Sparse-view novel view synthesis is a central problem in 3D content creation, but diffusion-based approaches remain limited by iterative denoising, making multi-view generation expensive at inference time. We introduce NAMVIS, a diffusion-free framework that reformulates multi-view image synthesis as geometry-condition...
R. Khafizov, I. Statsenko, Ruslan Rakhimov et al.· 0 citations
Multi-step matching models, including flow and diffusion models, produce high-quality outputs but incur substantial inference costs and may reproduce unwanted components of their training datasets. We introduce Inverse Distillation Unlearning (IDU), a unified framework that simultaneously distills a teacher multi-step...
Aleksei Leonov, N. Kornilov, Zhen-He Zhang et al.· 0 citations
This paper proposes a neural method for solving the simultaneous OT problem by learning a shared transport map that minimizes the average transport cost while aligning each source distribution with a prescribed target, and derives a max-min formulation for learning this map.
Milena Gazdieva, Kirill Sokolov, Jia-Wei Chen et al.· 0 citations
Tilted Schrodinger Bridge Matching (TSBM) is introduced, a post-training method for fine-tuning a learned bridge between source and target toward a reward-tilted target while preserving source, and theoretical justification and practical algorithm are derived.
S. Kholkin, Evgeny Burnaev, A. Korotin· 1 citation
This paper proposes a novel, lightweight evaluation strategy for logical reasoning that uses query-key alignments inside transformer attention heads that reveals latent representations that reliably separate valid from invalid inferences, offering a scalable alternative to traditional ablation-based techniques.
Eduard Tulchinskii, Anastasia Voznyuk, Laida Kushnareva et al.· Conference on Empirical Meth...· 0 citations
This paper introduces CodeTD -- the first approach to pre-execution assessment of code correctness based on topological data analysis (TDA) of Code LLMs' attention maps, which quantifies prompt-generation mismatch using topological patterns of attention maps.
D. Voronkova, I. Trofimov, Anton Dmitriev et al.· 0 citations
Effective flood monitoring is critical for minimizing the impacts of flood disasters on populations and infrastructure. Yet reliable remote sensing across extensive and environmentally diverse regions remains challenging, as most segmentation algorithms lack the generalisation capacity required for large-scale applicat...
I. Novikov, S. Illarionova, Ruslan B. Dzharkinov et al.· arXiv.org· 0 citations
A unified pipeline - coupling GA/LLM-driven synthesis with an LLM-based transformation agent - offers a feasible path toward end-to-end process design automation by producing validated, deployable outputs and substantially reduces manual engineering effort.
Timur Zakarin, S. Voitov, Sergei Shumilin et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
