Generative recommendation models have shown promising results by representing items as semantic IDs and generating these IDs autoregressively. We introduce an approach showing that explicitly incorporating hierarchical and attribute-level supervision into generative recommendation can simultaneously improve training ef...
Tripti Shukla, Shwetha Somasundaram, Akshat Gupta et al.· 0 citations
Formal verification proves that a program satisfies its specification, but says nothing about whether the specification captures what the author meant. As LLMs increasingly write both code and specifications, a gap between the author's natural-language requirement and the specification becomes a live risk. A machine-ch...
Martín Amster, One An, Holly Baker et al.· 0 citations
This work introduces MID (Mask-Image Distributional Divergence), a distribution-level evaluation metric for medical image segmentation that compares the joint distribution of images and masks between a reference set and a set of predictions, without requiring sample-wise correspondence.
Vincenzo Marcianó, Xiao-Ming Zhang, Gianluca Guglielmo et al.· 0 citations
We revisit the statistical mechanics of Transformer attention via modern Hopfield models. We present a free-energy formalism to characterize parameter regimes and critical thresholds for robust attention inference. The resulting free-energy landscape incorporates randomness in query states and attention weights. Attent...
Jerry Yao-Chieh Hu, Yu-An Chen, Maojiang Su et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
AI-generated outputs are frequently perceived as highly creative, but also tend to be more similar to each other (homogenized) than human ideas. Does the human heterogeneity that extends beyond AI reflect valuable thinking that AI misses? Alternatively, is greater human heterogeneity driven by lower-quality ideas and l...
Kibum Moon, Dan R. Johnson, Kostadin Kushlev et al.· 0 citations
Deep learning has become the dominant form of machine learning due in part, to its ability to automatically engineer complex meta features from data. However, even deep learning features can perform erratically because of unobserved latent factors. incorporating latent factor information explicitly, can improve perform...
We introduce StartLux-Decision, decision models from 0.8B to 27B parameters that combine efficient single-pass prediction with adaptive, confidence-guided reasoning. The Instant models use bidirectional attention in full-attention layers to improve decision accuracy while keeping single-pass inference. The AutoThink mo...
Xialie Zhuang, Zunhai Su, Jia Pan et al.· 0 citations
SE(3)-equivariance provides a useful geometric inductive bias for visuomotor policies, encoding that actions covary with rigid transformations of the observation. However, existing SE(3)-equivariant visuomotor policies build this bias on a global equivariance assumption that treats the entire observation as governed by...
Xinzhe Chen, Liqi Huang, Sihua Ren et al.· 0 citations
Learning symmetries through data augmentation offers an alternative to architectural equivariance, but does not guarantee that a network respects those symmetries. Measuring learned equivariance is especially difficult for intermediate representations, whose group actions are not specified. In a finite discrete setting...
Claire Schlesinger, Wolfgang Gatterbauer, Robin Walters· 0 citations
The original EneMonIE proposal describes a Web-based semantic system for continuously monitoring energy trends through targeted information extraction from heterogeneous online media. This article presents EneMonIE-Backend, an implementation-derived redesign that converts that conceptual pipeline into a modular, execut...
Janik Lesage, Khadim L\^o, and Jean-S\'ebastien Dessureault· 0 citations
Neural surrogates for Partial Differential Equations (PDEs) are usually trained on synthetic data from numerical simulators. As models grow and scaling laws demand larger datasets, the cost of data generation often outweighs the training cost and becomes the bottleneck in the scaling quest. Unlike data in other domains...
Paul Setinek, F. Paischer, Nils Thuerey et al.· 0 citations
In the age of "Software 3.0", when a complete program can be rewritten in minutes by an agent, the traditional approach of relying on code as the sole source of truth becomes questionable. Fowler advocated for a set of seven primitives, which lay the framework for regenerative software, so that programs can be deleted...
