Related papers: Retrieval Augmented Classification for Long-Tail V…
Retrieval-augmented models couple parametric predictors with non-parametric memories, but their use in streaming supervised learning with concept drift is not well understood. We study online classification in non-stationary environments…
Modern paradigms for robot imitation train expressive policy architectures on large amounts of human demonstration data. Yet performance on contact-rich, deformable-object, and long-horizon tasks plateau far below perfect execution, even…
Object-aware reasoning in vision-language tasks poses significant challenges for current models, particularly in handling unseen objects, reducing hallucinations, and capturing fine-grained relationships in complex visual scenes. To address…
Accurate visual re-localization is very critical to many artificial intelligence applications, such as augmented reality, virtual reality, robotics and autonomous driving. To accomplish this task, we propose an integrated visual…
We introduce the "Incremental Implicitly-Refined Classi-fication (IIRC)" setup, an extension to the class incremental learning setup where the incoming batches of classes have two granularity levels. i.e., each sample could have a…
Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn directly from image observations. However, these high-dimensional observation spaces present a number of challenges in practice, since the policy must…
It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes correctly. In the literature, several existing…
Retrieval-augmented generation (RAG) enhances large language models by incorporating context retrieved from external knowledge sources. While the effectiveness of the retrieval module is typically evaluated with relevance-based ranking…
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance large language models (LLMs) by conditioning generation on external evidence retrieved at inference time. While RAG addresses critical limitations of…
Long-tail distributions in driving datasets pose a fundamental challenge for 3D perception, as rare classes exhibit substantial intra-class diversity yet available samples cover this variation space only sparsely. Existing instance…
The efficient processing of long context poses a serious challenge for large language models (LLMs). Recently, retrieval-augmented generation (RAG) has emerged as a promising strategy for this problem, as it enables LLMs to make selective…
Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to extend their existing knowledge by dynamically incorporating external information. However, practical deployment is fundamentally constrained by the LLM's finite…
Composed Image Retrieval (CIR) aims to retrieve target images based on a hybrid query comprising a reference image and a modification text. Early dual-tower Vision-Language Models (VLMs) struggle with cross-modality compositional reasoning…
Long-tailed classification is challenging due to its heavy imbalance in class probabilities. While existing methods often focus on overall accuracy or accuracy for tail classes, they overlook a critical aspect: certain types of errors can…
Product recommendation is the task of recovering the closest items to a given query within a large product corpora. Generally, one can determine if top-ranked products are related to the query by applying a similarity threshold; exceeding…
The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs) still face heavy computational costs when extended from images to videos due to high frame rates and…
In vision domain, large-scale natural datasets typically exhibit long-tailed distribution which has large class imbalance between head and tail classes. This distribution poses difficulty in learning good representations for tail classes.…
In the real world, data tends to follow long-tailed distributions w.r.t. class or attribution, motivating the challenging Long-Tailed Recognition (LTR) problem. In this paper, we revisit recent LTR methods with promising Vision Transformers…
Retrieval-Augmented Generation (RAG) couples a retriever with a large language model (LLM) to ground generated responses in external evidence. While this framework enhances factuality and domain adaptability, it faces a key bottleneck:…
Traditional Retrieval-Augmented Generation (RAG) methods are limited by their reliance on a fixed number of retrieved documents, often resulting in incomplete or noisy information that undermines task performance. Although recent adaptive…