Related papers: ProCompNav: Proactive Instance Navigation with Com…
Intent detection is a key component of modern goal-oriented dialog systems that accomplish a user task by predicting the intent of users' text input. There are three primary challenges in designing robust and accurate intent detection…
In today's digitally driven world, dialogue systems play a pivotal role in enhancing user interactions, from customer service to virtual assistants. In these dialogues, it is important to identify user's goals automatically to resolve their…
Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness…
Reasoning-oriented Large Language Models (LLMs) have achieved remarkable progress with Chain-of-Thought (CoT) prompting, yet they remain fundamentally limited by a \emph{blind self-thinking} paradigm: performing extensive internal reasoning…
Modern supervised semantic segmentation methods are usually finetuned based on the supervised or self-supervised models pre-trained on ImageNet. Recent work shows that transferring the knowledge from CLIP to semantic segmentation via prompt…
Filtered ANN search is an increasingly important problem in vector retrieval, yet systems face a difficult trade-off due to the execution order: Pre-filtering (filtering first, then ANN over the passing subset) requires expensive…
In the last years, the research interest in visual navigation towards objects in indoor environments has grown significantly. This growth can be attributed to the recent availability of large navigation datasets in photo-realistic simulated…
Fine-tuning the pre-trained model with active learning holds promise for reducing annotation costs. However, this combination introduces significant computational costs, particularly with the growing scale of pre-trained models. Recent…
Large language model (LLM)-based agents have demonstrated remarkable capabilities in addressing complex tasks, thereby enabling more advanced information retrieval and supporting deeper, more sophisticated human information-seeking…
Open intent classification, which aims to correctly classify the known intents into their corresponding classes while identifying the new unknown (open) intents, is an essential but challenging task in dialogue systems. In this paper, we…
Route Recommendation (RR) is a core task in route planning within online navigation applications, aiming to recommend the optimal route among candidate routes to users. Industrially, RR adopts the two-stage recall-and-rank framework instead…
Understanding and classifying user personas is critical for delivering effective personalization. While persona information offers valuable insights, its full potential is realized only when contextualized, linking user characteristics with…
Prompt learning is a new paradigm for utilizing pre-trained language models and has achieved great success in many tasks. To adopt prompt learning in the NER task, two kinds of methods have been explored from a pair of symmetric…
Resolving ambiguities through interaction is a hallmark of natural language, and modeling this behavior is a core challenge in crafting AI assistants. In this work, we study such behavior in LMs by proposing a task-agnostic framework for…
Composed Image Retrieval (CIR) is a challenging image retrieval paradigm that enables to retrieve target images based on multimodal queries consisting of reference images and modification texts. Although substantial progress has been made…
Enterprise conversational AI systems are becoming increasingly popular to assist users in completing daily tasks such as those in marketing and customer management. However, new users often struggle to ask effective questions, especially in…
Pretrained visual-language models have extensive world knowledge and are widely used in visual and language navigation (VLN). However, they are not sensitive to indoor scenarios for VLN tasks. Another challenge for VLN is how the agent…
Graphical user interface (GUI) agents have shown promise in automating mobile tasks but still struggle with input redundancy and decision ambiguity. In this paper, we present \textbf{RecAgent}, an uncertainty-aware agent that addresses…
Visual navigation is essential for robotics and embodied AI. However, existing foundation models, particularly those with transformer decoders, suffer from high computational overhead and lack interpretability, limiting their deployment in…
Recommender systems help users deal with information overload by providing tailored item suggestions to them. The recommendation of news is often considered to be challenging, since the relevance of an article for a user can depend on a…