7 accepted papers
Today's strongest video-language models (VLMs) remain proprietary, and the strongest open-weight models often rely on synthetic data from proprietary VLMs and do not disclose their training data or recipe. As a result, the open-source community lacks the foundations needed to improve on the state-of
Unconditional flow matching trains diffusion models to transport samples from a source distribution to a target distribution by enforcing that the flows between sample pairs are unique. However, in conditional settings (e.g., class-conditioned models), this uniqueness is no longer guaranteed--flows…
Recent model merging methods demonstrate that the parameters of fully-finetuned models specializing in distinct tasks can be combined into one model capable of solving all tasks without retraining. Yet, this success does not transfer well when merging LoRA finetuned models. We study this phenomenon…
Typical deep visual recognition models are capable of performing the one task they were trained on. In this paper, we tackle the extremely difficult problem of combining distinct models with different initializations, each solving a separate task, into one multi-task model without any additional tra…
In this paper we introduce Backforward Propagation, a method of completely eliminating Internal Covariate Shift (ICS). Unlike previous methods, which only indirectly reduce the impact of ICS while introducing other biases, we are able to have a surgical view at the effects ICS has on training neural…
In this paper we introduce Efficient Dynamic Batch Adaptation (EDBA), which improves on a previous method that works by adjusting the composition and the size of the current batch. Our improvements allow for Dynamic Batch Adaptation to feasibly scale up for bigger models and datasets, drastically im…
TACRED is one of the largest and most widely used sentence-level relation extraction datasets. Proposed models that are evaluated using this dataset consistently set new state-of-the-art performance. However, they still exhibit large error rates despite leveraging external knowledge and unsupervised…