While established literature underscores the pivotal role of preprocessing in forecasting accuracy, this stage remains largely overlooked in current research. Modern benchmarks typically resort to simple scaling, failing to account for critical transformations required to address nonstationarity, such as differencing....
Guilherme Afonso Galindo Padilha, Paulo Salgado Gomes de Mattos Neto, Rafael Menelau Oliveira e Cruz· 0 citations
Decision-focused learning (DFL) trains predictive models for downstream optimization, but existing methods largely assume centralized data. In cross-silo settings, federated learning offers a natural alternative, yet standard federated methods optimize prediction over decision quality and do not address heterogeneity i...
Konstantinos Ziliaskopoulos, Alexander Vinel, Jiaqi Wang· 0 citations
The quadratic cost of self-attention limits scalability to long sequences from multidimensional data. We introduce Tucker bottleneck attention (TuBA), which exploits low-rank tensor structure for efficient global token mixing. TuBA projects hidden tensors into compact Tucker cores, performs multi-head self-attention an...
Ryan Solgi, Parsa Madinei, Zheng Zhang· 0 citations
Emerging long-horizon agentic tasks require repeated model calls, worsening the inference cost of already-costly language models. While narrow agentic tasks suggest potential for aggressive model pruning without performance drop, empirical results show existing methods proposed for question answering tasks severely deg...
Yuan-Zhe Li, Peng-Xin Wang, Yuxin Ren et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Multi-label topic assignment for user-generated content (UGC) -- including product reviews and buyer-seller conversations -- poses unique scalability challenges in large-scale e-commerce due to informal language, extreme label sparsity, and rapidly evolving taxonomies. While utilizing Large Language Models (LLMs) as la...
This work provides a combinatorial analysis of the per-epoch sampler, the composition step that draws a training graph from the cached decomposition, and derives a selector-agnostic conditional bound on high-score cut survival in composed training graphs.
S. Navuluru, Siddhartha Shankar Das, Franck Dernoncourt et al.· 0 citations
This work studies an activation alignment, a map from a source model's layerwise activations to a target's, and factors this map into a layer map, whose output is an explicit target-by-source matrix that can be extracted and inspected, and a layer-shared feature map between hidden spaces.
А. Ю. Судаков, Guy Bar-Shalom, Fabrizio Frasca et al.· 0 citations
We develop a geometry-based capacity theory for exact-key retrieval in compressed finite-feature Hebbian associative memory. For random or approximately isotropic values, retrieval interference separates into finite-feature noise, which decreases with feature dimension, and structural interference, which is determined...
Jianhai Zhang, Donghao Zhang, Pattarawut Charatpangoon et al.· 0 citations
BeatFlow-ECG is presented, a conditional rectified-flow model for reconstructing single-channel ECG from synchronized PPG and inertial measurements and achieves the best results among the evaluated deterministic, adversarial, and diffusion-based baselines across all reported waveform and beat-timing metrics.
Mohamed S. Kamel, Sahar Selim, Walaa Medhat et al.· 0 citations
The large KV-cache size of modern LLMs creates a barrier to efficient deployment. Recent work has explored replacing attention layers'RoPE positional embeddings with alternative decay-based mechanisms, which can then be used to prune KV-cache during inference. However, these decay functions have limited expressivity, a...
Davis Wertheimer, Hao-Chen Shen, Ahan Gupta et al.· 0 citations
Building a world model requires a state representation useful for planning and decision-making---potentially over tasks unknown at training time. In the context of financial markets, planning and decision-making may require a model to reason about market-wide conditions, asset-specific expected returns, liquidity, vola...
Humzah Merchant, Alec Guthrie, Simon Mahns et al.· 0 citations
Constraint handling methods typically intervene before the optimizer acts, by modifying the objective or the gradient. Yet momentum, adaptive scaling, and structured preconditioning can substantially reshape that signal before it becomes a parameter update. We formulate optimizer relative constrained learning, where co...
Utkarsh Grover, Wyatt Mackey, Kaixun Hua et al.· 0 citations
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.
