Archives AI News

arXiv:2411.16147v2 Announce Type: replace-cross Abstract: Zero-shot voice conversion is a technique that alters the speaker identity of an input speech to match a target speaker using only a single reference utterance, without requiring additional training. Recent approaches extensively utilize self-supervised learning features with K-means quantization to extract high-quality content representations while removing speaker identity. However, this quantization process also eliminates fine-grained phonetic and prosodic variations, degrading intelligibility and prosody preservation. While prior works have primarily focused on quantized representations, quantization residuals remain underutilized and deserve further exploration. In this paper, we introduce a novel approach that fully utilizes quantization residuals by leveraging temporal properties of speech components. This facilitates the disentanglement of speaker identity and the recovery of phonetic and prosodic details lost during quantization. By applying only K-means quantization and linear projections, our method achieves simple yet effective disentanglement, without requiring complex architectures or explicit supervision. This allows for high-fidelity voice conversion trained solely with reconstruction losses. Experiments show that the proposed model outperforms existing methods across both subjective and objective metrics. It achieves superior intelligibility and speaker similarity, along with improved prosody preservation, highlighting the impact of our Linear Disentangler module.

arXiv:2509.07998v1 Announce Type: cross Abstract: Language identification is the task of determining the languages for a given text. In many real world scenarios, text may contain more than one language, particularly in multilingual communities. Bilingual Language Identification (BLID) is the task of identifying and distinguishing between two languages in a given text. This paper presents BLID for languages spoken in the southern part of Ethiopia, namely Wolaita and Gofa. The presence of words similarities and differences between the two languages makes the language identification task challenging. To overcome this challenge, we employed various experiments on various approaches. Then, the combination of the BERT based pretrained language model and LSTM approach performed better, with an F1 score of 0.72 on the test set. As a result, the work will be effective in tackling unwanted social media issues and providing a foundation for further research in this area.

arXiv:2503.02733v2 Announce Type: replace-cross Abstract: Implicit Neural Representations (INRs) have demonstrated significant potential in video compression by representing videos as neural networks. However, as the number of frames increases, the memory consumption for training and inference increases substantially, posing challenges in resource-constrained scenarios. Inspired by the success of traditional video compression frameworks, which process video frame by frame and can efficiently compress long videos, we adopt this modeling strategy for INRs to decrease memory consumption, while aiming to unify the frameworks from the perspective of timeline-based autoregressive modeling. In this work, we present a novel understanding of INR models from an autoregressive (AR) perspective and introduce a Unified AutoRegressive Framework for memory-efficient Neural Video Compression (UAR-NVC). UAR-NVC integrates timeline-based and INR-based neural video compression under a unified autoregressive paradigm. It partitions videos into several clips and processes each clip using a different INR model instance, leveraging the advantages of both compression frameworks while allowing seamless adaptation to either in form. To further reduce temporal redundancy between clips, we design two modules to optimize the initialization, training, and compression of these model parameters. UAR-NVC supports adjustable latencies by varying the clip length. Extensive experimental results demonstrate that UAR-NVC, with its flexible video clip setting, can adapt to resource-constrained environments and significantly improve performance compared to different baseline models. The project page: "https://wj-inf.github.io/UAR-NVC-page/".

arXiv:2509.07999v1 Announce Type: cross Abstract: Why do collectives outperform individuals when solving some problems? Fundamentally, collectives have greater computational resources with more sensory information, more memory, more processing capacity, and more ways to act. While greater resources present opportunities, there are also challenges in coordination and cooperation inherent in collectives with distributed, modular structures. Despite these challenges, we show how collective resource advantages lead directly to well-known forms of collective intelligence including the wisdom of the crowd, collective sensing, division of labour, and cultural learning. Our framework also generates testable predictions about collective capabilities in distributed reasoning and context-dependent behavioural switching. Through case studies of animal navigation and decision-making, we demonstrate how collectives leverage their computational resources to solve problems not only more effectively than individuals, but by using qualitatively different problem-solving strategies.

arXiv:2504.11171v4 Announce Type: replace-cross Abstract: We present TerraMind, the first any-to-any generative, multimodal foundation model for Earth observation (EO). Unlike other multimodal models, TerraMind is pretrained on dual-scale representations combining both token-level and pixel-level data across modalities. On a token level, TerraMind encodes high-level contextual information to learn cross-modal relationships, while on a pixel level, TerraMind leverages fine-grained representations to capture critical spatial nuances. We pretrained TerraMind on nine geospatial modalities of a global, large-scale dataset. In this paper, we demonstrate that (i) TerraMind's dual-scale early fusion approach unlocks a range of zero-shot and few-shot applications for Earth observation, (ii) TerraMind introduces "Thinking-in-Modalities" (TiM) -- the capability of generating additional artificial data during finetuning and inference to improve the model output -- and (iii) TerraMind achieves beyond state-of-the-art performance in community-standard benchmarks for EO like PANGAEA. The pretraining dataset, the model weights, and our code are open-sourced under a permissive license.

arXiv:2509.08004v1 Announce Type: cross Abstract: As we increasingly use Artificial Intelligence (AI) in decision-making for industries like healthcare, finance, e-commerce, and even entertainment, it is crucial to also reflect on the ethical aspects of AI, for example the inclusivity and fairness of the information it provides. In this work, we aimed to evaluate different text-to-image AI models and compare the degree of gender bias they present. The evaluated models were Stable Diffusion XL (SDXL), Stable Diffusion Cascade (SC), DALL-E and Emu. We hypothesized that DALL-E and Stable Diffusion, which are comparatively older models, would exhibit a noticeable degree of gender bias towards men, while Emu, which was recently released by Meta AI, would have more balanced results. As hypothesized, we found that both Stable Diffusion models exhibit a noticeable degree of gender bias while Emu demonstrated more balanced results (i.e. less gender bias). However, interestingly, Open AI's DALL-E exhibited almost opposite results, such that the ratio of women to men was significantly higher in most cases tested. Here, although we still observed a bias, the bias favored females over males. This bias may be explained by the fact that OpenAI changed the prompts at its backend, as observed during our experiment. We also observed that Emu from Meta AI utilized user information while generating images via WhatsApp. We also proposed some potential solutions to avoid such biases, including ensuring diversity across AI research teams and having diverse datasets.

arXiv:2506.07104v2 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) demonstrate remarkable problem-solving capabilities through extended Chain-of-Thought (CoT) reasoning but often produce excessively verbose and redundant reasoning traces. This inefficiency incurs high inference costs and limits practical deployment. While existing fine-tuning methods aim to improve reasoning efficiency, assessing their efficiency gains remains challenging due to inconsistent evaluations. In this work, we introduce the reasoning efficiency frontiers, empirical upper bounds derived from fine-tuning base LRMs across diverse approaches and training configurations. Based on these frontiers, we propose the Reasoning Efficiency Gap (REG), a unified metric quantifying deviations of any fine-tuned LRMs from these frontiers. Systematic evaluation on challenging mathematical benchmarks reveals significant gaps in current methods: they either sacrifice accuracy for short length or still remain inefficient under tight token budgets. To reduce the efficiency gap, we propose REO-RL, a class of Reinforcement Learning algorithms that minimizes REG by targeting a sparse set of token budgets. Leveraging numerical integration over strategically selected budgets, REO-RL approximates the full efficiency objective with low error using a small set of token budgets. Through systematic benchmarking, we demonstrate that our efficiency metric, REG, effectively captures the accuracy-length trade-off, with low-REG methods reducing length while maintaining accuracy. Our approach, REO-RL, consistently reduces REG by >=50 across all evaluated LRMs and matching Qwen3-4B/8B efficiency frontiers under a 16K token budget with minimal accuracy loss. Ablation studies confirm the effectiveness of our exponential token budget strategy. Finally, our findings highlight that fine-tuning LRMs to perfectly align with the efficiency frontiers remains an open challenge.

arXiv:2509.08007v1 Announce Type: cross Abstract: Medical image analysis often faces significant challenges due to limited expert-annotated data, hindering both model generalization and clinical adoption. We propose an expert-guided explainable few-shot learning framework that integrates radiologist-provided regions-of-interests (ROIs) into model training to simultaneously enhance classification performance and interpretability. Leveraging Grad-CAM for spatial attention supervision, we introduce an explanation loss based on Dice similarity to align model attention with diagnostically relevant regions during training. This explanation loss is jointly optimized with a standard prototypical network objective, encouraging the model to focus on clinically meaningful features even under limited data conditions. We evaluate our framework on two distinct datasets: BraTS (MRI) and VinDr-CXR (Chest X-ray), achieving significant accuracy improvements from 77.09% to 83.61% on BraTS and from 54.33% to 73.29% on VinDr-CXR compared to non-guided models. Grad-CAM visualizations further confirm that expert-guided training consistently aligns attention with diagnostic regions, improving both predictive reliability and clinical trustworthiness. Our findings demonstrate the effectiveness of incorporating expert-guided attention supervision to bridge the gap between performance and interpretability in few-shot medical image diagnosis.

arXiv:2509.08008v1 Announce Type: cross Abstract: The proliferation of online misinformation videos poses serious societal risks. Current datasets and detection methods primarily target binary classification or single-modality localization based on post-processed data, lacking the interpretability needed to counter persuasive misinformation. In this paper, we introduce the task of Grounding Multimodal Misinformation (GroundMM), which verifies multimodal content and localizes misleading segments across modalities. We present the first real-world dataset for this task, GroundLie360, featuring a taxonomy of misinformation types, fine-grained annotations across text, speech, and visuals, and validation with Snopes evidence and annotator reasoning. We also propose a VLM-based, QA-driven baseline, FakeMark, using single- and cross-modal cues for effective detection and grounding. Our experiments highlight the challenges of this task and lay a foundation for explainable multimodal misinformation detection.

arXiv:2509.00268v2 Announce Type: replace-cross Abstract: Earthquake prediction has long been one of the most elusive challenges in science. Laboratory experiments and simulations suggest that failure precursors should exist, yet reliable signals have remained unobserved in real-world seismic records, leaving open the question of whether they are absent in nature or simply hidden within noise. Here we introduce a stress-sensitive frequency-domain transformation that tracks energy differences between adjacent frequency bands, isolating subtle spectral changes linked to evolving shear and normal stress. Applied to both laboratory acoustic emission data and seismic records from seven major earthquakes (Mw 5.9-9.0), including the 2011 Tohoku and 2023 Turkey-Syria events, the transform consistently reveals precursory signatures, arc-like trajectories and accelerations toward extrema, emerging hours to days before rupture. These features are robust across diverse tectonic settings, from induced seismicity and volcanic collapse to continental strike-slip and subduction megathrust earthquakes. Our findings demonstrate that hidden precursors are indeed encoded in ambient seismic noise, offering a pathway toward real-time fault monitoring and actionable short-term earthquake forecasting.