From the 1 of 11 linked papers with an AI index.
11 papers
CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport
Peng Ling, Yingda Yin, Lingting Zhu +5
While 3D Vision-Language Models (3D VLMs) have demonstrated remarkable spatial reasoning capabilities, they suffer from massive visual token counts that create severe computational…
A Direct Route to Markov Chain Convergence via Asymptotic Equivalence with the Target
Patrick Forré, Patrick Forré
For a Markov kernel with an invariant probability measure , we give a self-contained proof of the Markov chain convergence theorem via a criterion called asymptotic equivale…
AVQ-Attention: Adaptive Vector-Quantized Attention
Winfried van den dool, Patrick Forré, Amir Habibian +2
The paper introduces Adaptive Vector-Quantized (AVQ) Attention, which dynamically allocates codebook capacity to the most important regions of the key space, preserving O(MN) compl…
Möbius transforms and Shapley values for vector-valued functions on weighted directed acyclic multigraphs
Patrick Forré, Abel Jansma
Möbius inversion and Shapley values are two mathematical tools for characterizing and decomposing higher-order structure in complex systems. The former defines higher-order intera…
Abstract Markov Random Fields
Leon Lang, Clélia de Mulatier, Rick Quax +1
Markov random fields are known to be fully characterized by properties of their information diagrams, or I-diagrams. In particular, for Markov random fields, regions in the I-diagr…
Are Bayesian networks typically faithful?
Philip Boeken, Patrick Forré, Joris M. Mooij
Faithfulness is a common assumption in causal inference, often motivated by the fact that the faithful parameters of linear Gaussian and discrete Bayesian networks are typical, and…