimation of Sentence Probability by Combining Forward, Backward and Bi-directional LSTM-RNNs INTERSPEECH 2018 LSTM, GRU, Highway and a Bit of Attention: An Empirical Overview for Language Modeling in Speech Recognition INTERSPEECH 2016