127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “models”

95,135 results

Model Releases

b11412

DGX agent

llama : fix unexpected graph reallocation in the k-pool models (#29958) llama : fix unexpected graph reallocation in the k-pool models Both k-pool models built a graph shape that depends on state the

model-releasesllama-cpp-releases

5 Oct 2026

Research

FiberGeoText: A Vision-Language Model for Population- Level Organization of Superficial White Matter

DGX agent

arXiv:2610.02755v1 Announce Type: new Abstract: The superficial white matter (SWM), a critical brain region for cognition across the lifespan and brain disease, contains abundant short-range associati

Search: “models”

b11412

FiberGeoText: A Vision-Language Model for Population- Level Organization of Superficial White Matter

HakemBench: A Turkish Benchmark of Typed Decisions

Interpretable Deepfake Detection in Videos via Explicit Forensic Features and Temporal Modeling

My qwen model hallucinated a signed URL to Alibaba cloud, normal or sketchy?

Reflection unveils Beam, an open model it says rivals GLM 5.2 on reasoning while using 3x-4× less compute and approaches Qwen3.8-Max on coding and agentic tasks (Semafor)

Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation

Ask a Language Model for Lottery Numbers: Concentration in Repeated Six-of-49 Outputs

CAGE-NAS: Certified Functional Descent for Efficient Model Growth

EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes

Generative Modeling of Stochastic Dynamics for Long-Time Evolution

MedVL-SAM2: A unified 3D medical vision-language model for multimodal reasoning and prompt-driven segmentation

Model validation in machine learning: A scenario-based guide from hold-out splits to nested group cross-validation in biomedical and applied research

New Architecture from Percepta: Spotlight — separating intelligence from memory, allowing knowledge and skills to grow without changing the model's weights.

UniTrackPLA: Unified Panorama-Language-Action Model for Instruction-Guided Navigation and Dynamic Person Tracking

A memory-based active inference model of DishBrain-like adaptive behaviour

CAMOS: Coupled Oscillatory State-Space Model for Multimodal Clinical Time-Series

Compact Language, Complex Model Shifts: How and Where Ambiguity and Underspecification Affect LLMs

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Magic-W0: A Structured World-Action Foundation Model for Physical Intelligence

Manifold-Aware Perturbations for Constrained Generative Modeling

Provable Benefit of SignGD: A Minimal Model Under Heavy-Tailed Class Imbalance

Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions

Uncertainty-Normalized Margins for Direct Preference Optimization

What local AI model is good for game decomps/recomps?

A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses

A theoretical model of dynamical grammatical gender shifting based on set-valued set function

Announcing our first open-weights world-action model, Praxis-1. It turns out that, unsurprisingly, you can get predictably better robotics p…

Direct Experience World-Model Optimization: Learning the World Beyond Action Imitation

Explainability from Training with Applications to TCR-Epitope Prediction

GenoTrace: Inheritable Watermarks for Genome Foundation Model Distillation

HyperSAM: A Promptable Foundation Model for Hyperspectral Remote Sensing

Invariant Atoms: Sparse Coordinates of Local Semantic Geometry in Language Model Representations

LDM-is-AE: Latent Diffusion Model is an Auto-Encoder for End-to-End Image Generation

RelayVSR: Large-Small Model Collaboration for Efficient Real-World Video Super-Resolution

Rethinking Representations for World-Action Modeling

SemOPT: Fixing Semantic Errors in LLM-based Optimization Modeling via Reward-Guided Search

Waypoint-1.5: A Real-Time Video World Model for Consumer Hardware

Algorithmic Harms Associated with Generative Model-Augmented Recommendation Systems

Beyond Isolated Entities: Relation-Aware Multi-Entity Modeling for Unsupervised Video Anomaly Detection

Devanagari Handwritten Character Recognition Using TrOCR: A Transformer-Based Model with Real-Time Web Deployment

Efficient World Action Model Inference with Adaptive Intermediate States

Elastic Selective Spectral Hybrids for Train-Once, Export-Many Budgeted Inference

Endo-TSR: Temporal Spectral Modeling of Appearance and Motion for Endoscopic Reconstruction

InfiMed2: A Generalist Medical Multimodal Foundation Model from Contextual Evidence and Stability-Aware Supervision

Mycelium: A Generalizable Cross-Grid Multi-Task Model for Electrical Distribution Systems

Relation-Aware Graph Foundation Model

SMORE: Stability-Promoting Mesh-Agnostic Model Reduction for Time-Dependent PDEs