arXiv:2601.15370v1 Announce Type: new Abstract: Mixture-of-Experts layers achieve compute efficiency through weight sparsity: each token activates only a subset of experts. Data sparsity, where each expert processes only a subset of tokens, offers a complementary axis. Expert-choice routing implements data sparsity directly but violates causality in autoregressive models, creating train-inference mismatch. We recover data sparsity within causal token-choice MoE by leveraging zero-compute (null) experts within the routing pool. When a token routes to null experts, those slots consume […]

Ver mais

arXiv:2601.07944v1 Announce Type: new Abstract: Since the turn of the century, approximate Bayesian inference has steadily evolved as new computational techniques have been incorporated to handle increasingly complex and large-scale predictive problems. The recent success of deep neural networks and foundation models has now given rise to a new paradigm in statistical modeling, in which Bayesian inference can be amortized through large-scale learned predictors. In amortized inference, substantial computation is invested upfront to train a neural network that […]

Ver mais

This report is a first survey of a new, evolutionary narrative, called the Third Story, intended to replace and complement the earlier religious (First) and mechanistic (Second) worldviews. We first argue that the confusions created by a world that is ever more volatile, uncertain, complex and ambiguous (VUCA) have eroded people’s sense of coherence, that is, the degree to which they experience the world as comprehensible, manageable and meaningful. The First Story provides meaning and values, but its […]

Ver mais

arXiv:2602.23377v1 Announce Type: new Abstract: Current research on visual analytics systems largely follows the research paradigm of interactive system design in the field of Human-Computer Interaction (HCI), and includes key methodologies including design requirement development based on user needs, interactive system design, and system evaluation. However, most studies under this paradigm have a contradiction: there is a significant mismatch between the research methods developed for simple cognitive behaviors (e.g., color perception, the perception of spatial relationship among interactive […]

Ver mais

Multimodal machine learning, mimicking the human brain’s ability to integrate various modalities has seen rapid growth. Most previous multimodal models are trained on perfectly paired multimodal input to reach optimal performance. In real-world deployments, however, the presence of modality is highly variable and unpredictable, causing the pre-trained models in suffering significant performance drops and fail to remain robust with dynamic missing modalities circumstances. In this paper, we present a novel Cyclic INformative Learning framework (CyIN) to bridge the […]

Ver mais

arXiv:2603.24714v1 Announce Type: new Abstract: Analog design often slows down because even small changes to device sizes or biases require expensive simulation cycles, and high-quality solutions typically occupy only a narrow part of a very large search space. While existing optimizers reduce some of this burden, they largely operate without the kind of judgment designers use when deciding where to search next. This paper presents an actor-critic optimization framework (ACOF) for analog sizing that brings that form of […]

Ver mais

Mobile crowdsensing (MCS) is a distributed sensing architecture that utilizes existing sensors on mobile units (MUs) to perform sensing tasks. A mobile crowdsensing platform (MCSP) publishes the sensing tasks and the MUs decide whether to participate in exchange for money. The MCS system is dynamic: the task requirements, the MUs’ availability, and their available resources change over time. The MUs aim to find an efficient task participation strategy to maximize their income while the MCSP focuses on maximizing […]

Ver mais