Table of Links Abstract and 1. Introduction Related Work and Background Analysis 3.1 Limitations about Existing ReLUficatio 3.2 dReLU Are Neurons in Expert still Sparsely Activated? dReLU Sparsification Experiments Results 6.1 Downstream Tasks Performance 6.2 Sparsity of Sparsified Models Practical Inference Speedup Evaluation 7.1 Experiments Setting 7.2 Pure CPU Inference and 7.3 Hybrid GPU-CPU Inference 7.4 Deploy LLMs on mobile phones Conclusion and References A. Appendix / supplemental material B. Limitation C. Broader Impact 3 Analysis 3.1 Limitations […]

Ver mais

arXiv:2602.04472v2 Announce Type: replace-cross Abstract: We study asymmetric rank-one spiked tensor models in the high-dimensional regime, where the noise entries are independent and identically distributed with zero mean, unit variance, and finite fourth moment. This extends the classical Gaussian framework to a substantially broader class of noise distributions. We analyze the maximum-likelihood estimator associated with the best rank-one approximation of an order-$d$ tensor, for $dge 3$. Our approach is formulated along an informative, spectrally separated branch of stationary […]

Ver mais

arXiv:2603.06604v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed in critical decision-making systems, the lack of reliable methods to measure their uncertainty presents a fundamental trustworthiness risk. We introduce a normalized confidence score based on output anchor token probabilities: classification labels for structured tasks and self-evaluation responses (Yes/No) for open-ended generation. This enables direct detection of errors and hallucinations with minimal overhead and without external validation. We make three key contributions. First, we propose […]

Ver mais

arXiv:2601.12227v1 Announce Type: new Abstract: Foundation models trained on electronic health records show strong performance on many clinical prediction tasks but are limited by sparse and irregular documentation. Wearable devices provide dense continuous physiological signals but lack semantic grounding. Existing methods usually model these data sources separately or combine them through late fusion. We propose a multimodal foundation model that jointly represents electronic health records and wearable data as a continuous time latent process. The model uses modality […]

Ver mais

arXiv:2603.20939v1 Announce Type: cross Abstract: Large language models are increasingly used as personal assistants, yet most lack a persistent user model, forcing users to repeatedly restate preferences across sessions. We propose Vector-Adapted Retrieval Scoring (VARS), a pipeline-agnostic, frozen-backbone framework that represents each user with long-term and short-term vectors in a shared preference space and uses these vectors to bias retrieval scoring over structured preference memory. The vectors are updated online from weak scalar rewards from users’ feedback, enabling […]

Ver mais

To activate conscious reflection regarding personal identity and identity-building processes in our daily lives is an increasing social concern. With this aim, we designed an Alternate Reality Game that invites participants to collectively explore these themes. Participants played with a prototype, reflecting on identity through emergent dynamics from gameplay and interpersonal interactions. We analysed participants’ appropriation of the prototype through logged activity, direct observation and interviews. The patterns identified enabled iterative redesign and further exploration of interaction dynamics. […]

Ver mais

arXiv:2601.20009v1 Announce Type: new Abstract: Despite multilingual pretraining, large language models often struggle with non-English tasks, particularly in language control, the ability to respond in the intended language. We identify and characterize two key failure modes: the multilingual transfer bottleneck (correct language, incorrect task response) and the language consistency bottleneck (correct task response, wrong language). To systematically surface these issues, we design a four-scenario evaluation protocol spanning MMLU, MGSM, and XQuAD benchmarks. To probe these issues with interpretability, […]

Ver mais

arXiv:2602.13942v1 Announce Type: new Abstract: In the era of large language models (LLMs), fine-tuning pretrained models has become ubiquitous. Yet the theoretical underpinning remains an open question. A central question is why only a few epochs of fine-tuning are typically sufficient to achieve strong performance on many different tasks. In this work, we approach this question by developing a statistical framework, combining rigorous early stopping theory with the attention-based Neural Tangent Kernel (NTK) for LLMs, offering new theoretical […]

Ver mais