arXiv:2603.00105v1 Announce Type: cross Abstract: Large language models (LLMs) have gained significant attention by many researchers and practitioners in natural language processing (NLP) since the introduction of ChatGPT in 2022. One notable feature of ChatGPT is its ability to generate summaries based on prompts. Yet evaluating the quality of these summaries remains challenging due to the complexity of language. To this end, in this paper we suggest a new method of LLM summary inference with BERT-SVD-based direction metric […]

Ver mais

arXiv:2603.04323v1 Announce Type: cross Abstract: Federated learning (FL) faces two structural tensions: gradient sharing enables data-reconstruction attacks, while non-IID client distributions degrade aggregation quality. We introduce PTOPOFL, a framework that addresses both challenges simultaneously by replacing gradient communication with topological descriptors derived from persistent homology (PH). Clients transmit only 48-dimensional PH feature vectors-compact shape summaries whose many-to-one structure makes inversion provably ill-posed-rather than model gradients. The server performs topology-guided personalised aggregation: clients are clustered by Wasserstein similarity between […]

Ver mais

Mirroring Stripe’s API in your database creates errors and extra work. Use the “Master and Mirror” approach: store only Stripe Customer IDs and subscription status in Django, handle updates via webhooks, and query Stripe live for billing details. This keeps your SaaS fast, accurate, and resilient to API changes while eliminating premium access bugs.

Ver mais

arXiv:2601.05437v1 Announce Type: new Abstract: Large language models (LLMs) often produce human-like moral judgments, but it is unclear whether this reflects an internal conceptual structure or superficial “moral mimicry.” Using Moral Foundations Theory (MFT) as an analytic framework, we study how moral foundations are encoded, organized, and expressed within two instruction-tuned LLMs: Llama-3.1-8B-Instruct and Qwen2.5-7B-Instruct. We employ a multi-level approach combining (i) layer-wise analysis of MFT concept representations and their alignment with human moral perceptions, (ii) pretrained sparse […]

Ver mais

arXiv:2602.23535v1 Announce Type: new Abstract: We study the statistical complexity of estimating partition functions given sample access to a proposal distribution and an unnormalized density ratio for a target distribution. While partition function estimation is a classical problem, existing guarantees typically rely on structural assumptions about the domain or model geometry. We instead provide a general, information-theoretic characterization that depends only on the relationship between the proposal and target distributions. Our analysis introduces the integrated coverage profile, a […]

Ver mais

arXiv:2601.08017v1 Announce Type: new Abstract: We show that for a variety of concepts in adapter-based vision-language models, the representations of their images and their text descriptions are meaningfully aligned from the very first layer. This contradicts the established view that such image-text alignment only appears in late layers. We show this using a new synthesis-based method inspired by DeepDream: given a textual concept such as “Jupiter”, we extract its concept vector at a given layer, and then use […]

Ver mais

arXiv:2602.15902v1 Announce Type: new Abstract: Long input sequences are central to in-context learning, document understanding, and multi-step reasoning of Large Language Models (LLMs). However, the quadratic attention cost of Transformers makes inference memory-intensive and slow. While context distillation (CD) can transfer information into model parameters, per-prompt distillation is impractical due to training costs and latency. To address these limitations, we propose Doc-to-LoRA (D2L), a lightweight hypernetwork that meta-learns to perform approximate CD within a single forward pass. Given […]

Ver mais

Building world models is essential for planning in real-world domains such as businesses. Since such domains have rich semantics, we can leverage world knowledge to effectively model complex action effects and causal relationships from limited data. In this work, we propose CASSANDRA, a neurosymbolic world modeling approach that leverages an LLM as a knowledge prior to construct lightweight transition models for planning. CASSANDRA integrates two components: (1) LLM-synthesized code to model deterministic features, and (2) LLM-guided structure learning […]

Ver mais

Demis: “[to get to AGI] maybe there’s one or two big innovations needed” Sam: “everything based off what we see today is that it will happen.” Ilya: “But is the belief really that if you just 100x the scale, everything would be transformed? I don’t think that’s true.” Dario: “If you just kind of like eyeball the rate at which these capabilities are increasing, it does make you think that we’ll get there by 2026 or 2027.” Jerry: […]

Ver mais