AI Wiki — Knowledge Base

CrofAI 'cheapest inference provider in the world' gets exposed as an OpenRouter wrapper, routing requests to smaller, cheaper models at up to 20x markup. CrofAI responds to Wire Fraud allegations by denying everything, then backtracking, then 3 hours later wiping their entire online presence

Disclaimer: no AI was used whatsoever to write this post Cautionary tale about chasing cheap tokens. exposé: https://kendell.dev/blog/crofaifalse/ reaction by nahcrof, announcing the shutdown of the s

model-releasesr-localllama

15 Sept 2026

Search: “benchmark”

AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery

An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS

An Evolutionary Computation Framework for Multi-Agent Q-Learning with Mean-Field Environmental Feedback

ANASSA: An Agentic AI Orchestration Framework for Spatial Intelligence

AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation

Architecture--Optimization Co-Design for Physics-Informed Neural Networks via Layer-wise Coordinate Adaptation and Gradient Conflict Resolution

Assembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work Generation

Atria Dawn: The Dawn of Agentic Superintelligence

Attention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning

ATTRICITE: Training an Open 4B Model for Citation Recovery toward Faithful Attribution

Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception

Before You Poll with LLMs: A Deliberative Diagnostic Framework

Bellman Policy Optimization

Beyond Single-Axis Testing: Paired Evaluation of Compound Robustness in Vision-Language-Action Policies

BIG-CBF: Behavior-Imagination-Guided Control Barrier Function with Shared Uncertainty for Mobile Robot Navigation

Biomedical Reference Generation Remains Unreliable across 26 Large Language Models

Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment

Can Skills Learned in Games Transfer to Real-World Work?

CANAL: Channel-Aware Noise Allocation for Differentially Private Feature Distillation in Medical Image Segmentation

CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understanding

Carbon-Aware Routing for Function Calling in Edge-Cloud LLM Systems

CatchMonitor: a machine learning system for automated fish discard quantification

CCMAN: Cognitive Instability-Aware Cross-Modal Attention Network for Interpretable Temporal Biomarkers of Verbal Fluency Speech

Clean Scores, Buried Evidence, and Confident Wrong: A Receipt-Based Audit of Frontier Agentic QA

CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection

CLIMATEAGENT: Multi-Agent Orchestration for Complex Climate Data Science Workflows

CodeTS: Verifiable Text-to-Time Series Generation via Executable Code

CoMem: Collective-Individual Memory Synergy for Evolutionary Multi-Agent Systems

CompCQR: Compositional Query Generation for Training-Free Conversational Search

Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing

Conflict-Predictive Variable Horizons in Multi-Drone Distributed Model Predictive Control

Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control

Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection

CrofAI 'cheapest inference provider in the world' gets exposed as an OpenRouter wrapper, routing requests to smaller, cheaper models at up to 20x markup. CrofAI responds to Wire Fraud allegations by denying everything, then backtracking, then 3 hours later wiping their entire online presence

CWM: Controllable White-Box Meta-Prompting for Adaptive Retrieval-Augmented Generation and Reasoning Ability

Data-Efficient Agentic Graph Domain Adaptation via Reliability-Aware Prototype Learning

Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression?

Diagnosing Temporal Misalignment in Multichannel Time-Series Classification with Minimum Description Length

Diffusion-Based Multiple-Shooting Indirect Optimal Control for Fuel-Optimal Spacecraft Trajectory Generation

Domain Generalization for Smartphone-Based Human Activity Recognition: A Systematic Analysis of Components and Interactions

Donors and Recipients: On Asymmetric Transfer Across Tasks and Languages with Parameter-Efficient Fine-Tuning

Draining Fictitious Knots: Restoring Distance-Awareness Guarantees for High-Dimensional Spline Networks

Dreaming in Code for Curriculum Learning in Open-Ended Worlds

DuoTok: Source-Aware Dual-Track Music Tokenization for Vocal-Accompaniment Generation

DynEoMT: Learning Object Dynamicity from Online Segmentation Queries

EEG-Xplain: Decoding Neural Black-Boxes of EEG Foundation Models

Eigenvalue-Decomposition Cost Denoising as an Alternative to Predict-then-Optimize for Shortest-Path Problems

El Agente Potente: High-Throughput Agentic Atomistic Simulations