technocracy

The Day Your LLM Stops Talking and Starts Doing There’s a moment in every LLM project where you realize the “chat” part is the easy bit. The hard part is everything that happens between the user request and the final output: gathering missing facts, choosing which tools to call (and in what order), handling failures, remembering prior decisions, and not spiraling into confident nonsense when the world refuses to match the model’s assumptions. That’s the moment you’re no […]

Ver mais

Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability that modern language models increasingly require but do not natively encode. While prior work uses reinforcement learning or test-time training, planning remains external to the model architecture. We formulate reasoning as optimal control and introduce the Test-Time Control (TTC) layer, which performs finite-horizon LQR planning over latent states at inference time, represents a value […]

Ver mais

Class-Incremental Learning (CIL) requires models to learn new classes without forgetting old ones. A common method is to freeze a pre-trained model and train a new, lightweight adapter for each task. While this prevents forgetting, it treats the learned knowledge as a simple, unstructured collection and fails to use the relationships between tasks. To this end, we propose the Semantic-guided Adaptive Expert Forest (SAEF), a new method that organizes adapters into a structured hierarchy for better knowledge sharing. […]

Ver mais

We study a purely local inverse problem for non-reversible Randers metrics ( F = |cdot|_g + beta ) defined on smooth oriented surfaces. Using only the lengths of sufficiently small closed curves around a point ( p ), we prove that the exterior derivative ( dbeta(p) ) can be uniquely and stably recovered. Moreover, we establish that ( dbeta(p) ) is the only second-order local invariant retrievable from such local length measurements. Our approach is entirely metric-based, independent […]

Ver mais

Deep reinforcement learning (DRL) has driven major advances in autonomous control. Still, standard Deep Q-Network (DQN) agents tend to rely on fixed learning rates and uniform update scaling, even as updates are modulated by temporal-difference (TD) error. This rigidity destabilizes convergence, especially in sparse-reward settings where feedback is infrequent. We introduce Deep Intrinsic Surprise-Regularized Control (DISRC), a biologically inspired augmentation to DQN that dynamically scales Q-updates based on latent-space surprise. DISRC encodes states via a LayerNorm-based encoder and […]

Ver mais

arXiv:2601.00186v1 Announce Type: new Abstract: This paper tackles the pressing challenge of preserving semantic meaning in communication systems constrained by limited bandwidth. We introduce a novel reinforcement learning framework that achieves per-dimension unequal error protection via adaptive repetition coding. Central to our approach is a composite semantic distortion metric that balances global embedding similarity with entity-level preservation, empowering the reinforcement learning agent to allocate protection in a context-aware manner. Experiments show statistically significant gains over uniform protection, achieving […]

Ver mais

arXiv:2602.10305v1 Announce Type: new Abstract: Reward shaping has been applied widely to accelerate Reinforcement Learning (RL) agents’ training. However, a principled way of designing effective reward shaping functions, especially for complex continuous control problems, remains largely under-explained. In this work, we propose to automatically learn a reward shaping function for continuous control problems from offline datasets, potentially contaminated by unobserved confounding variables. Specifically, our method builds upon the recently proposed causal Bellman equation to learn a tight upper […]

Ver mais

The Challenge: IAM Role Proliferation in Multi-Tenant Architectures When building multi-tenant Kubernetes applications that require AWS resource access, teams traditionally face a difficult choice: either create separate IAM roles for each tenant (leading to IAM role sprawl) or implement complex application-level access controls. With AWS’s default limit of 1,000 IAM roles per account, this becomes a critical scalability bottleneck for platforms serving hundreds or thousands of tenants. Consider a typical multi-tenant SaaS platform running on Amazon EKS where […]

Ver mais

arXiv:2602.07207v1 Announce Type: new Abstract: We propose a novel recommender framework, MuSTRec (Multimodal and Sequential Transformer-based Recommendation), that unifies multimodal and sequential recommendation paradigms. MuSTRec captures cross-item similarities and collaborative filtering signals, by building item-item graphs from extracted text and visual features. A frequency-based self-attention module additionally captures the short- and long-term user preferences. Across multiple Amazon datasets, MuSTRec demonstrates superior performance (up to 33.5% improvement) over multimodal and sequential state-of-the-art baselines. Finally, we detail some interesting facets […]

Ver mais

This work introduces a novel approach for the joint selection of model structure and parameter learning for nonlinear dynamical systems identification. Focusing on a specific Recurrent Neural Networks (RNNs) family, i.e., Nonlinear Auto-Regressive with eXogenous inputs Echo State Networks (NARXESNs), the method allows to simultaneously select the optimal model class and learn model parameters from data through a new set-membership (SM) based procedure. The results show the effectiveness of the approach in identifying parsimonious yet accurate models suitable […]

Ver mais