Forecasting financial asset returns is challenging due to low signal-to-noise ratios, non-stationarity and heavy-tailed distributions. We benchmark 16 deep learning architectures for time series forecasting, including Transformers, State Space Models (SSMs), xLSTMs and recurrent hybrids, on a 15-year daily futures data...
Adir Saly-Kaufmann, Kieran Wood, Jan-Peter Calliess et al.· 0 citations
When a text description is extended with an additional detail, image-text similarity should drop if that detail is wrong. We show that CLIP-style dual encoders often violate this intuition: appending a plausible but incorrect object or relation to an otherwise correct description can increase the similarity score. We c...
Bora Kargi, Arnas Uselis, Seong Joon Oh· 0 citations
Varying the number of neurons while preserving function is difficult because neural networks' dense connectivity creates strong computational interdependence between units. Elementwise activation functions, particularly their limited equivariance properties, are identified as a central hurdle to achieving this. We prop...
Large Language Models (LLMs) are becoming increasingly autonomous assistants, capable of accomplishing series of complex tasks by interacting with open world domains such as software databases and the internet. This presents great opportunity but also great risk: open domains routinely present opportunities for autonom...
Sasha Robinson, Katherine M. Collins, Ilia Sucholutsky et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Accurate brain-age estimation from structural MRI provides a valuable biomarker for studying healthy aging and neurodegenerative disease. We propose BrainRotViT (Brain ResNet over trained Vision Transformer), a two-stage, slice-based (2.5D) framework that approximates volumetric context while combining the strengths of...
Wasif Jalal, Md Nafiu Rahman, Atif Hasan Rahman et al.· 0 citations
This work focuses on bipartite quantum states and presents a data-driven approach to entanglement classification using transformer-based neural networks, successfully adapts transformers for quantum state analysis, demonstrating their ability to systematically identify entanglement in bipartite systems.
Przemysław Sekuła, M. Romaszewski, P. Głomb et al.· International Conference on...· 1 citation
Inverse problems in physical or biological sciences often involve recovering an unknown parameter that is random. The sought-after quantity is a probability distribution of the unknown parameter, that produces data that aligns with measurements. Consequently, these problems are naturally framed as stochastic inverse pr...
This technical note explains three mechanisms behind the exponents of dense-to-equivariant excess-loss ratios, which cover visual resolution, conformational coverage and correlated-sample precision.
Diffusion models have emerged as the foundation of modern generative systems, yet their high memorization capacity raises privacy concerns. While differentially private (DP) training provides formal guarantees, it comes at a cost in sample quality. In this work, we study a complementary question: how much privacy loss...
William Cheng, Dongjun Kim, Mijung Park· 0 citations
End-to-end training is best suited to settings where resources are genuinely scarce and feasibility matters, and leads the delay-adjusted policy value wherever capacity is scarce, once a waiting period carries even a small cost.
M. Haghi, Mahdi Salmani, Nima Kelidari et al.· 0 citations
Language models can perform a wide range of tasks at various levels of abstraction. They flexibly infer tasks from context, execute multiple tasks simultaneously, and select among competing goals. Understanding and controlling how models represent these tasks is central to aligning them with human objectives. Researche...
Maximilian S. Ernst (Max Planck School of Cognition, Center for Lifespan Psychology Max Planck Institute for Human Development, Machine Learning Group Technische Universit\"at Berlin) et al.· 0 citations
Online learning in non-stationary streams is often formulated as tracking a point estimate, although many applications require predicting the full data-generating distribution. We study online distributional prediction under drift and bounded causal adversarial corruption. Candidate laws are represented by variable-siz...
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.
MIT News · Artificial Intelligence· news.mit.eduOct 28, 2026
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
MIT News · Artificial Intelligence· news.mit.eduOct 27, 2026
Prabha Jha used her experience with MIT Open Learning’s program for senior executives to develop AI solutions for her employer, Verizon, and to write a book.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
