technocracy

How Blitz scaled their game coaching app with lower latency and leaner operations Blitz is a fast-growing startup that provides personalized coaching for games such as League of Legends, Valorant, and Fortnite. They aim to help gamers become League of Legends legends through real-time insights and post-match analysis. While players play, the app does quite a lot of work. It captures live match data, analyzes it quickly, and uses it for real-time game screen overlays plus personalized post-game coaching. […]

Ver mais

Interpretable machine learning is essential in high-stakes domains where decision-making requires accountability, transparency, and trust. While rule-based models offer global and exact interpretability, learning rule sets that simultaneously achieve high predictive performance and low, human-understandable complexity remains challenging. To address this, we introduce TT-Sparse, a flexible neural building block that leverages differentiable truth tables as nodes to learn sparse, effective connections. A key contribution of our approach is a new soft TopK operator with straight-through estimation for learning […]

Ver mais

Current reinforcement learning objectives for large-model reasoning primarily focus on maximizing expected rewards. This paradigm can lead to overfitting to dominant reward signals, while neglecting alternative yet valid reasoning trajectories, thereby limiting diversity and exploration. To address this issue, we introduce Learning Advantage Distributions (LAD), a distribution-matching framework that replaces advantage maximization with learning the advantage-induced distribution. By establishing the equivalence between the optimal policy update and an advantage-based target distribution, we derive a practical LAD objective formulated […]

Ver mais

arXiv:2604.05111v1 Announce Type: new Abstract: Steerable needles have the potential to improve interstitial brachytherapy by enabling curved trajectories that avoid sensitive anatomical structures. However, existing modeling and control approaches are primarily developed for custom needle designs and are not directly applicable to stylets compatible with commercially available clinical needles. This paper presents a bilinear model predictive control (MPC) framework for a tendon-driven steerable stylet integrated with a standard brachytherapy needle. textcolor{black}{A geometric bilinear model is formulated with three […]

Ver mais

arXiv:2601.09805v1 Announce Type: new Abstract: Modern logical reasoning with LLMs primarily relies on employing complex interactive frameworks that decompose the reasoning process into subtasks solved through carefully designed prompts or requiring external resources (e.g., symbolic solvers) to exploit their strong logical structures. While interactive approaches introduce additional overhead, hybrid approaches depend on external components, which limit their scalability. A non-interactive, end-to-end framework enables reasoning to emerge within the model itself — improving generalization while preserving analyzability without any […]

Ver mais

arXiv:2604.14216v1 Announce Type: new Abstract: Predicting post-surgical seizure outcomes in pharmacoresistant epilepsy is a clinical challenge. Conventional deep-learning approaches operate on static, single-timepoint pre-operative scans, omitting longitudinal morphological changes. We propose emph{Neuro-Oracle}, a three-stage framework that: (i) distils pre-to-post-operative MRI changes into a compact 512-dimensional trajectory vector using a 3D Siamese contrastive encoder; (ii) retrieves historically similar surgical trajectories from a population archive via nearest-neighbour search; and (iii) synthesises a natural-language prognosis grounded in the retrieved evidence using […]

Ver mais

arXiv:2602.05230v1 Announce Type: cross Abstract: Linear attention methods offer Transformers $O(N)$ complexity but typically underperform standard softmax attention. We identify two fundamental limitations affecting these approaches: the restriction to convex combinations that only permits additive information blending, and uniform accumulated weight bias that dilutes attention in long contexts. We propose Zero-Sum Linear Attention (ZeroS), which addresses these limitations by removing the constant zero-order term $1/t$ and reweighting the remaining zero-sum softmax residuals. This modification creates mathematically stable weights, […]

Ver mais

arXiv:2601.22367v1 Announce Type: new Abstract: Generalized Bayesian Inference (GBI) tempers a loss with a temperature $beta>0$ to mitigate overconfidence and improve robustness under model misspecification, but existing GBI methods typically rely on costly MCMC or SDE-based samplers and must be re-run for each new dataset and each $beta$ value. We give the first fully amortized variational approximation to the tempered posterior family $p_beta(theta mid x) propto pi(theta),p(x mid theta)^beta$ by training a single $(x,beta)$-conditioned neural posterior estimator $q_phi(theta […]

Ver mais