arXiv:2603.16970v1 Announce Type: new Abstract: Multimodal egocentric activity recognition integrates visual and inertial cues for robust first-person behavior understanding. However, deploying such systems in open-world environments requires detecting novel activities while continuously learning from non-stationary streams. Existing methods rely on the main logits for novelty scoring, without fully exploiting the complementary evidence available from individual modalities. Because these logits are often dominated by RGB, cues from other modalities, particularly IMU, remain underutilized, and this imbalance worsens over time […]

Ver mais

Disease forecasting models typically rely on a single data stream, making models brittle when histories are short or noisy. Recent top-performing models have shown that synthesizing multiple reporting systems for the same disease improves performance. Other recent work takes this idea a step further, using transfer learning to train a forecasting model for one disease using data from a different disease. We expand upon each of these approaches greatly, training machine learning models on data that span 66 […]

Ver mais

At Amazon’s 2025 re:Invent conference, Amazon Web Services (AWS) announced the Nitro Isolation Engine (NIE), a software module tasked with providing resources to AWS clients while ensuring the security of customer data. AWS also announced the formal verification of the isolation engine’s correctness and security guarantees, using a proof assistant called Isabelle/HOL. As the first formally verified cloud hypervisor, NIE sets a new standard for cloud security. A proof assistant is an automated tool that can help human […]

Ver mais

arXiv:2602.22295v1 Announce Type: new Abstract: The discrete time queueing system is highly applicable to modern telecommunication systems, where it provides adaptive packet handling, congestion controlled security/inspection, energy efficient operation, and supports bursty traffic common in 5G, Internet of Things (IoT), and edge computing environments. In this article, we analyze an infinite-buffer discrete-time batch-arrival queue with single and multiple vacation policy where customers are served in batches, in two phases, namely first essential service (FES) and second optional service […]

Ver mais

Fine-tuning large vision models (LVMs) and large language models (LLMs) under differentially private federated learning (DPFL) is hindered by a fundamental privacy-utility trade-off. Low-Rank Adaptation (LoRA), a promising parameter-efficient fine-tuning (PEFT) method, reduces computational and communication costs by introducing two trainable low-rank matrices while freezing pre-trained weights. However, directly applying LoRA in DPFL settings leads to performance degradation, especially in LVMs. Our analysis reveals three previously underexplored challenges: (1) gradient coupling caused by the simultaneous update of two […]

Ver mais

In recent years, foundation models have become very popular due to their exceptional performance, mainly in natural language (NLP) tasks where they were first introduced. These models usually consist of hundreds of millions, or even billions, of parameters, making them resource-intensive during training and in production systems, leading to increased costs. This paper focuses on the reduction of a foundation’s model size when applied to music information retrieval (MIR) tasks. Our research combines the Branchformer architecture with SummaryMixing, […]

Ver mais

arXiv:2604.14324v1 Announce Type: new Abstract: Large language models (LLMs) often exhibit hallucinations due to their inability to accurately perceive their own knowledge boundaries. Existing abstention fine-tuning methods typically partition datasets directly based on response accuracy, causing models to suffer from severe label noise near the decision boundaries and consequently exhibit high rates of abstentions or hallucinations. This paper adopts a latent space representation perspective, revealing a “gray zone” near the decision hyperplane where internal belief ambiguity constitutes the […]

Ver mais

arXiv:2603.02250v1 Announce Type: new Abstract: Explaining the behavior of end-to-end audio language models via Shapley value attribution is intractable under native tokenization: a typical utterance yields over $150$ encoder frames, inflating the coalition space by roughly $10^{42}$ relative to text; individual audio frames lack standalone meaning; and token boundaries that bisect phonetic transitions introduce masking artifacts. We introduce Spectrogram-Guided Phonetic Alignment (SGPA), a four-stage pipeline that combines Connectionist Temporal Classification forced alignment with spectral boundary refinement to produce […]

Ver mais

ElevenLabs’ new model will let users regenerate a section of a song without affecting rest of the track

Ver mais