Generative AI

Image, video, audio, and text generation

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

Top This Week

Accelerating science with AI and simulations
Machine Learning

Accelerating science with AI and simulations

MIT Professor Rafael Gómez-Bombarelli discusses the transformative potential of AI in scientific research, emphasizing its role in materi...

AI News - General · 10 min ·
[2510.08005] Past, Present, and Future of Bug Tracking in the Generative AI Era
Generative Ai

[2510.08005] Past, Present, and Future of Bug Tracking in the Generative AI Era

Abstract page for arXiv paper 2510.08005: Past, Present, and Future of Bug Tracking in the Generative AI Era

arXiv - AI · 4 min ·
[2509.05841] Generative AI on Wall Street -- Opportunities and Risk Controls
Generative Ai

[2509.05841] Generative AI on Wall Street -- Opportunities and Risk Controls

Abstract page for arXiv paper 2509.05841: Generative AI on Wall Street -- Opportunities and Risk Controls

arXiv - AI · 3 min ·

All Content

[2602.21873] GFPL: Generative Federated Prototype Learning for Resource-Constrained and Data-Imbalanced Vision Task
Machine Learning

[2602.21873] GFPL: Generative Federated Prototype Learning for Resource-Constrained and Data-Imbalanced Vision Task

The GFPL framework enhances federated learning by addressing data imbalance and communication overhead in resource-constrained vision tas...

arXiv - Machine Learning · 4 min ·
[2602.21677] Trie-Aware Transformers for Generative Recommendation
Machine Learning

[2602.21677] Trie-Aware Transformers for Generative Recommendation

The paper introduces TrieRec, a trie-aware generative recommendation method that enhances Transformers by incorporating structural induct...

arXiv - Machine Learning · 3 min ·
[2602.21948] Bayesian Generative Adversarial Networks via Gaussian Approximation for Tabular Data Synthesis
Machine Learning

[2602.21948] Bayesian Generative Adversarial Networks via Gaussian Approximation for Tabular Data Synthesis

This paper introduces GACTGAN, a Bayesian Generative Adversarial Network that utilizes Gaussian approximation for synthesizing tabular da...

arXiv - Machine Learning · 3 min ·
[2602.21824] DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion
Llms

[2602.21824] DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion

DocDjinn introduces a framework for generating synthetic documents using Vision-Language Models (VLMs), addressing challenges in data acq...

arXiv - Machine Learning · 4 min ·
[2602.21593] Breaking Semantic-Aware Watermarks via LLM-Guided Coherence-Preserving Semantic Injection
Llms

[2602.21593] Breaking Semantic-Aware Watermarks via LLM-Guided Coherence-Preserving Semantic Injection

The paper introduces a novel attack method, Coherence-Preserving Semantic Injection (CSI), that exploits vulnerabilities in semantic-awar...

arXiv - Machine Learning · 4 min ·
[2602.21585] Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences
Llms

[2602.21585] Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences

The paper presents Duel-Evolve, an innovative algorithm that optimizes large language model outputs at test time using pairwise self-pref...

arXiv - AI · 4 min ·
[2602.21565] Training-free Composition of Pre-trained GFlowNets for Multi-Objective Generation
Machine Learning

[2602.21565] Training-free Composition of Pre-trained GFlowNets for Multi-Objective Generation

This article presents a novel approach to using pre-trained GFlowNets for multi-objective generation without the need for additional trai...

arXiv - Machine Learning · 3 min ·
[2602.21472] The Design Space of Tri-Modal Masked Diffusion Models
Llms

[2602.21472] The Design Space of Tri-Modal Masked Diffusion Models

This paper introduces the first tri-modal masked diffusion model, pretrained on text, image-text, and audio-text data, analyzing its perf...

arXiv - Machine Learning · 4 min ·
[2602.21469] D-Flow SGLD: Source-Space Posterior Sampling for Scientific Inverse Problems with Flow Matching
Machine Learning

[2602.21469] D-Flow SGLD: Source-Space Posterior Sampling for Scientific Inverse Problems with Flow Matching

The paper presents D-Flow SGLD, a method for source-space posterior sampling in scientific inverse problems, enhancing fidelity and uncer...

arXiv - Machine Learning · 4 min ·
[2602.21390] Defensive Generation
Machine Learning

[2602.21390] Defensive Generation

The paper 'Defensive Generation' presents a novel approach to creating generative models that are unfalsifiable based on observed data, e...

arXiv - Machine Learning · 3 min ·
[2602.21317] Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling
Llms

[2602.21317] Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling

The paper presents PRISM, a model-agnostic system designed to enhance large language models (LLMs) by fostering pluralistic reasoning thr...

arXiv - Machine Learning · 3 min ·
[2602.21319] Uncertainty-Aware Diffusion Model for Multimodal Highway Trajectory Prediction via DDIM Sampling
Machine Learning

[2602.21319] Uncertainty-Aware Diffusion Model for Multimodal Highway Trajectory Prediction via DDIM Sampling

The paper presents cVMDx, an advanced diffusion model for multimodal highway trajectory prediction, enhancing efficiency and accuracy in ...

arXiv - Machine Learning · 3 min ·
[2602.10953] Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models
Llms

[2602.10953] Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models

The paper presents SOAR, a novel decoding algorithm for Diffusion Language Models that adapts its search strategy based on model confiden...

arXiv - AI · 3 min ·
[2602.02137] DCoPilot: Generative AI-Empowered Policy Adaptation for Dynamic Data Center Operations
Generative Ai

[2602.02137] DCoPilot: Generative AI-Empowered Policy Adaptation for Dynamic Data Center Operations

DCoPilot is a hybrid framework utilizing generative AI to enhance policy adaptation in dynamic data center operations, ensuring efficient...

arXiv - Machine Learning · 4 min ·
[2602.02007] Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
Nlp

[2602.02007] Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation

The paper introduces xMemory, a novel approach to agent memory systems that enhances retrieval by decoupling and aggregating semantic com...

arXiv - AI · 4 min ·
[2601.19922] HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialogue
Llms

[2601.19922] HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialogue

The paper introduces HEART, a benchmark for evaluating emotional support dialogue in humans and LLMs, focusing on empathy and communicati...

arXiv - AI · 4 min ·
[2601.17064] Between Search and Platform: ChatGPT Under the DSA
Llms

[2601.17064] Between Search and Platform: ChatGPT Under the DSA

This article analyzes the classification of ChatGPT under the Digital Services Act (DSA), proposing it as a hybrid of search engine and p...

arXiv - AI · 3 min ·
[2511.06899] RPTS: Tree-Structured Reasoning Process Scoring for Faithful Multimodal Evaluation
Llms

[2511.06899] RPTS: Tree-Structured Reasoning Process Scoring for Faithful Multimodal Evaluation

The paper presents the Reasoning Process Tree Score (RPTS), a novel metric for evaluating reasoning in Large Vision-Language Models (LVLM...

arXiv - AI · 4 min ·
[2511.00062] World Simulation with Video Foundation Models for Physical AI
Llms

[2511.00062] World Simulation with Video Foundation Models for Physical AI

The paper presents Cosmos-Predict2.5, an advanced model for world simulation in Physical AI, integrating various generation methods and i...

arXiv - Machine Learning · 5 min ·
[2510.18060] SPACeR: Self-Play Anchoring with Centralized Reference Models
Machine Learning

[2510.18060] SPACeR: Self-Play Anchoring with Centralized Reference Models

The paper introduces SPACeR, a framework for enhancing autonomous vehicle behavior through self-play reinforcement learning anchored by a...

arXiv - Machine Learning · 4 min ·
Previous Page 40 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