127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “pretraining”

6,758 results

Local Ai

Local Support Learning

DGX agent

arXiv:2610.02126v1 Announce Type: cross Abstract: We explore catastrophic forgetting in the context of large pre-trained models. By considering forgetting as a geometric problem in the input space of

local-aiarxiv-cs-ai

2 Oct 2026

Local Ai

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

DGX agent

Search: “pretraining”

Local Support Learning

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

Meta-Multi-Agent Reinforcement Learning for Fast Adaptation of Interactive Policies with Applications to Autonomous Driving

No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agents

One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatars

OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous

T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning

TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-Tuning

The Geometry of Contextual Relations: Language Models Address Facts by Order of Mention

The hidden advantage of mask resampling: a theory of masked autoencoders

TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models

Training-Aware Target Coverage for Synthetic Data Selection

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

Universal interpolation for deep residual self-attention networks

Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography

A Comprehensive Benchmark of Source-Free Universal Domain Adaptation on Time Series Representations

A Generalizable and Explainable Framework for Synthetic Video Detection Using First-Digit Gradient Statistics

Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration

An Uncertainty-Guided Digital Twin Framework for Online Adaptive Proton Therapy in Head and Neck Cancer: A Feasibility Study

AneumoBench: A Source-Linked Benchmark for Synthetic-Geometry Transfer in Aneurysm CFD

Behavior-Grounded Semantic Enrichment for Financial Fraud Modeling and Reasoning

Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image Fusion

Beyond the Current Scene: Event-Referential Grasping with Active View Selection

CAST: Causal Advantage-Structured Training with Spatially Grounded Compositional Rewards for Diffusion Models

CellMSA: Context Modeling for Single-Cell Representation Learning

CoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video Understanding

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence

Disentangling Self-Distillation: Measuring and Modeling Acquisition and Retention

Enhancing Autoregressive Video Generation via Representation Adversarial Distillation

EWAM: Emergent Depth-Wise Specialization in a Unified Embodied Model -- From Semantic Understanding through Visual Foresight to Action

GestAdapt: Workspace-Conditioned Co-Speech Gesture Generation for Humanoid Robots

GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

Instruction Retrieval at Inference Time for Small Language Models

Learning Functional Subspaces for Neural Network Compression

Learning Reliable GUI Agents under Imperfect Priors

Learning Skills from Historical Action Trajectories: Action Experience Dictionary for World Action Models

Learning Where to Look: Anatomical Grounding and Guided Attention for Cardiac MRI Vision-Language Models

Matisse: Evidence-Space Reasoning for Active 3D Reconstruction

MatLoom: Layered Text-to-Material Generation in a Compact Program Space

Mitigating Memorization In Language Models

Molecular Property Prediction under Structural Shift with Tabular Foundation Models

Multi-Link Safety Filtering for VLA Policies Around Moving Hazards

OccluDex: Hierarchical 3D Visuo-Tactile Representation Learning for Egocentric Dexterous Manipulation under Self-Occlusion

OverdoseMoE: A Multi-Expert Framework for Opioid Overdose Risk Prediction

PartiCam: Camera Controlled Video Generation with Reward Guidance

Persistent Watermarking of Text-to-Image Models

PhasePlan: Ordered Future-Phase Planning for Robot Brain Models