arXiv:2601.22230v1 Announce Type: new Abstract: Test-time scaling for code generation commonly relies on Best-of-N selection, in which multiple candidate solutions are sampled from a base model, and the best one is selected by an LLM judge. However, training reliable LLM judges is challenging due to severe distribution shifts, including imbalances between easy and hard problems, mismatches between training tasks and evaluation benchmarks, and trajectory mismatch arising from training data generated by cheaper models whose behavior differs from that […]

Ver mais

We present cEntMax, an information-theoretic framework for training set optimization that selects classwise informative samples via cross-entropy divergence to prototype pivots. Under a noisy-channel generative view and local linearity of deep networks, the method connects predictive entropy, Fisher information, and G-optimal coverage. Experiments on EMNIST and KMNIST show faster convergence, lower validation loss, and greater stability than random sampling, especially for moderate sampling fractions.

Ver mais

I’m designing a web-based document OCR system and would like advice on the appropriate frontend, backend, database, and deployment setup. The system will be hosted and will support two user roles: a general user who uploads documents and reviews OCR results, and an admin who manages users and documents. There are five document types. Two document types have varying layouts, but I only need to OCR the person’s name and the document type so it can be matched […]

Ver mais

arXiv:2601.19920v1 Announce Type: new Abstract: Binary Neural Networks (BNNs), where weights and activations are constrained to binary values (+1, -1), are a highly efficient alternative to traditional neural networks. Unfortunately, typical BNNs, while binarizing linear layers (matrix-vector multiplication), still implement other network layers (batch normalization, softmax, output layer, and sometimes the input layer of a convolutional neural network) in full precision. This limits the area and energy benefits and requires architectural support for full precision operations. We propose […]

Ver mais

This thesis introduces Nexa, a blockchain architecture designed to balance the critical trade-offs between security, scalability, and decentralization in Electronic Health Record (EHR) systems. To address the blockchain trilemma (RQ1), Nexa strategically combines Avalanche’s high-performance public blockchain with decentralized IPFS storage, optimizing for the high throughput and low finality required in healthcare. To mitigate risks from centralized key management (RQ2), Nexa implements a distributed threshold cryptography scheme using Elliptic Curve Diffie-Hellman (ECDH), ChaCha20-Poly1305, and Shamir’s Secret Sharing (SSS). […]

Ver mais

Standard deep learning relies on Backpropagation (BP), which is constrained by biologically implausible weight symmetry and suffers from significant gradient interference within dense representations. To mitigate these bottlenecks, we propose Selective Adaptive Learning (SAL), a training method that combines selective parameter activation with adaptive area partitioning. Specifically, SAL decomposes the parameter space into mutually exclusive, sample-dependent regions. This decoupling mitigates gradient interference across divergent semantic patterns and addresses explicit weight symmetry requirements through our refined feedback alignment. Empirically, […]

Ver mais

Table of Links Abstract and 1. Introduction Some recent trends in theoretical ML 2.1 Deep Learning via continuous-time controlled dynamical system 2.2 Probabilistic modeling and inference in DL 2.3 Deep Learning in non-Euclidean spaces 2.4 Physics Informed ML Kuramoto model 3.1 Kuramoto models from the geometric point of view 3.2 Hyperbolic geometry of Kuramoto ensembles 3.3 Kuramoto models with several globally coupled sub-ensembles Kuramoto models on higher-dimensional manifolds 4.1 Non-Abelian Kuramoto models on Lie groups 4.2 Kuramoto models […]

Ver mais

Mobile Fortify, the new app used by Immigration and Customs Enforcement (ICE) to use face recognition technology (FRT) to identify people during street encounters, is an affront to the rights and dignity of migrants and U.S. citizens alike. That’s why a coalition of privacy, civil liberties and civil rights organizations are demanding the Department of Homeland Security (DHS) shut down the use of Mobile Fortify, release the agency’s privacy analyses of the app, and clarify the agency’s policy […]

Ver mais