A Variational Framework for Improving Naturalness in Generative Spoken Language Models

The success of large language models in text processing has inspired their adaptation to speech modeling. However, since speech is continuous and complex, it is often discretized for autoregressive modeling. Speech tokens derived from self-supervised models (known as semantic tokens) typically focus on the linguistic aspects of speech but neglect prosodic information. As a result, models trained on these tokens can generate speech with reduced naturalness. Existing approaches try to fix this by adding pitch features to the semantic tokens. However, pitch alone cannot fully represent the range of paralinguistic attributes, and selecting the right features requires careful hand-engineering. To overcome this, we propose an end-to-end variational approach that automatically learns to encode these continuous speech attributes to enhance the semantic tokens. Our approach eliminates the need for manual extraction and selection of paralinguistic features. Moreover, it produces preferred speech continuations according to human raters. Code, samples and models are available at https://github.com/b04901014/vae-gslm.

GenerationPrograms: Fine-grained Attribution with Executable Programs

Recent large language models (LLMs) achieve impressive performance in source-conditioned text generation but often fail to correctly provide fine-grained attributions for their outputs, undermining verifiability and trust. Moreover, existing attribution methods do not explain how and why models leverage the provided source documents to generate their final responses, limiting interpretability. To overcome these challenges, we introduce a modular generation framework, GenerationPrograms, inspired by recent advancements in executable "code agent" architectures. Unlike conventional generation methods that simultaneously generate outputs and attributions or rely on post-hoc attribution, GenerationPrograms decomposes the process into two distinct stages: first, creating an executable program plan composed of modular text operations (such as paraphrasing, compression, and fusion) explicitly tailored to the query, and second, executing these operations following the program's specified instructions to produce the final response. Empirical evaluations demonstrate that GenerationPrograms significantly improves attribution quality at both the document level and sentence level across two long-form question-answering tasks and a multi-document summarization task. We further demonstrate that GenerationPrograms can effectively function as a post-hoc attribution method, outperforming traditional techniques in recovering accurate attributions. In addition, the interpretable programs generated by GenerationPrograms enable localized refinement through modular-level improvements that further enhance overall attribution quality.

Hyper-Local Deformable Transformers for Text Spotting on Historical Maps

Text on historical maps contains valuable information providing georeferenced historical, political, and cultural contexts. However, text extraction from historical maps is challenging due to the lack of (1) effective methods and (2) training data. Previous approaches use ad-hoc steps tailored to only specific map styles. Recent machine learning-based text spotters (e.g., for scene images) have the potential to solve these challenges because of their flexibility in supporting various types of text instances. However, these methods remain challenges in extracting precise image features for predicting every sub-component (boundary points and characters) in a text instance. This is critical because map text can be lengthy and highly rotated with complex backgrounds, posing difficulties in detecting relevant image features from a rough text region. This paper proposes PALETTE, an end-to-end text spotter for scanned historical maps of a wide variety. PALETTE introduces a novel hyper-local sampling module to explicitly learn localized image features around the target boundary points and characters of a text instance for detection and recognition. PALETTE also enables hyper-local positional embeddings to learn spatial interactions between boundary points and characters within and across text instances. In addition, this paper presents a novel approach to automatically generate synthetic map images, SynthMap+, for training text spotters for historical maps. The experiment shows that PALETTE with SynthMap+ outperforms SOTA text spotters on two new benchmark datasets of historical maps, particularly for long and angled text. We have deployed PALETTE with SynthMap+ to process over 60,000 maps in the David Rumsey Historical Map collection and generated over 100 million text labels to support map searching. The project is released at https://github.com/kartta-foundation/mapkurator-palette-doc.

Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model

The emergence of GPT-4o-like large multimodal models (LMMs) has raised the exploration of integrating text, vision, and speech modalities to support more flexible multimodal interaction. Existing LMMs typically concatenate representation of modalities along the sequence dimension and feed them into a large language model (LLM) backbone. While sequence-dimension concatenation is straightforward for modality integration, it often relies heavily on large-scale data to learn modality alignments. In this paper, we aim to model the relationships between modalities more purposefully, thereby achieving more efficient and flexible modality alignments. To this end, we propose Stream-Omni, a large language-vision-speech model with efficient modality alignments, which can simultaneously support interactions under various modality combinations. Stream-Omni employs LLM as the backbone and aligns the vision and speech to the text based on their relationships. For vision that is semantically complementary to text, Stream-Omni uses sequence-dimension concatenation to achieve vision-text alignment. For speech that is semantically consistent with text, Stream-Omni introduces a CTC-based layer-dimension mapping to achieve speech-text alignment. In this way, Stream-Omni can achieve modality alignments with less data (especially speech), enabling the transfer of text capabilities to other modalities. Experiments on various benchmarks demonstrate that Stream-Omni achieves strong performance on visual understanding, speech interaction, and vision-grounded speech interaction tasks. Owing to the layer-dimensional mapping, Stream-Omni can simultaneously provide intermediate text outputs (such as ASR transcriptions and model responses) during speech interaction, offering users a comprehensive multimodal experience.

Fair Generation without Unfair Distortions: Debiasing Text-to-Image Generation with Entanglement-Free Attention

Recent advancements in diffusion-based text-to-image (T2I) models have enabled the generation of high-quality and photorealistic images from text descriptions. However, they often exhibit societal biases related to gender, race, and socioeconomic status, thereby reinforcing harmful stereotypes and shaping public perception in unintended ways. While existing bias mitigation methods demonstrate effectiveness, they often encounter attribute entanglement, where adjustments to attributes relevant to the bias (i.e., target attributes) unintentionally alter attributes unassociated with the bias (i.e., non-target attributes), causing undesirable distribution shifts. To address this challenge, we introduce Entanglement-Free Attention (EFA), a method that accurately incorporates target attributes (e.g., White, Black, Asian, and Indian) while preserving non-target attributes (e.g., background details) during bias mitigation. At inference time, EFA randomly samples a target attribute with equal probability and adjusts the cross-attention in selected layers to incorporate the sampled attribute, achieving a fair distribution of target attributes. Extensive experiments demonstrate that EFA outperforms existing methods in mitigating bias while preserving non-target attributes, thereby maintaining the output distribution and generation capability of the original model.

Anomaly Object Segmentation with Vision-Language Models for Steel Scrap Recycling

Recycling steel scrap can reduce carbon dioxide (CO2) emissions from the steel industry. However, a significant challenge in steel scrap recycling is the inclusion of impurities other than steel. To address this issue, we propose vision-language-model-based anomaly detection where a model is finetuned in a supervised manner, enabling it to handle niche objects effectively. This model enables automated detection of anomalies at a fine-grained level within steel scrap. Specifically, we finetune the image encoder, equipped with multi-scale mechanism and text prompts aligned with both normal and anomaly images. The finetuning process trains these modules using a multiclass classification as the supervision.

Fatigue-Aware Adaptive Interfaces for Wearable Devices Using Deep Learning

Wearable devices, such as smartwatches and head-mounted displays, are increasingly used for prolonged tasks like remote learning and work, but sustained interaction often leads to user fatigue, reducing efficiency and engagement. This study proposes a fatigue-aware adaptive interface system for wearable devices that leverages deep learning to analyze physiological data (e.g., heart rate, eye movement) and dynamically adjust interface elements to mitigate cognitive load. The system employs multimodal learning to process physiological and contextual inputs and reinforcement learning to optimize interface features like text size, notification frequency, and visual contrast. Experimental results show a 18% reduction in cognitive load and a 22% improvement in user satisfaction compared to static interfaces, particularly for users engaged in prolonged tasks. This approach enhances accessibility and usability in wearable computing environments.

Equitable Electronic Health Record Prediction with FAME: Fairness-Aware Multimodal Embedding

Electronic Health Record (EHR) data encompass diverse modalities -- text, images, and medical codes -- that are vital for clinical decision-making. To process these complex data, multimodal AI (MAI) has emerged as a powerful approach for fusing such information. However, most existing MAI models optimize for better prediction performance, potentially reinforcing biases across patient subgroups. Although bias-reduction techniques for multimodal models have been proposed, the individual strengths of each modality and their interplay in both reducing bias and optimizing performance remain underexplored. In this work, we introduce FAME (Fairness-Aware Multimodal Embeddings), a framework that explicitly weights each modality according to its fairness contribution. FAME optimizes both performance and fairness by incorporating a combined loss function. We leverage the Error Distribution Disparity Index (EDDI) to measure fairness across subgroups and propose a sign-agnostic aggregation method to balance fairness across subgroups, ensuring equitable model outcomes. We evaluate FAME with BEHRT and BioClinicalBERT, combining structured and unstructured EHR data, and demonstrate its effectiveness in terms of performance and fairness compared with other baselines across multiple EHR prediction tasks.

Learning Event Completeness for Weakly Supervised Video Anomaly Detection

Weakly supervised video anomaly detection (WS-VAD) is tasked with pinpointing temporal intervals containing anomalous events within untrimmed videos, utilizing only video-level annotations. However, a significant challenge arises due to the absence of dense frame-level annotations, often leading to incomplete localization in existing WS-VAD methods. To address this issue, we present a novel LEC-VAD, Learning Event Completeness for Weakly Supervised Video Anomaly Detection, which features a dual structure designed to encode both category-aware and category-agnostic semantics between vision and language. Within LEC-VAD, we devise semantic regularities that leverage an anomaly-aware Gaussian mixture to learn precise event boundaries, thereby yielding more complete event instances. Besides, we develop a novel memory bank-based prototype learning mechanism to enrich concise text descriptions associated with anomaly-event categories. This innovation bolsters the text's expressiveness, which is crucial for advancing WS-VAD. Our LEC-VAD demonstrates remarkable advancements over the current state-of-the-art methods on two benchmark datasets XD-Violence and UCF-Crime.

Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective

Machine unlearning focuses on efficiently removing specific data from trained models, addressing privacy and compliance concerns with reasonable costs. Although exact unlearning ensures complete data removal equivalent to retraining, it is impractical for large-scale models, leading to growing interest in inexact unlearning methods. However, the lack of formal guarantees in these methods necessitates the need for robust evaluation frameworks to assess their privacy and effectiveness. In this work, we first identify several key pitfalls of the existing unlearning evaluation frameworks, e.g., focusing on average-case evaluation or targeting random samples for evaluation, incomplete comparisons with the retraining baseline. Then, we propose RULI (Rectified Unlearning Evaluation Framework via Likelihood Inference), a novel framework to address critical gaps in the evaluation of inexact unlearning methods. RULI introduces a dual-objective attack to measure both unlearning efficacy and privacy risks at a per-sample granularity. Our findings reveal significant vulnerabilities in state-of-the-art unlearning methods, where RULI achieves higher attack success rates, exposing privacy risks underestimated by existing methods. Built on a game-based foundation and validated through empirical evaluations on both image and text data (spanning tasks from classification to generation), RULI provides a rigorous, scalable, and fine-grained methodology for evaluating unlearning techniques.