We study personalized multi-agent average reward TD learning, in which a collection of agents interacts with different environments and jointly learns their respective value functions. We focus on the setting where there exists a shared linear representation, and the agents’ optimal weights collectively lie in an unknown linear subspace. Inspired by the recent success of personalized federated learning (PFL), we study the convergence of cooperative single-timescale TD learning in which agents iteratively estimate the common subspace and local […]

Ver mais

arXiv:2601.20915v1 Announce Type: new Abstract: Federated Learning (FL) facilitates collaborative model training among distributed clients while ensuring that raw data remains on local devices.Despite this advantage, FL systems are still exposed to risks from malicious or unreliable participants. Such clients can interfere with the training process by sending misleading updates, which can negatively affect the performance and reliability of the global model. Many existing defense mechanisms rely on gradient inspection, complex similarity computations, or cryptographic operations, which introduce […]

Ver mais

Cross-site scripting (XSS) remains a persistent web security vulnerability, especially because obfuscation can change the surface form of a malicious payload while preserving its behavior. These transformations make it difficult for traditional and machine learning-based detection systems to reliably identify attacks. Existing approaches for generating obfuscated payloads often emphasize syntactic diversity, but they do not always ensure that the generated samples remain behaviorally valid. This paper presents a structured pipeline for generating and evaluating obfuscated XSS payloads using […]

Ver mais

arXiv:2601.21028v1 Announce Type: new Abstract: AI-generated media is radically changing the way content is both consumed and produced on the internet, and in no place is this potentially more visible than in sexual content. AI-generated sexual content (AIG-SC) is increasingly enabled by an ecosystem of individual AI developers, specialized third-party applications, and foundation model providers. AIG-SC raises a number of concerns from old debates about the line between pornography and obscenity, to newer debates about fair use and […]

Ver mais

arXiv:2604.02502v1 Announce Type: new Abstract: Lumbar Spinal Stenosis (LSS) diagnosis remains a critical clinical challenge, with diagnosis heavily dependent on labor-intensive manual interpretation of multi-view Magnetic Resonance Imaging (MRI), leading to substantial inter-observer variability and diagnostic delays. Existing vision-language models simultaneously fail to address the extreme class imbalance prevalent in clinical segmentation datasets while preserving spatial accuracy, primarily due to global pooling mechanisms that discard crucial anatomical hierarchies. We present an end-to-end Explainable Vision-Language Model framework designed to […]

Ver mais

Live Terraform refactors are risky because Terraform tracks resource addresses in state, not your intent. This guide shows how to safely move resources into modules with moved blocks, import existing infrastructure with import blocks, and add a small native test to confirm the refactor didn’t change the module contract or recreate production resources.

Ver mais

Working on a system that saves key context from multi-model conversations (across GPT, Gemini, Grok, Deepseek, Claude) to a persistent store. The memory layer is working – the interesting problem I’m now looking at is extracting “commitments” from unstructured conversation and attaching temporal context to them. The goal is session-triggered proactive recall: when a user logs in, the system surfaces relevant unresolved commitments from previous sessions without being prompted. The challenges I’m thinking through: How to reliably identify […]

Ver mais

I’m building a crowdsourced photo collection platform (contributors take photos with smartphones, we auto-label with YOLO/CLIP + enrich with 40+ metadata fields per image including weather, time, GPS, OCR). Before I decide what to collect first, I want to know: what image data do YOU wish existed but doesn’t? Some ideas I’m considering: – European street scenes (no dataset covers Switzerland/France) – Supermarket shelves with OCR-extracted prices – Analog utility meters – Restaurant menus with prices – EV […]

Ver mais

Recent research has shown that language models can learn to textit{reason}, often via reinforcement learning. Some work even trains low-rank parameterizations for reasoning, but conventional LoRA cannot scale below the model dimension. We question whether even rank=1 LoRA is necessary for learning to reason and propose TinyLoRA, a method for scaling low-rank adapters to sizes as small as one parameter. Within our new parameterization, we are able to train the 8B parameter size of Qwen2.5 to 91% accuracy […]

Ver mais