AI Wiki — Knowledge Base

Memory operations, including retrieval, prioritization, compaction awareness, should be native and baked into the harness. 𝐖𝐢𝐭𝐡𝐨𝐮𝐭 𝐭…

Memory operations, including retrieval, prioritization, compaction awareness, should be native and baked into the harness. 𝐖𝐢𝐭𝐡𝐨𝐮𝐭 𝐭𝐡𝐞 𝐩𝐫𝐨𝐩𝐞𝐫 𝐢𝐧𝐭𝐞𝐫𝐚𝐜𝐭𝐢𝐨𝐧 𝐛𝐞𝐭𝐰𝐞𝐞𝐧 𝐡𝐚𝐫𝐧𝐞𝐬𝐬 𝐚𝐧𝐝 𝐦𝐞𝐦𝐨𝐫𝐲, 𝐦𝐞𝐦𝐨𝐫𝐲 𝐚𝐥𝐨𝐧𝐞 𝐢𝐬 𝐩𝐨

model-releasesharrison-chase--x

13 Apr 2026

model releases

Lessons Without Borders? Evaluating Cultural Alignment of LLMs Using Multilingual Story Moral Generation

Listener-Rewarded Thinking in VLMs for Image Preferences

Litmus (Re)Agent: A Benchmark and Agentic System for Predictive Evaluation of Multilingual Models

Looking for people with different hardware to help benchmark local LLM behavioral reliability

Low-Data Supervised Adaptation Outperforms Prompting for Cloud Segmentation Under Domain Shift

Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks

LPLCv2: An Expanded Dataset for Fine-Grained License Plate Legibility Classification

LuMon: A Comprehensive Benchmark and Development Suite with Novel Datasets for Lunar Monocular Depth Estimation

Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space

Many-Tier Instruction Hierarchy in LLM Agents

Many Ways to Be Fake: Benchmarking Fake News Detection Under Strategy-Driven AI Generation

MARINER: A 3E-Driven Benchmark for Fine-Grained Perception and Complex Reasoning in Open-Water Environments

MATCHA: Efficient Deployment of Deep Neural Networks on Multi-Accelerator Heterogeneous Edge SoCs

MedConceal: A Benchmark for Clinical Hidden-Concern Reasoning Under Partial Observability

Medical Reasoning with Large Language Models: A Survey and MR-Bench

Memory-efficient Continual Learning with Prototypical Exemplar Condensation

Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation

Memory operations, including retrieval, prioritization, compaction awareness, should be native and baked into the harness. 𝐖𝐢𝐭𝐡𝐨𝐮𝐭 𝐭…

Mitigating Extrinsic Gender Bias for Bangla Classification Tasks

Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory

MolPaQ: Modular Quantum-Classical Patch Learning for Interpretable Molecular Generation

MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems

Multivariate Time Series Anomaly Detection via Dual-Branch Reconstruction and Autoregressive Flow-based Residual Density Estimation

Natural Riemannian gradient for learning functional tensor networks

NCL-BU at SemEval-2026 Task 3: Fine-tuning XLM-RoBERTa for Multilingual Dimensional Sentiment Regression

Neural networks for Text-to-Speech evaluation

Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima

Noise-Aware In-Context Learning for Hallucination Mitigation in ALLMs

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track 2)

Ocr benchmark

Ollama 0.20.6 is here with improved Gemma 4 tool calling! more improvements to come for Gemma 4!

Ollama / Mistral with MCP to Mempalace

On Semiotic-Grounded Interpretive Evaluation of Generative Art

On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs

Online Intention Prediction via Control-Informed Learning

Open-source AI is now matching GPT-4 — and you can run it privately for free

PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence

Parameterized Complexity Of Representing Models Of MSO Formulas

ParseBench is here!📊 We’ve just released ParseBench, an open benchmark + dataset for evaluating document parsing at scale. It includes: • 2…

PhysInOne: Visual Physics Learning and Reasoning in One Suite

PilotBench: A Benchmark for General Aviation Agents with Safety Constraints

PinpointQA: A Dataset and Benchmark for Small Object-Centric Spatial Understanding in Indoor Videos

Precise Shield: Explaining and Aligning VLLM Safety via Neuron-Level Guidance

Precomputing Multi-Agent Path Replanning using Temporal Flexibility

Prefer watching on @YouTube while scrolling through the comment section? We get it: http://youtu.be/b1Pvt072wKQ?si=NGPgm30ur1WFtKQS

Pretrain-then-Adapt: Uncertainty-Aware Test-Time Adaptation for Text-based Person Search

Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos

QARIMA: A Quantum Approach To Classical Time Series Analysis