Kenji Kawaguchi

Venues

Frequent coauthors

Papers

1. ComicVQA: A Benchmark for Visual Reasoning in Multimodal LLMs
   ACL 2026 ·

   Esther Gan

   DBLP profile ↗ORCID search ↗
2. AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging
   NAACL 2025 ·

   Yiran Zhao

   DBLP profile ↗ORCID search ↗
3. Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines
   ACL 2025 ·

   Do Xuan Long

   DBLP profile ↗ORCID search ↗
4. Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data
   NAACL 2025 ·

   Haonan Wang

   DBLP profile ↗ORCID search ↗
5. LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs
   NAACL 2025 ·

   Do Xuan Long

   DBLP profile ↗ORCID search ↗
6. Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning
   ICLR 2025 ·

   Seanie Lee

   DBLP profile ↗ORCID search ↗
7. Minimalist Concept Erasure in Generative Models
   ICML 2025 ·

   Yang Zhang

   DBLP profile ↗ORCID search ↗
8. NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation
   ICLR 2025 ·

   Zhiyuan Liu

   DBLP profile ↗ORCID search ↗
9. Pruning General Large Language Models into Customized Expert Models
   ACL 2025 ·

   Yiran Zhao

   DBLP profile ↗ORCID search ↗
10. Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation
    NeurIPS 2025 ·

    Yihong Luo

    DBLP profile ↗ORCID search ↗
11. Single Character Perturbations Break LLM Alignment
    AAAI 2025 ·

    Leon Lin

    DBLP profile ↗ORCID search ↗
12. The Emergence of Abstract Thought in Large Language Models Beyond Any Language
    NeurIPS 2025 ·

    Yuxin Chen

    DBLP profile ↗ORCID search ↗
13. Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling
    NeurIPS 2025 ·

    Yanchen Luo

    DBLP profile ↗ORCID search ↗
14. Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron
    ICLR 2025 ·

    Yiran Zhao

    DBLP profile ↗ORCID search ↗
15. Unnatural Languages Are Not Bugs but Features for LLMs
    ICML 2025 ·

    Keyu Duan

    DBLP profile ↗ORCID search ↗
16. What Makes a Good Natural Language Prompt?
    ACL 2025 ·

    Do Xuan Long

    DBLP profile ↗ORCID search ↗
17. Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
    NeurIPS 2024 ·

    Yiran Zhao

    DBLP profile ↗ORCID search ↗
18. Deep Regression Representation Learning with Topology
    ICML 2024 ·

    Shihao Zhang

    DBLP profile ↗ORCID search ↗
19. Drug Discovery with Dynamic Goal-aware Fragments
    ICML 2024 ·

    Seul Lee

    DBLP profile ↗ORCID search ↗
20. Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models
    ECCV 2024 ·

    Yang Zhang

    DBLP profile ↗ORCID search ↗
21. Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers
    ICML 2024 ·

    Brian K. Chen

    DBLP profile ↗ORCID search ↗
22. How do Large Language Models Handle Multilingualism?
    NeurIPS 2024 ·

    Yiran Zhao

    DBLP profile ↗ORCID search ↗
23. Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
    NeurIPS 2024 ·

    Qianli Shen

    DBLP profile ↗ORCID search ↗
24. Multi-expert Prompting Improves Reliability, Safety and Usefulness of Large Language Models
    EMNLP 2024 ·

    Do Xuan Long

    DBLP profile ↗ORCID search ↗
25. PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer
    ICML 2024 ·

    Chang Chen

    DBLP profile ↗ORCID search ↗
26. Prompt Optimization via Adversarial In-Context Learning
    ACL 2024 ·

    Do Xuan Long

    DBLP profile ↗ORCID search ↗
27. ProtT3: Protein-to-Text Generation for Text-based Protein Understanding
    ACL 2024 ·

    Zhiyuan Liu

    DBLP profile ↗ORCID search ↗
28. ReactXT: Understanding Molecular "Reaction-ship" via Reaction-Contextualized Molecule-Text Pretraining
    ACL 2024 ·

    Zhiyuan Liu

    DBLP profile ↗ORCID search ↗
29. Reasoning Robustness of LLMs to Adversarial Typographical Errors
    EMNLP 2024 ·

    Esther Gan

    DBLP profile ↗ORCID search ↗
30. Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion
    ICML 2024 ·

    Xuantong Liu

    DBLP profile ↗ORCID search ↗
31. Scalable and Effective Implicit Graph Neural Networks on Large Graphs
    ICLR 2024 ·

    Juncheng Liu

    DBLP profile ↗ORCID search ↗
32. Self-Supervised Dataset Distillation for Transfer Learning
    ICLR 2024 ·

    Dong Bok Lee

    DBLP profile ↗ORCID search ↗
33. Simple Hierarchical Planning with Diffusion
    ICLR 2024 ·

    Chang Chen

    DBLP profile ↗ORCID search ↗
34. Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators
    NeurIPS 2024 ·

    Zekun Shi

    DBLP profile ↗ORCID search ↗
35. The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline
    ICML 2024 ·

    Haonan Wang

    DBLP profile ↗ORCID search ↗
36. The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling
    ICML 2024 ·

    Jiajun Ma

    DBLP profile ↗ORCID search ↗
37. Towards 3D Molecule-Text Interpretation in Language Models
    ICLR 2024 ·

    Sihang Li

    DBLP profile ↗ORCID search ↗
38. Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding
    AAAI 2024 ·

    Depeng Li

    DBLP profile ↗ORCID search ↗
39. Towards Robust Out-of-Distribution Generalization Bounds via Sharpness
    ICLR 2024 ·

    Yingtian Zou

    DBLP profile ↗ORCID search ↗
40. Unsupervised Concept Discovery Mitigates Spurious Correlations
    ICML 2024 ·

    Md Rifat Arefin

    DBLP profile ↗ORCID search ↗
41. VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models
    CVPR 2024 ·

    Xiang Li

    DBLP profile ↗ORCID search ↗