arXiv:2601.05330v1 Announce Type: new Abstract: Predicting enzyme-substrate interactions has long been a fundamental problem in biochemistry and metabolic engineering. While existing methods could leverage databases of expert-curated enzyme-substrate pairs for models to learn from known pair interactions, the databases are often sparse, i.e., there are only limited and incomplete examples of such pairs, and also labor-intensive to maintain. This lack of sufficient training data significantly hinders the ability of traditional enzyme prediction models to generalize to unseen interactions. […]

Ver mais

Preliminaries ‘Mixtures of Gaussians’ Basic machine learning concepts Combining Models1 The mixture of Gaussians had been discussed in the post ‘Mixtures of Gaussians’. It was used to introduce the ‘EM algorithm’ but it gave us the inspiration of improving model performance. All models we have studied, besides neural networks, are all single-distribution models. That is just like that, to solve a problem we invite an expert who is very good at this kind of problem, then we just […]

Ver mais

Safety Is Not a Switch, It Is a Process For a long time, AI safety seemed like something you could install. You specified constraints, tested for edge cases, built guardrails, and deployed with confidence. This paradigm was fine when systems were largely static. It starts to break when systems change. Today, AI systems do not merely follow pre-programmed logic. They learn. They adapt. They interact with other agents. In multi-agent settings, systems negotiate, compete, coordinate, and sometimes, game […]

Ver mais

arXiv:2602.08862v1 Announce Type: cross Abstract: We give a randomized online algorithm that guarantees near-optimal $widetilde O(sqrt T)$ expected swap regret against any sequence of $T$ adaptively chosen Lipschitz convex losses on the unit interval. This improves the previous best bound of $widetilde O(T^{2/3})$ and answers an open question of Fishelson et al. [2025b]. In addition, our algorithm is efficient: it runs in $mathsf{poly}(T)$ time. A key technical idea we develop to obtain this result is to discretize the […]

Ver mais

arXiv:2603.28831v1 Announce Type: new Abstract: Combining different types of agents in uncrewed vehicle (UV) swarms has emerged as an approach to enhance mission resilience and operational capabilities across a wide range of applications. This study offers a systematic framework for grouping different types of swarms based on three main factors: agent nature (behavior and function), hardware structure (physical configuration and sensing capabilities), and operational space (domain of operation). A literature review indicates that strategic heterogeneity significantly improves swarm […]

Ver mais

arXiv:2604.15336v1 Announce Type: new Abstract: Large language models (LLMs) enable increasingly capable tutoring-style conversational agents, yet effective tutoring requires sensitivity to learners’ affective and cognitive states beyond text alone. Facial expressions provide immediate and practical cues of confusion, frustration, or engagement, but remain underexplored in LLM-driven tutoring. We investigate whether facial-expression-aware signals can improve empathetic tutoring responses through prompt-level integration, without end-to-end retraining. We build a scalable simulated tutoring environment where a student agent exhibits diverse facial behaviors […]

Ver mais

With the rapid development of the Internet of Things (IoT), AI model training on private data such as human sensing data is highly desired. Federated learning (FL) has emerged as a privacy-preserving distributed training framework for this purpuse. However, the data heterogeneity issue among IoT devices can significantly degrade the model performance and convergence speed in FL. Existing approaches limit in fixed client selection and aggregation on cloud server, making the privacy-preserving extraction of client-specific information during local […]

Ver mais

arXiv:2603.15655v1 Announce Type: new Abstract: In decentralized Multi-Agent Reinforcement Learning (MARL), steganographic collusion — where agents develop private protocols to evade monitoring — presents a critical AI safety threat. Existing defenses, limited to behavioral or reward layers, fail to detect coordination in latent communication channels. We introduce the Dynamic Representational Circuit Breaker (DRCB), an architectural defense operating at the optimization substrate. Building on the AI Mother Tongue (AIM) framework, DRCB utilizes a Vector Quantized Variational Autoencoder (VQ-VAE) bottleneck […]

Ver mais