Generative AI

Will Generative AI apps remain a revenue powerhouse in 2026?

[2601.08565] Rewriting Video: Text-Driven Reauthoring of Video Footage

Abstract page for arXiv paper 2601.08565: Rewriting Video: Text-Driven Reauthoring of Video Footage

[2512.18388] Exploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creation with Generative Models

Abstract page for arXiv paper 2512.18388: Exploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creatio...

[2508.03346] Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy

This article presents a novel framework for compressing Chain-of-Thought (CoT) prompts in Large Language Models (LLMs) to enhance inferen...

[2506.02873] It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics

This article evaluates the persuasive capabilities of frontier large language models (LLMs) on harmful topics, introducing a new benchmar...

[2505.04338] Riemannian Denoising Diffusion Probabilistic Models

The paper introduces Riemannian Denoising Diffusion Probabilistic Models (RDDPMs), which enhance generative modeling on submanifolds of E...

[2503.08796] Robust Multi-Objective Controlled Decoding of Large Language Models

This article presents Robust Multi-Objective Decoding (RMOD), an innovative algorithm designed to enhance the performance of Large Langua...

[2502.14560] Less is More: Improving LLM Alignment via Preference Data Selection

This article discusses a novel approach to improving large language model (LLM) alignment through effective preference data selection, en...

[2602.14968] PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement

The paper introduces PhyScensis, a framework that uses physics-augmented LLM agents to generate complex 3D physical scenes for robotic ma...

[2602.14941] AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories

AnchorWeave introduces a novel framework for video generation that enhances spatial consistency over long durations by utilizing multiple...

[2502.02415] Fast Graph Generation via Autoregressive Noisy Filtration Modeling

This paper presents Autoregressive Noisy Filtration Modeling (ANFM), a new framework for fast graph generation that balances quality and ...

[2412.11439] Bayesian Flow Is All You Need to Sample Out-of-Distribution Chemical Spaces

The paper presents a Bayesian flow network, specifically the ChemBFN model, which effectively generates out-of-distribution chemical samp...

[2410.18784] Denoising diffusion probabilistic models are optimally adaptive to unknown low dimensionality

This paper explores the efficiency of denoising diffusion probabilistic models (DDPM) in adapting to unknown low dimensionality, proving ...

[2410.10481] Model-based Large Language Model Customization as Service

The paper presents Llamdex, a framework for customizing large language models (LLMs) as a service, allowing clients to upload domain-spec...

[2410.03919] Online Posterior Sampling with a Diffusion Prior

The paper presents algorithms for online posterior sampling in contextual bandits using a diffusion model prior, enhancing the efficiency...

[2602.14783] What hackers talk about when they talk about AI: Early-stage diffusion of a cybercrime innovation

This article explores how cybercriminals are discussing and utilizing artificial intelligence (AI) to enhance their operations, revealing...

[2602.14778] A Geometric Analysis of Small-sized Language Model Hallucinations

This paper explores hallucinations in small-sized language models (LLMs) through a geometric lens, demonstrating that genuine responses c...

[2602.14770] Multi-Agent Comedy Club: Investigating Community Discussion Effects on LLM Humor Generation

This study investigates how community discussions influence humor generation in large language models (LLMs), demonstrating that feedback...

[2602.14681] ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies

The paper presents ST-EVO, a novel framework for generative spatio-temporal evolution of multi-agent communication topologies, enhancing ...

[2602.14885] Drift-Diffusion Matching: Embedding dynamics in latent manifolds of asymmetric neural networks

The paper introduces Drift-Diffusion Matching, a framework for training recurrent neural networks (RNNs) to model complex stochastic dyna...

[2602.14833] RF-GPT: Teaching AI to See the Wireless World

RF-GPT introduces a novel radio-frequency language model that bridges the gap between RF signal processing and high-level reasoning using...

[2602.14777] Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment

This research paper explores how emergently misaligned language models exhibit behavioral self-awareness, revealing shifts in their self-...

[2602.14642] GenPANIS: A Latent-Variable Generative Framework for Forward and Inverse PDE Problems in Multiphase Media

GenPANIS introduces a generative framework for solving forward and inverse PDE problems in multiphase media, enhancing accuracy and effic...