AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions

Data science tasks involving tabular data present complex challenges that require sophisticated problem-solving approaches. We propose AutoKaggle, a powerful and user-centric framework that assists data scientists in completing daily data pipelines through a collaborative multi-agent system. AutoKaggle implements an iterative development process that combines code execution, debugging, and comprehensive unit testing to ensure code correctness and logic consistency. The framework offers highly customizable workflows, allowing users to intervene at each phase, thus integrating automated intelligence with human expertise. Our universal data science toolkit, comprising validated functions for data cleaning, feature engineering, and modeling, forms the foundation of this solution, enhancing productivity by streamlining common tasks. We selected 8 Kaggle competitions to simulate data processing workflows in real-world application scenarios. Evaluation results demonstrate that AutoKaggle achieves a validation submission rate of 0.85 and a comprehensive score of 0.82 in typical data science pipelines, fully proving its effectiveness and practicality in handling complex data science tasks.

Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction

Automated red teaming is an effective method for identifying misaligned behaviors in large language models (LLMs). Existing approaches, however, often focus primarily on improving attack success rates while overlooking the need for comprehensive test case coverage. Additionally, most of these methods are limited to single-turn red teaming, failing to capture the multi-turn dynamics of real-world human-machine interactions. To overcome these limitations, we propose HARM (Holistic Automated Red teaMing), which scales up the diversity of test cases using a top-down approach based on an extensible, fine-grained risk taxonomy. Our method also leverages a novel fine-tuning strategy and reinforcement learning techniques to facilitate multi-turn adversarial probing in a human-like manner. Experimental results demonstrate that our framework enables a more systematic understanding of model vulnerabilities and offers more targeted guidance for the alignment process.

Fed-MUnet: Multi-modal Federated Unet for Brain Tumor Segmentation

Deep learning-based techniques have been widely utilized for brain tumor segmentation using both single and multi-modal Magnetic Resonance Imaging (MRI) images. Most current studies focus on centralized training due to the intrinsic challenge of data sharing across clinics. To mitigate privacy concerns, researchers have introduced Federated Learning (FL) methods to brain tumor segmentation tasks. However, currently such methods are focusing on single modal MRI, with limited study on multi-modal MRI. The challenges include complex structure, large-scale parameters, and overfitting issues of the FL based methods using multi-modal MRI. To address the above challenges, we propose a novel multi-modal FL framework for brain tumor segmentation (Fed-MUnet) that is suitable for FL training. We evaluate our approach with the BraTS2022 datasets, which are publicly available. The experimental results demonstrate that our framework achieves FL nature of distributed learning and privacy preserving. For the enhancing tumor, tumor core and whole tumor, the mean of five major metrics were 87.5%, 90.6% and 92.2%, respectively, which were higher than SOTA methods while preserving privacy. In terms of parameters count, quantity of floating-point operations (FLOPs) and inference, Fed-MUnet is Pareto optimal compared with the state-of-the-art segmentation backbone while achieves higher performance and tackles privacy issue. Our codes are open-sourced at https://github.com/Arnold-Jun/Fed-MUnet.

Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests

Indirect User Requests (IURs), such as "It's cold in here" instead of "Could you please increase the temperature?" are common in human-human task-oriented dialogue and require world knowledge and pragmatic reasoning from the listener. While large language models (LLMs) can handle these requests effectively, smaller models deployed on virtual assistants often struggle due to resource constraints. Moreover, existing task-oriented dialogue benchmarks lack sufficient examples of complex discourse phenomena such as indirectness. To address this, we propose a set of linguistic criteria along with an LLM-based pipeline for generating realistic IURs to test natural language understanding (NLU) and dialogue state tracking (DST) models before deployment in a new domain. We also release IndirectRequests, a dataset of IURs based on the Schema Guided Dialog (SGD) corpus, as a comparative testbed for evaluating the performance of smaller models in handling indirect requests.

IndirectRequests: Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests

Existing benchmark corpora of task-oriented dialogue are collected either using a "machines talking to machines" approach or by giving template-based goal descriptions to crowdworkers. These methods, however, often produce utterances that are markedly different from natural human conversations in which people often convey their preferences in indirect ways, such as through small talk. We term such utterances as Indirect User Requests (IURs). Understanding such utterances demands considerable world knowledge and reasoning capabilities on the listener's part. Our study introduces an LLM-based pipeline to automatically generate realistic, high-quality IURs for a given domain, with the ultimate goal of supporting research in natural language understanding (NLU) and dialogue state tracking (DST) for task-oriented dialogue systems. Our findings show that while large LLMs such as GPT-3.5 and GPT-4 generate high-quality IURs, achieving similar quality with smaller models is more challenging. We release IndirectRequests, a dataset of IURs that advances beyond the initial Schema-Guided Dialog (SGD) dataset in that it provides a challenging testbed for testing the "in the wild" performance of NLU and DST models.

RNG: Reducing Multi-level Noise and Multi-grained Semantic Gap for Joint Multimodal Aspect-Sentiment Analysis

As an important multimodal sentiment analysis task, Joint Multimodal Aspect-Sentiment Analysis (JMASA), aiming to jointly extract aspect terms and their associated sentiment polarities from the given text-image pairs, has gained increasing concerns. Existing works encounter two limitations: (1) multi-level modality noise, i.e., instance- and feature-level noise; and (2) multi-grained semantic gap, i.e., coarse- and fine-grained gap. Both issues may interfere with accurate identification of aspect-sentiment pairs. To address these limitations, we propose a novel framework named RNG for JMASA. Specifically, to simultaneously reduce multi-level modality noise and multi-grained semantic gap, we design three constraints: (1) Global Relevance Constraint (GR-Con) based on text-image similarity for instance-level noise reduction, (2) Information Bottleneck Constraint (IB-Con) based on the Information Bottleneck (IB) principle for feature-level noise reduction, and (3) Semantic Consistency Constraint (SC-Con) based on mutual information maximization in a contrastive learning way for multi-grained semantic gap reduction. Extensive experiments on two datasets validate our new state-of-the-art performance.

CodeEditorBench: Evaluating Code Editing Capability of Large Language Models

Large Language Models (LLMs) for code are rapidly evolving, with code editing emerging as a critical capability. We introduce CodeEditorBench, an evaluation framework designed to rigorously assess the performance of LLMs in code editing tasks, including debugging, translating, polishing, and requirement switching. Unlike existing benchmarks focusing solely on code generation, CodeEditorBench emphasizes real-world scenarios and practical aspects of software development. We curate diverse coding challenges and scenarios from five sources, covering various programming languages, complexity levels, and editing tasks. Evaluation of 19 LLMs reveals that closed-source models (particularly Gemini-Ultra and GPT-4), outperform open-source models in CodeEditorBench, highlighting differences in model performance based on problem types and prompt sensitivities. CodeEditorBench aims to catalyze advancements in LLMs by providing a robust platform for assessing code editing capabilities. We will release all prompts and datasets to enable the community to expand the dataset and benchmark emerging LLMs. By introducing CodeEditorBench, we contribute to the advancement of LLMs in code editing and provide a valuable resource for researchers and practitioners.

PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations

Learning a generalizable object manipulation policy is vital for an embodied agent to work in complex real-world scenes. Parts, as the shared components in different object categories, have the potential to increase the generalization ability of the manipulation policy and achieve cross-category object manipulation. In this work, we build the first large-scale, part-based cross-category object manipulation benchmark, PartManip, which is composed of 11 object categories, 494 objects, and 1432 tasks in 6 task classes. Compared to previous work, our benchmark is also more diverse and realistic, i.e., having more objects and using sparse-view point cloud as input without oracle information like part segmentation. To tackle the difficulties of vision-based policy learning, we first train a state-based expert with our proposed part-based canonicalization and part-aware rewards, and then distill the knowledge to a vision-based student. We also find an expressive backbone is essential to overcome the large diversity of different objects. For cross-category generalization, we introduce domain adversarial learning for domain-invariant feature extraction. Extensive experiments in simulation show that our learned policy can outperform other methods by a large margin, especially on unseen object categories. We also demonstrate our method can successfully manipulate novel objects in the real world.

Collaborative Remote Control of Unmanned Ground Vehicles in Virtual Reality

Virtual reality (VR) technology is commonly used in entertainment applications; however, it has also been deployed in practical applications in more serious aspects of our lives, such as safety. To support people working in dangerous industries, VR can ensure operators manipulate standardized tasks and work collaboratively to deal with potential risks. Surprisingly, little research has focused on how people can collaboratively work in VR environments. Few studies have paid attention to the cognitive load of operators in their collaborative tasks. Once task demands become complex, many researchers focus on optimizing the design of the interaction interfaces to reduce the cognitive load on the operator. That approach could be of merit; however, it can actually subject operators to a more significant cognitive load and potentially more errors and a failure of collaboration. In this paper, we propose a new collaborative VR system to support two teleoperators working in the VR environment to remote control an uncrewed ground vehicle. We use a compared experiment to evaluate the collaborative VR systems, focusing on the time spent on tasks and the total number of operations. Our results show that the total number of processes and the cognitive load during operations were significantly lower in the two-person group than in the single-person group. Our study sheds light on designing VR systems to support collaborative work with respect to the flow of work of teleoperators instead of simply optimizing the design outcomes.

IGLU 2022: Interactive Grounded Language Understanding in a Collaborative Environment at NeurIPS 2022

Human intelligence has the remarkable ability to adapt to new tasks and environments quickly. Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provided natural language instructions. To facilitate research in this direction, we propose IGLU: Interactive Grounded Language Understanding in a Collaborative Environment. The primary goal of the competition is to approach the problem of how to develop interactive embodied agents that learn to solve a task while provided with grounded natural language instructions in a collaborative environment. Understanding the complexity of the challenge, we split it into sub-tasks to make it feasible for participants. This research challenge is naturally related, but not limited, to two fields of study that are highly relevant to the NeurIPS community: Natural Language Understanding and Generation (NLU/G) and Reinforcement Learning (RL). Therefore, the suggested challenge can bring two communities together to approach one of the crucial challenges in AI. Another critical aspect of the challenge is the dedication to perform a human-in-the-loop evaluation as a final evaluation for the agents developed by contestants.