Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams. Due to the time-varying training setting, the model learned from a changing distribution easily forgets the previously learned knowledge and biases toward the newly received task. To address this problem, we propose a Continual Bias Adaptor (CBA) module to augment the classifier network to adapt to catastrophic distribution change during training, such that the classifier network is able to learn a stable consolidation of previously learned tasks. In the testing stage, CBA can be removed which introduces no additional computation cost and memory overhead. We theoretically reveal the reason why the proposed method can effectively alleviate catastrophic distribution shifts, and empirically demonstrate its effectiveness through extensive experiments based on four rehearsal-based baselines and three public continual learning benchmarks.

Our test sets were too small and too haphazard to support statistically valid conclusions, but they were suggestive of a number of conclusions. We summarize these here, and discuss them at greater length in section 7. Over the kinds of problems tested, GPT-4 with either plug-in is significantly stronger than GPT-4 by itself, or, almost certainly, than any AI that existed a year ago. However it is still far from reliable; it often outputs a wrong answer or fails to output any answer. In terms of overall score, we would judge that these systems performs on the level of a middling undergraduate student. However, their capacities and weaknesses do not align with a human student; the systems solve some problems that even capable students would find challenging, whereas they fail on some problems that even middling high school students would find easy.

As large language models, such as GPT, continue to advance the capabilities of natural language processing (NLP), the question arises: does the problem of correction still persist? This paper investigates the role of correction in the context of large language models by conducting two experiments. The first experiment focuses on correction as a standalone task, employing few-shot learning techniques with GPTlike models for error correction. The second experiment explores the notion of correction as Figure 1: The illustration shows the feedback results of a preparatory task for other NLP tasks, examining LLM, humans, and other models (such as Bert) when whether large language models can tolerate encountering the wrong text. LLM can ignore the wrong and perform adequately on texts containing certain text very well. Human beings may be confused when levels of noise or errors. By addressing encountering the wrong text, and if the model encounters these experiments, we aim to shed light on the the wrong text, there is a high probability of error.

Many models of learning in teams assume that team members can share solutions or learn concurrently. However, these assumptions break down in multidisciplinary teams where team members often complete distinct, interrelated pieces of larger tasks. Such contexts make it difficult for individuals to separate the performance effects of their own actions from the actions of interacting neighbors. In this work, we show that individuals can overcome this challenge by learning from network neighbors through mediating artifacts (like collective performance assessments). When neighbors' actions influence collective outcomes, teams with different networks perform relatively similarly to one another. However, varying a team's network can affect performance on tasks that weight individuals' contributions by network properties. Consequently, when individuals innovate (through ``exploring'' searches), dense networks hurt performance slightly by increasing uncertainty. In contrast, dense networks moderately help performance when individuals refine their work (through ``exploiting'' searches) by efficiently finding local optima. We also find that decentralization improves team performance across a battery of 34 tasks. Our results offer design principles for multidisciplinary teams within which other forms of learning prove more difficult.

We introduce generative interpretation, a new approach to estimating contractual meaning using large language models. As AI triumphalism is the order of the day, we proceed by way of grounded case studies, each illustrating the capabilities of these novel tools in distinct ways. Taking well-known contracts opinions, and sourcing the actual agreements that they adjudicated, we show that AI models can help factfinders ascertain ordinary meaning in context, quantify ambiguity, and fill gaps in parties' agreements. We also illustrate how models can calculate the probative value of individual pieces of extrinsic evidence. After offering best practices for the use of these models given their limitations, we consider their implications for judicial practice and contract theory. Using LLMs permits courts to estimate what the parties intended cheaply and accurately, and as such generative interpretation unsettles the current interpretative stalemate. Their use responds to efficiency-minded textualists and justice-oriented contextualists, who argue about whether parties will prefer cost and certainty or accuracy and fairness. Parties--and courts--would prefer a middle path, in which adjudicators strive to predict what the contract really meant, admitting just enough context to approximate reality while avoiding unguided and biased assimilation of evidence. As generative interpretation offers this possibility, we argue it can become the new workhorse of contractual interpretation.

The generation of co-speech gestures for digital humans is an emerging area in the field of virtual human creation. Prior research has made progress by using acoustic and semantic information as input and adopting classify method to identify the person's ID and emotion for driving co-speech gesture generation. However, this endeavour still faces significant challenges. These challenges go beyond the intricate interplay between co-speech gestures, speech acoustic, and semantics; they also encompass the complexities associated with personality, emotion, and other obscure but important factors. This paper introduces "diffmotion-v2," a speech-conditional diffusion-based and non-autoregressive transformer-based generative model with WavLM pre-trained model. It can produce individual and stylized full-body co-speech gestures only using raw speech audio, eliminating the need for complex multimodal processing and manually annotated. Firstly, considering that speech audio not only contains acoustic and semantic features but also conveys personality traits, emotions, and more subtle information related to accompanying gestures, we pioneer the adaptation of WavLM, a large-scale pre-trained model, to extract low-level and high-level audio information. Secondly, we introduce an adaptive layer norm architecture in the transformer-based layer to learn the relationship between speech information and accompanying gestures. Extensive subjective evaluation experiments are conducted on the Trinity, ZEGGS, and BEAT datasets to confirm the WavLM and the model's ability to synthesize natural co-speech gestures with various styles.

Conversational AI systems have emerged as key enablers of human-like interactions across diverse sectors. Nevertheless, the balance between linguistic nuance and factual accuracy has proven elusive. In this paper, we first introduce LLMXplorer, a comprehensive tool that provides an in-depth review of over 150 Large Language Models (LLMs), elucidating their myriad implications ranging from social and ethical to regulatory, as well as their applicability across industries. Building on this foundation, we propose a novel functional architecture that seamlessly integrates the structured dynamics of Knowledge Graphs with the linguistic capabilities of LLMs. Validated using real-world AI news data, our architecture adeptly blends linguistic sophistication with factual rigour and further strengthens data security through Role-Based Access Control. This research provides insights into the evolving landscape of conversational AI, emphasizing the imperative for systems that are efficient, transparent, and trustworthy.

The Michigan Robotics Undergraduate Program owes a tremendous debt of gratitude to many people across our Robotics Institute and Robotics Department, the University of Michigan, the College of Engineering, the State of Michigan, and the greater national and global robotics community. Creating a first-of-a-kind robotics program is an incredibly bold and daring undertaking that would not be possible without the support, contributions, empathy, and insights from all corners of our amazing university (Go Blue!). While it would be impossible to recognize everyone who played important roles in realizing the Robotics Major, we would like to acknowledge some individuals who were especially critical to the formation of the program. We must first thank Dean Alec Gallimore and the College of Engineering for their visionary leadership throughout our evolution. Under the guidance and stewardship of Dean Gallimore, the Robotics Institute was able to grow, thrive, and prove it has the right stuff to become a viable academic department and undergraduate program. None of this would be possible without your confidence in us and willingness to innovate for the Common Good. The Robotics Institute owes its origins to Dawn Tilbury - the founding Director of the Robotics Institute (in 2014 under Dean David Munson) and now the inaugural Chair of the Robotics Department - and her foresight to envision what has become the home of Michigan Robotics - the Ford Motor Company Robotics Building. Nadine Sarter, Associate Dean Michael Wellman, and the Robotics Future Committee did tremendous work between 2018-20 to explore the potential and opportunities for Michigan to establish a department and undergraduate program in robotics. Their work identified the path for Michigan to earn distinguished leadership in robotics.

The application of video captioning models aims at translating the content of videos by using accurate natural language. Due to the complex nature inbetween object interaction in the video, the comprehensive understanding of spatio-temporal relations of objects remains a challenging task. Existing methods often fail in generating sufficient feature representations of video content. In this paper, we propose a video captioning model based on dual graphs and gated fusion: we adapt two types of graphs to generate feature representations of video content and utilize gated fusion to further understand these different levels of information. Using a dual-graphs model to generate appearance features and motion features respectively can utilize the content correlation in frames to generate various features from multiple perspectives. Among them, dual-graphs reasoning can enhance the content correlation in frame sequences to generate advanced semantic features; The gated fusion, on the other hand, aggregates the information in multiple feature representations for comprehensive video content understanding. The experiments conducted on worldly used datasets MSVD and MSR-VTT demonstrate state-of-the-art performance of our proposed approach.

Large vision-language models have recently achieved remarkable progress, exhibiting great perception and reasoning abilities concerning visual information. However, how to effectively evaluate these large vision-language models remains a major obstacle, hindering future model development. Traditional benchmarks like VQAv2 or COCO Caption provide quantitative performance measurements but suffer from a lack of fine-grained ability assessment and non-robust evaluation metrics. Recent subjective benchmarks, such as OwlEval, offer comprehensive evaluations of a model's abilities by incorporating human labor, but they are not scalable and display significant bias. In response to these challenges, we propose MMBench, a novel multi-modality benchmark. MMBench methodically develops a comprehensive evaluation pipeline, primarily comprised of two elements. The first element is a meticulously curated dataset that surpasses existing similar benchmarks in terms of the number and variety of evaluation questions and abilities. The second element introduces a novel CircularEval strategy and incorporates the use of ChatGPT. This implementation is designed to convert free-form predictions into pre-defined choices, thereby facilitating a more robust evaluation of the model's predictions. MMBench is a systematically-designed objective benchmark for robustly evaluating the various abilities of vision-language models. We hope MMBench will assist the research community in better evaluating their models and encourage future advancements in this domain. Project page: https://opencompass.org.cn/mmbench.