Embedding tables are critical components of large-scale recommendation systems, facilitating the efficient mapping of high-cardinality categorical features into dense vector representations. However, as the volume of unique IDs expands, traditional hash-based indexing methods suffer from collisions that degrade model p...
Ziliang Zhao, Bi Xue, Emma Lin et al.· 0 citations
Linear attention offers an efficient alternative to full attention with a fixed-size recurrent state. However, this state is shared by all tokens, so information from distinct tokens becomes superposed within it and produces inter-token interference that degrades long-range fine-grained recall. To address this issue, w...
Kaicheng Xiao, Haotian Li, Liran Dong et al.· 0 citations
We study the mean-field Langevin descent-ascent (MFL-DA), a coupled optimization dynamics on the space of probability measures for entropically regularized two-player zero-sum games, together with its associated interacting particle system. For general nonconvex-nonconcave payoffs, Wang and Chizat (COLT 2024) asked whe...
Geuntaek Seo, Minseop Shin, Pierre Monmarch\'e et al.· 0 citations
Asynchronous primal-dual methods for decentralized non-smooth convex optimization often require each node to maintain $\mathcal{O}(d)$ auxiliary variables, where $d$ is its degree. This dependence on degree increases memory requirements and can amplify the effects of stale information, especially in dense networks. Mot...
Anna van Elst, Olivier Fercoq, Igor Colin et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
It is argued that true fairness requires addressing bias at the intersections of protected groups, and a unified framework that leverages Mixed-Integer Optimization (MIO) to train intersectionally fair and intrinsically interpretable classifiers is proposed.
Jiri Nemecek, Mark Kozdoba, Illia Kryvoviaz et al.· arXiv.org· 0 citations
Temporally aware image representations are crucial for capturing disease progression in 3D volumes of longitudinal medical datasets. However, recent state-of-the-art self-supervised learning approaches like Masked Autoencoding (MAE), despite their strong representation learning capabilities, lack temporal awareness. In...
Taha Emre, Arunava Chakravarty, Thomas Pinetz et al.· 0 citations
Fine-tuning has become the dominant paradigm for adapting Vision-Language Models (VLMs), yet most approaches rely on explicit weight updates that introduce a fundamental trade-off. Full Fine-Tuning (FFT) may perturb pretrained representations due to cross-modal gradient interference, whereas Parameter-Efficient Fine-Tu...
Mingyuan Zhang, Yue Bai, Yifan Wang et al.· 0 citations
A variational physics-informed ansatz is introduced that represents the unknown operator as a trainable object and minimizes the resulting steady-state residuals across experiments, clarifying a concrete steady-state reconstruction regime in which equilibrium observations alone can determine hidden interaction operator...
Optimal transport (OT) and Gromov-Wasserstein (GW) alignment provide interpretable geometric frameworks for comparing, transforming, and aggregating heterogeneous datasets---tasks ubiquitous in data science and machine learning. Because these frameworks are computationally expensive, large-scale applications often rely...
Sanjit Dandapanthula, Aleksandr Podkopaev, Shiva Prasad Kasiviswanathan et al.· 0 citations
Eddy-covariance (EC) flux towers provide in situ measurements of $CO_2$ flux and serve as the ground-truth data for predictive `upscaling' models derived from satellite products. However, many satellites now resolve spatial scales smaller than an EC tower's footprint. We show theoretically that upscaling models trained...
Jacob Searcy, Anish Dulal, Courtney Mathers et al.· 0 citations
Engineering LLMs to accelerate life sciences research requires a robust alignment with biomedical knowledge. We observe that biomedical text exhibits a fundamentally different uncertainty structure from general text: dense low-confidence runs encode epistemic knowledge gaps (dense causal chains, rare entities) rather t...
Zhenchao Tang, Fang Wang, Haohuai He et al.· 0 citations
Reinforcement learning (RL) algorithms such as PPO and GRPO are widely used to train large language models (LLMs) for multi-turn agentic tasks. However, in off-policy training pipelines, these methods can exhibit unstable optimization dynamics and are prone to perfor- mance collapse. Through empirical analysis, we iden...
Chenliang Li, Adel Elmahdy, Alex Boyd 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.
