AI研究論文每日精選

OmniGen: Unified Image Generation

NVLM: Open Frontier-Class Multimodal LLMs

Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models

EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer

A Comprehensive Evaluation of Quantized Instruction-Tuned Large Language Models: An Experimental Analysis up to 405B

OSV: One Step is Enough for High-Quality Image to Video Generation

On the limits of agency in agent-based models

Agile Continuous Jumping in Discontinuous Terrains

SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction

Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse

Human-like Affective Cognition in Foundation Models

Single-Layer Learnable Activation for Implicit Neural Representation (SL^{2}A-INR)

PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processing

Implicit Neural Representations with Fourier Kolmogorov-Arnold Networks