I’ve been getting a lot of questions about how I manage AI-assisted development and what exactly my workflow looks like when I am building features with Claude Code and Codex, so I decided to write this down, not just as a guide, but as a real experience from months of trial and error that changed the way I approach software development. The key insight? Stop treating AI as a single tool that does everything. Split the responsibilities. Make […]

Ver mais

In modern Retrieval-Augmented Generation (RAG) systems, handling large documents efficiently is critical. Embedding models have token limits that, when exceeded, can lead to incomplete processing or errors. This is where chunking becomes critical. By breaking large documents into smaller, manageable pieces, chunking ensures that information remains accessible, relevant, and optimized for retrieval and processing. In this blog post, we will dive deep into chunking techniques with Langformers, exploring all three Fixed-size, Semantic and Recursive chunking strategies — complete […]

Ver mais

Continual learning requires balancing plasticity and stability while mitigating catastrophic forgetting. Inspired by human dreaming as a mechanism for internal simulation and knowledge restructuring, we introduce Dream2Learn (D2L), a framework in which a model autonomously generates structured synthetic experiences from its own internal representations and uses them for self-improvement. Rather than reconstructing past data as in generative replay, D2L enables a classifier to create novel, semantically distinct dreamed classes that are coherent with its learned knowledge yet do […]

Ver mais

Cultural historian Thomas Berry issues a profound summons to reimagine humanity’s place within the living fabric of the Earth. He envisions a radical transformation—from a species that wounds its home to one that nurtures it—calling for the “resacralization of nature” and a renewal of our ecological consciousness. More than a philosophical reflection, Berry’s work is a moral and spiritual manifesto, demanding an overhaul of our ethics, politics, economics, and education. Only through this sweeping reorientation, he insists, can […]

Ver mais

arXiv:2606.18254v1 Announce Type: new Abstract: Human performance in digital control rooms is strongly influenced by interface characteristics, which shape visual search, cognitive processing, and motor execution. Accurate prediction of operator action time is therefore essential for ergonomic evaluation, interface design, and performance optimization in safety critical systems. However, existing approaches typically rely on extensive experimental data or black box models, limiting their interpretability and practical applicability. This study proposes ATIM (ACTR based Task Interface Model), a theory guided […]

Ver mais

arXiv:2601.12212v1 Announce Type: new Abstract: Inference time latency has remained an open challenge for real world applications of large language models (LLMs). State-of-the-art (SOTA) speculative sampling (SpS) methods for LLMs, like EAGLE-3, use tree-based drafting to explore multiple candidate continuations in parallel. However, the hyperparameters controlling the tree structure are static, which limits flexibility and efficiency across diverse contexts and domains. We introduce Reinforcement learning for Speculative Sampling (Re-SpS), the first reinforcement learning (RL)-based framework for draft tree […]

Ver mais

Membership inference attacks (MIAs) pose a serious threat to the privacy of machine learning models by allowing adversaries to determine whether a specific data sample was included in the training set. Although federated learning (FL) is widely regarded as a privacy-aware training paradigm due to its decentralized nature, recent evidence shows that the final global model can still leak sensitive membership information through black-box access. In this paper, we introduce Res-MIA, a novel training-free and black-box membership inference […]

Ver mais

arXiv:2601.04199v1 Announce Type: new Abstract: Medical Multimodal Large Language Models (Medical MLLMs) have achieved remarkable progress in specialized medical tasks; however, research into their safety has lagged, posing potential risks for real-world deployment. In this paper, we first establish a multidimensional evaluation framework to systematically benchmark the safety of current SOTA Medical MLLMs. Our empirical analysis reveals pervasive vulnerabilities across both general and medical-specific safety dimensions in existing models, particularly highlighting their fragility against cross-modality jailbreak attacks. Furthermore, […]

Ver mais

arXiv:2601.22355v1 Announce Type: new Abstract: We study the problem of quantifying how far an empirical distribution deviates from Gaussianity under the framework of optimal transport. By exploiting the cone geometry of the relative translation invariant quadratic Wasserstein space, we introduce two novel geometric quantities, the relative Wasserstein angle and the orthogonal projection distance, which provide meaningful measures of non-Gaussianity. We prove that the filling cone generated by any two rays in this space is flat, ensuring that angles, […]

Ver mais

arXiv:2604.02390v1 Announce Type: new Abstract: Audio-visual navigation tasks require agents to locate and navigate toward continuously vocalizing targets using only visual observations and acoustic cues. However, existing methods mainly rely on simple feature concatenation or late fusion, and lack an explicit discrete representation of the target’s relative position, which limits learning efficiency and generalization. We propose Spatial-Aware Conditioned Fusion (SACF). SACF first discretizes the target’s relative direction and distance from audio-visual cues, predicts their distributions, and encodes them […]

Ver mais