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...

[2508.21285] A Financial Brain Scan of the LLM

This article presents a novel approach to analyzing large language models (LLMs) in finance, enabling researchers to identify and manipul...

[2508.18210] Why Synthetic Isn't Real Yet: A Diagnostic Framework for Contact Center Dialogue Generation

This article presents a diagnostic framework for evaluating synthetic dialogue generation in contact centers, highlighting the limitation...

[2307.14397] A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot

This survey explores generative modeling under constraints of limited data, few shots, and zero shots, presenting challenges and methodol...

[2507.04704] SPATIA: Multimodal Generation and Prediction of Spatial Cell Phenotypes

The paper introduces SPATIA, a novel multimodal model for predicting spatial cell phenotypes by integrating cellular morphology, gene exp...

[2602.06801] On the Non-Identifiability of Steering Vectors in Large Language Models

This paper explores the non-identifiability of steering vectors in large language models (LLMs), revealing that these vectors cannot be u...

[2506.04051] High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning

The paper presents HALT, a method for finetuning large language models (LLMs) to enhance reliability by generating responses only when co...

[2602.05319] Accelerated Sequential Flow Matching: A Bayesian Filtering Perspective

This paper introduces Accelerated Sequential Flow Matching, a Bayesian filtering framework that enhances real-time inference in stochasti...

[2506.03407] Multi-Spectral Gaussian Splatting with Neural Color Representation

The paper presents MS-Splatting, a novel multi-spectral 3D Gaussian Splatting framework that generates consistent views from images captu...

[2602.00628] From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs

This paper examines the relationship between behavioral and hidden-state semantic geometry in large language models (LLMs) through psycho...

[2505.07861] Scalable LLM Reasoning Acceleration with Low-rank Distillation

The paper presents Caprese, a low-rank distillation method designed to enhance reasoning capabilities in large language models (LLMs) whi...

[2505.07671] Benchmarking Retrieval-Augmented Generation for Chemistry

This article presents ChemRAG-Bench, a benchmark for evaluating retrieval-augmented generation (RAG) in chemistry, demonstrating signific...

[2601.13190] LAViG-FLOW: Latent Autoregressive Video Generation for Fluid Flow Simulations

LAViG-FLOW introduces a novel framework for generating fluid flow simulations, significantly improving efficiency and consistency in mode...

[2601.12415] Orthogonalized Policy Optimization:Decoupling Sampling Geometry from Optimization Geometry in RLHF

This paper introduces Orthogonalized Policy Optimization (OPO), a new approach in reinforcement learning that separates sampling and opti...

[2503.04641] Simulating the Real World: A Unified Survey of Multimodal Generative Models

This article presents a comprehensive survey of multimodal generative models, focusing on their integration from 2D to 4D representations...

[2601.03213] Critic-Guided Reinforcement Unlearning in Text-to-Image Diffusion

The paper presents a novel reinforcement learning framework for unlearning targeted concepts in text-to-image diffusion models, enhancing...

[2502.16730] RapidPen: Fully Automated IP-to-Shell Penetration Testing with LLM-based Agents

RapidPen is a novel automated penetration testing framework that utilizes large language models to autonomously exploit vulnerabilities, ...

[2512.10858] Scaling Behavior of Discrete Diffusion Language Models

This article explores the scaling behavior of discrete diffusion language models (DLMs) compared to autoregressive language models (ALMs)...

[2511.22693] Generative Anchored Fields: Controlled Data Generation via Emergent Velocity Fields and Transport Algebra

The paper introduces Generative Anchored Fields (GAF), a novel generative model that enhances data generation through controlled interpol...

[2511.17879] Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction

This paper presents a novel method using generative adversarial training to address reward hacking in real-time human-AI music interactio...

[2511.07833] MURPHY: Multi-Turn GRPO for Self Correcting Code Generation

The paper presents MURPHY, a multi-turn reinforcement learning framework that enhances code generation by incorporating execution feedbac...