Related papers: FARM: Field-Aware Resolution Model for Intelligent…

While multilingual pretrained language models (LMs) fine-tuned on a single language have shown substantial cross-lingual task transfer capabilities, there is still a wide performance gap in semantic parsing tasks when target language…

Attribute-controlled translation (ACT) is a subtask of machine translation that involves controlling stylistic or linguistic attributes (like formality and gender) of translation outputs. While ACT has garnered attention in recent years due…

Recent breakthroughs in generative simulation have harnessed Large Language Models (LLMs) to generate diverse robotic task curricula, yet these open-loop paradigms frequently produce linguistically coherent but physically infeasible goals,…

Recent pre-trained vision-language models (PT-VLMs) often face a Multi-Domain Task Incremental Learning (MTIL) scenario in practice, where several classes and domains of multi-modal tasks are incrementally arrived. Without access to…

Tables are pervasive in diverse documents, making table recognition (TR) a fundamental task in document analysis. Existing modular TR pipelines separately model table structure and content, leading to suboptimal integration and complex…

Large Language Models are being increasingly deployed as the decision-making core of autonomous agents capable of effecting change in external environments. Yet, in conversational benchmarks, which simulate real-world customer-centric issue…

The advancements in cloud-based Large Languages Models (LLMs) have revolutionized AI-assisted programming. However, their integration into certain local development environments like ones within the Apple software ecosystem (e.g., iOS apps,…

Response timing judgment is a critical component of interactive speech agents. Although there exists substantial prior work on turn modeling and voice wake-up, there is a lack of research on response timing judgments continuously aligned…

Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAct rely on sequential reasoning and execution, failing to…

Executing multiple tasks simultaneously in medical image analysis, including segmentation, classification, detection, and regression, often introduces significant challenges regarding model generalizability and the optimization of shared…

Retrieval-Augmented Generation (RAG) represents a transformative approach within natural language processing (NLP), combining neural information retrieval with generative language modeling to enhance both contextual accuracy and factual…

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding responses in external knowledge during inference. However, conventiona RAG systems under-perform on structured tabular data, largely due to coarse…

Many important tasks are defined in terms of object. To generalize across these tasks, a reinforcement learning (RL) agent needs to exploit the structure that the objects induce. Prior work has either hard-coded object-centric features,…

Responding to rising global food security needs, precision agriculture and deep learning-based plant disease diagnosis have become crucial. Yet, deploying high-precision models on edge devices is challenging. Most lightweight networks use…

Prompt learning has proven effective in adapting vision language models for downstream tasks. However, existing methods usually append learnable prompt tokens solely with the category names to obtain textual features, which fails to fully…

AgroLLM is an AI-powered chatbot designed to enhance knowledge-sharing and education in agriculture using Large Language Models (LLMs) and a Retrieval-Augmented Generation (RAG) framework. By using a comprehensive open-source agricultural…

Tool-augmented language models have demonstrated strong capabilities, but their reliance on live API access creates scalability and reliability challenges during training and deployment. We propose MTR, a simulation-first training framework…

The affine rank minimization (ARM) problem arises in many real-world applications. The goal is to recover a low-rank matrix from a small amount of noisy affine measurements. The original problem is NP-hard, and so directly solving the…

We introduce Reactive Action and Motion Planner (RAMP), which combines the strengths of sampling-based and reactive approaches for motion planning. In essence, RAMP is a hierarchical approach where a novel variant of a Model Predictive Path…

Trigger-action programming (TAP) is a popular end-user programming framework that can simplify the Internet of Things (IoT) automation with simple trigger-action rules. However, it also introduces new security and safety threats. A lot of…