Multimodal Large Language Models (MLLMs), built upon LLMs, have recently gained attention for their capabilities in image recognition and understanding. However, while MLLMs are vulnerable to adversarial attacks, the transferability of these attacks across different models remains limited, especially under targeted attack setting. Existing methods primarily focus on vision-specific perturbations but struggle with the complex nature of vision-language modality alignment. In this work, we introduce the Dynamic Vision-Language Alignment (DynVLA) Attack, a novel approach that injects dynamic perturbations into the vision-language connector to enhance generalization across diverse vision-language alignment of different models. Our experimental results show that DynVLA significantly improves the transferability of adversarial examples across various MLLMs, including BLIP2, InstructBLIP, MiniGPT4, LLaVA, and closed-source models such as Gemini.

Training dense LLMs requires enormous amounts of data and centralized compute, which introduces fundamental bottlenecks and ever-growing costs for large models. Several studies aim to reduce this dependency on centralization by reducing the communication overhead of training dense models. Taking this idea of reducing communication overhead to a natural extreme, by training embarrassingly parallelizable ensembles of small independent experts, has been shown to outperform large dense models trained in traditional centralized settings. However, existing studies do not take into account underlying differences amongst data domains and treat them as monolithic, regardless of their underlying complexity, size, or distribution. In this paper, we explore the effects of introducing heterogeneity to these ensembles of domain expert models. Specifically, by allowing models within the ensemble to vary in size--as well as the number of training steps taken depending on the training data's domain--we study the effect heterogeneity has on these ensembles when evaluated against domains included in, and excluded from, the training set. We use the same compute budget to train heterogeneous ensembles and homogeneous baselines for comparison. We show that the heterogeneous ensembles achieve the lowest perplexity scores in $20$ out of the $21$ data domains used in the evaluation. Our code is available at https://github.com/gensyn-ai/hdee.

Modern foundation models rely heavily on using scaling laws to guide crucial training decisions. Researchers often extrapolate the optimal architecture and hyper parameters settings from smaller training runs by describing the relationship between, loss, or task performance, and scale. All components of this process vary, from the specific equation being fit, to the training setup, to the optimization method. Each of these factors may affect the fitted law, and therefore, the conclusions of a given study. We discuss discrepancies in the conclusions that several prior works reach, on questions such as the optimal token to parameter ratio. We augment this discussion with our own analysis of the critical impact that changes in specific details may effect in a scaling study, and the resulting altered conclusions. Additionally, we survey over 50 papers that study scaling trends: while 45 of these papers quantify these trends using a power law, most under-report crucial details needed to reproduce their findings. To mitigate this, we we propose a checklist for authors to consider while contributing to scaling law research.

Language models are often miscalibrated, leading to confidently incorrect answers. We introduce GRACE, a benchmark for language model calibration that incorporates comparison with human calibration. GRACE consists of question-answer pairs, in which each question contains a series of clues that gradually become easier, all leading to the same answer; models must answer correctly as early as possible as the clues are revealed. This setting permits granular measurement of model calibration based on how early, accurately, and confidently a model answers. After collecting these questions, we host live human vs. model competitions to gather 1,749 data points on human and model teams' timing, accuracy, and confidence. We propose a metric, CalScore, that uses GRACE to analyze model calibration errors and identify types of model miscalibration that differ from human behavior. We find that although humans are less accurate than models, humans are generally better calibrated. Since state-of-the-art models struggle on GRACE, it effectively evaluates progress on improving model calibration.

Autonomous graphical user interface (GUI) agents powered by multimodal large language models have shown great promise. However, a critical yet underexplored issue persists: over-execution, where the agent executes tasks in a fully autonomous way, without adequate assessment of its action confidence to compromise an adaptive human-agent collaboration. This poses substantial risks in complex scenarios, such as those involving ambiguous user instructions, unexpected interruptions, and environmental hijacks. To address the issue, we introduce OS-Kairos, an adaptive GUI agent capable of predicting confidence levels at each interaction step and efficiently deciding whether to act autonomously or seek human intervention. OS-Kairos is developed through two key mechanisms: (i) collaborative probing that annotates confidence scores at each interaction step; (ii) confidence-driven interaction that leverages these confidence scores to elicit the ability of adaptive interaction. Experimental results show that OS-Kairos substantially outperforms existing models on our curated dataset featuring complex scenarios, as well as on established benchmarks such as AITZ and Meta-GUI, with 24.59\%$\sim$87.29\% improvements in task success rate. OS-Kairos facilitates an adaptive human-agent collaboration, prioritizing effectiveness, generality, scalability, and efficiency for real-world GUI interaction. The dataset and codes are available at https://github.com/Wuzheng02/OS-Kairos.

When executed well, project-based learning (PBL) engages students' intrinsic motivation, encourages students to learn far beyond a course's limited curriculum, and prepares students to think critically and maturely about the skills and tools at their disposal. However, educators experience mixed results when using PBL in their classrooms: some students thrive with minimal guidance and others flounder. Early evaluation of project proposals could help educators determine which students need more support, yet evaluating project proposals and student aptitude is time-consuming and difficult to scale. In this work, we design, implement, and conduct an initial user study ( n = 36) for a software system that collects project proposals and aptitude information to support educators in determining whether a student is ready to engage with PBL. We find that (1) users perceived the system as helpful for writing project proposals and identifying tools and technologies to learn more about, (2) educator ratings indicate that users with less technical experience in the project topic tend to write lower-quality project proposals, and (3) GPT-4o's ratings show agreement with educator ratings. While the prospect of using LLMs to rate the quality of students' project proposals is promising, its long-term effectiveness strongly hinges on future efforts at characterizing indicators that reliably predict students' success and motivation to learn.

This literature review interrogates the intersections between artificial intelligence, poetry, and art, offering a comprehensive exploration of both historical evolution and current debates in digital creative practices. It traces the development of computer-generated poetry from early template-based systems to generative models, critically assessing evaluative frameworks such as adaptations of the Turing Test, the FACE model, and ProFTAP. It also examines how these frameworks endeavour to measure creativity, semantic coherence, and cultural relevance in AI-generated texts, whilst highlighting the persistent challenges in replicating the nuance of human poetic expression. The review contributes a Marketing Theory discussion that deconstructs the figurative marketing narratives employed by AI companies, which utilise sanitised language and anthropomorphic metaphors to humanise their technologies. This discussion reveals the reductive nature of such narratives and underscores the tension between algorithmic precision and the realities of human creativity.The review also incorporates an auto-ethnographic account that offers a self-reflexive commentary on its own composition. By acknowledging the use of AI in crafting this review, the auto-ethnographic account destabilises conventional notions of authorship and objectivity, resonating with deconstruction and challenging logocentric assumptions in academic discourse. Ultimately, the review calls for a re-evaluation of creative processes that recognises the interdependence of technological innovation and human subjectivity. It advocates for interdisciplinary dialogue addressing ethical, cultural, and philosophical concerns, while reimagining the boundaries of artistic production.

Recent advancements in Artificial Intelligence have led to the development of Multimodal Large Language Models (MLLMs). However, adapting these pre-trained models to dynamic data distributions and various tasks efficiently remains a challenge. Fine-tuning MLLMs for specific tasks often causes performance degradation in the model's prior knowledge domain, a problem known as 'Catastrophic Forgetting'. While this issue has been well-studied in the Continual Learning (CL) community, it presents new challenges for MLLMs. This review paper, the first of its kind in MLLM continual learning, presents an overview and analysis of 440 research papers in this area.The review is structured into four sections. First, it discusses the latest research on MLLMs, covering model innovations, benchmarks, and applications in various fields. Second, it categorizes and overviews the latest studies on continual learning, divided into three parts: non-large language models unimodal continual learning (Non-LLM Unimodal CL), non-large language models multimodal continual learning (Non-LLM Multimodal CL), and continual learning in large language models (CL in LLM). The third section provides a detailed analysis of the current state of MLLM continual learning research, including benchmark evaluations, architectural innovations, and a summary of theoretical and empirical studies.Finally, the paper discusses the challenges and future directions of continual learning in MLLMs, aiming to inspire future research and development in the field. This review connects the foundational concepts, theoretical insights, method innovations, and practical applications of continual learning for multimodal large models, providing a comprehensive understanding of the research progress and challenges in this field, aiming to inspire researchers in the field and promote the advancement of related technologies.

Large Language Models (LLMs) have shown remarkable capabilities across various domains, but their potential for solving combinatorial optimization problems remains largely unexplored. In this paper, we investigate the applicability of LLMs to the Job Shop Scheduling Problem (JSSP), a classic challenge in combinatorial optimization that requires efficient job allocation to machines to minimize makespan. To this end, we introduce Starjob, the first supervised dataset for JSSP, comprising 130k instances specifically designed for training LLMs. Leveraging this dataset, we fine-tune the LLaMA 8B 4-bit quantized model with the LoRA method to develop an end-to-end scheduling approach. Our evaluation on standard benchmarks demonstrates that the proposed LLM-based method not only surpasses traditional Priority Dispatching Rules (PDRs) but also achieves notable improvements over state-of-the-art neural approaches like L2D, with an average improvement of 15.36% on DMU and 7.85% on Taillard benchmarks. These results highlight the untapped potential of LLMs in tackling combinatorial optimization problems, paving the way for future advancements in this area.

Time series data are foundational in finance, healthcare, and energy domains. However, most existing methods and datasets remain focused on a narrow spectrum of tasks, such as forecasting or anomaly detection. To bridge this gap, we introduce Time Series Multi-Task Question Answering (Time-MQA), a unified framework that enables natural language queries across multiple time series tasks - numerical analytical tasks and open-ended question answering with reasoning. Central to Time-MQA is the TSQA dataset, a large-scale dataset containing $\sim$200k question-answer pairs derived from diverse time series spanning environment, traffic, etc. This comprehensive resource covers various time series lengths and promotes robust model development. We further demonstrate how continually pre-training large language models (Mistral 7B, Llama-3 8B, and Qwen-2.5 7B) on the TSQA dataset enhanced time series reasoning capabilities, moving beyond mere numeric tasks and enabling more advanced and intuitive interactions with temporal data. The complete TSQA dataset, models, executable codes, user study questionnaires for evaluation, and results have all been open-sourced.