Metaphors are a Source of Cross-Domain Misalignment of Large Reasoning Models

⋅

arXiv:2601.03388v1 Announce Type: new Abstract: Earlier research has shown that metaphors influence human’s decision making, which raises the question of whether metaphors also influence large language models (LLMs)’ reasoning pathways, considering their training data contain a large number of metaphors. In this work, we investigate the problem in the scope of the emergent misalignment problem where LLMs can generalize patterns learned from misaligned content in one domain to another domain. We discover a strong causal relationship between metaphors […]

Ver mais

Liked Liked

Navigating Crypto’s 2026 Reset: Why Retail-First Exchanges Are Winning 

⋅

Victoria, Seychelles, February 9, 2026 As Bitcoin trades below $69,000 following its October 2025 peak of $126,000, MEXC Chief Operating Officer Vugar Usi outlined why retail-focused exchanges are gaining ground in an increasingly institutionalized market during last week’s CoinGecko Meetup #33. Leading MEXC, the fastest-growing global cryptocurrency exchange redefining a user-first approach to digital assets through true zero-fee trading, Usi charted a strategic path forward that leverages retail strength in uncertain times. The smartest investors aren’t just getting […]

Ver mais

Liked Liked

SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model

⋅

arXiv:2601.21031v1 Announce Type: new Abstract: Current foundation model for photoplethysmography (PPG) signals is challenged by the intrinsic redundancy and noise of the signal. Standard masked modeling often yields trivial solutions while contrastive methods lack morphological precision. To address these limitations, we propose a Statistical-prior Informed Generative Masking Architecture (SIGMA-PPG), a generative foundation model featuring a Prior-Guided Adversarial Masking mechanism, where a reinforcement learning-driven teacher leverages statistical priors to create challenging learning paths that prevent overfitting to noise. We […]

Ver mais

Liked Liked

V-MORALS: Visual Morse Graph-Aided Estimation of Regions of Attraction in a Learned Latent Space

⋅

arXiv:2602.23524v1 Announce Type: new Abstract: Reachability analysis has become increasingly important in robotics to distinguish safe from unsafe states. Unfortunately, existing reachability and safety analysis methods often fall short, as they typically require known system dynamics or large datasets to estimate accurate system models, are computationally expensive, and assume full state information. A recent method, called MORALS, aims to address these shortcomings by using topological tools to estimate3DR-eEgnciodnesr of Attraction (ROA) in a low-dimensional latent space. However, MORALS […]

Ver mais

Liked Liked

The life of a prescription at Amazon Pharmacy

⋅

The life of a prescription at Amazon Pharmacy From pricing estimation and regulatory compliance to inventory management and chatbot assistants, machine learning models help Amazon Pharmacy customers stay healthy and save time and money. Conversational AI Alexandre Alves Anita Vila September 30, 01:32 PM October 02, 11:42 AM Pharmacies play a vital role in ensuring patients health, but the process of dispensing medications is far more complex than it may appear. At Amazon Pharmacy, we are using artificial […]

Ver mais

Liked Liked
The Illustrated DeepSeek-R1

The Illustrated DeepSeek-R1

⋅

DeepSeek-R1 is the latest resounding beat in the steady drumroll of AI progress. For the ML R&D community, it is a major release for reasons including: Thanks for reading Language Models & Co.! Subscribe for free to receive new posts and support my work. It is an open weights model with smaller, distilled versions and It shares and reflects upon a training method to reproduce a reasoning model like OpenAI O1. In this post, we’ll see how it […]

Ver mais

Liked Liked
Multimodal Large Language Models: Architectures, Training, and Real-World Applications

Multimodal Large Language Models: Architectures, Training, and Real-World Applications

⋅

Author(s): Hamza Boulahia Originally published on Towards AI. A breakdown of main architectures, training pipeline stages, and where current models actually work With the rise of AI Agents in these last few years, we reached what we could describe as an inflection point, where models can no longer afford to be confined to a single modality. Image created by the AuthorThis article explores the emergence of Multimodal Large Language Models (MLLMs), which integrate multiple forms of data such […]

Ver mais

Liked Liked

Finite-sample performance of the maximum likelihood estimator in logistic regression

⋅

arXiv:2411.02137v3 Announce Type: replace-cross Abstract: Logistic regression is a classical model for describing the probabilistic dependence of binary responses to multivariate covariates. We consider the predictive performance of the maximum likelihood estimator (MLE) for logistic regression, assessed in terms of logistic risk. We consider two questions: first, that of the existence of the MLE (which occurs when the dataset is not linearly separated), and second, that of its accuracy when it exists. These properties depend on both the […]

Ver mais

Liked Liked

HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialogue

⋅

arXiv:2601.19922v1 Announce Type: new Abstract: Supportive conversation depends on skills that go beyond language fluency, including reading emotions, adjusting tone, and navigating moments of resistance, frustration, or distress. Despite rapid progress in language models, we still lack a clear way to understand how their abilities in these interpersonal domains compare to those of humans. We introduce HEART, the first-ever framework that directly compares humans and LLMs on the same multi-turn emotional-support conversations. For each dialogue history, we pair […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2025