Understanding how LLMs work in their most fundamental phase helps you understand how they behave and why they behave like that. Building one helps debunk any theory of consciousness in LLMs, but to do so, you would have to choose carefully what text you are training the LLM with— the book “Frankenstein” is the first thought I had in my mind, for some ironic reason. This tutorial will guide you through all the steps of building an LLM […]

Ver mais

arXiv:2603.18404v2 Announce Type: replace Abstract: Causal representation learning (CRL) aims to learn low-dimensional causal latent variables from high-dimensional observations. While identifiability has been extensively studied for CRL, estimation has been less explored. In this paper, we explore the use of empirical Bayes (EB) to estimate causal representations. In particular, we consider the problem of learning from data from multiple domains, where differences between domains are modeled by interventions in a shared underlying causal model. Multi-domain CRL naturally poses […]

Ver mais

Visual speaker recognition based on lip motion offers a silent, hands-free, and behavior-driven biometric solution that remains effective even when acoustic cues are unavailable. Compared to traditional methods that rely heavily on appearance-dependent representations, lip motion encodes subject-specific behavioral dynamics driven by consistent articulation patterns and muscle coordination, offering inherent stability across environmental changes. However, capturing these robust, fine-grained dynamics is challenging for conventional frame-based cameras due to motion blur and low dynamic range. To exploit the intrinsic […]

Ver mais

arXiv:2601.09879v1 Announce Type: new Abstract: Recent progress in medical vision-language models (VLMs) has achieved strong performance on image-level text-centric tasks such as report generation and visual question answering (VQA). However, achieving fine-grained visual grounding and volumetric spatial reasoning in 3D medical VLMs remains challenging, particularly when aiming to unify these capabilities within a single, generalizable framework. To address this challenge, we proposed MedVL-SAM2, a unified 3D medical multimodal model that concurrently supports report generation, VQA, and multi-paradigm segmentation, […]

Ver mais

arXiv:2510.25154v2 Announce Type: replace-cross Abstract: Bayesian inference provides principled uncertainty quantification but is often limited by challenges of prior and likelihood elicitation. The martingale posterior (MGP) (Fong et al., 2023) offers an alternative by replacing these requirements with a predictive rule. Additionally MGP focuses inference on parameters defined through a loss function. This framework is especially resonant in the era of foundation transformers; practitioners increasingly leverage models like TabPFN for their state-of-the-art capabilities, yet often require epistemic uncertainty […]

Ver mais

Riyadh is quickly emerging into a dynamic hub of global influence and innovation. Guided by Vision 2030, Saudi Arabia is embracing forward-thinking policies, entrepreneurship, and technology to expand its economy and promote a creativity culture. Known for its commercial and political significance primarily, Riyadh now redefines its personality as an innovation center, attracting global startups, investors, and talent. Now, the city stands as a testament to the power of planning, progress, and ambition to shape a futuristic, dynamic […]

Ver mais

Designing reward functions remains a central challenge in reinforcement learning (RL) for healthcare, where outcomes are sparse, delayed, and difficult to specify. While structured data capture physiological states, they often fail to reflect the overall quality of a patient’s clinical trajectory, including recovery dynamics, treatment burden, and stability. Clinical narratives, in contrast, summarize longitudinal reasoning and implicitly encode evaluations of treatment effectiveness. We propose Clinical Narrative-informed Preference Rewards (CN-PR), a framework for learning reward functions directly from discharge […]

Ver mais

arXiv:2601.21081v1 Announce Type: new Abstract: Multimodal models for text-to-image generation have achieved strong visual fidelity, yet they remain brittle under compositional structural constraints-notably generative numeracy, attribute binding, and part-level relations. To address these challenges, we propose Shape-of-Thought (SoT), a visual CoT framework that enables progressive shape assembly via coherent 2D projections without external engines at inference time. SoT trains a unified multimodal autoregressive model to generate interleaved textual plans and rendered intermediate states, helping the model capture shape-assembly […]

Ver mais