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...

[2602.13376] An Online Reference-Free Evaluation Framework for Flowchart Image-to-Code Generation

This article presents a novel reference-free evaluation framework for assessing the quality of flowchart image-to-code generation, utiliz...

[2602.13363] Assessing Spear-Phishing Website Generation in Large Language Model Coding Agents

This article evaluates the capabilities of large language models (LLMs) in generating spear-phishing websites, highlighting the potential...

[2602.14761] Universal Algorithm-Implicit Learning

The paper presents a theoretical framework for meta-learning, introducing the concept of algorithm-implicit learning through a new model ...

[2602.14728] D2-LoRA: A Synergistic Approach to Differential and Directional Low-Rank Adaptation

D2-LoRA introduces a novel method for efficient fine-tuning in machine learning, achieving significant accuracy improvements while minimi...

[2602.13357] AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers

The paper introduces AdaCorrection, a framework that enhances the efficiency of Diffusion Transformers by correcting cache misalignment, ...

[2602.13349] From Prompt to Production:Automating Brand-Safe Marketing Imagery with Text-to-Image Models

This paper discusses a new automated pipeline for generating brand-safe marketing imagery using text-to-image models, balancing automatio...

[2602.14682] Exposing Diversity Bias in Deep Generative Models: Statistical Origins and Correction of Diversity Error

This paper investigates the diversity bias in deep generative models, revealing that these models often underestimate the diversity of th...

[2602.13347] Visual Foresight for Robotic Stow: A Diffusion-Based World Model from Sparse Snapshots

The paper presents FOREST, a diffusion-based world model for robotic stow operations, enhancing the prediction of post-stow configuration...

[2602.14490] Parameter-Efficient Fine-Tuning of LLMs with Mixture of Space Experts

This paper introduces Mixture of Space (MoS), a novel framework for parameter-efficient fine-tuning of large language models (LLMs) that ...

[2602.13306] Fine-Tuning a Large Vision-Language Model for Artwork's Scoring and Critique

This paper presents a framework for automating the scoring and critique of artwork using a fine-tuned vision-language model, achieving hi...

[2602.14468] LACONIC: Length-Aware Constrained Reinforcement Learning for LLM

LACONIC introduces a novel reinforcement learning method for large language models that balances response length and task performance, ac...

[2602.13303] Spectral Collapse in Diffusion Inversion

The paper discusses 'spectral collapse' in diffusion inversion, highlighting failures in standard deterministic methods for image transla...

[2602.13253] Implicit Bias in LLMs for Transgender Populations

This article examines implicit biases in large language models (LLMs) against transgender populations, highlighting disparities in health...

[2602.14301] DeepFusion: Accelerating MoE Training via Federated Knowledge Distillation from Heterogeneous Edge Devices

DeepFusion introduces a scalable framework for federated training of Mixture-of-Experts (MoE) models, leveraging knowledge distillation f...

[2602.13244] Responsible AI in Business

The paper discusses the concept of Responsible AI in business, focusing on its implementation in small and medium-sized enterprises. It c...

[2602.13243] Judging the Judges: Human Validation of Multi-LLM Evaluation for High-Quality K--12 Science Instructional Materials

This study evaluates AI-generated assessments of K-12 science instructional materials, comparing them with expert reviews to enhance futu...

[2602.13241] Real-World Design and Deployment of an Embedded GenAI-powered 9-1-1 Calltaking Training System: Experiences and Lessons Learned

This article discusses the design and deployment of a GenAI-powered training system for 9-1-1 call-takers, highlighting the challenges fa...

[2602.14233] Evaluating LLMs in Finance Requires Explicit Bias Consideration

This paper discusses the need for explicit bias consideration in evaluating Large Language Models (LLMs) used in finance, identifying fiv...

[2602.14209] MAGE: All-[MASK] Block Already Knows Where to Look in Diffusion LLM

The paper presents MAGE, a novel approach to block diffusion LLMs that optimizes memory access and enhances performance by predicting key...

[2602.13200] Traffic Simulation in Ad Hoc Network of Flying UAVs with Generative AI Adaptation

This paper presents a model for traffic simulation in an Ad Hoc network of Unmanned Aerial Vehicles (UAVs) using generative AI to adapt c...