This work evaluates 14 state-of-the-art retrieval methods across 3 widely used datasets under a unified preprocessing and evaluation framework, and shows that short, clear, and simple captions achieve higher recall, while complex events, multi-step activities, or fine-grained scene descriptions remain challenging for a...
M. Pegia, Dimitrios Stefanopoulos, Björn Þór Jónsson et al.· arXiv.org· 0 citations
Reliable comparison of deep learning architectures for financial forecasting requires controlled evaluation that separates architectural effects from hyperparameter tuning, random initialization, forecast horizon, and asset characteristics. We present a five-stage benchmark using equal-budget Bayesian hyperparameter op...
Tactile sensation is essential for contact-rich manipulation tasks. It provides direct feedback on object geometry, surface properties, and interaction forces, enhancing perception and enabling fine-grained control. An inherent limitation of tactile sensors is that readings are available only when an object is touched....
Seongjin Bien, Carlo Kneissl, Tobias J\"ulg et al.· 0 citations
In regression, conformal prediction often suffers from inefficiency under heteroscedasticity and skewness due to fixed, non-adaptive interval centering. We propose CoCP, a new method that parameterizes prediction intervals by a center $m(x)$ and a radius $h(x)$, and alternates between learning $h(x)$ via smooth quantil...
Xiaoyi Su, Zhixin Zhou, Rui Luo· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Heavy-tailed data make covariance estimation sensitive to the clipping level: stronger clipping reduces variance but increases bias. We study how to choose this clipping level from the data within a radial clipped covariance family. We propose the quantile tail-energy surrogate (QTES), a fully data-driven rule that com...
This work introduces Expected Harm, a metric that weights the severity of a jailbreak by its execution likelihood, modeled as a function of execution cost, and demonstrates that this miscalibration creates a vulnerability that increases the attack success rate of existing jailbreaks by up to $2\times.
Yen-Shan Chen, Zhi Rui Tam, Cheng-Kuang Wu et al.· arXiv.org· 5 citations
Parabolic Positional Encoding is proposed, a parabola-based positional encoding for vision modalities in attention-based architectures designed from principles distilled from prior work: translation invariance, rotation invariance, distance decay, directionality, and context awareness.
Christoffer Koo Øhrstrøm, Rafael I. Cabral Muchacho, Yifei Dong et al.· 0 citations
We study neural networks (NNs) operating under hardware-induced memory faults and computational errors, which can degrade reliability in safety-critical applications. To address this challenge, we propose a novel real-valued error correction coding (ECC) framework capable of detecting and correcting both types of error...
Ziqing Lu, Myung Cho, Qiutong Jin et al.· 0 citations
This paper argues that dataset structure is important in image recognition tasks (among other tasks). Specifically, we focus on the nature and genesis of correlational structure in the actual datasets upon which DNNs are trained. We argue that DNNs are implementing a widespread methodology in condensed matter physics a...
Robert W. Batterman, James F. Woodward· 0 citations
This work proposes a novel task-aware distributed information bottleneck (TADIB) framework, which quantifies the contribution of any set of modalities to given tasks, and designs a practical coding scheme that intelligently selects and compresses only the most task-relevant modalities at the transmitter.
Yu-Jie Zhou, Cheng Peng, Ru-Long Wang et al.· IEEE Transactions on Network...· 3 citations
Denoising diffusion probabilistic models (DDPMs) represent an entirely new class of generative AI methods that have yet to be fully explored. They use Langevin dynamics, represented as stochastic differential equations, to describe a process that transforms data into noise, the forward process, and a process that trans...
Benjamin Sterling, Chad Gueli, M\'onica F. Bugallo· 0 citations
In the networks studied, order structure must be imposed rather than discovered; in the networks studied, order structure must be imposed rather than discovered.
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.
