Goal-oriented chatbots often operate in sparse-reward settings, where meaningful feedback (task success or user satisfaction) arrives only after many dialogue turns. This makes exploration and policy learning challenging. We propose a novel hierarchical reinforcement learning (HRL) framework that performs automated ski...
This paper introduces the Structural Contextual Probabilistic Topic Model (SCPTM), an architecture that incorporates syntactic dependency relations into topic inference and concludes that syntactic encoding matters conditionally: it benefits action-oriented, argumentative texts, but introduces noise in informational or...
As nonlinearity strengthens, the accuracy advantage of discretization-based constraints becomes increasingly pronounced, with smaller optimization errors compensating for the truncation errors, and the more complex the nonlinearity and boundary conditions, the greater the advantage of GNN over MLP.
Xing Guo, Hong-Wei Tang, Ze-Wei Meng et al.· 0 citations
PASC constructs a structure-only prior representation, estimates a target-edge structural prior score, and compares this score with a local signed-context cue to derive a conflict residual, which calibrates signed attention aggregation, target-edge gated fusion, and regime-adaptive optimization.
To adapt open-set graph neural networks to heterophilic scenarios, HOPE uses a structure-augmented feature initialization layer to capture multi-hop structural patterns, and introduces a heterophily-guided pseudo-extrapolation strategy to enhance unknown-class rejection.
Yumeng Dai, Yue Tan, Yi-Xin Liu et al.· 0 citations
HFS turns a classical heat field into a practical interface for multiscale geometric analysis in modern point-cloud learning, and introduces the Heat Dimension Spectrum (HDS), a compact summary of multiscale geometric composition.
Yuan-Qing Wang, Ya-Peng Tian, B. Coskunuzer· 0 citations
Graph modeling, a crucial task for representing complex relationships in graph-structured data, has achieved significant success in recent years. However, current graph modeling methods rely on traditional Graph Neural Networks and pre-training approaches to implicitly learn the underlying relational structure of graph...
Thanh-Dat Truong, Sarah Alharbi, Susan Gauch et al.· 0 citations
Comparisons of statistical and machine-learning-based methods for post-processing ECMWF 2-m temperature and 10-m wind speed forecasts at observed and unobserved stations in Germany consider EMOS-based approaches, distributional regression networks, Transformers, and graph neural networks under both limited and extended...
Oversmoothing is a well-known failure mode of Graph Neural Networks (GNNs). However, most existing diagnostics rely on global aggregation measures that fail to capture the heterogeneous dynamics of message passing. Real-world graphs exhibit pronounced community structure, and message passing operates on two timescales,...
Asela Hevapathige, Ahad N. Zehmakan, Asiri Wijesinghe et al.· 0 citations
SPIRE, a Structural Entropy-Driven Graph Diffusion Generation method that introduces topology-aware client differentiation into one-shot FGL, employs first-order degree-distribution structural entropy as a compact descriptor of degree-mass dispersion and uses it to derive structural client weights, providing an inducti...
Shu-Tong Zheng, Le-Le Fu, Sheng Huang et al.· 0 citations
The proposed approach based on the concept of Instance Graphs is evaluated on multiple real-world event logs, and the experimental results demonstrate that incorporating contextual process instances benefits prediction performance.
A comprehensive evaluation of 17 state-of-the-art methods across Temporal Graph Neural Networks (TGNNs) and Large Language Model (LLM)-based paradigms reveals a clear capability divide between the two paradigms: TGNN-based methods excel at structural prediction but fail at semantic tracking, whereas LLM-based predictor...
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduJul 15, 2026
Assistant Professor Pat Pataranutaporn describes a new interface that lets everyday users glimpse inside an AI's neural network before their chatbot ever says a word.
Microsoft Research Blog· microsoft.comJul 13, 2026
Cryptographic code supports vital protections in modern computing systems. Learn how a new method helps verify code as developers write it while preserving speed and adaptability as it gets implemented and evolves. The post Verifying Rust cryptography in SymCrypt, from standards to code appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduJul 6, 2026
PhD student Rachel Sava, winner of the Envisioning the Future of Computing Prize, explores transformative improvements and dystopian risks of neural technology.
