Breast cancer remains one of the leading causes of cancer-related deaths worldwide. Early detection is crucial for improving patient outcomes, yet the diagnostic process is often complex and prone to inconsistencies among pathologists. Computer-aided diagnostic approaches have significantly enhanced breast cancer detection, particularly in binary classification (benign vs. malignant). However, these methods face challenges in multiclass classification, leading to frequent mispredictions. In this work, we propose a novel adaptive learning approach for multiclass breast cancer classification using H&E-stained histopathology images. First, we introduce a misprediction risk analysis framework that quantifies and ranks the likelihood of an image being mislabeled by a classifier. This framework leverages an interpretable risk model that requires only a small number of labeled samples for training. Next, we present an adaptive learning strategy that fine-tunes classifiers based on the specific characteristics of a given dataset. This approach minimizes misprediction risk, allowing the classifier to adapt effectively to the target workload. We evaluate our proposed solutions on real benchmark datasets, demonstrating that our risk analysis framework more accurately identifies mispredictions compared to existing methods. Furthermore, our adaptive learning approach significantly improves the performance of state-of-the-art deep neural network classifiers.

This paper presents the systems and results for the Multimodal Social Media Data Analysis in Dravidian Languages (MSMDA-DL) shared task at the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages (DravidianLangTech-2025). We took a `bag-of-sounds' approach by training our hate speech detection system on the speech (audio) data using transformed Mel spectrogram measures. While our candidate model performed poorly on the test set, our approach offered promising results during training and development for Malayalam and Tamil. With sufficient and well-balanced training data, our results show that it is feasible to use both text and speech (audio) data in the development of multimodal hate speech detection systems.

Data pipeline frameworks provide abstractions for implementing sequences of data-intensive transformation operators, automating the deployment and execution of such transformations in a cluster. Deploying a data pipeline, however, requires computing resources to be allocated in a data center, ideally minimizing the overhead for communicating data and executing operators in the pipeline while considering each operator's execution requirements. In this paper, we model the problem of optimal data pipeline deployment as planning with action costs, where we propose heuristics aiming to minimize total execution time. Experimental results indicate that the heuristics can outperform the baseline deployment and that a heuristic based on connections outperforms other strategies.

Conventional self-attention mechanisms exhibit quadratic complexity in sequence length, making them challenging to scale for long inputs. We present FFTNet, an adaptive spectral filtering framework that uses the Fast Fourier Transform (FFT) to achieve global token mixing in O(n log n) time. By mapping inputs into the frequency domain, FFTNet exploits orthogonality and energy preservation-- guaranteed by Parseval's theorem--to efficiently model long-range dependencies. Our main theoretical contributions include 1) An adaptive spectral filter that highlights salient frequency components, 2) A hybrid scheme combining local windowing with a global FFT branch, 3) Nonlinear feature transformations applied in both the frequency and token domains. Experiments on Long Range Arena and ImageNet validate our theoretical insights and demonstrate superior performance over fixed Fourier-based and standard attention models.

Decades of research have produced robust methods for unsupervised data visualization, yet supervised visualization$\unicode{x2013}$where expert labels guide representations$\unicode{x2013}$remains underexplored, as most supervised approaches prioritize classification over visualization. Recently, RF-PHATE, a diffusion-based manifold learning method leveraging random forests and information geometry, marked significant progress in supervised visualization. However, its lack of an explicit mapping function limits scalability and prevents application to unseen data, posing challenges for large datasets and label-scarce scenarios. To overcome these limitations, we introduce Random Forest Autoencoders (RF-AE), a neural network-based framework for out-of-sample kernel extension that combines the flexibility of autoencoders with the supervised learning strengths of random forests and the geometry captured by RF-PHATE. RF-AE enables efficient out-of-sample supervised visualization and outperforms existing methods, including RF-PHATE's standard kernel extension, in both accuracy and interpretability. Additionally, RF-AE is robust to the choice of hyper-parameters and generalizes to any kernel-based dimensionality reduction method.

The low battery autonomy of Unnamed Aerial Vehicles (UAVs or drones) can make smart farming (precision agriculture), disaster recovery, and the fighting against dengue vector applications difficult. This article considers two approaches, first enumerating the characteristics observed in these three IoT application types and then modeling an UAV's battery recharge coordination using the Agent-Based Simulation (ABS) approach. In this way, we propose that each drone inside the swarm does not communicate concerning this recharge coordination decision, reducing energy usage and permitting remote usage. A total of 6000 simulations were run to evaluate how two proposed policies, the BaseLine (BL) and ChargerThershold (CT) coordination recharging policy, behave in 30 situations regarding how each simulation sets conclude the simulation runs and how much time they work until recharging results. CT policy shows more reliable results in extreme system usage. This work conclusion presents the potential of these three IoT applications to achieve their perpetual service without communication between drones and ground stations. This work can be a baseline for future policies and simulation parameter enhancements.

We propose the notion of empirical privacy variance and study it in the context of differentially private fine-tuning of language models. Specifically, we show that models calibrated to the same $(\varepsilon, \delta)$-DP guarantee using DP-SGD with different hyperparameter configurations can exhibit significant variations in empirical privacy, which we quantify through the lens of memorization. We investigate the generality of this phenomenon across multiple dimensions and discuss why it is surprising and relevant. Through regression analysis, we examine how individual and composite hyperparameters influence empirical privacy. The results reveal a no-free-lunch trade-off: existing practices of hyperparameter tuning in DP-SGD, which focus on optimizing utility under a fixed privacy budget, often come at the expense of empirical privacy. To address this, we propose refined heuristics for hyperparameter selection that explicitly account for empirical privacy, showing that they are both precise and practically useful. Finally, we take preliminary steps to understand empirical privacy variance. We propose two hypotheses, identify limitations in existing techniques like privacy auditing, and outline open questions for future research.

We propose a cheaper alternative bilinear operator to matrix-multiplication in deep neural networks (DNNs). Unlike many stubborn attempts to accelerate MatMuls in DNN inference, this operator is supported by capabilities of existing GPU hardware, most notably NVIDIA TensorCores. To our knowledge, this is the first GPU-native acceleration technique which \emph{does not decrease} (in fact, increases) the number of trainable parameters of the network, mitigating the accuracy-loss of compression-based techniques. Hence, this operator is at the same time more expressive than MatMul, yet requires substantially \emph{fewer} FLOPs to evaluate. We term this new operator \emph{Strassen-Tile} (STL). The main idea behind STL$(X,W)$ is a \emph{local} change-of-basis (learnable encoder) on weights and activation \emph{tiles}, after which we perform batched \emph{elementwise} products between tiles, and a final decoding transformation (inspired by algebraic pipelines from fast matrix and polynomial multiplication). We compare STL against two benchmarks. The first one is SoTA T2T-ViT on Imagenet-1K. Here we show that replacing \emph{all} linear layers with STL and training from scratch, results in factor x2.7 reduction in FLOPs with a 0.5 \emph{accuracy improvement}. Our second speed-accuracy comparison benchmark for pretrained LLMs is the most practical GPU-acceleration technique, \twofour structured Sparsity. Finetuning TinyLlama \cite{tinyllama24} with STL layers on the Slim Pajama dataset, achieves similar accuracy to 2:4, with x2.2 FLOP speedup compared to x1.7 of the latter. Finally, we discuss a group-theoretic approach for discovering \emph{universal} encoders for STL, which could lead to fast \emph{black-box} acceleration via approximate matrix-multiplication (AMM).

Recent works in cross-modal understanding and generation, notably through models like CLAP (Contrastive Language-Audio Pretraining) and CAVP (Contrastive Audio-Visual Pretraining), have significantly enhanced the alignment of text, video, and audio embeddings via a single contrastive loss. However, these methods often overlook the bidirectional interactions and inherent noises present in each modality, which can crucially impact the quality and efficacy of cross-modal integration. To address this limitation, we introduce DiffGAP, a novel approach incorporating a lightweight generative module within the contrastive space. Specifically, our DiffGAP employs a bidirectional diffusion process tailored to bridge the cross-modal gap more effectively. This involves a denoising process on text and video embeddings conditioned on audio embeddings and vice versa, thus facilitating a more nuanced and robust cross-modal interaction. Our experimental results on VGGSound and AudioCaps datasets demonstrate that DiffGAP significantly improves performance in video/text-audio generation and retrieval tasks, confirming its effectiveness in enhancing cross-modal understanding and generation capabilities.

With the advent of large vision-language models (LVLMs) demonstrating increasingly human-like abilities, a pivotal question emerges: do different LVLMs interpret multimodal sarcasm differently, and can a single model grasp sarcasm from multiple perspectives like humans? To explore this, we introduce an analytical framework using systematically designed prompts on existing multimodal sarcasm datasets. Evaluating 12 state-of-the-art LVLMs over 2,409 samples, we examine interpretive variations within and across models, focusing on confidence levels, alignment with dataset labels, and recognition of ambiguous "neutral" cases. Our findings reveal notable discrepancies -- across LVLMs and within the same model under varied prompts. While classification-oriented prompts yield higher internal consistency, models diverge markedly when tasked with interpretive reasoning. These results challenge binary labeling paradigms by highlighting sarcasm's subjectivity. We advocate moving beyond rigid annotation schemes toward multi-perspective, uncertainty-aware modeling, offering deeper insights into multimodal sarcasm comprehension. Our code and data are available at: https://github.com/CoderChen01/LVLMSarcasmAnalysis