Forecasting pandemic spread across heterogeneous regions demands models that are both accurate and interpretable for public health action. This paper proposes a hybrid forecasting framework that integrates an SEIR epidemiological model enhanced with a Temporal Fusion Transformer (TFT) to produce interpretable multi-hor...
Ashish Anton Abraham, Gopi Krishnan R, Aiswarya Anil Nair et al.· 0 citations
Deep neural networks often struggle to provide reliable confidence estimates, making post-hoc calibration essential for reliable decision-making. Existing post-hoc methods largely rely on score-based transformations, which improve marginal calibration but often fail to capture spatially varying miscalibration in local...
Reinforcement learning for large language models often uses separate systems for inference and training. Even with identical weights and BF16 tensors, implementation differences can make an intended on-policy update off-policy and destabilize training. Existing remedies align the entire inference and training stacks, c...
State inference and parameter learning for nonlinear filters is a core computation for scientific machine learning with varied applications in engineering and neuroscience. The unnormalized filtering distribution is governed by the Zakai equation, a stochastic partial differential equation (SPDE) that combines the forw...
Aaditya Prasad, Steven W. Flavell, Brian DePasquale· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Physics-constrained machine learning (PCML) integrates domain knowledge, first-principles, and physical constraints into AI/ML models. In this work, we present a step-by-step tutorial of a modular PCML framework, KKT-HardNet, and illustrate how it could be used for hybrid modeling, process simulation, optimization and...
Rahul Golder, Bimol Nath Roy, MM Faruque Hasan· 0 citations
Regularised reinforcement learning (RL) algorithms rely on estimators, like Monte Carlo tree search or one-step look-ahead, to provide policy, value, or Q-value estimates in training and inference. However, existing bandit-based estimation frameworks evaluate sampling efficiency, not the quality of estimates. We addres...
Danilo Vucetic, Alexandre Larouche, Mohammad Pedramfar et al.· 0 citations
Multi-step predictions of future transition realizations can improve reinforcement learning, but their value remains difficult to quantify. Directly including these predictions in the state can lead to exponential state-space growth, making direct dynamic programming computationally expensive. We study discounted finit...
Chen-Bei Lu, Zai-Wei Chen, Tong-Xin Li et al.· 0 citations
Time Series Foundation Models (TSFMs) offer strong zero-shot forecasting capabilities, but their high pretraining cost raises a practical sustainability question: does this upfront investment pay off over a full deployment lifecycle, compared to supervised standalone models that must be periodically retrained? We model...
Regularised reinforcement learning (RL) has provable robustness guarantees that should ease the transfer of policies from simulation to robots, known as sim-to-real. Yet, weakly regularised algorithms like Proximal Policy Optimisation (PPO) remain the de facto choice in sim-to-real pipelines, while the practical benefi...
Danilo Vucetic, Mohamad H. Danesh, Florence Clerc et al.· 0 citations
We study the list replicability number in the realizable PAC learning framework and prove that every concept class $H$ over a countable domain with Littlestone dimension $d$ and dual VC dimension $v^*$ satisfies \[ \mathrm{LR}(H)\leq 2^{O(d\min\{\log d,v^*\})}. \] This matches the worst-case lower bound of $2^{\Omega(d...
Ari Blondal, Pooya Hatami, Chavdar Lalov et al.· 0 citations
During joint training, backpropagation allows later layers to reshape earlier representations, a feedback mechanism absent from purely layer-wise learning. We extend Neural Low-Degree Filtering (Neural LoFi), a recently proposed layer-wise spectral surrogate for feature learning, to capture this interaction. Starting f...
Yatin Dandi, Matteo Vilucchio, Hugo Tabanelli et al.· 0 citations
By extending the score attack framework to user-level data, a new lower bound of $\Omega$ is established for any user-level $(\epsilon,\delta)$-DP, showing that the proposed algorithm is near-optimal with only a gap of the factor $\log(d/k)$.
Yan Zhang, Jiong Tuo, Meng Ding et al.· 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.
