AI Wiki — Knowledge Base

Last week some of South Korea's biggest banks were hit by a cyberattack. We now know the entire hack may have been done by a single person. He used a combined stack of an open-source AI penetration tool named ARTEX, DeepSeek v4.1-Flash, GLM-5.3, Grok 4.6, and Claude Code (CrowdStrike)

CrowdStrike report: https://www.crowdstrike.com/en-us/blog/unknown-threat-actor-uses-artex-to-target-south-korean-finance/ From: Andrew Curran on 𝕏: https://x.com/AndrewCurran_/status/2108108695876092

model-releasesr-localllama

8 Oct 2026

Search: “benchmark”

My 'Anthropic/ChatGPT in a box' is... now open source and publicly hosted on Github.

Neural Networks for Temporal Pattern Recognition and Dynamic Arm Gesture Speed Estimation for Robot Control

One Skill Too Many: How Co-Installed Skills Conflict in Coding Agents

OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video

Perception Test 2026: Challenge Summary and Extension to City-scale Audio-Visual Reasoning

Reconstruction of Multiscale Plasma Dynamics Across Operating Regimes

RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees

SteerablePlex: Can We Steer Full-Duplex Models?

StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents

Test-Time Compute for Tabular Foundation Models: Mechanisms, Gains, and Limits

WARP-VLA: Wrist-Camera Adaptation for View-Robust Policy Execution in Vision-Language-Action Models

What to Admit and How to Present: Governing Persistent Memory in LLM Agents

Why machines will still not rule the world

Workerville: Towards an Organizational Behavior Account of Agent Safety

2 months (meme-d) research, Do People Notice the Difference Between AI Models?

Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution

Another great paper from Salesforce AI Research. The finding is that a 31B open Gemma-4 web agent scores 74.6% on the 9-app WebArena Infinit…

Argos: Adapt Rich Geometric Priors for Generalizable Online Scene-Change-Detection

[audio.cpp] Recent updates you might have missed: Higgs Audio TTS use 48% less VRAM (< 6GB), HTDemucs 2.2× faster, PocketTTS 2.2× faster on CPU, and WebUI generation history feature

Autonomous Driving Research Requires a Community-Driven Data Paradigm

Beyond Anonymous Captions: Grounding Character Identity in Video Captioning and Question Answering

Cache the Encoder Within:Compact, Reusable Memory across LLM Queries

CERO: Where and When to Allocate Rollouts for RL Post-Training

CircuitGate: Logic-Consistent Circuit-Level Functional Modeling for And-Inverter Graphs

Cost Agent: find where your LLM and agent spend goes with your traces

ECHO: Embodied Camera Observations of Human Object Carrying

EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks

FinVector-Market-4B: A Controlled Study of LoRA Adaptation for Structured Financial Tasks

From Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMs

From Uncertainty to Action: Learning to Steer LLM Agents

InterView-C: A Synchronized Multimodal Corpus of VR Avatar-Mediated Survey Interviews

Java vllm-like framework claims 90% of perfomance of llama.cpp on local inference on NVIDIA GPUs by compiling Java to CUDA and cuTile

Last week some of South Korea's biggest banks were hit by a cyberattack. We now know the entire hack may have been done by a single person. He used a combined stack of an open-source AI penetration tool named ARTEX, DeepSeek v4.1-Flash, GLM-5.3, Grok 4.6, and Claude Code (CrowdStrike)

MultiFly: A Real-World Multimodal Aerial Dataset with Annotation-Efficient Label Transfer and Cross-Modal Semantic Consistency

PVSync: A Unified Lip-Sync Expert for Timing and Articulation

Quantifying Volumetric Risk: Class-Aware Asymmetric Weighted Conformal Prediction for 3D Medical Image Segmentation

Route-Verify-Vote: Procedure-Conditioned Self-Consistency for Mixed-Domain Reasoning

SEER: Self-Enhancing Chain-of-Thought Compression for Reasoning Models

SoccerNet-FoulRet: Retrieving Semantically Similar Soccer Foul Videos

Tokka-Bench: Evaluating Tokenizers Across 100 Natural and 20 Programming Languages

Training Advisors for LLM Agents from Task Outcomes

Video Prediction Policy 2: Predict Better, Act Better

A Novel Sentence Stress Detection Framework Leveraging Auxiliary Word-Stress Modeling and Loss Optimization

AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory

AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines

Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses

Bayesian Optimization on Function Spaces via Sparse RKHS Manifolds

Beyond Marginal Monitoring: Distributed Joint-Distribution Testing for Data Concept Drift in Large Scale E-Commerce Operations