Asia
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.
Learning Large-scale Neural Fields via Context Pruned Meta-Learning
We introduce an efficient optimization-based meta-learning technique for large-scale neural field training by realizing significant memory savings through automated online context point selection.
DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation Qingkai Fang 1,2, Y an Zhou 1,2, Y ang Feng 1,2 1
In this paper, we propose DASpeech, a non-autoregressive direct S2ST model which realizes both fast and high-quality S2ST.
Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients
However, due to the heterogeneity between the clients' data distributions, the model obtained through the use of FL algorithms may perform poorly on some client's data.
Boosting Spectral Clustering on Incomplete Data via Kernel Correction and Affinity Learning Fangchen Y u
These techniques calibrate an initial non-metric distance matrix estimated on incomplete data to a distance metric.
Supplementary File for ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Evaluation Capability for Large Vision-Language Models
We calculate the agreement of human judgment and our automatic evaluation (i.e., ConvBenchEval()) and find it reaches 81.83% (seeing Table 3 - 6 for detailed agreement of each turn of overall). It demonstrates the effectiveness of ConvBenchEval(), which uses ChatGPT. The agreement between ChatGPT and GPT4 is very high at 87.38%. It demonstrates that using different LLMs as judges slightly influences the evaluation results. ConvBenchEval() armed with ChatGPT can is reliable and low-cost. From the above tables, we also observe that though GPT4V is expensive and can capture images, its judgment performs worse than GPT4's judgment.
