Image, video, audio, and text generation
MIT Professor Rafael Gómez-Bombarelli discusses the transformative potential of AI in scientific research, emphasizing its role in materi...
![[2603.12057] Coarse-Guided Visual Generation via Weighted h-Transform Sampling](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Abstract page for arXiv paper 2603.12057: Coarse-Guided Visual Generation via Weighted h-Transform Sampling
Abstract page for arXiv paper 2603.07455: Image Generation Models: A Technical History
This paper introduces ConflictScope, a tool for evaluating how large language models (LLMs) prioritize conflicting values, revealing insi...
The paper explores how vision-language models can simulate dyslexia by disrupting word processing mechanisms, providing insights into rea...
This article evaluates the diversity and quality of content generated by large language models (LLMs), highlighting the trade-offs betwee...
The paper presents Geometric Autoencoders for Bayesian Inversion (GABI), a novel framework for uncertainty quantification in engineering,...
This paper presents MixCache, a novel caching framework designed to enhance the efficiency of text-to-video diffusion models, significant...
LayerT2V presents a novel framework for multi-layer video generation, enabling the creation of editable video layers that enhance profess...
The paper presents Dual-IPO, a novel framework for optimizing text-to-video generation by iteratively improving both the reward and video...
The paper presents VALTEST, a framework for validating test cases generated by large language models (LLMs) using semantic entropy, impro...
The G-reasoner paper introduces a unified framework that enhances reasoning over graph-structured knowledge using a new graph foundation ...
The paper presents FHIR-RAG-MEDS, a system that integrates HL7 FHIR with Retrieval-Augmented Generation models to enhance personalized me...
The paper presents an economic framework for evaluating language models by analyzing the tradeoff between performance and inference costs...
LLM4AD introduces a unified Python platform for algorithm design using large language models, featuring modular components for various ta...
The paper introduces SeeThrough3D, a model for occlusion-aware 3D control in text-to-image generation, enhancing the realism of synthesiz...
This article presents a novel approach to improving masked diffusion models (MDMs) for language modeling by introducing a learned schedul...
This article presents rBridge, a small proxy model that predicts reasoning performance in large language models (LLMs), demonstrating sig...
The paper presents MovieTeller, a novel framework for generating movie synopses using tool-augmented progressive abstraction to enhance c...
This paper introduces a novel approach called Silent Gradients for training Variational Autoencoders (VAEs), which eliminates gradient es...
This article presents a novel framework for probabilistic forecasting of dynamical systems, utilizing flow matching and physical perturba...
This paper investigates why Diffusion Language Models (DLMs) often default to autoregressive decoding instead of utilizing their potentia...
ColoDiff introduces a novel framework for generating colonoscopy videos that ensures dynamic consistency and content awareness, addressin...
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime