AlignSAE is introduced, a method that aligns SAE features with a predefined ontology through a "pre-train, then post-train"curriculum and achieves disentanglement improvements of $9$--$\infty\times$ over standard SAEs, and further supports multi-hop reasoning and a mechanistic probe of grokking-like generalization dyna...
Minglai Yang, Xin-Yu Guo, Zheng-Liang Shi et al.· arXiv.org· 4 citations
Deep neural networks (DNNs) and Kolmogorov-Arnold networks (KANs) are flexible function approximators, but their accuracy can require substantial network depth, width, and trainable parameter counts. Beyond making the resulting networks less transparent, large parameter spaces can increase training cost and produce sol...
Zachary Morrow, Michael Penwarden, Brian Chen et al.· 0 citations
A large driver of the complexity of graph learning is the interplay between structure and features. When analyzing the expressivity of graph neural networks, however, existing approaches ignore features in favor of structure, making it nigh-impossible to assess to what extent two graphs with close features should be co...
Martin Carrasco, Olga Zaghen, Kavir Sumaraj et al.· 0 citations
Reinforcement Learning with Verifiable Reward (RLVR) effectively solves complex tasks but demands extremely long context lengths during training, leading to substantial computational costs. While multi-stage training can partially mitigate this, starting with overly short contexts often causes irreversible performance...
Xin Xu, Clive Bai, Kai Yang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
We consider a remote inference system with multiple modalities, where a multimodal machine learning (ML) model performs real-time inference using features collected from remote sensors. When sensor observations evolve dynamically over time, fresh features are critical for inference tasks. However, timely delivery of fe...
The modality gap is intrinsic to multimodal alignment, where embeddings from different modalities remain partially separated in a shared representation space. In continual learning, CLIP-based vision-language models (VLMs) not only suffer catastrophic forgetting but also experience modality gap drift that disrupts the...
Tiantian Peng, Yuyang Liu, Shuo Yang et al.· 0 citations
In the era of Industry 5.0, data-driven decision-making has become indispensable for planning in service systems such as tourism. This paper proposes a non-linear hybrid approach for forecasting tourist arrivals to Hong Kong from five major source markets before COVID-19 and to Sanya, China, through the COVID-19 shock....
Layer Normalization (LN) is usually studied for its role in optimization, but it also acts as a multivariate nonlinearity between affine layers. We investigate how grouping LN units affects the approximation power of neural networks as width grows. In Parallel Layer Normalization networks (PLN-Nets), fixed-dimensional...
Yunhao Ni, Yuxin Guo, Yuhe Liu et al.· 0 citations
Electroencephalography (EEG) classification has shown significant promise in applications ranging from neurodegenerative disease detection to brain-computer interfaces (BCIs). Whilst deep learning methods have increasingly dominated the research landscape in recent years; these models remain largely opaque 'black boxes...
This paper introduces Fuzzy Attention Network-Based Transformer (FANTF), an approach for time series forecasting, classification, and anomaly detection. FANTF combines fuzzy logic concepts with transformer architectures through a novel fuzzy attention mechanism. The proposed mechanism is inspired by Type-2 fuzzy set th...
This work introduces a novel approach to compute a universal upper bound on the Bayes error rate (BER) from classifier-output samples, which serves as a Bayes-error-related performance criterion for the underlying classification task. We show that the bound is tight in the binary case and characterize the max-sum gap t...
Mohammadreza Tavasoli Naeini, Ali Bereyhi, Morteza Noshad et al.· 0 citations
By aggregating distributed energy resources (DERs) into a single dispatchable resource, virtual power plants (VPPs) enable the grid to use the flexibility of numerous small-scale DERs. Delivering an aggregate VPP commitment requires multi-agent coordination, where agents manage local DER models and operating constraint...
Meiyi Li, Lucas Ruda, Javad Mohammadi· 0 citations
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.
