Genre
Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
For example, hats and sunglasses are placed on incorrect objects. We introduce a novel method T oMeto address these challenges.
Benchmarking Complex Instruction-Following with Multiple Constraints Composition
LLMs has become a critical research problem.
Transformers on Markov data: Constant depth suffices
Attention-based transformers have been remarkably successful at modeling generative processes across various domains and modalities.
Confusion-Resistant Federated Learning via Diffusion-Based Data Harmonization on Non-IID Data Xiaohong Chen
Federated learning has become a pivotal distributed learning paradigm, involving collaborative model updates across multiple nodes with private data.
Linguistic Collapse: Neural Collapse in (Large) Language Models
Convergence to a simplex ETF: Class means tend towards equinorm and equiangular vectors when centred about the global average.
Task-oriented Time Series Imputation Evaluation via Generalized Representers Zhixian Wang 1,2, Linxiao Y ang
Specifically, we summarize our contributions into the following points.
ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition Mohammadreza Salehi Jae Sung Park
Each video in the dataset is paired with a question and four or five choices.