Knowing the layout of the physical world matters for many applications, yet the sensors we rely on for it (e.g., cameras and LiDAR) can fail in darkness, in adverse weather, or behind walls. Wireless signals do not face these limitations: every link between a base station and a user is shaped by the buildings it passes...
An extensive benchmark of tropical cyclone forecasting is conducted, comparing GenCast, FourCastNet 3, and FGN with ECMWF's operational physics-based ensemble, IFS-ENS, finding that leading AI models substantially outperform IFS-ENS in cyclone tracking.
N. Chalumeau, X. Renard, R. Meynadier et al.· 0 citations
Transformer-based models have become the backbone of a wide range of tasks, but their intensive computation and data movement incur substantial energy overhead. Analog compute-in-memory (CIM) offers an energy-efficient alternative, yet its inherent hardware non-idealities perturb stored weights and can significantly de...
Wen-Shuai Yao, Wen-Yong Zhou, Han-Yong Shao et al.· 0 citations
Verifying the final answer of a long reasoning trace may show that the trace is wrong but it does not distinguish three cases. The problem may lie beyond the model's capability, another attempt would succeed, or one step in an otherwise recoverable trace made the trace fail. Standard hidden-state probes are trained on...
Shubham Subhnil, Yannis Belkhiter, Erik Miehling et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Multi-agent systems built from frozen language models communicate through text, which discards the internal state the sender already computed and makes the receiver pay to rebuild it. Work on internal channels avoids that cost, framing the problem as transfer: agent A sends information to agent B. Every agent pair that...
Semi-supervised learning (SSL) is particularly attractive in domains where labels are expensive to obtain, while unlabeled examples are readily available. Quantitative Structure-Activity Relationship (QSAR) modeling, which predicts molecular biological activity from chemical structure, is one such domain. Obtaining act...
Oliver Majer, S. Džeroski, J. Levatić· 0 citations
Multi-agent LLM systems communicate in text, which is lossy and wasteful: the sender throws away the reading it already did. A growing literature instead transmits the KV cache, the natural carrier of that reading. We study the most appealing form of the idea: both models stay frozen and the sender's cache is substitut...
Weight-space learning across architectures requires representations that respect parameter symmetries and scale to large networks. Existing equivariant tensor encoders require architecture-specific symmetry specifications, while neuron graphs make global attention costly. We introduce a typed graph organized around sha...
This work introduces Page-to-Token Policy Optimization (P2TPO), a structure-aligned credit-assignment framework that operates on full-page policy trajectories that outperforms all evaluated policy optimization baselines in seed-averaged scores on each of the six document parsing benchmarks.
Yong-Zhou-Shi-、-Lan-Shan-Xian-Ti-Gai-Wei-Lian-He-D Zu, Ning-Hua Yang, Ze-Zhong Tan et al.· 0 citations
Physics-informed Gaussian processes (GPs) provide a principled framework for scientific inference by expressing uncertainty over empirical measurements, boundary conditions, and governing equations. However, they struggle to scale to larger datasets and nonlinear information. Conversely, diffusion models excel at learn...
Tobias Weber, Carla Sagebiel, Philipp Hennig· 0 citations
This work introduces a spectral sheaf Laplacian, defined jointly over space and time, such that a single operator regulates signal propagation across both the spatial graph and the temporal domain, and introduces ChronoSheaf, a spatio-temporal sheaf network with two key components.
Active Feature Acquisition (AFA) sequentially selects features to maximize predictive accuracy under an acquisition budget. A natural heuristic greedily maximizes Expected Information Gain minus a cost penalty, EIG(j|x_S)-lam*c_j (EIG-Cost), but its theoretical guarantees are unclear. We provide an a-posteriori certifi...
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.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
