Related papers: Exquisitor: Interactive Learning at Large
Sequential recommendation is to predict the next item of interest for a user, based on her/his interaction history with previous items. In conventional sequential recommenders, a common approach is to model item sequences using discrete…
The task of retrieving clips within videos based on a given natural language query requires cross-modal reasoning over multiple frames. Prior approaches such as sliding window classifiers are inefficient, while text-clip similarity driven…
As a fundamental and extensively studied task in computer vision, image segmentation aims to locate and identify different semantic concepts at the pixel level. Recently, inspired by In-Context Learning (ICL), several generalist…
Diffusion-based generative models' impressive ability to create convincing images has garnered global attention. However, their complex internal structures and operations often pose challenges for non-experts to grasp. We introduce…
We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale up model size or context length, MiroThinker explores…
Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of…
Information Pursuit (IP) is an explainable prediction algorithm that greedily selects a sequence of interpretable queries about the data in order of information gain, updating its posterior at each step based on observed query-answer pairs.…
We introduce iterative retrieval, a novel framework that empowers retrievers to make iterative decisions through policy optimization. Finding an optimal portfolio of retrieved items is a combinatorial optimization problem, generally…
Conversational interfaces are likely to become more efficient, intuitive and engaging way for human-computer interaction than today's text or touch-based interfaces. Current research efforts concerning conversational interfaces focus…
Interactive segmentation aims to segment the specified target on the image with positive and negative clicks from users. Interactive ambiguity is a crucial issue in this field, which refers to the possibility of multiple compliant outcomes…
The emergence of large-scale pre-trained models has heightened their application in various downstream tasks, yet deployment is a challenge in environments with limited computational resources. Knowledge distillation has emerged as a…
People often struggle to interpret data with extremely large or small values, or ranges spanning multiple orders of magnitude. While traditional approaches, such as log scales and multiscale visualizations, can help, we explore in this…
A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy,…
Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually…
At the core of Deep Research is knowledge mining, the task of extracting structured information from massive unstructured text in response to user instructions. Large language models (LLMs) excel at interpreting such instructions but are…
Existing machine reading comprehension (MRC) models do not scale effectively to real-world applications like web-level information retrieval and question answering (QA). We argue that this stems from the nature of MRC datasets: most of…
Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications. To capture context at both global and local granularity, we propose ASpanFormer, a Transformer-based detector-free matcher…
Prior research has shown how 'content preview tools' improve speed and accuracy of user relevance judgements across different information retrieval tasks. This paper describes a novel user interface tool, the Content Flow Bar, designed to…
Existing methods to fine-tune LLMs, like Adapter, Prefix-tuning, and LoRA, which introduce extra modules or additional input sequences to inject new skills or knowledge, may compromise the innate abilities of LLMs. In this paper, we propose…
Composed Image Retrieval (CIR) allows users to search for images by combining a reference image with a text prompt that describes desired modifications. While vision-language models like CLIP have popularized this task by embedding multiple…