PyTorchKR Papers

최신 논문

총 2,097편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2402.12234공식 코드 · Papers with Code

Task-Oriented Dialogue with In-Context Learning

We describe a system for building task-oriented dialogue systems combining the in-context learning abilities of large language models (LLMs) with the deterministic execution of business logic. LLMs are used to translate between the surface form of the conversation and a domain-specific language (DSL) which is used to progress the business logic. We compare our approach to the intent-based NLU approach predominantly used in industry today. Our experiments show that developing chatbots with our system requires significantly less effort than established approaches, that these chatbots can successfully navigate complex dialogues which are extremely challenging for NLU-based systems, and that our system has desirable properties for scaling task-oriented dialogue systems to a large number of tasks. We make our implementation available for use and further study.

arXiv:2402.10670공식 코드 · Papers with Code

OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models

Object navigation (ObjectNav) requires an agent to navigate through unseen environments to find queried objects. Many previous methods attempted to solve this task by relying on supervised or reinforcement learning, where they are trained on limited household datasets with close-set objects. However, two key challenges are unsolved: understanding free-form natural language instructions that demand open-set objects, and generalizing to new environments in a zero-shot manner. Aiming to solve the two challenges, in this paper, we propose OpenFMNav, an Open-set Foundation Model based framework for zero-shot object Navigation. We first unleash the reasoning abilities of large language models (LLMs) to extract proposed objects from natural language instructions that meet the user's demand. We then leverage the generalizability of large vision language models (VLMs) to actively discover and detect candidate objects from the scene, building a Versatile Semantic Score Map (VSSM). Then, by conducting common sense reasoning on VSSM, our method can perform effective language-guided exploration and exploitation of the scene and finally reach the goal. By leveraging the reasoning and generalizing abilities of foundation models, our method can understand free-form human instructions and perform effective open-set zero-shot navigation in diverse environments. Extensive experiments on the HM3D ObjectNav benchmark show that our method surpasses all the strong baselines on all metrics, proving our method's effectiveness. Furthermore, we perform real robot demonstrations to validate our method's open-set-ness and generalizability to real-world environments.

arXiv:2402.10290

Experiments with Encoding Structured Data for Neural Networks

The project's aim is to create an AI agent capable of selecting good actions in a game-playing domain called Battlespace. Sequential domains like Battlespace are important testbeds for planning problems, as such, the Department of Defense uses such domains for wargaming exercises. The agents we developed combine Monte Carlo Tree Search (MCTS) and Deep Q-Network (DQN) techniques in an effort to navigate the game environment, avoid obstacles, interact with adversaries, and capture the flag. This paper will focus on the encoding techniques we explored to present complex structured data stored in a Python class, a necessary precursor to an agent.

arXiv:2402.10236공식 코드 · Papers with Code

Discovering Sensorimotor Agency in Cellular Automata using Diversity Search

The research field of Artificial Life studies how life-like phenomena such as autopoiesis, agency, or self-regulation can self-organize in computer simulations. In cellular automata (CA), a key open-question has been whether it it is possible to find environment rules that self-organize robust "individuals" from an initial state with no prior existence of things like "bodies", "brain", "perception" or "action". In this paper, we leverage recent advances in machine learning, combining algorithms for diversity search, curriculum learning and gradient descent, to automate the search of such "individuals", i.e. localized structures that move around with the ability to react in a coherent manner to external obstacles and maintain their integrity, hence primitive forms of sensorimotor agency. We show that this approach enables to find systematically environmental conditions in CA leading to self-organization of such basic forms of agency. Through multiple experiments, we show that the discovered agents have surprisingly robust capabilities to move, maintain their body integrity and navigate among various obstacles. They also show strong generalization abilities, with robustness to changes of scale, random updates or perturbations from the environment not seen during training. We discuss how this approach opens new perspectives in AI and synthetic bioengineering.

arXiv:2402.10077

Towards a large-scale fused and labeled dataset of human pose while interacting with robots in shared urban areas

Over the last decade, Autonomous Delivery Robots (ADRs) have transformed conventional delivery methods, responding to the growing e-commerce demand. However, the readiness of ADRs to navigate safely among pedestrians in shared urban areas remains an open question. We contend that there are crucial research gaps in understanding their interactions with pedestrians in such environments. Human Pose Estimation is a vital stepping stone for various downstream applications, including pose prediction and socially aware robot path-planning. Yet, the absence of an enriched and pose-labeled dataset capturing human-robot interactions in shared urban areas hinders this objective. In this paper, we bridge this gap by repurposing, fusing, and labeling two datasets, MOT17 and NCLT, focused on pedestrian tracking and Simultaneous Localization and Mapping (SLAM), respectively. The resulting unique dataset represents thousands of real-world indoor and outdoor human-robot interaction scenarios. Leveraging YOLOv7, we obtained human pose visual and numeric outputs and provided ground truth poses using manual annotation. To overcome the distance bias present in the traditional MPJPE metric, this study introduces a novel human pose estimation error metric called Mean Scaled Joint Error (MSJE) by incorporating bounding box dimensions into it. Findings demonstrate that YOLOv7 effectively estimates human pose in both datasets. However, it exhibits weaker performance in specific scenarios, like indoor, crowded scenes with a focused light source, where both MPJPE and MSJE are recorded as 10.89 and 25.3, respectively. In contrast, YOLOv7 performs better in single-person estimation (NCLT seq 2) and outdoor scenarios (MOT17 seq1), achieving MSJE values of 5.29 and 3.38, respectively.

arXiv:2402.08787

Rethinking Machine Unlearning for Large Language Models

We explore machine unlearning (MU) in the domain of large language models (LLMs), referred to as LLM unlearning. This initiative aims to eliminate undesirable data influence (e.g., sensitive or illegal information) and the associated model capabilities, while maintaining the integrity of essential knowledge generation and not affecting causally unrelated information. We envision LLM unlearning becoming a pivotal element in the life-cycle management of LLMs, potentially standing as an essential foundation for developing generative AI that is not only safe, secure, and trustworthy, but also resource-efficient without the need of full retraining. We navigate the unlearning landscape in LLMs from conceptual formulation, methodologies, metrics, and applications. In particular, we highlight the often-overlooked aspects of existing LLM unlearning research, e.g., unlearning scope, data-model interaction, and multifaceted efficacy assessment. We also draw connections between LLM unlearning and related areas such as model editing, influence functions, model explanation, adversarial training, and reinforcement learning. Furthermore, we outline an effective assessment framework for LLM unlearning and explore its applications in copyright and privacy safeguards and sociotechnical harm reduction.

arXiv:2402.07939공식 코드 · Papers with Code

UFO: A UI-Focused Agent for Windows OS Interaction

We introduce UFO, an innovative UI-Focused agent to fulfill user requests tailored to applications on Windows OS, harnessing the capabilities of GPT-Vision. UFO employs a dual-agent framework to meticulously observe and analyze the graphical user interface (GUI) and control information of Windows applications. This enables the agent to seamlessly navigate and operate within individual applications and across them to fulfill user requests, even when spanning multiple applications. The framework incorporates a control interaction module, facilitating action grounding without human intervention and enabling fully automated execution. Consequently, UFO transforms arduous and time-consuming processes into simple tasks achievable solely through natural language commands. We conducted testing of UFO across 9 popular Windows applications, encompassing a variety of scenarios reflective of users' daily usage. The results, derived from both quantitative metrics and real-case studies, underscore the superior effectiveness of UFO in fulfilling user requests. To the best of our knowledge, UFO stands as the first UI agent specifically tailored for task completion within the Windows OS environment. The open-source code for UFO is available on https://github.com/microsoft/UFO.

arXiv:2402.08030

Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking

Large Language Model (LLM) assistants, such as ChatGPT, have emerged as potential alternatives to search methods for helping users navigate complex, feature-rich software. LLMs use vast training data from domain-specific texts, software manuals, and code repositories to mimic human-like interactions, offering tailored assistance, including step-by-step instructions. In this work, we investigated LLM-generated software guidance through a within-subject experiment with 16 participants and follow-up interviews. We compared a baseline LLM assistant with an LLM optimized for particular software contexts, SoftAIBot, which also offered guidelines for constructing appropriate prompts. We assessed task completion, perceived accuracy, relevance, and trust. Surprisingly, although SoftAIBot outperformed the baseline LLM, our results revealed no significant difference in LLM usage and user perceptions with or without prompt guidelines and the integration of domain context. Most users struggled to understand how the prompt's text related to the LLM's responses and often followed the LLM's suggestions verbatim, even if they were incorrect. This resulted in difficulties when using the LLM's advice for software tasks, leading to low task completion rates. Our detailed analysis also revealed that users remained unaware of inaccuracies in the LLM's responses, indicating a gap between their lack of software expertise and their ability to evaluate the LLM's assistance. With the growing push for designing domain-specific LLM assistants, we emphasize the importance of incorporating explainable, context-aware cues into LLMs to help users understand prompt-based interactions, identify biases, and maximize the utility of LLM assistants.

arXiv:2402.07214

Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification

In legal decisions, split votes (SV) occur when judges cannot reach a unanimous decision, posing a difficulty for lawyers who must navigate diverse legal arguments and opinions. In high-stakes domains, understanding the alignment of perceived difficulty between humans and AI systems is crucial to build trust. However, existing NLP calibration methods focus on a classifier's awareness of predictive performance, measured against the human majority class, overlooking inherent human label variation (HLV). This paper explores split votes as naturally observable human disagreement and value pluralism. We collect judges' vote distributions from the European Court of Human Rights (ECHR), and present SV-ECHR, a case outcome classification (COC) dataset with SV information. We build a taxonomy of disagreement with SV-specific subcategories. We further assess the alignment of perceived difficulty between models and humans, as well as confidence- and human-calibration of COC models. We observe limited alignment with the judge vote distribution. To our knowledge, this is the first systematic exploration of calibration to human judgements in legal NLP. Our study underscores the necessity for further research on measuring and enhancing model calibration considering HLV in legal decision tasks.

arXiv:2402.07429

Particle Filter SLAM for Vehicle Localization

Simultaneous Localization and Mapping (SLAM) presents a formidable challenge in robotics, involving the dynamic construction of a map while concurrently determining the precise location of the robotic agent within an unfamiliar environment. This intricate task is further compounded by the inherent "chicken-and-egg" dilemma, where accurate mapping relies on a dependable estimation of the robot's location, and vice versa. Moreover, the computational intensity of SLAM adds an additional layer of complexity, making it a crucial yet demanding topic in the field. In our research, we address the challenges of SLAM by adopting the Particle Filter SLAM method. Our approach leverages encoded data and fiber optic gyro (FOG) information to enable precise estimation of vehicle motion, while lidar technology contributes to environmental perception by providing detailed insights into surrounding obstacles. The integration of these data streams culminates in the establishment of a Particle Filter SLAM framework, representing a key endeavor in this paper to effectively navigate and overcome the complexities associated with simultaneous localization and mapping in robotic systems.

arXiv:2402.07320

Towards Explainable, Safe Autonomous Driving with Language Embeddings for Novelty Identification and Active Learning: Framework and Experimental Analysis with Real-World Data Sets

This research explores the integration of language embeddings for active learning in autonomous driving datasets, with a focus on novelty detection. Novelty arises from unexpected scenarios that autonomous vehicles struggle to navigate, necessitating higher-level reasoning abilities. Our proposed method employs language-based representations to identify novel scenes, emphasizing the dual purpose of safety takeover responses and active learning. The research presents a clustering experiment using Contrastive Language-Image Pretrained (CLIP) embeddings to organize datasets and detect novelties. We find that the proposed algorithm effectively isolates novel scenes from a collection of subsets derived from two real-world driving datasets, one vehicle-mounted and one infrastructure-mounted. From the generated clusters, we further present methods for generating textual explanations of elements which differentiate scenes classified as novel from other scenes in the data pool, presenting qualitative examples from the clustered results. Our results demonstrate the effectiveness of language-driven embeddings in identifying novel elements and generating explanations of data, and we further discuss potential applications in safe takeovers, data curation, and multi-task active learning.

arXiv:2402.07282

How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?

In day-to-day communication, people often approximate the truth - for example, rounding the time or omitting details - in order to be maximally helpful to the listener. How do large language models (LLMs) handle such nuanced trade-offs? To address this question, we use psychological models and experiments designed to characterize human behavior to analyze LLMs. We test a range of LLMs and explore how optimization for human preferences or inference-time reasoning affects these trade-offs. We find that reinforcement learning from human feedback improves both honesty and helpfulness, while chain-of-thought prompting skews LLMs towards helpfulness over honesty. Finally, GPT-4 Turbo demonstrates human-like response patterns including sensitivity to the conversational framing and listener's decision context. Our findings reveal the conversational values internalized by LLMs and suggest that even these abstract values can, to a degree, be steered by zero-shot prompting.

논문 ID: document/1004299

Multidimensional Particle Filter for Long-Term Visual Teach and Repeat in Changing Environments

When a mobile robot is asked to navigate intelligently in an environment, it needs to estimate its own and the environment's state. One of the popular methods for robot state and position estimation is particle filtering (PF). Visual Teach and Repeat (VT&R) is a type of navigation that uses a camera to navigate the robot along the previously traversed path. Particle filters are usually used in VT&R to fuse data from odometry and camera to estimate the distance traveled along the path. However, in VT&R, there are other valuable states that the robot can benefit from, especially when moving through changing environments. We propose a multidimensional particle filter to estimate the robot state in VT&R navigation. Apart from the traveled distance, our particle filter estimates lateral and heading deviation from the taught path as well as the current appearance of the environment. This appearance is estimated using maps created across various environmental conditions recorded during the previous traversals. The joint state estimation is based on contrastive neural network architecture, allowing self-supervised learning. This architecture can process multiple images in parallel, alleviating the potential overhead caused by computing the particle filter over the maps simultaneously. We conducted experiments to show that the joint robot/environment state estimation improves navigation accuracy and robustness in a continual mapping setup. Unlike the other frameworks, which treat the robot position and environment appearance separately, our PF represents them as one multidimensional state, resulting in a more general uncertainty model for VT&R.

arXiv:2402.05825

Predicting concentration changes via discrete sampling

To successfully navigate chemical gradients, microorganisms need to predict how the ligand concentration changes in space. Due to their limited size, they do not take a spatial derivative over their body length but rather a temporal derivative, comparing the current signal with that in the recent past, over the so-called adaptation time. This strategy is pervasive in biology, but it remains unclear what determines the accuracy of such measurements. Using a generalized version of the previously established sampling framework, we investigate how resource limitations and the statistics of the input signal set the optimal design of a well-characterized network that measures temporal concentration changes: the Escherichia coli chemotaxis network. Our results show how an optimal adaptation time arises from the trade-off between the sampling error, caused by the stochastic nature of the network, and the dynamical error, caused by uninformative fluctuations in the input. A larger resource availability reduces the sampling error, which allows for a smaller adaptation time, thereby simultaneously decreasing the dynamical error. Similarly, we find that the optimal adaptation time scales inversely with the gradient steepness, because steeper gradients lift the signal above the noise and reduce the sampling error. These findings shed light on the principles that govern the optimal design of the E. coli chemotaxis network specifically, and any system measuring temporal changes more broadly.

arXiv:2402.05662

Stochastic COLREGs Evaluation for Safe Navigation under Uncertainty

The encounter situation between marine vessels determines how they should navigate to obey COLREGs, but time-varying and stochastic uncertainty in estimation of angles of encounter, and of closest point of approach, easily give rise to different assessment of situation at two approaching vessels. This may lead to high-risk conditions and could cause collision. This article considers decision making under uncertainty and suggests a novel method for probabilistic interpretation of vessel encounters that is explainable and provides a measure of uncertainty in the evaluation. The method is equally useful for decision support on a manned bridge as on Marine Autonomous Surface Ships (MASS) where it provides input for automated navigation. The method makes formal safety assessment and validation feasible. We obtain a resilient algorithm for machine interpretation of COLREGs under uncertainty and show its efficacy by simulations.

arXiv:2402.05379

Trade-Offs of Diagonal Fisher Information Matrix Estimators

The Fisher information matrix can be used to characterize the local geometry of the parameter space of neural networks. It elucidates insightful theories and useful tools to understand and optimize neural networks. Given its high computational cost, practitioners often use random estimators and evaluate only the diagonal entries. We examine two popular estimators whose accuracy and sample complexity depend on their associated variances. We derive bounds of the variances and instantiate them in neural networks for regression and classification. We navigate trade-offs for both estimators based on analytical and numerical studies. We find that the variance quantities depend on the non-linearity wrt different parameter groups and should not be neglected when estimating the Fisher information.

arXiv:2402.05290

Do Transformer World Models Give Better Policy Gradients?

A natural approach for reinforcement learning is to predict future rewards by unrolling a neural network world model, and to backpropagate through the resulting computational graph to learn a policy. However, this method often becomes impractical for long horizons since typical world models induce hard-to-optimize loss landscapes. Transformers are known to efficiently propagate gradients over long horizons: could they be the solution to this problem? Surprisingly, we show that commonly-used transformer world models produce circuitous gradient paths, which can be detrimental to long-range policy gradients. To tackle this challenge, we propose a class of world models called Actions World Models (AWMs), designed to provide more direct routes for gradient propagation. We integrate such AWMs into a policy gradient framework that underscores the relationship between network architectures and the policy gradient updates they inherently represent. We demonstrate that AWMs can generate optimization landscapes that are easier to navigate even when compared to those from the simulator itself. This property allows transformer AWMs to produce better policies than competitive baselines in realistic long-horizon tasks.

arXiv:2402.05090공식 코드 · Papers with Code

Language-Based Augmentation to Address Shortcut Learning in Object Goal Navigation

Deep Reinforcement Learning (DRL) has shown great potential in enabling robots to find certain objects (e.g., `find a fridge') in environments like homes or schools. This task is known as Object-Goal Navigation (ObjectNav). DRL methods are predominantly trained and evaluated using environment simulators. Although DRL has shown impressive results, the simulators may be biased or limited. This creates a risk of shortcut learning, i.e., learning a policy tailored to specific visual details of training environments. We aim to deepen our understanding of shortcut learning in ObjectNav, its implications and propose a solution. We design an experiment for inserting a shortcut bias in the appearance of training environments. As a proof-of-concept, we associate room types to specific wall colors (e.g., bedrooms with green walls), and observe poor generalization of a state-of-the-art (SOTA) ObjectNav method to environments where this is not the case (e.g., bedrooms with blue walls). We find that shortcut learning is the root cause: the agent learns to navigate to target objects, by simply searching for the associated wall color of the target object's room. To solve this, we propose Language-Based (L-B) augmentation. Our key insight is that we can leverage the multimodal feature space of a Vision-Language Model (VLM) to augment visual representations directly at the feature-level, requiring no changes to the simulator, and only an addition of one layer to the model. Where the SOTA ObjectNav method's success rate drops 69%, our proposal has only a drop of 23%.

arXiv:2402.04382

Counterfactual Generation with Answer Set Programming

Machine learning models that automate decision-making are increasingly being used in consequential areas such as loan approvals, pretrial bail approval, hiring, and many more. Unfortunately, most of these models are black-boxes, i.e., they are unable to reveal how they reach these prediction decisions. A need for transparency demands justification for such predictions. An affected individual might also desire explanations to understand why a decision was made. Ethical and legal considerations may further require informing the individual of changes in the input attribute that could be made to produce a desirable outcome. This paper focuses on the latter problem of automatically generating counterfactual explanations. We propose a framework Counterfactual Generation with s(CASP) (CFGS) that utilizes answer set programming (ASP) and the s(CASP) goal-directed ASP system to automatically generate counterfactual explanations from rules generated by rule-based machine learning (RBML) algorithms. In our framework, we show how counterfactual explanations are computed and justified by imagining worlds where some or all factual assumptions are altered/changed. More importantly, we show how we can navigate between these worlds, namely, go from our original world/scenario where we obtain an undesired outcome to the imagined world/scenario where we obtain a desired/favourable outcome.

arXiv:2402.03561

VLN-Video: Utilizing Driving Videos for Outdoor Vision-and-Language Navigation

Outdoor Vision-and-Language Navigation (VLN) requires an agent to navigate through realistic 3D outdoor environments based on natural language instructions. The performance of existing VLN methods is limited by insufficient diversity in navigation environments and limited training data. To address these issues, we propose VLN-Video, which utilizes the diverse outdoor environments present in driving videos in multiple cities in the U.S. augmented with automatically generated navigation instructions and actions to improve outdoor VLN performance. VLN-Video combines the best of intuitive classical approaches and modern deep learning techniques, using template infilling to generate grounded navigation instructions, combined with an image rotation similarity-based navigation action predictor to obtain VLN style data from driving videos for pretraining deep learning VLN models. We pre-train the model on the Touchdown dataset and our video-augmented dataset created from driving videos with three proxy tasks: Masked Language Modeling, Instruction and Trajectory Matching, and Next Action Prediction, so as to learn temporally-aware and visually-aligned instruction representations. The learned instruction representation is adapted to the state-of-the-art navigator when fine-tuning on the Touchdown dataset. Empirical results demonstrate that VLN-Video significantly outperforms previous state-of-the-art models by 2.1% in task completion rate, achieving a new state-of-the-art on the Touchdown dataset.