Kenji Kawaguchi

DeRaDiff: Denoising Time Realignment of Diffusion Models

Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning

PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention

Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture

Learnable Sparsity for Vision Generative Models

HSG-12M: A Large-Scale Benchmark of Spatial Multigraphs from the Energy Spectra of Non-Hermitian Crystals

SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From

Fostering Video Reasoning via Next-Event Prediction

Gradually Compacting Large Language Models for Reasoning Like a Boiling Frog

From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs

Binary Node Clustering via Contrastive Learning for Haplotype Phasing in de novo Genome Assembly

Flow-Distorted Plane Waves

PromptArmor: An Essential Baseline for Prompt Injection Defenses

Unlocking More Granular Control of Memory-efficient LLM Finetuning

Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation

Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning

Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling

The Emergence of Abstract Thought in Large Language Models Beyond Any Language

Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron

Beyond In-Context Learning: Enhancing Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines

NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation

Minimalist Concept Erasure in Generative Models

Unnatural Languages Are Not Bugs but Features for LLMs

From General to Expert: Custom Pruning LLMs Across Language, Domain, and Task