AI Wiki — Knowledge Base

8月より、Sakana AI @SakanaAILabs にApplied Research Engineer Internship として入社しました 🐟🐠🐡！大学の夏季休業期間にフルタイム勤務予定です！ LLMの研究開発と社会実装を頑張ります💪🏻

Horiyuki 'horiyuki42' joined Sakana AI Labs in August 2026 as an Applied Research Engineer Intern. He plans to work full‑time during the university summer recess while concentrating on large‑language‑

researchdavid-ha--x

3 Aug 2026

Search: “papers”

PolymerGPT: Multi-property Optimization with a Decoder-Based GPT Model for Generative Polymer Design

Probing the 3D Object-Level Understanding of Pre-Trained Detection Transformers

Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detection

Protocol generalisation for brain tissue microstructure estimation via hypernetwork-controlled geometric deep learning

Pruned BPE: Post-training Visibility Pruning and Token Reallocation for Byte Pair Encoding

Push-Wiper: Toward General-Purpose Robotic Cleaning across Varied Stains and Surfaces with Segmented Pushing Trajectories

PyDPF: A Python Package for Differentiable Particle Filtering

Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models

QuASH: Using Natural-Language Heuristics to Query Visual-Language Robotic Maps

Real-Time Visual Obstruction Detection in Surgical Augmented Reality

ReasonCast: Towards Explainable Time Series Forecasting with Reasoning

Regularized Schrodinger Bridge via Distortion-Perception Perturbation for High-Fidelity Speech Enhancement

Rethinking IRSTD: Single-Point Supervision Guided Encoder-only Framework is Enough for Infrared Small Target Detection

Riemannian Attention Mechanisms for Transformers: A Theoretical Framework and Architecture Design

RubricReviewer: From Direct Critique to Objective and Comprehensive Rubric-Driven Peer Review

S^4R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching

Sampling-Based Visibility Task Planning

Score-Based Turbo Message Passing for Plug-and-Play Compressive Imaging

Secrets Everywhere: Auditing Memorization in Mobility Prediction Models

Self-Certification of Representation Adequacy: Sequential Certification at Minimum Task Loss

Sheaf-theoretic Signal Processing on Graphs: Spectral Theory, Filtering, and Sampling

Simplified Quadratic Gradient: A Unified Framework Bridging Gradient Descent and Newton-Type Methods by Synthesizing Hessians and Gradients

Situation Aware Frontier Prioritization for Quadruped Search and Rescue

Spatiotemporal Proximal Causal Inference under Hidden Confounding and Interference

Statistical Mechanics of Learning on Product Wasserstein Manifolds

STC-Net: Electroluminescence-Based Solar Cell Crack Segmentation for Power Loss Estimation

Stochastic Sequential Search in Very-High-Dimensional Feature Selection

Stress-Relief Annealing: Polynomial-Time Simulation-Free Layout Optimization for Automated Warehouses

The Bayesian Reflex: A Predictive Coding Engine for Artificial Intelligence

The No-Clash Teaching Dimension is Bounded by VC Dimension

Towards a theory of morphology-driven marking in the lexicon: The case of the state

Towards General Language-Conditioned Latent Safety Filters

Track-Guided Hierarchical Reinforcement Learning for Autonomous Vehicle Drifting with Minimum-Lap-Time Planning

Training nGPT

Transformers perform adaptive partial pooling

TravKAN: Fast and Interpretable Nonlinear Traversability Analysis with Kolmogorov-Arnold Networks

Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture Empirical Study

Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability

TS-MAMP: A Remanufactured Agricultural Robot Powered by Second-Life EV Components and NMS-Free On-Device Weed Detection

TWINS: A Tactile Wearable Isomorphic Arm Networked System for Contact-Rich Manipulation Learning

Uncovering and Mitigating Positional Blind Spots in Vision-Language-Action Models

Understanding and Overcoming Cross-modal Fusion Bias in Multimodal Anomaly Detection From A Fisher Information Perspective

UpliftBench: Revealing Outcome-Regime and Objective Mismatch in Uplift Evaluation

Using Non-Lipschitz Signum-based Functions for Distributed Optimization and Machine Learning: Trade-off Between Con-vergence Rate and Optimality Gap

When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems

8月より、Sakana AI @SakanaAILabs にApplied Research Engineer Internship として入社しました 🐟🐠🐡！ 大学の夏季休業期間にフルタイム勤務予定です！ LLMの研究開発と社会実装を頑張ります💪🏻

A Machine Learning Surrogate for Component Criticality Ranking in Interdependent Power-Communication Networks

A Model-Driven Approach for Developing Families of Reinforcement Learning Environments

8月より、Sakana AI @SakanaAILabs にApplied Research Engineer Internship として入社しました 🐟🐠🐡！大学の夏季休業期間にフルタイム勤務予定です！ LLMの研究開発と社会実装を頑張ります💪🏻