AI Wiki — Knowledge Base

LLMは頭の中でコイントスができるか？ブログ：https://pub.sakana.ai/ssot 論文（#ICLR2026）：https://arxiv.org/abs/2510.21150 一見簡単そうで奥深いこの問題を「プロンプトだけ」で解決した論文 'SSoT: Pro…

LLMは頭の中でコイントスができるか？ブログ：https://pub.sakana.ai/ssot 論文（#ICLR2026）：https://arxiv.org/abs/2510.21150 一見簡単そうで奥深いこの問題を「プロンプトだけ」で解決した論文 'SSoT: Prompting LLMs for Distribution-Faithful and Diverse Generation

researchdavid-ha--x

20 Apr 2026

Search: “research”

In a capitalist economy, absolute levels of value creation and productivity take a backseat to relative competitive advantage. That's why jo…

In a hypothetical world where literally everything could be automated at no cost (we're very far from that), everybody would work in interpe…

LACE: Lattice Attention for Cross-thread Exploration

Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners

Learning Behaviorally Grounded Item Embeddings via Personalized Temporal Contexts

Learning to Reason with Insight for Informal Theorem Proving

Learning Uncertainty from Sequential Internal Dispersion in Large Language Models

Lightweight Geometric Adaptation for Training Physics-Informed Neural Networks

LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens

LLMは頭の中でコイントスができるか？ ブログ：https://pub.sakana.ai/ssot 論文（#ICLR2026）：https://arxiv.org/abs/2510.21150 一見簡単そうで奥深いこの問題を「プロンプトだけ」で解決した論文 'SSoT: Pro…

LLM Reasoning Is Latent, Not the Chain of Thought

Losses that Cook: Topological Optimal Transport for Structured Recipe Generation

LP^{2}DH: A Locality-Preserving Pixel-Difference Hashing Framework for Dynamic Texture Recognition

Machine learning approaches to uncover the neural mechanisms of motivated behaviour: from ADHD to individual differences in effort and reward sensitivity

Majority Voting for Code Generation

Make Tracking Easy: Neural Motion Retargeting for Humanoid Whole-body Control

Mapping High-Performance Regions in Battery Scheduling across Data Uncertainty, Battery Design, and Planning Horizons

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

Mitigating hallucinations and omissions in LLMs for invertible problems: An application to hardware logic design automation

MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation

Modeling Parkinson's Disease Progression Using Longitudinal Voice Biomarkers: A Comparative Study of Statistical and Neural Mixed-Effects Models

Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection

Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction

Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstruction

Neuro-Symbolic ODE Discovery with Latent Grammar Flow

NeuroLip: An Event-driven Spatiotemporal Learning Framework for Cross-Scene Lip-Motion-based Visual Speaker Recognition

Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models

One-Shot Generative Flows: Existence and Obstructions

Optimizing Stochastic Gradient Push under Broadcast Communications

Photonic AI: A Hybrid Diffractive Holographic Neural System for Passive Optical Real-Time Image Classification

Placing Puzzle Pieces Where They Matter: A Question Augmentation Framework for Reinforcement Learning

Plateaus, Optima, and Overfitting in Multi-Layer Perceptrons: A Saddle-Saddle-Attractor Scenario

PRIM-cipal components analysis

Privacy-Preserving LLMs Routing

Proper Body Landmark Subset Enables More Accurate and 5X Faster Recognition of Isolated Signs in LIBRAS

Protecting Language Models Against Unauthorized Distillation through Trace Rewriting

Python library supporting Discrete Variational Formulations and training solutions with Collocation-based Robust Variational Physics Informed Neural Networks (DVF-CRVPINN)

RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration

Ranking XAI Methods for Head and Neck Cancer Outcome Prediction

Reading today's open-closed performance gap

RelativeFlow: Taming Medical Image Denoising Learning with Noisy Reference

Resource-efficient equivariant quantum convolutional neural networks

Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking

Reward Modeling for Scientific Writing Evaluation

Robust Fleet Sizing for Multi-UAV Inspection Missions under Synchronized Replacement Demand

Scalable spatial point process models for forensic footwear analysis

Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning

SegMix:Shuffle-based Feedback Learning for Semantic Segmentation of Pathology Images

LLMは頭の中でコイントスができるか？ブログ：https://pub.sakana.ai/ssot 論文（#ICLR2026）：https://arxiv.org/abs/2510.21150 一見簡単そうで奥深いこの問題を「プロンプトだけ」で解決した論文 'SSoT: Pro…