Institution profile

IDSIA

Academic institutioneurope · ch
Official website
Research library114linked papers
Opportunities0open roles
Selected work

Representative Papers

Annotated History of Modern AI and Deep Learning

Dec 21, 2022arXiv.org

This paper addresses the fragmentation of AI historiography, the obscuration of neural networks’ intellectual origins, and the marginalization of cybernetics in mainstream narratives. It proposes a unified historical reconstruction framework centered on the concept of “credit assignment.” Through rigorous historical document analysis, interdisciplinary knowledge graph construction, and scholarly provenance tracing, the study systematically traces the mathematical and technical lineage—from the 17th-century chain rule and 19th-century linear regression to the first implementation of deep learning in 1965—thereby correcting widespread textbook misconceptions and reaffirming cybernetics’ foundational role in modern AI. The resulting contribution is the most comprehensive chronology of deep learning to date (as of 2022), documenting over one hundred pivotal events, rigorously attributing original contributions, and embedding hundreds of hyperlinked authoritative sources. This chronology has been published as a core chapter in an academic monograph on AI.

43 citationsRead paper

Approximating Nash Social Welfare by Matching and Local Search

Nov 07, 2022Symposium on the Theory of Computing

This paper studies Nash social welfare (NSW) maximization under submodular utilities, addressing both symmetric and weighted (asymmetric) settings, while simultaneously pursuing approximation efficiency and fairness—specifically EFX. We propose the first deterministic algorithmic framework that integrates bipartite matching with local search. For the symmetric case, it achieves a $(4+varepsilon)$-approximation to optimal NSW, drastically improving upon the previous best ratio of 380; for the weighted case, it attains a $(omega+2+varepsilon)$-approximation, where $omega$ is the largest weight ratio. Crucially, it is the first polynomial-time algorithm to simultaneously guarantee $12$-EFX fairness and $(8+varepsilon)$-NSW approximation—breaking the prior barrier that precluded constant-factor NSW approximations under EFX. Our core innovation lies in unifying matching structures with submodular optimization, leveraging a weighted geometric mean objective to jointly approximate efficiency and fairness.

18 citations5 influentialRead paper

Decoupling the "What" and "Where" With Polar Coordinate Positional Embeddings

Sep 05, 2025arXiv.org

In Transformer architectures, content (“what”) and position (“where”) representations are deeply entangled in mainstream positional encodings such as RoPE, inducing modeling bias—particularly degrading zero-shot length extrapolation. This work first identifies and formalizes the “what–where” coupling mechanism inherent in RoPE. To address it, we propose Polar Coordinate Positional Encoding (PoPE): it explicitly decouples content and position at the geometric level by encoding relative position as angular coordinates and content-dependent modulation as radial coordinates. PoPE is parameter-free, plug-and-play, and fully compatible with standard Transformers. Experiments across music, genomic, and language modeling tasks demonstrate consistent perplexity reduction across model scales (124M–774M parameters). Crucially, PoPE significantly improves zero-shot length extrapolation—enabling coherent generation far beyond training sequence lengths—without interpolation or fine-tuning.

1 citations1 influentialRead paper

Safe and Efficient Social Navigation through Explainable Safety Regions Based on Topological Features

Feb 14, 2025arXiv.org

This work addresses the critical challenge of safe, efficient, and interpretable navigation for autonomous robots in human-robot cohabited social environments under dynamic conditions. We propose the first topological data analysis (TDA)-based safety region modeling framework: TDA extracts robust topological features of the environment to construct explainable safety regions with rigorously bounded approximation error (ε). We further introduce a novel safety boundary generation method integrating global support vector machines (SVM) with sequential statistics, ensuring deadlock-free navigation. Additionally, we extract locally interpretable decision rules to jointly guarantee robustness and transparency. Experiments demonstrate that our approach significantly improves collision detection accuracy while simultaneously enhancing behavioral predictability and human trust in compliant simulation environments.

1 citationsRead paper

Improved fixed-parameter bounds for Min-Sum-Radii and Diameters $k$-clustering and their fair variants

Jan 29, 2025

This paper studies the Min-Sum-Radii (MSR) and Min-Sum-Diameters (MSD) clustering problems under a cluster count constraint $k$, along with their fairness-aware, outlier-robust, and mergeable extensions. We present the first exact algorithm for MSD with time complexity $n^{O(k)}$, and establish a tight ETH lower bound for $alpha$-MSD when $alpha > log 3$. A unified $(1+varepsilon)$-approximation algorithm is designed, running in $O(kn) + (1/varepsilon)^{O(dk)}$ time and enabling dimension-sensitive analysis under the doubling-dimension assumption. We further introduce a general fairness-constrained modeling framework, extending all results to multi-group fair variants and settings with outliers. Key contributions include: (i) the first exact algorithm for MSD; (ii) a tight ETH-based hardness characterization; and (iii) a unified algorithmic framework achieving efficiency, fairness, robustness to outliers, and mergeability simultaneously.

1 citationsRead paper
Recent publications

Latest Papers