YODA: Teacher-Student Progressive Learning for Language Models

Although large language models (LLMs) have demonstrated adeptness in a range of tasks, they still lag behind human learning efficiency. This disparity is often linked to the inherent human capacity to learn from basic examples, gradually generalize and handle more complex problems, and refine their skills with continuous feedback. Inspired by this, this paper introduces YODA, a novel teacher-student progressive learning framework that emulates the teacher-student education process to improve the efficacy of model fine-tuning. The framework operates on an interactive \textit{basic-generalized-harder} loop. The teacher agent provides tailored feedback on the student's answers, and systematically organizes the education process. This process unfolds by teaching the student basic examples, reinforcing understanding through generalized questions, and then enhancing learning by posing questions with progressively enhanced complexity. With the teacher's guidance, the student learns to iteratively refine its answer with feedback, and forms a robust and comprehensive understanding of the posed questions. The systematic procedural data, which reflects the progressive learning process of humans, is then utilized for model training. Taking math reasoning as a testbed, experiments show that training LLaMA2 with data from YODA improves SFT with significant performance gain (+17.01\% on GSM8K and +9.98\% on MATH). In addition, we find that training with curriculum learning further improves learning robustness.

Software Engineering for Robotics: Future Research Directions; Report from the 2023 Workshop on Software Engineering for Robotics

Robots are experiencing a revolution as they permeate many aspects of our daily lives, from performing house maintenance to infrastructure inspection, from efficiently warehousing goods to autonomous vehicles, and more. This technical progress and its impact are astounding. This revolution, however, is outstripping the capabilities of existing software development processes, techniques, and tools, which largely have remained unchanged for decades. These capabilities are ill-suited to handling the challenges unique to robotics software such as dealing with a wide diversity of domains, heterogeneous hardware, programmed and learned components, complex physical environments captured and modeled with uncertainty, emergent behaviors that include human interactions, and scalability demands that span across multiple dimensions. Looking ahead to the need to develop software for robots that are ever more ubiquitous, autonomous, and reliant on complex adaptive components, hardware, and data, motivated an NSF-sponsored community workshop on the subject of Software Engineering for Robotics, held in Detroit, Michigan in October 2023. The goal of the workshop was to bring together thought leaders across robotics and software engineering to coalesce a community, and identify key problems in the area of SE for robotics that that community should aim to solve over the next 5 years. This report serves to summarize the motivation, activities, and findings of that workshop, in particular by articulating the challenges unique to robot software, and identifying a vision for fruitful near-term research directions to tackle them.

DACR: Distribution-Augmented Contrastive Reconstruction for Time-Series Anomaly Detection

Anomaly detection in time-series data is crucial for identifying faults, failures, threats, and outliers across a range of applications. Recently, deep learning techniques have been applied to this topic, but they often struggle in real-world scenarios that are complex and highly dynamic, e.g., the normal data may consist of multiple distributions, and various types of anomalies may differ from the normal data to different degrees. In this work, to tackle these challenges, we propose Distribution-Augmented Contrastive Reconstruction (DACR). DACR generates extra data disjoint from the normal data distribution to compress the normal data's representation space, and enhances the feature extractor through contrastive learning to better capture the intrinsic semantics from time-series data. Furthermore, DACR employs an attention mechanism to model the semantic dependencies among multivariate time-series features, thereby achieving more robust reconstruction for anomaly detection. Extensive experiments conducted on nine benchmark datasets in various anomaly detection scenarios demonstrate the effectiveness of DACR in achieving new state-of-the-art time-series anomaly detection.

Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns

Recently, the paradigm of pre-training and fine-tuning graph neural networks has been intensively studied and applied in a wide range of graph mining tasks. Its success is generally attributed to the structural consistency between pre-training and downstream datasets, which, however, does not hold in many real-world scenarios. Existing works have shown that the structural divergence between pre-training and downstream graphs significantly limits the transferability when using the vanilla fine-tuning strategy. This divergence leads to model overfitting on pre-training graphs and causes difficulties in capturing the structural properties of the downstream graphs. In this paper, we identify the fundamental cause of structural divergence as the discrepancy of generative patterns between the pre-training and downstream graphs. Furthermore, we propose G-Tuning to preserve the generative patterns of downstream graphs. Given a downstream graph G, the core idea is to tune the pre-trained GNN so that it can reconstruct the generative patterns of G, the graphon W. However, the exact reconstruction of a graphon is known to be computationally expensive. To overcome this challenge, we provide a theoretical analysis that establishes the existence of a set of alternative graphons called graphon bases for any given graphon. By utilizing a linear combination of these graphon bases, we can efficiently approximate W. This theoretical finding forms the basis of our proposed model, as it enables effective learning of the graphon bases and their associated coefficients. Compared with existing algorithms, G-Tuning demonstrates an average improvement of 0.5% and 2.6% on in-domain and out-of-domain transfer learning experiments, respectively.

Federated Continual Novel Class Learning

In a privacy-focused era, Federated Learning (FL) has emerged as a promising machine learning technique. However, most existing FL studies assume that the data distribution remains nearly fixed over time, while real-world scenarios often involve dynamic and continual changes. To equip FL systems with continual model evolution capabilities, we focus on an important problem called Federated Continual Novel Class Learning (FedCN) in this work. The biggest challenge in FedCN is to merge and align novel classes that are discovered and learned by different clients without compromising privacy. To address this, we propose a Global Alignment Learning (GAL) framework that can accurately estimate the global novel class number and provide effective guidance for local training from a global perspective, all while maintaining privacy protection. Specifically, GAL first locates high-density regions in the representation space through a bi-level clustering mechanism to estimate the novel class number, with which the global prototypes corresponding to novel classes can be constructed. Then, GAL uses a novel semantic weighted loss to capture all possible correlations between these prototypes and the training data for mitigating the impact of pseudo-label noise and data heterogeneity. Extensive experiments on various datasets demonstrate GAL's superior performance over state-of-the-art novel class discovery methods. In particular, GAL achieves significant improvements in novel-class performance, increasing the accuracy by 5.1% to 10.6% in the case of one novel class learning stage and by 7.8% to 17.9% in the case of two novel class learning stages, without sacrificing known-class performance. Moreover, GAL is shown to be effective in equipping a variety of different mainstream FL algorithms with novel class discovery and learning capability, highlighting its potential for many real-world applications.

Data Management For Large Language Models: A Survey

Data plays a fundamental role in the training of Large Language Models (LLMs). Effective data management, particularly in the formulation of a well-suited training dataset, holds significance for enhancing model performance and improving training efficiency during pretraining and supervised fine-tuning phases. Despite the considerable importance of data management, the current research community still falls short in providing a systematic analysis of the rationale behind management strategy selection, its consequential effects, methodologies for evaluating curated datasets, and the ongoing pursuit of improved strategies. Consequently, the exploration of data management has attracted more and more attention among the research community. This survey provides a comprehensive overview of current research in data management within both the pretraining and supervised fine-tuning stages of LLMs, covering various noteworthy aspects of data management strategy design: data quantity, data quality, domain/task composition, etc. Looking toward the future, we extrapolate existing challenges and outline promising directions for development in this field. Therefore, this survey serves as a guiding resource for practitioners aspiring to construct powerful LLMs through effective data management practices. The collection of the latest papers is available at https://github.com/ZigeW/data_management_LLM.

Empowering Autonomous Driving with Large Language Models: A Safety Perspective

Autonomous Driving (AD) faces crucial hurdles for commercial launch, notably in the form of diminished public trust and safety concerns from long-tail unforeseen driving scenarios. This predicament is due to the limitation of deep neural networks in AD software, which struggle with interpretability and exhibit poor generalization capabilities in out-of-distribution and uncertain scenarios. To this end, this paper advocates for the integration of Large Language Models (LLMs) into the AD system, leveraging their robust common-sense knowledge, reasoning abilities, and human-interaction capabilities. The proposed approach deploys the LLM as an intelligent decision-maker in planning, incorporating safety verifiers for contextual safety learning to enhance overall AD performance and safety. We present results from two case studies that affirm the efficacy of our approach. We further discuss the potential integration of LLM for other AD software components including perception, prediction, and simulation. Despite the observed challenges in the case studies, the integration of LLMs is promising and beneficial for reinforcing both safety and performance in AD.

State-wise Safe Reinforcement Learning With Pixel Observations

Reinforcement Learning(RL) in the context of safe exploration has long grappled with the challenges of the delicate balance between maximizing rewards and minimizing safety violations, the complexities arising from contact-rich or non-smooth environments, and high-dimensional pixel observations. Furthermore, incorporating state-wise safety constraints in the exploration and learning process, where the agent is prohibited from accessing unsafe regions without prior knowledge, adds an additional layer of complexity. In this paper, we propose a novel pixel-observation safe RL algorithm that efficiently encodes state-wise safety constraints with unknown hazard regions through the introduction of a latent barrier function learning mechanism. As a joint learning framework, our approach first involves constructing a latent dynamics model with low-dimensional latent spaces derived from pixel observations. Subsequently, we build and learn a latent barrier function on top of the latent dynamics and conduct policy optimization simultaneously, thereby improving both safety and the total expected return. Experimental evaluations on the safety-gym benchmark suite demonstrate that our proposed method significantly reduces safety violations throughout the training process and demonstrates faster safety convergence compared to existing methods while achieving competitive results in reward return.

Sensory Manipulation as a Countermeasure to Robot Teleoperation Delays: System and Evidence

In the field of robotics, robot teleoperation for remote or hazardous environments has become increasingly vital. A major challenge is the lag between command and action, negatively affecting operator awareness, performance, and mental strain. Even with advanced technology, mitigating these delays, especially in long-distance operations, remains challenging. Current solutions largely focus on machine-based adjustments. Yet, there's a gap in using human perceptions to improve the teleoperation experience. This paper presents a unique method of sensory manipulation to help humans adapt to such delays. Drawing from motor learning principles, it suggests that modifying sensory stimuli can lessen the perception of these delays. Instead of introducing new skills, the approach uses existing motor coordination knowledge. The aim is to minimize the need for extensive training or complex automation. A study with 41 participants explored the effects of altered haptic cues in delayed teleoperations. These cues were sourced from advanced physics engines and robot sensors. Results highlighted benefits like reduced task time and improved perceptions of visual delays. Real-time haptic feedback significantly contributed to reduced mental strain and increased confidence. This research emphasizes human adaptation as a key element in robot teleoperation, advocating for improved teleoperation efficiency via swift human adaptation, rather than solely optimizing robots for delay adjustment.

Parallelizing non-linear sequential models over the sequence length

Sequential models, such as Recurrent Neural Networks and Neural Ordinary Differential Equations, have long suffered from slow training due to their inherent sequential nature. For many years this bottleneck has persisted, as many thought sequential models could not be parallelized. We challenge this long-held belief with our parallel algorithm that accelerates GPU evaluation of sequential models by up to 3 orders of magnitude faster without compromising output accuracy. The algorithm does not need any special structure in the sequential models' architecture, making it applicable to a wide range of architectures. Using our method, training sequential models can be more than 10 times faster than the common sequential method without any meaningful difference in the training results. Leveraging this accelerated training, we discovered the efficacy of the Gated Recurrent Unit in a long time series classification problem with 17k time samples. By overcoming the training bottleneck, our work serves as the first step to unlock the potential of non-linear sequential models for long sequence problems.