AI Wiki — Knowledge Base

こちらのポジション、とても面白い環境でLLMの研究開発に取り組めます！意外と小規模なチームで取り組んでおり、様々な能力を持った優秀なメンバーがいるので学びもめちゃくちゃ多いです！最近は論文やProductなどいろいろな形で成果を公開できるのも魅力だと思います！少しでもご興味ある方…

こちらのポジション、とても面白い環境でLLMの研究開発に取り組めます！意外と小規模なチームで取り組んでおり、様々な能力を持った優秀なメンバーがいるので学びもめちゃくちゃ多いです！最近は論文やProductなどいろいろな形で成果を公開できるのも魅力だと思います！少しでもご興味ある方はぜひ🙌 【採用情報】Member of Technical Staff (LLM Development) の募集を開

researchdavid-ha--x

24 Aug 2026

research

GRAFT: Adaptive DLM-Based Draft Tree Construction with Target-Distilled Edge Scoring

Graphon Particle Systems, Part II: Dynamics of Distributed Stochastic Continuum Optimization

Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation

Hybrid Roller-Jamming Gripper for Object Acquisition and Retention Under Pose Uncertainty

IMU-Free Body-Frame State Estimation with Sparse Scene Flow for Quadcopters

Infinite-dimensional generative diffusions via Doob's h-transform

InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter

Inhibitory Attention for Clinical Long-Context Reasoning: Characterizing and Mitigating Lost-in-the-Middle Effects in EHR Processing

Interpretable clustering via optimal multi-way decision trees

Interpretable Information-Decomposed Brain Graph Learning for fMRI-based Disease Diagnosis

Interpretable Multimodal Classification with Linear Discriminant Tree Ensembles

InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting

Jokes Aside: Measuring the Semantic Distance of Double Meanings

Learning Prostate Anatomy at Test Time for Cancer Detection in Micro-Ultrasound

Learning to Orchestrate Vision Foundation Models for Multi-Task Dense Prediction

Lift, Associate, and Fuse: A Decision-Centric Framework for 2D-to-3D Foundation Model Transfer

LTR-ICD: A Ranking-Aware Framework for Automatic ICD Coding

M2Depth: Unifying Monocular Depth Foundation Priors with Multi-View Stereo

Masking Is Not Enough: Generative Restoration for Multimodal De-Identification in Medical AI

Memory Augmentation Unlocks Efficient Chain-of-Thought Reasoning

MentorPulse: Refreshing Cross-Model Latent Guidance for Long-Form Generation

Meta-clustering of milk mid-infrared spectra identifies dairy cow groups associated with negative energy balance in early lactation

Minimax Optimality of Score-Entropy Discrete Diffusion

MultiCube: Compositional 3D Generation With Part-Level Semantic and Spatial Control

Mutual information and sensitivity analysis for feature selection in customer targeting: a comparative study

MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model

NeuroStrata: An Electroencephalographic Connectivity-Aware Deep Representation Learning Framework for Dynamic Brain Network Analysis of Mental Stress

On the Within-class Variation Issue in Alzheimer's Disease Detection

One Hierarchy, Two Systems: Semantic Product IDs for Discovery-Surface Ranking and Search-Page Query Reformulation

Online design of dynamic networks

Ontology-Driven Structural Regularization for Document-Level Relation Extraction

Ontology-supported AI Model and Dataset Management

Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation

PerturbRx: Learning Treatment-Conditioned Latent Transitions for Patient Drug Response Prediction

Pneumatic Units for Logic-based Sequential Excitation (PULSE) in Wearable Haptic Devices

Poly-InstructTTS: Learning In-the-Wild Expressive Speech Synthesis from Open-Ended Instructions

Predicting Resource Efficient Hamiltonian Decomposition for Continuous-Time Quantum Walk Simulations

Prediction certification cannot replace explanation certification: a competence envelope for trustworthy AI under compound stress

Privacy-Preserving Object Detection for Vision Transformer-Based Models

Prompt-Model Interaction Reaches the Fixed Points: A deterministic, task-free structural readout -- and the factorizations of it that failed

Query Efficient Structured Matrix Learning

[R] Using AI as a spatial software generator to create 3D objects that are inherently programmable

RARE: Decoupling Representation Steering from Expert Routing in Mixture-of-Experts Language Models

RDANet: Relative Degradation Aware Network for Infrared Small Target Detection

Recognition-Conditioned Reasoning: A Training-Free Multimodal-LLM Pipeline for Fine-Grained Micro-Action Understanding

Recognizing Artificial Minds: A Philosophical Defense of AI Cognition

Rethinking Expressivity and Efficiency in Test-Time Training