KK
Kenji Kawaguchi
cs.LGcs.AIcs.CLstat.MLcs.CVmath.OCcs.NAmath.NAcs.NEmath.DS
On Valency
published · living versionsW_7ufmqht5·v1 · currentpublished
When Self-Verification Hurts: Calibrated Answer Repair for Financial Question Answering
with Celine Guo, Weida Liang, Yujian Fu, Anqi Dang +2
1 version
Preprints & journals
170 papers in the corpus · 2013–2026Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning2610.20836v1 · Weida Liang, Kenji Kawaguchi2026 · 0 citationsarXiv
SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents2610.18206v1 · Do Xuan Trong, Duc Anh Nguyen, Do Xuan Long et al.2026 · 0 citationsarXiv
Bayesian Test-Time Inference of Task-Aligned Similarity from Weak Interactive Feedback2610.18656v1 · Weida Liang, Kenji Kawaguchi2026 · 0 citationsarXiv
AlphaPADI: Formulaic Alpha Discovery via Pool-Aware Hierarchical Discrete Diffusion2610.04959v2 · Yanzheng Jin, Pengyang Shao, Yunshan Ma et al.2026 · 0 citationsarXiv
Rethinking Soft Tokens for Parallel Decoding in Diffusion Language Models2609.37391v1 · Kodai Kawamura, Kenji Kawaguchi, Anji Liu2026 · 0 citationsarXiv
PAWS: Policy-driven Agentic World Simulation2609.28547v1 · Tiviatis Sim, Jia Hui Woon, Xinming Gao et al.2026 · 0 citationsarXiv
Beyond Cross-Lingual Transfer: Benchmarking Propagation Boundaries in Multilingual LLM Unlearning2609.05976v1 · Pengyang Shao, Chuanpeng Lu, Wei Qin et al.2026 · 0 citationsarXiv
CoLAS: Multimodal Corroboration of Latent Asset Signals for Financial Trading2607.28446v2 · Yanzheng Jin, Pengyang Shao, Xiaohao Liu et al.2026 · 0 citationsarXiv
Rethinking pathology image analysis through shuffling.42527448 · Liu, Zeyu, Zhang, Tianyi, Chen, Brian K et al.2026 · 0 citationsnpj biomedical innovations. 2026;3(1)
Binary node clustering via contrastive learning for haplotype phasing in de novo genome assembly10.64898/2026.07.17.739091v1 · Schmitz, M., Rauschning, L., Kawaguchi, K. et al.2026 · 0 citationsbioRxiv
Speculative Correction: Draft-then-Refine Decoding for Diffusion Language Models2608.02625v1 · Brian K Chen, Chong Wu, Kenji Kawaguchi2026 · 0 citationsarXiv
Heavy-Tailed Flow Matching via Random Clocks2607.13841v1 · Zhouhao Yang, Yezhen Wang, Kenji Kawaguchi et al.2026 · 0 citationsarXiv
Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior2606.02453v1 · Xiang Li, Dianbo Liu, Kenji Kawaguchi2026 · 0 citationsarXiv
Lost in Adaptation: Layer-Selective Recovery of Temporal Reasoning in Video-Language Models2604.11399v3 · Zihang Fu, Haonan Wang, Jian Kang et al.2026 · 0 citationsarXiv
In-Context Reinforcement Learning for Tool Use in Large Language Models2603.08068v1 · Yaoqi Ye, Yiran Zhao, Keyu Duan et al.2026 · 0 citationsarXiv
Strategy Executability in Mathematical Reasoning: Leveraging Human-Model Differences for Effective Guidance2602.22583v2 · Weida Liang, Yiyou Sun, Shuyuan Nan et al.2026 · 0 citationsarXiv
Gradually Compacting Large Language Models for Reasoning Like a Boiling Frog2602.04919v1 · Yiran Zhao, Shengyang Zhou, Zijian Wu et al.2026 · 0 citationsarXiv
DeRaDiff: Denoising Time Realignment of Diffusion Models2601.20198v2 · Ratnavibusena Don Shahain Manujith, Teoh Tze Tzun, Kenji Kawaguchi et al.2026 · 0 citationsarXiv
PMNO: A novel physics guided multi-step neural operator predictor for partial differential equations.41576555 · Song, Jin, Kawaguchi, Kenji, Yan, Zhenya2026 · 3 citationsNeural networks : the official journal of the International Neural Network Society. 2026;198:108593
State-space models are accurate and efficient neural operators for dynamical systems.41447828 · Hu, Zheyuan, Daryakenari, Nazanin Ahmadi, Shen, Qianli et al.2026 · 19 citationsNeural networks : the official journal of the International Neural Network Society. 2026;197:108496
Unconsciously Forget: Mitigating Memorization; Without Knowing What is being Memorized2512.09687v2 · Er Jin, Yang Zhang, Yongli Mou et al.2025 · 0 citationsarXiv
Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning2512.02874v1 · Haonan Wang, Chao Du, Kenji Kawaguchi et al.2025 · 0 citationsarXiv
SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From2509.26404v2 · Yao Tong, Haonan Wang, Siquan Li et al.2025 · 0 citationsarXiv
From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs2509.23196v1 · Haonan Wang, Weida Liang, Zihang Fu et al.2025 · 0 citationsarXiv
DipGNNome: Diploid de novo genome assembly with geometric deep learning and beam-search10.1101/2025.09.16.676474v1 · Schmitz, M., Vrcek, L., Kawaguchi, K. et al.2025 · 1 citationbioRxiv
LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning2507.22499v1 · Xiang Li, Qianli Shen, Haonan Wang et al.2025 · 0 citationsarXiv
Who's important? -- SUnSET: Synergistic Understanding of Stakeholder, Events and Time for Timeline Generation2507.21903v3 · Tiviatis Sim, Kaiwen Yang, Shen Xin et al.2025 · 0 citationsarXiv
PromptArmor: Simple yet Effective Prompt Injection Defenses2507.15219v1 · Tianneng Shi, Kaijie Zhu, Zhun Wang et al.2025 · 0 citationsarXiv
Minimalist Concept Erasure in Generative Models2507.13386v1 · Yang Zhang, Er Jin, Yanfei Dong et al.2025 · 0 citationsarXiv
Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture2506.19935v2 · Shuchen Xue, Tianyu Xie, Tianyang Hu et al.2025 · 0 citationsarXiv
PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention2506.13674v3 · Haonan Wang, Brian Chen, Siquan Li et al.2025 · 0 citationsarXiv
The Emergence of Abstract Thought in Large Language Models Beyond Any Language2506.09890v1 · Yuxin Chen, Yiran Zhao, Yang Zhang et al.2025 · 1 citationarXiv
HSG-12M: A Large-Scale Benchmark of Spatial Multigraphs from the Energy Spectra of Non-Hermitian Crystals2506.08618v5 · Xianquan Yan, Hakan Akgun, Kenji Kawaguchi et al.2025 · 0 citationsThe Fourteenth International Conference on Learning Representations (ICLR 2026)
What Makes a Good Natural Language Prompt?2506.06950v1 · Do Xuan Long, Duy Dinh, Ngoc-Hai Nguyen et al.2025 · 6 citationsarXiv
Pruning General Large Language Models into Customized Expert Models2506.02561v1 · Yirao Zhao, Guizhen Chen, Kenji Kawaguchi et al.2025 · 0 citationsarXiv
Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines2506.01265v1 · Do Xuan Long, Duong Ngoc Yen, Do Xuan Trong et al.2025 · 0 citationsarXiv
Fostering Video Reasoning via Next-Event Prediction2505.22457v1 · Haonan Wang, Hongfu Liu, Xiangyan Liu et al.2025 · 0 citationsarXiv
Memory-Efficient LLM Training by Various-Grained Low-Rank Projection of Gradients2505.01744v1 · Yezhen Wang, Zhouhao Yang, Brian K Chen et al.2025 · 0 citationsarXiv
Geometric deep learning framework for de novo genome assembly.39472021 · Vrček, Lovro, Bresson, Xavier, Laurent, Thomas et al.2025 · 12 citationsGenome research. 2025;35(4):839-849
Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling2503.15567v4 · Yanchen Luo, Zhiyuan Liu, Yi Zhao et al.2025 · 1 citationarXiv
Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation2503.13070v2 · Yihong Luo, Tianyang Hu, Weijian Luo et al.2025 · 0 citationsarXiv
Unnatural Languages Are Not Bugs but Features for LLMs2503.01926v2 · Keyu Duan, Yiran Zhao, Zhili Feng et al.2025 · 1 citationarXiv
NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation2502.12638v2 · Zhiyuan Liu, Yanchen Luo, Han Huang et al.2025 · 2 citationsarXiv
Tensor neural networks for high-dimensional Fokker-Planck equations.39879868 · Wang, Taorui, Hu, Zheyuan, Kawaguchi, Kenji et al.2025 · 19 citationsNeural networks : the official journal of the International Neural Network Society. 2025;185:107165
Functional Risk Minimization2412.21149v1 · Ferran Alet, Clement Gehring, Tom'as Lozano-P'erez et al.2024 · 0 citationsarXiv
Learnable Sparsity for Vision Generative Models2412.02852v3 · Yang Zhang, Er Jin, Wenzhong Liang et al.2024 · 0 citationsarXiv
Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators2412.00088v2 · Zekun Shi, Zheyuan Hu, Min Lin et al.2024 · 3 citationsarXiv
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training2411.13476v2 · Haonan Wang, Qian Liu, Chao Du et al.2024 · 0 citationsarXiv
Reasoning Robustness of LLMs to Adversarial Typographical Errors2411.05345v1 · Esther Gan, Yiran Zhao, Liying Cheng et al.2024 · 5 citationsarXiv
Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models2411.00492v1 · Do Xuan Long, Duong Ngoc Yen, Anh Tuan Luu et al.2024 · 20 citationsarXiv
Career total: 221 works. 170 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.