AI Wiki — Knowledge Base

【採用情報】Product Designerのポジションをオープンしました🐟 https://sakana.ai/careers/product-designer/ Sakana Chat🐟・Marlin🐬・Fugu🐡をはじめとした、プロダクトの体験をリードするProdu…

【採用情報】Product Designerのポジションをオープンしました🐟 https://sakana.ai/careers/product-designer/ Sakana Chat🐟・Marlin🐬・Fugu🐡をはじめとした、プロダクトの体験をリードするProduct Designerを募集しています。このような役割を担っていただきます。・コンセプト設計からUI、プロトタイプ、ブラン

researchdavid-ha--x

30 Jun 2026

research

Open Problems in Constitutional Preference Reconstruction

OpenSPM: An Environment-Transferable Robotic Key Spatial Pose Memory and Closed-Loop High-Frequency Flow-Matching Action Generation Model

Operating Regimes of Decentralized Learning Under Mobility and Bandwidth Constraints

Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms

Optimizer Memory Makes Shuffle Order a First-Order Source of Fine-Tuning Noise

Optimizing Image Preparation and Compression for Face Recognition within 1024 Bytes

Orca: The World is in Your Mind

Overcoming Dependent Censoring in the Evaluation of Survival Models

PASTA: A Paraphrasing And Self-Training Approach for Knowledge Updating in LLMs

PCP-GAN: Property-Constrained Pore-scale image reconstruction via conditional Generative Adversarial Networks

Personalized Additive Modeling for Multi-level Federated Learning

Personalizing MLLMs via Reinforced Multimodal Reference Game

Perspectives on Latent Factor Indeterminacy and its Implications for Data Representation

Physically-Constrained Harmonic Separation for Robust Heart and Respiratory Rate Estimation from Wrist Photoplethysmography

Physics-Informed Distillation of Diffusion Models for PDE-Constrained Generation

PinNet: Keypoint-Aware Learned Local Descriptors with Geometric Embedding for Loop Closure in LiDAR SLAM

PLAA: Packet-level Adversarial Attacks in Network Traffic Detection

Poller: Are LLMs Suitable for Evaluating the Poetry Understanding Task?

Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding

Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management

Predicting Metastatic Risk from Primary Tissue Architecture via Distance-Aware Spatial Modeling

Preference-ASR: A Preference-Aware Test Set for Benchmarking ASR in the Era of Speech LLMs

Privacy-Preserving Decentralized Cooperative Localization with Range-Only Measurements: A Convex Optimization Based Approach

【採用情報】Product Designerのポジションをオープンしました🐟 https://sakana.ai/careers/product-designer/ Sakana Chat🐟・Marlin🐬・Fugu🐡をはじめとした、プロダクトの体験をリードするProdu…

Projection-based coupling of infrared thermography and stereocorrelation-based digital image correlation

Proofs of Ownership for Machine Learning Models

PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking

PSP: Harnessing Position and Shape Priors for Cross-Domain Few-Shot Medical Image Segmentation

Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs

RadarTwin: Scene-Specific mmWave Radar Simulation and Learning for Mobile Indoor Perception

Randomized Exploration for Linear Bandits via Absolute Perturbations

RBE-Flow: Recurrent Bayesian Estimation on Feature Manifolds for Cross-Modal Registration

Real-Time Compliance and Position Control of a Hyper-redundant Soft Robotic Arm

Realtime Wind Estimation using Low Cost Quadrotor Uncrewed Aerial Vehicles

Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning

Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios

Reliability, Faithfulness, and the Limits of Post-hoc Explanations of Opaque Scientific Models

RenderFormer++: Scalable and Physically Grounded Feed-Forward Neural Rendering

Resonant Brane Splatting for Arbitrary-Scale Super-Resolution

Rethinking Forgery Attacks on Semantic Watermarks in Black-Box Settings: A Geometric Distortion Perspective

Revealing the Technology Development of Natural Language Processing: A Scientific Entity-Centric Perspective

Reweighting Framewise Attention in Video Transformers for Facial Expression Understanding

Room Scene Discovery and Grouping in Unstructured Vacation Rental Image Collections

Roundtables: Longevity’s Next Frontier: “Reprogramming” Your Body

S-GAI: Spectral Geometry-Aware Initialization for Sigmoidal MLPs -- From Dataset Geometry to Network Weights

SA-VIS: Sparse frame Annotations for training Video Instance Segmentation

SAD-GS: Learning Reliable 3D Semantic Gaussian Fields via Dynamic Geo-Semantic Anchoring

Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders