Deep Learning
T ell What You Hear From What You See - Video to Audio Generation Through Text
When the audio caption is provided as a prompt, V A TT achieves even more refined performance (with lowest KLD score of 1.41).
From Causal to Concept-Based Representation Learning
A key question in this growing field is to provide rigorous conditions under which latent factors can be identified and thus, potentially learned.
Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models
The function space diffusion models need to be equivariant with respect to the underlying spatial transformations. To ensure temporal consistency, we introduce a simple post-hoc test-time guidance towards (self)-equivariant solutions.
T APTRv2: Attention-based Position Update Improves Tracking Any Point Hongyang Li1,2 Hao Zhang
Thus most methods are not general and have to be fine-tuned for each video.
MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings Laxman Dhulipala Google Research and UMD Majid Hadian Google DeepMind Rajesh Jayaram
Neural embedding models have become a fundamental component of modern information retrieval (IR) pipelines.
Wenkai Y ang
LLM-based agents are currently under-explored.
Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models
In this work, we present MuDI, a novel framework that enables multi-subject personalization by effectively decoupling identities from multiple subjects.
HYDRA: Model Factorization Framework for Black-Box LLM Personalization Y uchen Zhuang
Personalization has emerged as a critical research area in modern intelligent systems, focusing on mining users' behavioral history and adapting to their preferences