127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “pretraining”

6,571 results

Research

Draw This First

DGX agent

arXiv:2608.12064v1 Announce Type: new Abstract: We invert the typical formulation of sketch generation: instead of drawing strokes in order, we predict a 2D field that defines the order in which strok

researcharxiv-cs-cv

13 Aug 2026

Tutorials

Dual Modality Prompted Diffusion Priors for Zero Shot Hyperspectral Pansharpening

DGX agent

arXiv:2608.11748v1 Announce Type: new Abstract: Hyperspectral pansharpening aims to reconstruct a high resolution hyperspectral (HRHS) image from a panchromatic (PAN) image and a low resolution hypers

Search: “pretraining”

Draw This First

Dual Modality Prompted Diffusion Priors for Zero Shot Hyperspectral Pansharpening

Foresight Without Seeing: Latent Futures for World Action Models

From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection

GCPO: Diagnosing and Constraining Subspace Geometry in Rollout RL for LLMs

Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction

GeoUniPR: A Geometry-Consistent Unified Framework for Cross-Modal Place Recognition

Grounding Large Language Models as Generalizable Policies in Network Control

HAMP-LIC: Hessian-Aware Mixed-Precision Post-Training Quantization for Learned Image Compression

Hand Visibility Detector: Per-Keypoint Visibility Estimation for Hands

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge

Is Convergence Inevitable? Tracing Output Homogeneity Back to Base Models

LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time

Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus

Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

Qwen-MusicAVQA-7B: A Multimodal Model for Music Audio-Visual QA

ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening

Test-Time Hallucination Control in Large Vision-Language Models

UniSwap: Streaming Audio-Visual Identity Swapping for Talking Videos

XYZFlow:Scaling Multi dimensional Shortcut Flows for Efficient Generative Modeling

A Cost-Efficient Routing Pipeline for Multilingual Short-Text Classification Using Small Language Models

Accelerated Learning of High Dimensional Functions with a Tensor-Featured Training Network

AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss

An adaptive and evolvable deep reinforcement learning framework for weather prediction

Assessing Reliability of BERT-Based Models on Question Answering Tasks

Beyond Pixels: From Video Priors to 4D Worlds

CurveFP: Rational-Radix Logarithmic Datatypes with Closed Products for Language Models

Embodied Multimodal Grounding for Open-Vocabulary Mobile Manipulation via Semantic 3D Gaussian Splatting

FiGuRO: Intrinsic Dimension Estimation for Multi-Modal Data

GLAM: Efficient Continual Learning at Scale via Grouped LoRA Adapter Merging

Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models

HyWA: Architecture-Preserving Personalized Voice Activity Detection for Full-Duplex Voice Assistants

Learning Representations from Incomplete EHR Data with Dual-Masked Autoencoding

LoRCA: LoRA Cycle Adaptation for Histology to HiP-CT Translation with DINOv3

Motion Artifact-Aware Self-Supervised Representation Learning for 3D Brain MRI Motion Artifact Reduction

Multimodal Ambivalence and Hesitancy Recognition via Cross-Attention and Gated Fusion

ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization

Seeds Before Objectives: Rethinking Evaluation for Low-Resource Garhwali ASR

Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching

Visual Geometry Foundation-Aware Gaussians for Single-Frame Surround-View Driving Reconstruction

VoxSumm: A Multilingual Corpus of Long-Form Spoken News for Joint Summarization and Translation

X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction

Agentic Visual Reasoning in Whole-Slide Pathology Images via Active Perception

Beyond Hazard Resemblance: Contrastive Event Adjudication for Training-Free Video Anomaly Detection

Beyond Routing: Decoupling Expert Dispatch and Aggregation in Sparse Mixture-of-Experts

Bootstrapping Vision-Language Model for Hysteroscopic Surgical Scene Segmentation

Compositional Cross-Modality Translation via Whole-Volume Multitask Latent Flow Matching

Contamination Means Overestimation? A Fine-Grained Empirical Study in Code Intelligence