arXiv:2603.00629v1 Announce Type: new Abstract: Large time series models (LTMs) have emerged as powerful tools for universal forecasting, yet they often struggle with the inherent diversity and nonstationarity of real-world time series data, leading to an unsatisfactory trade-off between forecasting accuracy and generalization. Rather than continually finetuning new LTM instances for each domain, we propose a data-centric framework, time-series adaptive transformation optimization (TATO), that enables a single frozen pre-trained LTM to adapt to diverse downstream domains through an […]

Ver mais

The ongoing market downturn has forced many investors to reassess their portfolios. While major assets like XRP continue to trade under pressure amid broader macro uncertainty, a growing segment of holders appears to be reallocating capital toward earlier-stage opportunities. One project increasingly drawing attention in this environment is Mutuum Finance (MUTM), a DeFi protocol currently in presale. XRP Faces Consolidation as Market Momentum Slows XRP remains one of the largest cryptocurrencies by market capitalization, but like much of […]

Ver mais

The evolution of cloud computing and artificial intelligence has fundamentally transformed how enterprises build and scale technology platforms. Modern cloud infrastructure must handle millions of concurrent users across dozens of geographic regions while maintaining security, reliability, and performance standards that meet the demands of government agencies and Fortune 500 companies alike. Engineers working at this scale navigate complex distributed systems, automate buildout pipelines, and build sophisticated monitoring frameworks that can detect potential outages before they impact customers. The […]

Ver mais

Paper: https://arxiv.org/abs/2602.15950 TL;DR: Vision-Language Models achieve ~84% F1 reading binary grids rendered as text characters (. and #) but collapse to 29-39% F1 when the exact same grids are rendered as filled squares, despite both being images through the same visual encoder. The 34-54 point F1 gap replicates across Claude Opus, ChatGPT 5.2, and Gemini 3 Thinking. Hi everyone, I ran a simple experiment: generate fifteen 15×15 binary grids at varying density, render each as both text symbols […]

Ver mais

arXiv:2601.00221v1 Announce Type: new Abstract: The increasing complexity and interconnectedness of systems across various fields have led to a growing interest in studying complex networks, particularly Scale-Free (SF) networks, which best model real-world systems. This paper investigates the influence of clustering on the observability and controllability of complex SF networks, framing these characteristics in the context of structured systems theory. In this paper, we show that densely clustered networks require fewer driver and observer nodes due to better […]

Ver mais

arXiv:2601.02400v1 Announce Type: cross Abstract: Text-based causal inference increasingly employs textual data as proxies for unobserved confounders, yet this approach introduces a previously undertheorized source of bias: treatment leakage. Treatment leakage occurs when text intended to capture confounding information also contains signals predictive of treatment status, thereby inducing post-treatment bias in causal estimates. Critically, this problem can arise even when documents precede treatment assignment, as authors may employ future-referencing language that anticipates subsequent interventions. Despite growing recognition of […]

Ver mais

arXiv:2602.07226v1 Announce Type: new Abstract: In the era of Model-as-a-Service, organizations increasingly rely on third-party AI models for rapid deployment. However, the dynamic nature of emerging AI applications, the continual introduction of new datasets, and the growing number of models claiming superior performance make efficient and reliable validation of model services increasingly challenging. This motivates the development of sample-efficient performance estimators, which aim to estimate model performance by strategically selecting instances for labeling, thereby reducing annotation cost. Yet […]

Ver mais

arXiv:2603.02426v1 Announce Type: new Abstract: 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 […]

Ver mais

Reinforcement learning with verifiable rewards has driven recent advances in LLM post-training, in particular for reasoning. Policy optimization algorithms generate a number of responses for a given prompt and then effectively weight the corresponding gradients depending on the rewards. The most popular algorithms including GRPO, DAPO, and RLOO focus on ambiguous prompts, i.e., prompts with intermediate success probability, while downgrading gradients with very easy and very hard prompts. In this paper, we consider asymmetric prompt weightings that assign […]

Ver mais