Generative Large Multimodal Models (LMMs) like LLaVA and Qwen-VL excel at a wide variety of vision-language (VL) tasks such as image captioning or visual question answering. Despite strong performance, LMMs are not directly suited for foundational discriminative vision-language tasks (i.e., tasks requiring discrete label predictions) such as image classification and multiple-choice VQA. One key challenge in utilizing LMMs for discriminative tasks is the extraction of useful features from generative models. To overcome this issue, we propose an approach for finding features in the model's latent space to more effectively leverage LMMs for discriminative tasks. Toward this end, we present Sparse Attention Vectors (SAVs) -- a finetuning-free method that leverages sparse attention head activations (fewer than 1\% of the heads) in LMMs as strong features for VL tasks. With only few-shot examples, SAVs demonstrate state-of-the-art performance compared to a variety of few-shot and finetuned baselines on a collection of discriminative tasks. Our experiments also imply that SAVs can scale in performance with additional examples and generalize to similar tasks, establishing SAVs as both effective and robust multimodal feature representations.

By defining To improve the inference efficiency without sacrificing accuracy, knowledge as different frequency components of the features, we many studies [10, 11, 13, 31] have adopted Knowledge Distillation theoretically demonstrate that regular feature-based knowledge distillation (KD) to recommender system. KD is a model-agnostic is equivalent to equally minimizing losses on all knowledge approach for model compression [6, 8]. In knowledge distillation and further analyze how this equal loss weight allocation method for recommendation, the common process is first to train a large leads to important knowledge being overlooked. In light of this, teacher model using the user-item interactions, then train a small we propose to emphasize important knowledge by redistributing student model using the user-item interactions as well as the features knowledge weights. Furthermore, we propose FreqD, a lightweight in the intermediate layer [10, 11, 13] and the predictions in knowledge reweighting method, to avoid the computational cost the output layer [1, 10, 15, 17] provided by the teacher model.

A good idea should be relevant to the scientist's interests and novel within the scientific community. Research papers are a major source of inspiration for relevant and novel ideas, as they expose scientists to relevant concepts to re-combine and form new ideas [4, 21, 36]. However, generating relevant and novel scientific ideas by recombining concepts from research papers is difficult for multiple reasons. For one, scientists must wade through an ever-expanding scientific literature to find relevant concepts [2, 19]. Moreover, the phenomenon of fixation biases scientists against considering more diverse concepts and concept recombinations for their research; instead, they are predisposed to thinking about a problem in familiar terms, which hinders the stimulation of novel ideas [11, 37]. Even if a scientist manages to identify interesting concept recombinations to form potential research ideas, assessing the ideas' novelty in comparison to the existing literature is a cumbersome yet critical task. Building a fully or semi-automated ideation system has been an ambition of researchers for decades, and Scideatorbuilds on strong prior work from many other researchers, filling a unique niche. We extend a line of work that presents systems for finding analogies between research papers [4, 21, 36], adopting their facet-based framework but using modern large language model (LLM) methods to identify relevant facets and perform facet recombinations. We are also inspired by recent work showing that LLMs have promise to assist ideation in domains outside science, helping people to generate more ideas [6] and more diverse ideas [27, 40].

Statistical methods for causal inference with continuous treatments mainly focus on estimating the mean potential outcome function, commonly known as the dose-response curve. However, it is often not the dose-response curve but its derivative function that signals the treatment effect. In this paper, we investigate nonparametric inference on the derivative of the dose-response curve with and without the positivity condition. Under the positivity and other regularity conditions, we propose a doubly robust (DR) inference method for estimating the derivative of the dose-response curve using kernel smoothing. When the positivity condition is violated, we demonstrate the inconsistency of conventional inverse probability weighting (IPW) and DR estimators, and introduce novel bias-corrected IPW and DR estimators. In all settings, our DR estimator achieves asymptotic normality at the standard nonparametric rate of convergence. Additionally, our approach reveals an interesting connection to nonparametric support and level set estimation problems. Finally, we demonstrate the applicability of our proposed estimators through simulations and a case study of evaluating a job training program.

Predicting the impact of single-point amino acid mutations on protein stability is essential for understanding disease mechanisms and advancing drug development. Protein stability, quantified by changes in Gibbs free energy ($\Delta\Delta G$), is influenced by these mutations. However, the scarcity of data and the complexity of model interpretation pose challenges in accurately predicting stability changes. This study proposes the application of deep neural networks, leveraging transfer learning and fusing complementary information from different models, to create a feature-rich representation of the protein stability landscape. We developed four models, with our third model, ThermoMPNN+, demonstrating the best performance in predicting $\Delta\Delta G$ values. This approach, which integrates diverse feature sets and embeddings through latent transfusion techniques, aims to refine $\Delta\Delta G$ predictions and contribute to a deeper understanding of protein dynamics, potentially leading to advancements in disease research and drug discovery.

The use of robots in education represents a challenge for teachers and a fixed vision of what robots can do for students. This paper presents the development of Sthymuli, a static educational robot designed to explore new classroom interactions between robots, students and teachers. We propose the use of the Thymio II educational platform as a base, ensuring a robust benchmark for a fair comparison of the commonly available wheeled robots and our exploratory approach with Sthymuli. This paper outlines the constraints and requirements for developing such a robot, the current state of development and future work.

The global AI surge demands crowdworkers from diverse languages and cultures. They are pivotal in labeling data for enabling global AI systems. Despite global significance, research has primarily focused on understanding the perspectives and experiences of US and India crowdworkers, leaving a notable gap. To bridge this, we conducted a survey with 100 crowdworkers across 16 Latin American and Caribbean countries. We discovered that these workers exhibited pride and respect for their digital labor, with strong support and admiration from their families. Notably, crowd work was also seen as a stepping stone to financial and professional independence. Surprisingly, despite wanting more connection, these workers also felt isolated from peers and doubtful of others' labor quality. They resisted collaboration and gender-based tools, valuing gender-neutrality. Our work advances HCI understanding of Latin American and Caribbean crowdwork, offering insights for digital resistance tools for the region.

Large Language Models (LLMs) have demonstrated impressive capabilities in role-playing scenarios, particularly in simulating domain-specific experts using tailored prompts. This ability enables LLMs to adopt the persona of individuals with specific backgrounds, offering a cost-effective and efficient alternative to traditional, resource-intensive user studies. By mimicking human behavior, LLMs can anticipate responses based on concrete demographic or professional profiles. In this paper, we evaluate the effectiveness of LLMs in simulating individuals with diverse backgrounds and analyze the consistency of these simulated behaviors compared to real-world outcomes. In particular, we explore the potential of LLMs to interpret and respond to discharge summaries provided to patients leaving the Intensive Care Unit (ICU). We evaluate and compare with human responses the comprehensibility of discharge summaries among individuals with varying educational backgrounds, using this analysis to assess the strengths and limitations of LLM-driven simulations. Notably, when LLMs are primed with educational background information, they deliver accurate and actionable medical guidance 88% of the time. However, when other information is provided, performance significantly drops, falling below random chance levels. This preliminary study shows the potential benefits and pitfalls of automatically generating patient-specific health information from diverse populations. While LLMs show promise in simulating health personas, our results highlight critical gaps that must be addressed before they can be reliably used in clinical settings. Our findings suggest that a straightforward query-response model could outperform a more tailored approach in delivering health information. This is a crucial first step in understanding how LLMs can be optimized for personalized health communication while maintaining accuracy.

Generative AI, powered by large language models (LLMs), has revolutionized applications across text, audio, images, and video. This study focuses on developing and evaluating encoder-decoder architectures for the American Sign Language (ASL) image dataset, consisting of 87,000 images across 29 hand sign classes. Three approaches were compared: Feedforward Autoencoders, Convolutional Autoencoders, and Diffusion Autoencoders. The Diffusion Autoencoder outperformed the others, achieving the lowest mean squared error (MSE) and highest Mean Opinion Score (MOS) due to its probabilistic noise modeling and iterative denoising capabilities. The Convolutional Autoencoder demonstrated effective spatial feature extraction but lacked the robustness of the diffusion process, while the Feedforward Autoencoder served as a baseline with limitations in handling complex image data. Objective and subjective evaluations confirmed the superiority of the Diffusion Autoencoder for high-fidelity image reconstruction, emphasizing its potential in multimodal AI applications such as sign language recognition and generation. This work provides critical insights into designing robust encoder-decoder systems to advance multimodal AI capabilities.

This study introduces a novel method that employs tag annotation coupled with the ChatGPT language model to analyze student learning behaviors and generate personalized feedback. Central to this approach is the conversion of complex student data into an extensive set of tags, which are then decoded through tailored prompts to deliver constructive feedback that encourages rather than discourages students. This methodology focuses on accurately feeding student data into large language models and crafting prompts that enhance the constructive nature of feedback. The effectiveness of this approach was validated through surveys conducted with over 20 mathematics teachers, who confirmed the reliability of the generated reports. This method can be seamlessly integrated into intelligent adaptive learning systems or provided as a tool to significantly reduce the workload of teachers, providing accurate and timely feedback to students. By transforming raw educational data into interpretable tags, this method supports the provision of efficient and timely personalized learning feedback that offers constructive suggestions tailored to individual learner needs.