Large Multimodal Models (LMMs) have emerged as powerful models capable of understanding various data modalities, including text, images, and videos. LMMs encode both text and visual data into tokens that are then combined and processed by an integrated Large Language Model (LLM). Including visual tokens substantially increases the total token count, often by thousands. The increased input length for LLM significantly raises the complexity of inference, resulting in high latency in LMMs. To address this issue, token pruning methods, which remove part of the visual tokens, are proposed. The existing token pruning methods either require extensive calibration and fine-tuning or rely on suboptimal importance metrics which results in increased redundancy among the retained tokens. In this paper, we first formulate token pruning as Max-Min Diversity Problem (MMDP) where the goal is to select a subset such that the diversity among the selected {tokens} is maximized. Then, we solve the MMDP to obtain the selected subset and prune the rest. The proposed method, DivPrune, reduces redundancy and achieves the highest diversity of the selected tokens. By ensuring high diversity, the selected tokens better represent the original tokens, enabling effective performance even at high pruning ratios without requiring fine-tuning. Extensive experiments with various LMMs show that DivPrune achieves state-of-the-art accuracy over 16 image- and video-language datasets. Additionally, DivPrune reduces both the end-to-end latency and GPU memory usage for the tested models. The code is available $\href{https://github.com/vbdi/divprune}{\text{here}}$.

Current LLM pipelines account for only one possible tokenization for a given string, ignoring exponentially many alternative tokenizations during training and inference. For example, the standard Llama3 tokenization of penguin is [p,enguin], yet [peng,uin] is another perfectly valid alternative. In this paper, we show that despite LLMs being trained solely on one tokenization, they still retain semantic understanding of other tokenizations, raising questions about their implications in LLM safety. Put succinctly, we answer the following question: can we adversarially tokenize an obviously malicious string to evade safety and alignment restrictions? We show that not only is adversarial tokenization an effective yet previously neglected axis of attack, but it is also competitive against existing state-of-the-art adversarial approaches without changing the text of the harmful request. We empirically validate this exploit across three state-of-the-art LLMs and adversarial datasets, revealing a previously unknown vulnerability in subword models.

Synthetic tabular data have widespread applications in industrial domains such as healthcare, finance, and supply chains, owing to their potential to protect privacy and mitigate data scarcity. However, generating realistic synthetic tabular data while preserving inter-column logical relationships remains a significant challenge for the existing generative models. To address these challenges, we propose LLM-TabFlow, a novel approach that leverages Large Language Model (LLM) reasoning to capture complex inter-column relationships and compress tabular data, while using Score-based Diffusion to model the distribution of the compressed data in latent space. Additionally, we introduce an evaluation framework, which is absent in literature, to fairly assess the performance of synthetic tabular data generation methods in real-world contexts. Using this framework, we conduct extensive experiments on two real-world industrial datasets, evaluating LLM-TabFlow against other five baseline methods, including SMOTE (an interpolation-based approach) and other state-of-the-art generative models. Our results show that LLM-TabFlow outperforms all baselines, fully preserving inter-column relationships while achieving the best balance between data fidelity, utility, and privacy. This study is the first to explicitly address inter-column relationship preservation in synthetic tabular data generation, offering new insights for developing more realistic and reliable tabular data generation methods.

Large Vision Language Models (LVLMs) are becoming increasingly important in the medical domain, yet Medical LVLMs (Med-LVLMs) frequently generate hallucinations due to limited expertise and the complexity of medical applications. Existing benchmarks fail to effectively evaluate hallucinations based on their underlying causes and lack assessments of mitigation strategies. To address this gap, we introduce MedHEval, a novel benchmark that systematically evaluates hallucinations and mitigation strategies in Med-LVLMs by categorizing them into three underlying causes: visual misinterpretation, knowledge deficiency, and context misalignment. We construct a diverse set of close- and open-ended medical VQA datasets with comprehensive evaluation metrics to assess these hallucination types. We conduct extensive experiments across 11 popular (Med)-LVLMs and evaluate 7 state-of-the-art hallucination mitigation techniques. Results reveal that Med-LVLMs struggle with hallucinations arising from different causes while existing mitigation methods show limited effectiveness, especially for knowledge- and context-based errors. These findings underscore the need for improved alignment training and specialized mitigation strategies to enhance Med-LVLMs' reliability. MedHEval establishes a standardized framework for evaluating and mitigating medical hallucinations, guiding the development of more trustworthy Med-LVLMs.

--Federated Learning (FL) has garnered widespread interest in recent years. However, owing to strict privacy policies or limited storage capacities of training participants such as IoT devices, its effective deployment is often impeded by the scarcity of training data in practical decentralized learning environments. In this paper, we study enhancing FL with the aid of (large) pre-trained models (PMs), that encapsulate wealthy general/domain-agnostic knowledge, to alleviate the data requirement in conducting FL from scratch. Specifically, we consider a networked FL system formed by a central server and distributed clients. First, we formulate the PM-aided personalized FL as a regularization-based federated meta-learning problem, where clients join forces to learn a meta-model with knowledge transferred from a private PM stored at the server . FL, to optimize the problem with no need to expose the PM or incur additional computational costs to local clients. EDERA TED Learning (FL) [2]-[4] has gained prominence as a distributed learning paradigm allowing a large number of decentralized users to collaboratively train models without sharing their local data, which has garnered significant attention from both academia and industry [5]-[11]. Despite its rapid advancements, the effective deployment of FL has been hampered by a significant hurdle: in practice, the participants, such as IoT devices [12], can provide only scarce training data due to limited storage capacities or strict privacy policies [13], [14]. Therefore, it is often unsatisfactory to carry out FL from scratch in many modern data-hungry applications like natural language processing [15] and robotic control [16]. This work was accepted in part by the 22nd International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc) [1]. Sheng Y ue is with the School of Cyber Science and Technology, Sun Y at-sen University. Zerui Qin, Y ongheng Deng, Ju Ren (corresponding author), and Y aoxue Zhang are with the Department of Computer Science and Technology, Tsinghua University. Junshan Zhang is with the Department of Electrical and Computer Engineering, University of California, Davis.

While advances in large language models (LLMs) have greatly improved the quality of synthetic text data in recent years, synthesizing tabular data has received relatively less attention. We address this disparity with Tabby, a simple but powerful post-training modification to the standard Transformer language model architecture, enabling its use for tabular dataset synthesis. Tabby enables the representation of differences across columns using Gated Mixture-of-Experts, with column-specific sets of parameters. Empirically, Tabby results in data quality near or equal to that of real data. By pairing our novel LLM table training technique, Plain, with Tabby, we observe up to a 44% improvement in quality over previous methods. We also show that Tabby extends beyond tables to more general structured data, reaching parity with real data on a nested JSON dataset as well.

In this study, we measure the Intrinsic Dimension (ID) of token embedding to estimate the intrinsic dimensions of the manifolds spanned by the representations, so as to evaluate their redundancy quantitatively compared to their extrinsic dimensionality. In detail, (1) we estimate the ID of token embeddings in small-scale language models and also modern large language models, finding that the embedding spaces often reside on lower-dimensional manifolds compared to their extrinsic dimensionality; (2) we measure the ID across various model sizes and observe an increase in redundancy rates as the model scale grows; (3) we measure the dynamics of IDs during the training process, and find a rapid ID drop in the early stages of training. Moreover, (4) when LoRA is applied to the embedding layers, we observe a sudden drop in perplexity around the estimated IDs, suggesting that the ID can serve as a useful guideline for LoRA application.

This study uses various models to address network traffic classification, categorizing traffic into web, browsing, IPSec, backup, and email . We collected a comprehensive dataset from Arbor Edge Defender (AED) devices, comprising of 30,959 observations and 19 features. Multiple models were evaluated, including Naive Bayes, Decision Tree, Random Forest, Gradient Boosting, XGBoost, Deep Neural Networks (DNN), Transformer, and two Large Language Models (LLMs) including GPT - 4o and Gemini with zero - and few - shot learning. Transformer and XGBoost showed the best performance, achieving the highest accuracy of 98.95 and 97.56%, respectively . GPT - 4o and Gemini showed promising results with few - shot learning, improving accuracy significantly from initial zero - shot performance. While Gemini Few - Shot and GPT - 4 o Few - Shot performed well in categories like Web and Email, misclassifications occurred in more complex categories like IPSec and Backup. The study highlights the importance of model selection, fine - tuning, and the balance between training data siz e and model complexity for achieving reliable classification results.

An essential component of modern recurrent sequence models is the forget gate. While Transformers do not have an explicit recurrent form, we show that a forget gate can be naturally incorporated into Transformers by down-weighting the unnormalized attention scores in a data-dependent way. We name this attention mechanism the Forgetting Attention and the resulting model the Forgetting Transformer (FoX). We show that FoX outperforms the Transformer on long-context language modeling, length extrapolation, and short-context downstream tasks, while performing on par with the Transformer on long-context downstream tasks. Moreover, it is compatible with the FlashAttention algorithm and does not require any positional embeddings. Several analyses, including the needle-in-the-haystack test, show that FoX also retains the Transformer's superior long-context capabilities over recurrent sequence models such as Mamba-2, HGRN2, and DeltaNet. We also introduce a "Pro" block design that incorporates some common architectural components in recurrent sequence models and find it significantly improves the performance of both FoX and the Transformer. Our code is available at https://github.com/zhixuan-lin/forgetting-transformer.

The Test and Measurement domain, known for its strict requirements for accuracy and efficiency, is increasingly adopting Generative AI technologies to enhance the performance of data analysis, automation, and decision-making processes. Among these, Large Language Models (LLMs) show significant promise for advancing automation and precision in testing. However, the evaluation of LLMs in this specialized area remains insufficiently explored. To address this gap, we introduce the Test and Measurement Intelligence Quotient (TMIQ), a benchmark designed to quantitatively assess LLMs across a wide range of electronic engineering tasks. TMIQ offers a comprehensive set of scenarios and metrics for detailed evaluation, including SCPI command matching accuracy, ranked response evaluation, Chain-of-Thought Reasoning (CoT), and the impact of output formatting variations required by LLMs on performance. In testing various LLMs, our findings indicate varying levels of proficiency, with exact SCPI command match accuracy ranging from around 56% to 73%, and ranked matching first-position scores achieving around 33% for the best-performing model. We also assess token usage, cost-efficiency, and response times, identifying trade-offs between accuracy and operational efficiency. Additionally, we present a command-line interface (CLI) tool that enables users to generate datasets using the same methodology, allowing for tailored assessments of LLMs. TMIQ and the CLI tool provide a rigorous, reproducible means of evaluating LLMs for production environments, facilitating continuous monitoring and identifying strengths and areas for improvement, and driving innovation in their selections for applications within the Test and Measurement industry.