arXiv:2604.15364v1 Announce Type: new Abstract: Edge intelligence is constrained by the energy and latency costs of shuttling data through electronic memory hierarchies. Optical systems offer a fundamentally different computational regime: once an input wavefront is launched into a structured medium, propagation, diffraction, and interference jointly enact a linear transformation whose cost is determined by wave physics rather than by clocked arithmetic. This paper develops a rigorous systems-level treatment of that regime and introduces a hybrid diffractive holographic architecture […]

Ver mais

arXiv:2603.26734v1 Announce Type: new Abstract: The Mixture-of-Experts (MoE) model uses a set of expert networks that specialize on subsets of a dataset under the supervision of a gating network. A common issue in MoE architectures is “expert collapse” where overlapping class boundaries in the raw input feature space cause multiple experts to learn redundant representations, thus forcing the gating network into rigid routing to compensate. We propose an enhanced MoE architecture that utilizes a feature extractor network optimized […]

Ver mais

arXiv:2603.24597v1 Announce Type: new Abstract: We study algorithmic barriers to detecting and repairing a systematic form of structural overspecification in adaptive data-structure selection. An input instance induces an implied workload signature, such as ordering, sparsity, dynamism, locality, or substring structure, and candidate implementations may be preferred because they match that full signature even when the measured workload evidence supports only a strict subset of it. Under a model in which pairwise evaluators favor implementations that realize the implied […]

Ver mais

arXiv:2601.16234v1 Announce Type: new Abstract: The use of algorithms is increasing across various fields such as healthcare, justice, finance, and education. This growth has significantly accelerated with the advent of Artificial Intelligence (AI) technologies based on Large Language Models (LLMs) since 2022. This expansion presents substantial challenges related to accountability, ethics, and transparency. This article explores the potential of the Digital Object Identifier (DOI) to identify algorithms, aiming to enhance accountability, transparency, and reliability in their development and […]

Ver mais

arXiv:2601.21942v1 Announce Type: new Abstract: Transformers have revolutionized deep learning across various domains but understanding the precise token dynamics remains a theoretical challenge. Existing theories of deep Transformers with layer normalization typically predict that tokens cluster to a single point; however, these results rely on deterministic weight assumptions, which fail to capture the standard initialization scheme in Transformers. In this work, we show that accounting for the intrinsic stochasticity of random initialization alters this picture. More precisely, we […]

Ver mais

arXiv:2602.13315v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities, yet they encounter significant computational bottlenecks due to the massive volume of visual tokens. Consequently, visual token pruning, which substantially reduces the token count, has emerged as a critical technique for accelerating MLLM inference. Existing approaches focus on token importance, diversity, or an intuitive combination of both, without a principled framework for their optimal integration. To address this issue, we first conduct a systematic […]

Ver mais

Key Highlights – ChatGPT has had a shopping function for a while. What OpenAI shipped this week is a meaningful upgrade to how it looks and works with products. This includes side-by-side comparisons, image uploads to find similar items, and fresher catalog data pulled directly from participating merchants. The rollout covers all tiers, not just paid subscribers. For most users, the practical change is that product research that previously sent you across multiple tabs can now stay inside […]

Ver mais