The application of GPT-4 in grading design university students' assignment and providing feedback: An exploratory study

This study aims to investigate whether GPT-4 can effectively grade assignments for design university students and provide useful feedback. In design education, assignments do not have a single correct answer and often involve solving an open-ended design problem. This subjective nature of design projects often leads to grading problems,as grades can vary between different raters,for instance instructor from engineering background or architecture background. This study employs an iterative research approach in developing a Custom GPT with the aim of achieving more reliable results and testing whether it can provide design students with constructive feedback. The findings include: First,through several rounds of iterations the inter-reliability between GPT and human raters reached a level that is generally accepted by educators. This indicates that by providing accurate prompts to GPT,and continuously iterating to build a Custom GPT, it can be used to effectively grade students' design assignments, serving as a reliable complement to human raters. Second, the intra-reliability of GPT's scoring at different times is between 0.65 and 0.78. This indicates that, with adequate instructions, a Custom GPT gives consistent results which is a precondition for grading students. As consistency and comparability are the two main rules to ensure the reliability of educational assessment, this study has looked at whether a Custom GPT can be developed that adheres to these two rules. We finish the paper by testing whether Custom GPT can provide students with useful feedback and reflecting on how educators can develop and iterate a Custom GPT to serve as a complementary rater.

Exploring the Use of ChatGPT for a Systematic Literature Review: a Design-Based Research

ChatGPT has been used in several educational contexts,including learning, teaching and research. It also has potential to conduct the systematic literature review (SLR). However, there are limited empirical studies on how to use ChatGPT in conducting a SLR. Based on a SLR published,this study used ChatGPT to conduct a SLR of the same 33 papers in a design-based approach, to see what the differences are by comparing the reviews' results,and to answer: To what extent can ChatGPT conduct SLR? What strategies can human researchers utilize to structure prompts for ChatGPT that enhance the reliability and validity of a SLR? This study found that ChatGPT could conduct a SLR. It needs detailed and accurate prompts to analyze the literature. It also has limitations. Guiding principles are summarized from this study for researchers to follow when they need to conduct SLRs using ChatGPT.

KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition

Point cloud sequence-based 3D action recognition has achieved impressive performance and efficiency. However, existing point cloud sequence modeling methods cannot adequately balance the precision of limb micro-movements with the integrity of posture macro-structure, leading to the loss of crucial information cues in action inference. To overcome this limitation, we introduce D-Hyperpoint, a novel data type generated through a D-Hyperpoint Embedding module. D-Hyperpoint encapsulates both regional-momentary motion and global-static posture, effectively summarizing the unit human action at each moment. In addition, we present a D-Hyperpoint KANsMixer module, which is recursively applied to nested groupings of D-Hyperpoints to learn the action discrimination information and creatively integrates Kolmogorov-Arnold Networks (KAN) to enhance spatio-temporal interaction within D-Hyperpoints. Finally, we propose KAN-HyperpointNet, a spatio-temporal decoupled network architecture for 3D action recognition. Extensive experiments on two public datasets: MSR Action3D and NTU-RGB+D 60, demonstrate the state-of-the-art performance of our method.

AvaTaR: Optimizing LLM Agents for Tool-Assisted Knowledge Retrieval

Large language model (LLM) agents have demonstrated impressive capability in utilizing external tools and knowledge to boost accuracy and reduce hallucinations. However, developing the prompting techniques that make LLM agents able to effectively use external tools and knowledge is a heuristic and laborious task. Here, we introduce AvaTaR, a novel and automatic framework that optimizes an LLM agent to effectively use the provided tools and improve its performance on a given task/domain. During optimization, we design a comparator module to iteratively provide insightful and holistic prompts to the LLM agent via reasoning between positive and negative examples sampled from training data. We demonstrate AvaTaR on four complex multimodal retrieval datasets featuring textual, visual, and relational information. We find AvaTaR consistently outperforms state-of-the-art approaches across all four challenging tasks and exhibits strong generalization ability when applied to novel cases, achieving an average relative improvement of 14% on the Hit@1 metric. Code and dataset are available at https://github.com/zou-group/avatar.

BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments

Agents based on large language models have shown great potential in accelerating scientific discovery by leveraging their rich background knowledge and reasoning capabilities. Here, we develop BioDiscoveryAgent, an agent that designs new experiments, reasons about their outcomes, and efficiently navigates the hypothesis space to reach desired solutions. We demonstrate our agent on the problem of designing genetic perturbation experiments, where the aim is to find a small subset out of many possible genes that, when perturbed, result in a specific phenotype (e.g., cell growth). Utilizing its biological knowledge, BioDiscoveryAgent can uniquely design new experiments without the need to train a machine learning model or explicitly design an acquisition function. Moreover, BioDiscoveryAgent achieves an average of 18% improvement in detecting desired phenotypes across five datasets, compared to existing Bayesian optimization baselines specifically trained for this task. Our evaluation includes one dataset that is unpublished, ensuring it is not part of the language model's training data. Additionally, BioDiscoveryAgent predicts gene combinations to perturb twice as accurately as a random baseline, a task so far not explored in the context of closed-loop experiment design. The agent also has access to tools for searching the biomedical literature, executing code to analyze biological datasets, and prompting another agent to critically evaluate its predictions. Overall, BioDiscoveryAgent is interpretable at every stage, representing an accessible new paradigm in the computational design of biological experiments with the potential to augment scientists' capabilities.

STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases

Answering real-world user queries, such as product search, often requires accurate retrieval of information from semi-structured knowledge bases or databases that involve blend of unstructured (e.g., textual descriptions of products) and structured (e.g., entity relations of products) information. However, previous works have mostly studied textual and relational retrieval tasks as separate topics. To address the gap, we develop STARK, a large-scale Semi-structure retrieval benchmark on Textual and Relational Knowledge Bases. We design a novel pipeline to synthesize natural and realistic user queries that integrate diverse relational information and complex textual properties, as well as their ground-truth answers. Moreover, we rigorously conduct human evaluation to validate the quality of our benchmark, which covers a variety of practical applications, including product recommendations, academic paper searches, and precision medicine inquiries. Our benchmark serves as a comprehensive testbed for evaluating the performance of retrieval systems, with an emphasis on retrieval approaches driven by large language models (LLMs). Our experiments suggest that the STARK datasets present significant challenges to the current retrieval and LLM systems, indicating the demand for building more capable retrieval systems that can handle both textual and relational aspects.

An Improved Artificial Fish Swarm Algorithm for Solving the Problem of Investigation Path Planning

Informationization is a prevailing trend in today's world. The increasing demand for information in decision-making processes poses significant challenges for investigation activities, particularly in terms of effectively allocating limited resources to plan investigation programs. This paper addresses the investigation path planning problem by formulating it as a multi-traveling salesman problem (MTSP). Our objective is to minimize costs, and to achieve this, we propose a chaotic artificial fish swarm algorithm based on multiple population differential evolution (DE-CAFSA). To overcome the limitations of the artificial fish swarm algorithm, such as low optimization accuracy and the inability to consider global and local information, we incorporate adaptive field of view and step size adjustments, replace random behavior with the 2-opt operation, and introduce chaos theory and sub-optimal solutions to enhance optimization accuracy and search performance. Additionally, we integrate the differential evolution algorithm to create a hybrid algorithm that leverages the complementary advantages of both approaches. Experimental results demonstrate that DE-CAFSA outperforms other algorithms on various public datasets of different sizes, as well as showcasing excellent performance on the examples proposed in this study.

Multiscale Motion-Aware and Spatial-Temporal-Channel Contextual Coding Network for Learned Video Compression

Recently, learned video compression has achieved exciting performance. Following the traditional hybrid prediction coding framework, most learned methods generally adopt the motion estimation motion compensation (MEMC) method to remove inter-frame redundancy. However, inaccurate motion vector (MV) usually lead to the distortion of reconstructed frame. In addition, most approaches ignore the spatial and channel redundancy. To solve above problems, we propose a motion-aware and spatial-temporal-channel contextual coding based video compression network (MASTC-VC), which learns the latent representation and uses variational autoencoders (VAEs) to capture the characteristics of intra-frame pixels and inter-frame motion. Specifically, we design a multiscale motion-aware module (MS-MAM) to estimate spatial-temporal-channel consistent motion vector by utilizing the multiscale motion prediction information in a coarse-to-fine way. On the top of it, we further propose a spatial-temporal-channel contextual module (STCCM), which explores the correlation of latent representation to reduce the bit consumption from spatial, temporal and channel aspects respectively. Comprehensive experiments show that our proposed MASTC-VC is surprior to previous state-of-the-art (SOTA) methods on three public benchmark datasets. More specifically, our method brings average 10.15\% BD-rate savings against H.265/HEVC (HM-16.20) in PSNR metric and average 23.93\% BD-rate savings against H.266/VVC (VTM-13.2) in MS-SSIM metric.

Benchmarking Large Language Models As AI Research Agents

Scientific experimentation involves an iterative process of creating hypotheses, designing experiments, running experiments, and analyzing the results. Can we build AI research agents to perform these long-horizon tasks? To take a step towards building and evaluating research agents on such open-ended decision-making tasks, we focus on the problem of machine learning engineering: given a task description and a dataset, build a high-performing model. In this paper, we propose MLAgentBench, a suite of ML tasks for benchmarking AI research agents. Agents can perform actions like reading/writing files, executing code, and inspecting outputs. With these actions, agents could run experiments, analyze the results, and modify the code of entire machine learning pipelines, such as data processing, architecture, training processes, etc. The benchmark then automatically evaluates the agent's performance objectively over various metrics related to performance and efficiency. We also design an LLM-based research agent to automatically perform experimentation loops in such an environment. Empirically, we find that a GPT-4-based research agent can feasibly build compelling ML models over many tasks in MLAgentBench, displaying highly interpretable plans and actions. However, the success rates vary considerably; they span from almost 90\% on well-established older datasets to as low as 10\% on recent Kaggle Challenges -- unavailable during the LLM model's pretraining -- and even 0\% on newer research challenges like BabyLM. Finally, we identify several key challenges for LLM-based research agents such as long-term planning and hallucination. Our code is released at https://github.com/snap-stanford/MLAgentBench.

DD-GCN: Directed Diffusion Graph Convolutional Network for Skeleton-based Human Action Recognition

Graph Convolutional Networks (GCNs) have been widely used in skeleton-based human action recognition. In GCN-based methods, the spatio-temporal graph is fundamental for capturing motion patterns. However, existing approaches ignore the physical dependency and synchronized spatio-temporal correlations between joints, which limits the representation capability of GCNs. To solve these problems, we construct the directed diffusion graph for action modeling and introduce the activity partition strategy to optimize the weight sharing mechanism of graph convolution kernels. In addition, we present the spatio-temporal synchronization encoder to embed synchronized spatio-temporal semantics. Finally, we propose Directed Diffusion Graph Convolutional Network (DD-GCN) for action recognition, and the experiments on three public datasets: NTU-RGB+D, NTU-RGB+D 120, and NW-UCLA, demonstrate the state-of-the-art performance of our method.