Rooted in the explosion of deep learning over the past decade, this thesis spans from AlphaGo to ChatGPT to empirically examine the fundamental concepts needed to realize the vision of an artificial scientist: a machine with the capacity to autonomously generate original research and contribute to the expansion of human knowledge. The investigation begins with {\sc Olivaw}, an AlphaGo Zero-like agent that discovers Othello knowledge from scratch but is unable to communicate it. This realization leads to the development of the Explanatory Learning (EL) framework, a formalization of the problem faced by a scientist when trying to explain a new phenomenon to their peers. The effective EL prescriptions allow us to crack Zendo, a board game simulating the scientific endeavor. This success comes with a fundamental insight: an artificial scientist must develop its own interpretation of the language used to explain its findings. This perspective then leads us to see modern multimodal models as interpreters, and to devise a new way to build interpretable and cost-effective CLIP-like models: by coupling two unimodal models using little multimodal data and no further training. Finally, we discuss what ChatGPT and its siblings are still missing to become artificial scientists, and introduce Odeen, a benchmark about interpreting explanations that sees LLMs going no further than random chance while being instead fully solved by humans.

Spatial intelligence is important in Architecture, Construction, Science, Technology, Engineering, and Mathematics (STEM), and Medicine. Understanding three-dimensional (3D) spatial rotations can involve verbal descriptions and visual or interactive examples, illustrating how objects change orientation in 3D space. Recent studies show Artificial Intelligence (AI) with language and vision capabilities still face limitations in spatial reasoning. In this paper, we have studied generative AI's spatial capabilities of understanding rotations of objects utilizing its image and language processing features. We examined the spatial intelligence of the GPT-4 model with vision in understanding spatial rotation process with diagrams based on the Revised Purdue Spatial Visualization Test: Visualization of Rotations (Revised PSVT:R). Next, we incorporated a layer of coordinate system axes on Revised PSVT:R to study the variations in GPT-4's performance. We also examined GPT-4's understanding of 3D rotations in Augmented Reality (AR) scenes that visualize spatial rotations of an object in 3D space and observed increased accuracy of GPT-4's understanding of the rotations by adding supplementary textual information depicting the rotation process or mathematical representations of the rotation (e.g., matrices). The results indicate that while GPT-4 as a major current Generative AI model lacks the understanding of a spatial rotation process, it has the potential to understand the rotation process with additional information that can be provided by methods such as AR. By combining the potentials in spatial intelligence of AI with AR's interactive visualization abilities, we expect to offer enhanced guidance for students' spatial learning activities. Such spatial guidance can benefit understanding spatial transformations and additionally support processes like assembly, fabrication, and manufacturing.

Following human instructions to explore and search for a specified target in an unfamiliar environment is a crucial skill for mobile service robots. Most of the previous works on object goal navigation have typically focused on a single input modality as the target, which may lead to limited consideration of language descriptions containing detailed attributes and spatial relationships. To address this limitation, we propose VLN-Game, a novel zero-shot framework for visual target navigation that can process object names and descriptive language targets effectively. To be more precise, our approach constructs a 3D object-centric spatial map by integrating pre-trained visual-language features with a 3D reconstruction of the physical environment. Then, the framework identifies the most promising areas to explore in search of potential target candidates. A game-theoretic vision language model is employed to determine which target best matches the given language description. Experiments conducted on the Habitat-Matterport 3D (HM3D) dataset demonstrate that the proposed framework achieves state-of-the-art performance in both object goal navigation and language-based navigation tasks. Moreover, we show that VLN-Game can be easily deployed on real-world robots. The success of VLN-Game highlights the promising potential of using game-theoretic methods with compact vision-language models to advance decision-making capabilities in robotic systems. The supplementary video and code can be accessed via the following link: https://sites.google.com/view/vln-game.

The rapid evolution of Large Language Models (LLMs) has transformed them from basic conversational tools into sophisticated entities capable of complex reasoning and decision-making. These advancements have led to the development of specialized LLM-based agents designed for diverse tasks such as coding and web browsing. As these agents become more capable, the need for a robust framework that facilitates global communication and collaboration among them towards advanced objectives has become increasingly critical. Distributed Agents in a Worldwide Network (DAWN) addresses this need by offering a versatile framework that integrates LLM-based agents with traditional software systems, enabling the creation of agentic applications suited for a wide range of use cases. DAWN enables distributed agents worldwide to register and be easily discovered through Gateway Agents. Collaborations among these agents are coordinated by a Principal Agent equipped with reasoning strategies. DAWN offers three operational modes: No-LLM Mode for deterministic tasks, Copilot for augmented decision-making, and LLM Agent for autonomous operations. Additionally, DAWN ensures the safety and security of agent collaborations globally through a dedicated safety, security, and compliance layer, protecting the network against attackers and adhering to stringent security and compliance standards. These features make DAWN a robust network for deploying agent-based applications across various industries.

Recent studies reveal that Large Language Models (LLMs) are susceptible to backdoor attacks, where adversaries embed hidden triggers that manipulate model responses. Existing backdoor defense methods are primarily designed for vision or classification tasks, and are thus ineffective for text generation tasks, leaving LLMs vulnerable. We introduce Internal Consistency Regularization (CROW), a novel defense using consistency regularization finetuning to address layer-wise inconsistencies caused by backdoor triggers. CROW leverages the intuition that clean models exhibit smooth, consistent transitions in hidden representations across layers, whereas backdoored models show noticeable fluctuation when triggered. By enforcing internal consistency through adversarial perturbations and regularization, CROW neutralizes backdoor effects without requiring clean reference models or prior trigger knowledge, relying only on a small set of clean data. This makes it practical for deployment across various LLM architectures. Experimental results demonstrate that CROW consistently achieves a significant reductions in attack success rates across diverse backdoor strategies and tasks, including negative sentiment, targeted refusal, and code injection, on models such as Llama-2 (7B, 13B), CodeLlama (7B, 13B) and Mistral-7B, while preserving the model's generative capabilities.

Individuals have been increasingly interacting with online Large Language Models (LLMs), both in their work and personal lives. These interactions raise privacy issues as the LLMs are typically hosted by third-parties who can gather a variety of sensitive information about users and their companies. Text Sanitization techniques have been proposed in the literature and can be used to sanitize user prompts before sending them to the LLM. However, sanitization has an impact on the downstream task performed by the LLM, and often to such an extent that it leads to unacceptable results for the user. This is not just a minor annoyance, with clear monetary consequences as LLM services charge on a per use basis as well as great amount of computing resources wasted. We propose an architecture leveraging a Small Language Model (SLM) at the user-side to help estimate the impact of sanitization on a prompt before it is sent to the LLM, thus preventing resource losses. Our evaluation of this architecture revealed a significant problem with text sanitization based on Differential Privacy, on which we want to draw the attention of the community for further investigation.

This paper addresses the problem of task planning for robots that must comply with operational manuals in real-world settings. Task planning under these constraints is essential for enabling autonomous robot operation in domains that require adherence to domain-specific knowledge. Current methods for generating robot goals and plans rely on common sense knowledge encoded in large language models. However, these models lack grounding of robot plans to domain-specific knowledge and are not easily transferable between multiple sites or customers with different compliance needs. In this work, we present SayComply, which enables grounding robotic task planning with operational compliance using retrieval-based language models. We design a hierarchical database of operational, environment, and robot embodiment manuals and procedures to enable efficient retrieval of the relevant context under the limited context length of the LLMs. We then design a task planner using a tree-based retrieval augmented generation (RAG) technique to generate robot tasks that follow user instructions while simultaneously complying with the domain knowledge in the database. We demonstrate the benefits of our approach through simulations and hardware experiments in real-world scenarios that require precise context retrieval across various types of context, outperforming the standard RAG method. Our approach bridges the gap in deploying robots that consistently adhere to operational protocols, offering a scalable and edge-deployable solution for ensuring compliance across varied and complex real-world environments. Project website: saycomply.github.io.

Open domain question answering systems frequently rely on information retrieved from large collections of text (such as the Web) to answer questions. However, such collections of text often contain conflicting information, and indiscriminately depending on this information may result in untruthful and inaccurate answers. To understand the gravity of this problem, we collect a human-annotated dataset, Question Answering with Conflicting Contexts (QACC), and find that as much as 25% of unambiguous, open domain questions can lead to conflicting contexts when retrieved using Google Search. We evaluate and benchmark three powerful Large Language Models (LLMs) with our dataset QACC and demonstrate their limitations in effectively addressing questions with conflicting information. To explore how humans reason through conflicting contexts, we request our annotators to provide explanations for their selections of correct answers. We demonstrate that by finetuning LLMs to explain their answers, we can introduce richer information into their training that guide them through the process of reasoning with conflicting contexts.

Currently, deep learning-based instance segmentation for various applications (e.g., Agriculture) is predominantly performed using a labor-intensive process involving extensive field data collection using sophisticated sensors, followed by careful manual annotation of images, presenting significant logistical and financial challenges to researchers and organizations. The process also slows down the model development and training process. In this study, we presented a novel method for deep learning-based instance segmentation of apples in commercial orchards that eliminates the need for labor-intensive field data collection and manual annotation. Utilizing a Large Language Model (LLM), we synthetically generated orchard images and automatically annotated them using the Segment Anything Model (SAM) integrated with a YOLO11 base model. This method significantly reduces reliance on physical sensors and manual data processing, presenting a major advancement in "Agricultural AI". The synthetic, auto-annotated dataset was used to train the YOLO11 model for Apple instance segmentation, which was then validated on real orchard images. The results showed that the automatically generated annotations achieved a Dice Coefficient of 0.9513 and an IoU of 0.9303, validating the accuracy and overlap of the mask annotations. All YOLO11 configurations, trained solely on these synthetic datasets with automated annotations, accurately recognized and delineated apples, highlighting the method's efficacy. Specifically, the YOLO11m-seg configuration achieved a mask precision of 0.902 and a mask mAP@50 of 0.833 on test images collected from a commercial orchard. Additionally, the YOLO11l-seg configuration outperformed other models in validation on 40 LLM-generated images, achieving the highest mask precision and mAP@50 metrics. Keywords: YOLO, SAM, SAMv2, YOLO11, YOLOv11, Segment Anything, YOLO-SAM

Large Language Models (LLMs) are revolutionizing the landscape of Generative Artificial Intelligence (GenAI), with innovative LLM-backed solutions emerging rapidly. However, when applied to database technologies, specifically query generation for graph databases and Knowledge Graphs (KGs), LLMs still face significant challenges. While research on LLM-driven query generation for Structured Query Language (SQL) exists, similar systems for graph databases remain underdeveloped. This paper presents a comparative study addressing the challenge of generating Cypher queries a powerful language for interacting with graph databases using open-access LLMs. We rigorously evaluate several LLM agents (OpenAI ChatGPT 4o, Claude Sonnet 3.5, Google Gemini Pro 1.5, and a locally deployed Llama 3.1 8B) using a designed few-shot learning prompt and Retrieval Augmented Generation (RAG) backed by Chain-of-Thoughts (CoT) reasoning. Our empirical analysis of query generation accuracy reveals that Claude Sonnet 3.5 outperforms its counterparts in this specific domain. Further, we highlight promising future research directions to address the identified limitations and advance LLM-driven query generation for graph databases.