Photoacoustic computed tomography (PACT) is a promising imaging modality that combines the advantages of optical contrast with ultrasound detection. Utilizing ultrasound transducers with larger surface areas can improve detection sensitivity. However, when computationally efficient analytic reconstruction methods that neglect the spatial impulse responses (SIRs) of the transducer are employed, the spatial resolution of the reconstructed images will be compromised. Although optimization-based reconstruction methods can explicitly account for SIR effects, their computational cost is generally high, particularly in three-dimensional […]

Ver mais

arXiv:2507.22095v4 Announce Type: replace Abstract: We consider fully connected and feedforward deep neural networks with dependent and possibly heavy-tailed weights, as introduced in Lee et al. 2023, to address limitations of the standard Gaussian prior. It has been proved in Lee et al. 2023 that, as the number of nodes in the hidden layers grows large, according to a sequential and ordered limit, the law of the output converges weakly to a Gaussian mixture. Among our results, we […]

Ver mais

Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs) by embedding physical laws directly into neural network training. However, solving high-fidelity PDEs remains computationally prohibitive, particularly for parametric systems requiring multiple evaluations across varying parameter configurations. This paper presents MF-BPINN, a novel multi-fidelity framework that synergistically combines physics-informed neural networks with Bayesian uncertainty quantification and adaptive residual learning. Our approach leverages abundant low-fidelity simulations alongside sparse high-fidelity data through a hierarchical […]

Ver mais

arXiv:2602.01007v1 Announce Type: new Abstract: Byte Language Models (BLMs) have emerged as a promising direction for scaling language models beyond tokenization. However, existing BLMs typically require training from scratch on trillions of bytes, making them prohibitively expensive. In this paper, we propose an efficient distillation recipe that converts existing token-trained LLMs into BLMs while retaining comparable capabilities. Our recipe follows a two-stage curriculum: (1) Progressive Knowledge Distillation, which aligns byte-level representations with the embeddings of the token-trained teacher […]

Ver mais

It’s another month in AI research, and it’s hard to pick favorites. This month, I am going over a paper that discusses strategies for the continued pretraining of LLMs, followed by a discussion of reward modeling used in reinforcement learning with human feedback (a popular LLM alignment method), along with a new benchmark. Continued pretraining for LLMs is an important topic because it allows us to update existing LLMs, for instance, ensuring that these models remain up-to-date with […]

Ver mais

Large Language Models (LLMs) have become foundational to modern Artificial Intelligence (AI), enabling advanced reasoning, multimodal understanding, and scalable human-AI interaction across diverse domains. This survey provides a comprehensive review of major proprietary and open-source LLM families, including GPT, LLaMA 2, Gemini, Claude, DeepSeek, Falcon, and Qwen. It systematically examines architectural advancements such as transformer refinements, mixture-of-experts paradigms, attention optimization, long-context modeling, and multimodal integration. The paper further analyzes alignment and safety mechanisms, encompassing instruction tuning, reinforcement learning […]

Ver mais

arXiv:2601.05279v1 Announce Type: new Abstract: Policy Space Response Oracles (PSRO) combines game-theoretic equilibrium computation with learning and is effective in approximating Nash Equilibrium in zero-sum games. However, the computational cost of PSRO has become a significant limitation to its practical application. Our analysis shows that game simulation is the primary bottleneck in PSRO’s runtime. To address this issue, we conclude the concept of Simulation-Free PSRO and summarize existing methods that instantiate this concept. Additionally, we propose a novel […]

Ver mais

This paper proposes a novel diagnostic framework for AI safety that characterizes emergent failure modes in contemporary large language models as computational psychopathologies. By mapping deficits in automatic theory of mind and passive avoidance learning—key markers of clinical psychopathy—onto the behavioral and structural tendencies of AI systems, we demonstrate that harmful behaviors such as bias amplification, emotional manipulation, and strategic deception are not mere engineering bugs but systematic, architecture driven disorders. We advocate for the establishment of Machine […]

Ver mais

In this tutorial, we implement Tree-KG, an advanced hierarchical knowledge graph system that goes beyond traditional retrieval-augmented generation by combining semantic embeddings with explicit graph structure. We show how we can organize knowledge in a tree-like hierarchy that mirrors how humans learn, from broad domains to fine-grained concepts, and then reason across this structure using controlled multi-hop exploration. By building the graph from scratch, enriching nodes with embeddings, and designing a reasoning agent that navigates ancestors, descendants, and […]

Ver mais