Related papers: Hot-Refresh Model Upgrades with Regression-Allevia…
In past years model-agnostic meta-learning (MAML) has been one of the most promising approaches in meta-learning. It can be applied to different kinds of problems, e.g., reinforcement learning, but also shows good results on few-shot…
Reinforcement learning post-training has substantially improved the reasoning accuracy of vision-language models, yet the resulting policies remain poorly calibrated. Terminal correctness rewards provide no gradient that penalizes confident…
Since the launch of ChatGPT at the end of 2022, generative dialogue models represented by ChatGPT have quickly become essential tools in daily life. As user expectations increase, enhancing the capability of generative dialogue models to…
Recently, Retrieval Augmented Generation (RAG) has shifted focus to multi-retrieval approaches to tackle complex tasks such as multi-hop question answering. However, these systems struggle to decide when to stop searching once enough…
Advanced persistent threats (APTs) pose significant challenges for organizations, leading to data breaches, financial losses, and reputational damage. Existing provenance-based approaches for APT detection often struggle with high false…
To address the sequential changes of images including poses, in this paper we propose a recurrent regression neural network(RRNN) framework to unify two classic tasks of cross-pose face recognition on still images and video-based face…
Machine learning models are updated as new data is acquired or new architectures are developed. These updates usually increase model performance, but may introduce backward compatibility errors, where individual users or groups of users see…
Retrieval-augmented generation (RAG) has emerged as a popular solution to mitigate the hallucination issues of large language models. However, existing studies on RAG seldom address the issue of predictive uncertainty, i.e., how likely it…
Test-Time Adaptation (TTA) aims to enhance the generalization of deep learning models when faced with test data that exhibits distribution shifts from the training data. In this context, only a pre-trained model and unlabeled test data are…
Contrastive Language-Image Pre-training (CLIP) stands as one of the most effective and scalable methods for training transferable vision models using paired image and text data. CLIP models are trained using contrastive loss, which…
Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and…
With the shift towards on-device deep learning, ensuring a consistent behavior of an AI service across diverse compute platforms becomes tremendously important. Our work tackles the emergent problem of reducing predictive inconsistencies…
Survival analysis is complicated by censored data, high-dimensional features, and non-linear interactions. Classical models offer interpretability and superior calibration but are restricted to linear or predefined functional forms, while…
The discriminability of feature representation is the key to open-set face recognition. Previous methods rely on the learnable weights of the classification layer that represent the identities. However, the evaluation process learns no…
Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable…
Multilingual vision-language models have made significant strides in image captioning, yet they still lag behind their English counterparts due to limited multilingual training data and costly large-scale model parameterization.…
We present our submission to the LiveRAG Challenge 2025, which evaluates retrieval-augmented generation (RAG) systems on dynamic test sets using the FineWeb-10BT corpus. Our final hybrid approach combines sparse (BM25) and dense (E5)…
Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results. To overcome these challenges, the current research proposes an…
Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…
Incorporating specific knowledge into large language models via retrieval-augmented generation (RAG) is a widespread technique that fuels many of today's industry AI applications. A fundamental problem is to assess if the context retrieved…