AI Wiki — Knowledge Base

剑桥这回直接扔王炸了！！ AI & ML经典教材全集直接免费开放，PDF随便下。想学机器学习又不想被割韭菜买高价课的，这十本刷完，底子基本就硬了。顺序从易到难排好了： 1️⃣ 《机器学习理解》——理论算法一把抓，零基础入门首选 🔗 https://cs.huji.ac.il…

剑桥这回直接扔王炸了！！ AI & ML经典教材全集直接免费开放，PDF随便下。想学机器学习又不想被割韭菜买高价课的，这十本刷完，底子基本就硬了。顺序从易到难排好了： 1️⃣ 《机器学习理解》——理论算法一把抓，零基础入门首选 🔗 https://cs.huji.ac.il/~shais/UnderstandingMachineLearning/understanding-machine-le

researchyann-lecun--x

30 Aug 2026

research

Unsupervised Continual Learning with Growing Self-Organizing Maps and Synthetic Replay

VersaGauss: A Versatile Framework for Generating Multiphase Dynamics with 3D Gaussians

Video Generative Models as Geometry Learner

VidParse: Online Parsing of Egocentric Procedures Like a Pro

Visual Token Coding for Video Multimodal Large Language Models

Banger paper from Stanford on efficient test-time scaling. If you run agents that think for a long time, this one is worth your time. (bookm…

Interesting paper on prompt optimization. They claim that a single-lineage prompt optimizer just matched GEPA on a smaller rollout budget. P…

6.5% of the Neuro-Symbolic Literature Can Be Reproduced from Its Published Artifacts, a Six-Stage Audit Framework and First Instantiation

A Dynamic Likelihood Approach to Filtering for Advection-Diffusion Dynamics

A Finite Sample Analysis for Quantile Temporal Difference Learning in Distributional Reinforcement Learning

A Flexible Empirical Bayes Approach to Generalized Linear Models, with Applications to Sparse Logistic Regression

A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation

A Multi-Modal AI Framework for Real-Time Queue Prediction, Management and Optimisation in Intelligent Border Control Systems

A Reranker for Orchestrating Heterogeneous Speech and Text Retrievers

A Task-Centric Ontology and Deterministic Domain Rules as a Verifiable Core for AI-Assisted Chemistry Problem Solving

Activation Outliers Matter: Robust Recovery for Quantized Multimodal LLMs

Active Surface-Driven Reconfigurable Gripper: Robust Grasping and Sequential Manipulation of Thin Objects

Adversarial Training Without Input Gradients via Low-Rank Householder Expansions

AffectOmni: RL-Verifiable People-Centric Grounded Affective Reasoning for Social and Art-Related Scenes

Affix Cache for Diffusion Large Language Models

Algebraic Multigrid Acceleration for Efficient Label Spreading

Algorithmic Principles For Multiclass Learning Are Hard To Come By: Limits of Regularization and Proper Learning

ANTShapes Benchmarking Datasets for Event-Based Neuromorphic Object Classification

Arbitrary-Order Hermite Interpolation of Rigid-Motion Jets via Hyper-Multidual Quaternions

Artificial Intelligence Models Can Predict and Collaboratively Modulate Human Memory Search

Attention-Guided Reliability Scaling for Contrastive Decoding in Robust Audio-Visual Speech Recognition

Automated 2D and 3D Segmentation of AMD and DME Lesions in OCT

Beyond Discrete Samples: High Information Density Replay for Efficient Lifelong Person Re-Identification

Beyond Execution: Auditing Experimental Fidelity in LLM-Driven Scientific Research

Beyond Linearization: Attributed Table Graphs for Table Reasoning

Beyond Reflection: Affirmation as a Promising Behavioral Marker Associated with Quality in Text-Based Counseling

Beyond Shallow-Water Photorealism: Physically and Sensor-Grounded Simulation for Deep-Sea Robotics

Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics

Bridging short- and medium-range weather forecasting with machine learning

C-Unseen: Weak Signal Detection in Dynamic Temporal Knowledge Graphs via LLM Reasoning

Can a Model Catch Its Own Hallucinations for Free?: Label-Free Doubt Signals Hold Their Own Against a Labelled Dataset for Abstention

Can You Say This for Me? Speaking Up by Proxy in Co-Located Discussion

Cascaded Batch Prompting

Chart2SVG: Editable SVG Generation from Raster Chart Images

Circuit Condensation: Post-Training that Concentrates a Behavior's Causal Circuit

Clinically Aligned Geometry Constraints for Robust IVUS Vessel Boundary Segmentation

ClusterAttention: A training-free speedup of bidirectional attention

Co-Evolving Structured Knowledge and Reasoning in Language Models

CoGeo-GS: Concept-Driven and Geometry-Aware Multi-Object Removal in 3D Scenes

Common Geodesics Do Not Guarantee Fisher Consistency of the Structured SVM: Minimal Counterexamples and a Tree-Metric Classification

Comparative Evaluation of 3D Reconstruction Methods for Immersive Visualization of Laboratory Objects

Comparing Chunking and Embedding Strategies for Turkish RAG Systems