We focus on designing efficient Task and Motion Planning (TAMP) approach for long-horizon manipulation tasks involving multi-step manipulation of multiple objects. TAMP solvers typically require exponentially longer planning time as the planning horizon and the number of environmental objects increase. To address this challenge, we first propose Learn2Decompose, a Learning from Demonstrations (LfD) approach that learns embedding task rules from demonstrations and decomposes the long-horizon problem into several subproblems. These subproblems require planning over shorter horizons with fewer objects and can be solved in parallel. We then design a parallelized hierarchical TAMP framework that concurrently solves the subproblems and concatenates the resulting subplans for the target task, significantly improving the planning efficiency of classical TAMP solvers. The effectiveness of our proposed methods is validated in both simulation and real-world experiments.

The analysis of students' emotions and behaviors is crucial for enhancing learning outcomes and personalizing educational experiences. Traditional methods often rely on intrusive visual and physiological data collection, posing privacy concerns and scalability issues. This paper proposes a novel method leveraging large language models (LLMs) and prompt engineering to analyze textual data from students. Our approach utilizes tailored prompts to guide LLMs in detecting emotional and engagement states, providing a non-intrusive and scalable solution. We conducted experiments using Qwen, ChatGPT, Claude2, and GPT-4, comparing our method against baseline models and chain-of-thought (CoT) prompting. Results demonstrate that our method significantly outperforms the baselines in both accuracy and contextual understanding. This study highlights the potential of LLMs combined with prompt engineering to offer practical and effective tools for educational emotion and behavior analysis.

Advanced Large language models (LLMs) like GPT-4 or LlaMa 3 provide superior performance in complex human-like interactions. But they are costly, or too large for edge devices such as smartphones and harder to self-host, leading to security and privacy concerns. This paper introduces a novel interpretable knowledge distillation approach to enhance the performance of smaller, more economical LLMs that firms can self-host. We study this problem in the context of building a customer service agent aimed at achieving high customer satisfaction through goal-oriented dialogues. Unlike traditional knowledge distillation, where the "student" model learns directly from the "teacher" model's responses via fine-tuning, our interpretable "strategy" teaching approach involves the teacher providing strategies to improve the student's performance in various scenarios. This method alternates between a "scenario generation" step and a "strategies for improvement" step, creating a customized library of scenarios and optimized strategies for automated prompting. The method requires only black-box access to both student and teacher models; hence it can be used without manipulating model parameters. In our customer service application, the method improves performance, and the learned strategies are transferable to other LLMs and scenarios beyond the training set. The method's interpretabilty helps safeguard against potential harms through human audit.

The dominant The current trend to improve language trend in improving language models model performance seems to be based on seems to be based on scaling up the scaling up with the number of parameters number of parameters (e.g. GPT4 has (e.g. the state of the art GPT4 model has approximately 1.7 trillion parameters) or approximately 1.7 trillion parameters) or the amount of training data fed into the the amount of training data fed into the model (e.g. the Common Crawl dataset model. However this comes at significant currently has more than 75 TB of textual costs in terms of computational resources data). However, this scaling usually comes and energy costs that compromise the sustainability at significant costs in terms of computational of AI solutions, as well as risk relating resources, which translate to energy to privacy and misuse. In this paper (Emma, Ananya, & Andrew, 2019), financial, we present the Erasmian Language Model and environmental costs, and data collection, (ELM) a small context specific, 900 million which in turn raise concerns regarding parameter model, pre-trained and finetuned legal, privacy, quality, and responsibility by and for Erasmus University Rotterdam.

Binary program vulnerability detection is critical for software security, yet existing deep learning approaches often rely on source code analysis, limiting their ability to detect unknown vulnerabilities. To address this, we propose VulCatch, a binary-level vulnerability detection framework. VulCatch introduces a Synergy Decompilation Module (SDM) and Kolmogorov-Arnold Networks (KAN) to transform raw binary code into pseudocode using CodeT5, preserving high-level semantics for deep analysis with tools like Ghidra and IDA. KAN further enhances feature transformation, enabling the detection of complex vulnerabilities. VulCatch employs word2vec, Inception Blocks, BiLSTM Attention, and Residual connections to achieve high detection accuracy (98.88%) and precision (97.92%), while minimizing false positives (1.56%) and false negatives (2.71%) across seven CVE datasets.

This study examines the impact of Generative Artificial Intelligence (GenAI) on academic research, focusing on its application to qualitative and quantitative data analysis. As GenAI tools evolve rapidly, they offer new possibilities for enhancing research productivity and democratising complex analytical processes. However, their integration into academic practice raises significant questions regarding research integrity and security, authorship, and the changing nature of scholarly work. Through an examination of current capabilities and potential future applications, this study provides insights into how researchers may utilise GenAI tools responsibly and ethically. We present case studies that demonstrate the application of GenAI in various research methodologies, discuss the challenges of replicability and consistency in AI-assisted research, and consider the ethical implications of increased AI integration in academia. This study explores both qualitative and quantitative applications of GenAI, highlighting tools for transcription, coding, thematic analysis, visual analytics, and statistical analysis. By addressing these issues, we aim to contribute to the ongoing discourse on the role of AI in shaping the future of academic research and provide guidance for researchers exploring the rapidly evolving landscape of AI-assisted research tools and research.

This chapter critically examines the potential contributions of modern language models to theoretical linguistics. Despite their focus on engineering goals, these models' ability to acquire sophisticated linguistic knowledge from mere exposure to data warrants a careful reassessment of their relevance to linguistic theory. I review a growing body of empirical evidence suggesting that language models can learn hierarchical syntactic structure and exhibit sensitivity to various linguistic phenomena, even when trained on developmentally plausible amounts of data. While the competence/performance distinction has been invoked to dismiss the relevance of such models to linguistic theory, I argue that this assessment may be premature. By carefully controlling learning conditions and making use of causal intervention methods, experiments with language models can potentially constrain hypotheses about language acquisition and competence. I conclude that closer collaboration between theoretical linguists and computational researchers could yield valuable insights, particularly in advancing debates about linguistic nativism.

As large language models (LLMs) continue to scale, their enhanced performance often proves insufficient for solving domain-specific tasks. Systematically analyzing their failures and effectively enhancing their performance remain significant challenges. This paper introduces the Re-TASK framework, a novel theoretical model that Revisits LLM Tasks from cApability, Skill, Knowledge perspectives, guided by the principles of Bloom's Taxonomy and Knowledge Space Theory. The Re-TASK framework provides a systematic methodology to deepen our understanding, evaluation, and enhancement of LLMs for domain-specific tasks. It explores the interplay among an LLM's capabilities, the knowledge it processes, and the skills it applies, elucidating how these elements are interconnected and impact task performance. Our application of the Re-TASK framework reveals that many failures in domain-specific tasks can be attributed to insufficient knowledge or inadequate skill adaptation. With this insight, we propose structured strategies for enhancing LLMs through targeted knowledge injection and skill adaptation. Specifically, we identify key capability items associated with tasks and employ a deliberately designed prompting strategy to enhance task performance, thereby reducing the need for extensive fine-tuning. Alternatively, we fine-tune the LLM using capability-specific instructions, further validating the efficacy of our framework. Experimental results confirm the framework's effectiveness, demonstrating substantial improvements in both the performance and applicability of LLMs.

Med42-v2 introduces a suite of clinical large language models (LLMs) designed to address the limitations of generic models in healthcare settings. These models are built on Llama3 architecture and fine-tuned using specialized clinical data. They underwent multi-stage preference alignment to effectively respond to natural prompts. While generic models are often preference-aligned to avoid answering clinical queries as a precaution, Med42-v2 is specifically trained to overcome this limitation, enabling its use in clinical settings. Med42-v2 models demonstrate superior performance compared to the original Llama3 models in both 8B and 70B parameter configurations and GPT-4 across various medical benchmarks. These LLMs are developed to understand clinical queries, perform reasoning tasks, and provide valuable assistance in clinical environments. The models are now publicly available at \href{https://huggingface.co/m42-health}{https://huggingface.co/m42-health}.

Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life applications. To improve audio quality, an enhancement module, which can be developed independently, is explicitly used at the front-end of the target audio applications. In this paper, we present an end-to-end learning solution to jointly optimise the models for audio enhancement (AE) and the subsequent applications. To guide the optimisation of the AE module towards a target application, and especially to overcome difficult samples, we make use of the sample-wise performance measure as an indication of sample importance. In experiments, we consider four representative applications to evaluate our training paradigm, i.e., ASR, speech command recognition (SCR), speech emotion recognition (SER), and ASC. These applications are associated with speech and non-speech tasks concerning semantic and non-semantic features, transient and global information, and the experimental results indicate that our proposed approach can considerably boost the noise robustness of the models, especially at low signal-to-noise ratios (SNRs), for a wide range of computer audition tasks in everyday-life noisy environments.