Generative AI

Image, video, audio, and text generation

This Week's Best | Monthly Best | Guide | Trending

Top This Week

[2602.08277] PISCO: Precise Video Instance Insertion with Sparse Control
Generative Ai

[2602.08277] PISCO: Precise Video Instance Insertion with Sparse Control

Abstract page for arXiv paper 2602.08277: PISCO: Precise Video Instance Insertion with Sparse Control

arXiv - AI · 4 min ·
[2511.18746] Any4D: Open-Prompt 4D Generation from Natural Language and Images
Machine Learning

[2511.18746] Any4D: Open-Prompt 4D Generation from Natural Language and Images

Abstract page for arXiv paper 2511.18746: Any4D: Open-Prompt 4D Generation from Natural Language and Images

arXiv - AI · 4 min ·
[2512.14549] Dual-objective Language Models: Training Efficiency Without Overfitting
Llms

[2512.14549] Dual-objective Language Models: Training Efficiency Without Overfitting

Abstract page for arXiv paper 2512.14549: Dual-objective Language Models: Training Efficiency Without Overfitting

arXiv - AI · 3 min ·

All Content

[2603.00233] Scaling Quantum Machine Learning without Tricks: High-Resolution and Diverse Image Generation
Machine Learning

[2603.00233] Scaling Quantum Machine Learning without Tricks: High-Resolution and Diverse Image Generation

Abstract page for arXiv paper 2603.00233: Scaling Quantum Machine Learning without Tricks: High-Resolution and Diverse Image Generation

arXiv - Machine Learning · 4 min ·
[2603.02012] MAP-Diff: Multi-Anchor Guided Diffusion for Progressive 3D Whole-Body Low-Dose PET Denoising
Machine Learning

[2603.02012] MAP-Diff: Multi-Anchor Guided Diffusion for Progressive 3D Whole-Body Low-Dose PET Denoising

Abstract page for arXiv paper 2603.02012: MAP-Diff: Multi-Anchor Guided Diffusion for Progressive 3D Whole-Body Low-Dose PET Denoising

arXiv - AI · 4 min ·
[2603.01953] Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy
Machine Learning

[2603.01953] Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy

Abstract page for arXiv paper 2603.01953: Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy

arXiv - AI · 3 min ·
[2603.02028] Latent attention on masked patches for flow reconstruction
Machine Learning

[2603.02028] Latent attention on masked patches for flow reconstruction

Abstract page for arXiv paper 2603.02028: Latent attention on masked patches for flow reconstruction

arXiv - Machine Learning · 4 min ·
[2603.02005] Mitigating topology biases in Graph Diffusion via Counterfactual Intervention
Machine Learning

[2603.02005] Mitigating topology biases in Graph Diffusion via Counterfactual Intervention

Abstract page for arXiv paper 2603.02005: Mitigating topology biases in Graph Diffusion via Counterfactual Intervention

arXiv - Machine Learning · 4 min ·
[2603.01509] Retrieval, Refinement, and Ranking for Text-to-Video Generation via Prompt Optimization and Test-Time Scaling
Machine Learning

[2603.01509] Retrieval, Refinement, and Ranking for Text-to-Video Generation via Prompt Optimization and Test-Time Scaling

Abstract page for arXiv paper 2603.01509: Retrieval, Refinement, and Ranking for Text-to-Video Generation via Prompt Optimization and Tes...

arXiv - AI · 4 min ·
[2603.01837] Constrained Particle Seeking: Solving Diffusion Inverse Problems with Just Forward Passes
Machine Learning

[2603.01837] Constrained Particle Seeking: Solving Diffusion Inverse Problems with Just Forward Passes

Abstract page for arXiv paper 2603.01837: Constrained Particle Seeking: Solving Diffusion Inverse Problems with Just Forward Passes

arXiv - Machine Learning · 3 min ·
[2603.01780] D3LM: A Discrete DNA Diffusion Language Model for Bidirectional DNA Understanding and Generation
Llms

[2603.01780] D3LM: A Discrete DNA Diffusion Language Model for Bidirectional DNA Understanding and Generation

Abstract page for arXiv paper 2603.01780: D3LM: A Discrete DNA Diffusion Language Model for Bidirectional DNA Understanding and Generation

arXiv - Machine Learning · 4 min ·
[2603.01331] MetaState: Persistent Working Memory for Discrete Diffusion Language Models
Llms

[2603.01331] MetaState: Persistent Working Memory for Discrete Diffusion Language Models

Abstract page for arXiv paper 2603.01331: MetaState: Persistent Working Memory for Discrete Diffusion Language Models

arXiv - Machine Learning · 4 min ·
[2603.01591] FAST-DIPS: Adjoint-Free Analytic Steps and Hard-Constrained Likelihood Correction for Diffusion-Prior Inverse Problems
Machine Learning

[2603.01591] FAST-DIPS: Adjoint-Free Analytic Steps and Hard-Constrained Likelihood Correction for Diffusion-Prior Inverse Problems

Abstract page for arXiv paper 2603.01591: FAST-DIPS: Adjoint-Free Analytic Steps and Hard-Constrained Likelihood Correction for Diffusion...

arXiv - Machine Learning · 4 min ·
[2603.01563] LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models
Llms

[2603.01563] LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models

Abstract page for arXiv paper 2603.01563: LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models

arXiv - Machine Learning · 4 min ·
[2603.01367] DUEL: Exact Likelihood for Masked Diffusion via Deterministic Unmasking
Machine Learning

[2603.01367] DUEL: Exact Likelihood for Masked Diffusion via Deterministic Unmasking

Abstract page for arXiv paper 2603.01367: DUEL: Exact Likelihood for Masked Diffusion via Deterministic Unmasking

arXiv - Machine Learning · 4 min ·
[2603.01023] An Open-Source Modular Benchmark for Diffusion-Based Motion Planning in Closed-Loop Autonomous Driving
Generative Ai

[2603.01023] An Open-Source Modular Benchmark for Diffusion-Based Motion Planning in Closed-Loop Autonomous Driving

Abstract page for arXiv paper 2603.01023: An Open-Source Modular Benchmark for Diffusion-Based Motion Planning in Closed-Loop Autonomous ...

arXiv - AI · 4 min ·
[2603.00978] EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization
Machine Learning

[2603.00978] EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization

Abstract page for arXiv paper 2603.00978: EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Objec...

arXiv - AI · 4 min ·
[2603.00992] Compensation-free Machine Unlearning in Text-to-Image Diffusion Models by Eliminating the Mutual Information
Machine Learning

[2603.00992] Compensation-free Machine Unlearning in Text-to-Image Diffusion Models by Eliminating the Mutual Information

Abstract page for arXiv paper 2603.00992: Compensation-free Machine Unlearning in Text-to-Image Diffusion Models by Eliminating the Mutua...

arXiv - Machine Learning · 4 min ·
[2603.00918] Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards
Machine Learning

[2603.00918] Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards

Abstract page for arXiv paper 2603.00918: Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards

arXiv - AI · 3 min ·
[2603.00975] Forgetting is Competition: Rethinking Unlearning as Representation Interference in Diffusion Models
Machine Learning

[2603.00975] Forgetting is Competition: Rethinking Unlearning as Representation Interference in Diffusion Models

Abstract page for arXiv paper 2603.00975: Forgetting is Competition: Rethinking Unlearning as Representation Interference in Diffusion Mo...

arXiv - Machine Learning · 4 min ·
[2603.00877] Active Flow Matching
Machine Learning

[2603.00877] Active Flow Matching

Abstract page for arXiv paper 2603.00877: Active Flow Matching

arXiv - Machine Learning · 3 min ·
[2603.00756] Stroke outcome and evolution prediction from CT brain using a spatiotemporal diffusion autoencoder
Machine Learning

[2603.00756] Stroke outcome and evolution prediction from CT brain using a spatiotemporal diffusion autoencoder

Abstract page for arXiv paper 2603.00756: Stroke outcome and evolution prediction from CT brain using a spatiotemporal diffusion autoencoder

arXiv - AI · 3 min ·
[2603.00607] IdGlow: Dynamic Identity Modulation for Multi-Subject Generation
Machine Learning

[2603.00607] IdGlow: Dynamic Identity Modulation for Multi-Subject Generation

Abstract page for arXiv paper 2603.00607: IdGlow: Dynamic Identity Modulation for Multi-Subject Generation

arXiv - AI · 4 min ·
Previous Page 20 Next

Related Topics

Machine Learning Large Language Models Natural Language Processing Computer Vision Robotics & Embodied AI AI Safety & Ethics

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Subscribe to Newsletter

Daily or weekly digest • Unsubscribe anytime