Generative AI

Image, video, audio, and text generation

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

Top This Week

[2512.23994] PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation
Machine Learning

[2512.23994] PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation

Abstract page for arXiv paper 2512.23994: PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-A...

arXiv - AI · 4 min ·
[2512.10785] Developing and Evaluating a Large Language Model-Based Automated Feedback System Grounded in Evidence-Centered Design for Supporting Physics Problem Solving
Llms

[2512.10785] Developing and Evaluating a Large Language Model-Based Automated Feedback System Grounded in Evidence-Centered Design for Supporting Physics Problem Solving

Abstract page for arXiv paper 2512.10785: Developing and Evaluating a Large Language Model-Based Automated Feedback System Grounded in Ev...

arXiv - AI · 4 min ·
[2510.13870] Unlocking the Potential of Diffusion Language Models through Template Infilling
Llms

[2510.13870] Unlocking the Potential of Diffusion Language Models through Template Infilling

Abstract page for arXiv paper 2510.13870: Unlocking the Potential of Diffusion Language Models through Template Infilling

arXiv - AI · 3 min ·

All Content

[2407.03888] Continuous-time q-Learning for Jump-Diffusion Models under Tsallis Entropy
Machine Learning

[2407.03888] Continuous-time q-Learning for Jump-Diffusion Models under Tsallis Entropy

This paper explores continuous-time q-Learning in jump-diffusion models, utilizing Tsallis entropy to derive optimal policies and develop...

arXiv - Machine Learning · 4 min ·
[2602.11151] Diffusion-Pretrained Dense and Contextual Embeddings
Llms

[2602.11151] Diffusion-Pretrained Dense and Contextual Embeddings

The paper introduces pplx-embed, a family of multilingual embedding models utilizing diffusion-pretrained language models for enhanced re...

arXiv - Machine Learning · 3 min ·
[2602.07744] Riemannian MeanFlow
Machine Learning

[2602.07744] Riemannian MeanFlow

The paper introduces Riemannian MeanFlow (RMF), a novel framework for generative modeling on Riemannian manifolds, significantly reducing...

arXiv - Machine Learning · 3 min ·
[2512.09654] Membership and Dataset Inference Attacks on Large Audio Generative Models
Machine Learning

[2512.09654] Membership and Dataset Inference Attacks on Large Audio Generative Models

This paper explores membership and dataset inference attacks on large audio generative models, assessing their implications for copyright...

arXiv - Machine Learning · 4 min ·
[2510.11834] Don't Walk the Line: Boundary Guidance for Filtered Generation
Machine Learning

[2510.11834] Don't Walk the Line: Boundary Guidance for Filtered Generation

The paper presents Boundary Guidance, a reinforcement learning method designed to improve the safety and utility of generative models by ...

arXiv - Machine Learning · 3 min ·
[2510.01022] VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
Machine Learning

[2510.01022] VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks

The paper introduces Vector Diffusion Wavelets (VDWs) for geometric graph neural networks (VDW-GNNs), demonstrating their effectiveness o...

arXiv - Machine Learning · 3 min ·
[2508.10587] Self-Supervised Temporal Super-Resolution of Energy Data using Generative Adversarial Transformer
Machine Learning

[2508.10587] Self-Supervised Temporal Super-Resolution of Energy Data using Generative Adversarial Transformer

This paper presents a novel self-supervised method for temporal super-resolution of energy data using Generative Adversarial Transformers...

arXiv - Machine Learning · 4 min ·
[2508.01504] Instruction-based Time Series Editing
Generative Ai

[2508.01504] Instruction-based Time Series Editing

The paper introduces Instruction-based Time Series Editing, a novel approach that allows users to modify time series data using natural l...

arXiv - Machine Learning · 4 min ·
[2507.09043] GAGA: Gaussianity-Aware Gaussian Approximation for Efficient 3D Molecular Generation
Machine Learning

[2507.09043] GAGA: Gaussianity-Aware Gaussian Approximation for Efficient 3D Molecular Generation

The paper presents GAGA, a method enhancing the efficiency of 3D molecular generation by leveraging Gaussian approximations, improving bo...

arXiv - Machine Learning · 4 min ·
[2503.03704] Memory Injection Attacks on LLM Agents via Query-Only Interaction
Llms

[2503.03704] Memory Injection Attacks on LLM Agents via Query-Only Interaction

The paper discusses Memory Injection Attacks (MINJA) on LLM agents, demonstrating how attackers can manipulate agent memory through query...

arXiv - Machine Learning · 4 min ·
[2409.00730] Generating Physical Dynamics under Priors
Machine Learning

[2409.00730] Generating Physical Dynamics under Priors

This article presents a novel framework for generating physically realistic dynamics in data-driven contexts by incorporating physical pr...

arXiv - Machine Learning · 4 min ·
[2602.13168] Realistic Face Reconstruction from Facial Embeddings via Diffusion Models
Machine Learning

[2602.13168] Realistic Face Reconstruction from Facial Embeddings via Diffusion Models

This paper presents a novel framework for reconstructing realistic high-resolution face images from facial embeddings using diffusion mod...

arXiv - Machine Learning · 3 min ·
[2602.12932] TFTF: Training-Free Targeted Flow for Conditional Sampling
Machine Learning

[2602.12932] TFTF: Training-Free Targeted Flow for Conditional Sampling

The paper presents a novel training-free method for conditional sampling in flow matching models, addressing the limitations of importanc...

arXiv - Machine Learning · 3 min ·
[2602.13103] R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training
Llms

[2602.13103] R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training

The paper presents R-Diverse, a method aimed at addressing the Diversity Illusion in self-play training for large language models (LLMs),...

arXiv - Machine Learning · 4 min ·
[2602.13042] GPTZero: Robust Detection of LLM-Generated Texts
Llms

[2602.13042] GPTZero: Robust Detection of LLM-Generated Texts

GPTZero introduces a robust solution for detecting AI-generated texts, addressing concerns over text authenticity and misinformation in t...

arXiv - Machine Learning · 3 min ·
[2602.12704] QTabGAN: A Hybrid Quantum-Classical GAN for Tabular Data Synthesis
Machine Learning

[2602.12704] QTabGAN: A Hybrid Quantum-Classical GAN for Tabular Data Synthesis

QTabGAN introduces a hybrid quantum-classical generative adversarial network designed for synthesizing tabular data, addressing challenge...

arXiv - Machine Learning · 3 min ·
[2602.12683] Flow Matching from Viewpoint of Proximal Operators
Machine Learning

[2602.12683] Flow Matching from Viewpoint of Proximal Operators

This article presents a reformulation of Optimal Transport Conditional Flow Matching (OT-CFM) through proximal operators, demonstrating i...

arXiv - Machine Learning · 3 min ·
[2602.12624] Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps
Machine Learning

[2602.12624] Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps

This paper presents a framework for optimizing sampling in diffusion-based generative models, addressing high sampling costs through adap...

arXiv - Machine Learning · 4 min ·
[2602.12533] AMPS: Adaptive Modality Preference Steering via Functional Entropy
Llms

[2602.12533] AMPS: Adaptive Modality Preference Steering via Functional Entropy

The paper presents AMPS, a method for Adaptive Modality Preference Steering in Multimodal Large Language Models (MLLMs), addressing the c...

arXiv - Machine Learning · 4 min ·
[2602.12529] Flow-Factory: A Unified Framework for Reinforcement Learning in Flow-Matching Models
Machine Learning

[2602.12529] Flow-Factory: A Unified Framework for Reinforcement Learning in Flow-Matching Models

Flow-Factory presents a unified framework for reinforcement learning in flow-matching models, addressing fragmentation and complexity in ...

arXiv - Machine Learning · 3 min ·
Previous Page 105 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