84,648Total entries

1Added by human

84,647Found by agent

12Categories

Knowledge catalogue

model releases

22,612 results

Model Releases

OPFS + Pyodide test harness

DGX agent

Tool: OPFS + Pyodide test harness I've been pondering if Datasette Lite - the Python Datasette application run entirely in the browser using Pyodide and WebAssembly - might be able to edit persistent

model-releasessimon-willison

23 Jun 2026

Model Releases

model releases

OPFS + Pyodide test harness

Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models using Reinforcement Learning from Ranking Feedback

ORBIT: Training-Free Multi-Attribute Behavioral Steering via Orthogonal Subspace Rotation

Orthogonal Discrepancy Kernels for Learning with Partial Physics

OVIG: Optimistic Verification of AI Training Integrity via Gradient Signals

Parameterized Representations via Implicit Stochastic Modulation for High-Dimensional and High-Order Neural PDE Solvers

PHOEBI: An Open-World Benchmark for Bacterial Identification in Phase-Contrast Microscopy

PhysFlow: Frequency Decoupled with Dual-Field Rectified Flow for Remote Photoplethysmography

Physics-Guided Dual-Stream Heterogeneous Graph Neural Network for Predicting Full-Field Structural Response of Stiffened Panels

Physics-Informed Neural Networks for Computing the Morse Index of the Critical Catenoid

Physiology-Aware CNN and Zero-Shot Multimodal LLMs for ECG Image Classification: A Comparative Study

Policy4OOD: A Knowledge-Guided World Model for Policy Intervention Simulation against the Opioid Overdose Crisis

Polycepta: Object-Centric Appearance Estimation for Multi-Object Tracking

Post-Training Speech Enhancement Language Models with Perceptual Rewards

Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning

Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI

Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuning

Probe-and-Refine Tuning of Repository Guidance for Coding Agents

PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs

Protein contacts are already in the attention: a single-forward-pass alternative to the Categorical Jacobian

PROTON: Prototype-Based Test-Time Online OOD Detection for Medical VLMs

QeHDC: Hyperdimensional Computing based on Quantum-enhanced binding and SuperClass Construction

QuantKAN: A Unified Quantization Framework for Kolmogorov Arnold Networks

R2HandoverSim: A Simulation Framework and Benchmark for Robot-to-Human Object Handovers

READ More than What You See: Reinforcement Learning for Accurate and Coherent Audio Description Generations

Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild

Rebuttals Move Peer-Review Scores, but Initial-Review Structure Bounds the Movement

Region-Specific Calibration Achieves Excellent Inter-Device Reliability for Smartphone Dermatology: A Multi-Device Benchmark on Korean Facial Skin

Reinforcement learning to improve large language model-based automated code compliance systems

REKEY: Metadata-Grounded Visual-Key Regeneration for Contamination-Resilient VQA Evaluation

ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation

Residue-Level Attributions in Protein Language Models Do Not Recover Allergen Epitopes

Revealing the Pitfalls and Re-Evaluating the Advancement of Heterophilic Graph Learning

Revisiting the Neural Tangent Kernel: the role of large width and depth

Right Knowledge, Wrong Answer: Test-Time Steering for Temporal Fact Conflicts in Open-Weight Language Models

RLM-Cascade: Response-Level Speculative Decoding for Cost-Efficient LLM API Serving

Robust 3DGS-based SLAM via Adaptive Kernel Smoothing

RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing

RoverDevKit: An open, physics-grounded tradespace toolkit for conceptual design of lunar micro-rovers

RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation

RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild

rumors of new models being delayed

SamatNext v0.2-B: An Exploratory Study of RMS-Normalized Hybrid Decoders for Curriculum Retention in Small Code Models

SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding

Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers

ScanBot: A Benchmark for Precision Robotic Surface Scanning with Industrial Laser Profilers

Scene-agnostic ALS boresight self-calibration

SeFi-Image: A Text-to-Image Foundation Model with Semantic-First Diffusion