· ai
2025년의 AI 5대 뉴스
2025년 IT업계를 수놓은 뉴스는 온통 인공지능AI이었다. 연초부터 연말까지 AI 관련 소식이 연일......
-
- · ai
ML Systems: The Part They Skip in the Diagram
The Unspoken Reality of Production ML “This classic meme, in all its simplicity, explains more about ML systems in organizations than most articles you’ll find...
- · ai
How I Found 1,370 Fraudsters Hiding in Our Data (And Saved My Company $51,000)
Tuesday, 9:14 AM My manager's message was short: > “We need to talk about fraud losses. My office.” That’s how it started—three CSV files, millions of transacti...
- · ai
[Paper] Training AI Co-Scientists Using Rubric Rewards
AI co-scientists are emerging as a tool to assist human researchers in achieving their research goals. A crucial feature of these AI co-scientists is the abilit...
- · ai
[Paper] Eliciting Behaviors in Multi-Turn Conversations
Identifying specific and often complex behaviors from large language models (LLMs) in conversational settings is crucial for their evaluation. Recent work propo...
- · ai
[Paper] Bellman Calibration for V-Learning in Offline Reinforcement Learning
We introduce Iterated Bellman Calibration, a simple, model-agnostic, post-hoc procedure for calibrating off-policy value predictions in infinite-horizon Markov ...
- · ai
[Paper] Multilingual Hidden Prompt Injection Attacks on LLM-Based Academic Reviewing
Large language models (LLMs) are increasingly considered for use in high-impact workflows, including academic peer review. However, LLMs are vulnerable to docum...
- · ai
[Paper] Web World Models
Language agents increasingly require persistent worlds in which they can act, remember, and learn. Existing approaches sit at two extremes: conventional web fra...
- · ai
[Paper] End-to-End Test-Time Training for Long Context
We formulate long-context language modeling as a problem in continual learning rather than architecture design. Under this formulation, we only use a standard a...
- · software
Cómo 'Vemos' los Datos: Por Qué tus Gráficos Engañan y Cómo Usar PCA para Arreglarlo
Una guía técnica sobre cómo reducir dimensiones y acelerar tus modelos sin perder información crítica. El problema típico Como mentores en Python Baires, vemos...
- · ai
[Paper] Calibrated Multi-Level Quantile Forecasting
We present an online method for guaranteeing calibration of quantile forecasts at multiple quantile levels simultaneously. A sequence of α-level quantile foreca...
- · ai
[Paper] Random Controlled Differential Equations
We introduce a training-efficient framework for time-series learning that combines random features with controlled differential equations (CDEs). In this approa...