Tootfinder

MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
Xi Chen, Mingkang Zhu, Shaoteng Liu, Xiaoyang Wu, Xiaogang Xu, Yu Liu, Xiang Bai, Hengshuang Zhao
https://arxiv.org/abs/2506.22434

MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
This work explores enabling Chain-of-Thought (CoT) reasoning to link visual cues across multiple images. A straightforward solution is to adapt rule-based reinforcement learning for Vision-Language Models (VLMs). However, such methods typically rely on manually curated question-answer pairs, which can be particularly challenging when dealing with fine grained visual details and complex logic across images. Inspired by self-supervised visual representation learning, we observe that images contai…

“America’s Pivot to the Pacific” by #AngryPlanet [PODCAST]
https://pca.st/episode/535d72f1-3347-4b94-b69c-3ddba08c83cca

HLTCOE at LiveRAG: GPT-Researcher using ColBERT retrieval
Kevin Duh, Eugene Yang, Orion Weller, Andrew Yates, Dawn Lawrie
https://arxiv.org/abs/2506.22356 …

HLTCOE at LiveRAG: GPT-Researcher using ColBERT retrieval
The HLTCOE LiveRAG submission utilized the GPT-researcher framework for researching the context of the question, filtering the returned results, and generating the final answer. The retrieval system was a ColBERT bi-encoder architecture, which represents a passage with many dense tokens. Retrieval used a local, compressed index of the FineWeb10-BT collection created with PLAID-X, using a model fine-tuned for multilingual retrieval. Query generation from context was done with Qwen2.5-7B-Instruct…

Toroidal graph manifolds with small homology are not SU(2)-abelian
Giacomo Bascape
https://arxiv.org/abs/2506.21729 https://arxiv.org…

Toroidal graph manifolds with small homology are not SU(2)-abelian
We show that if $Y$ is a toroidal closed graph manifold rational homology $3$-sphere with $|H_1(Y;\mathbb{Z})| \le 5$, then there exists an irreducible representation $\fund{Y} \to SU(2)$. This answers positively to a conjecture by Baldwin and Sivek in the case of graph manifolds.

"I think it is a huge mistake for people to assume that they can trust AI when they do not trust each other. The safest way to develop superintelligence is to first strengthen trust between humans, and then cooperate with each other to develop superintelligence in a safe manner. But what we are doing now is exactly the opposite. Instead, all efforts are being directed toward developing a superintelligence."
#AGI #AI
https://www.wired.com/story/questions-answered-by-yuval-noah-harari-for-wired-ai-artificial-intelligence-singularity/

Action Language BC
Joseph Babb, Joohyung Lee
https://arxiv.org/abs/2506.18044 https://arxiv.org/pdf/2506.18044

Action Language BC+
Action languages are formal models of parts of natural language that are designed to describe effects of actions. Many of these languages can be viewed as high level notations of answer set programs structured to represent transition systems. However, the form of answer set programs considered in the earlier work is quite limited in comparison with the modern Answer Set Programming (ASP) language, which allows several useful constructs for knowledge representation, such as choice rules, aggrega…

Detecting Atmospheric CO2 Trends as Population-Level Signatures for Long-Term Stable Water Oceans and Biotic Activity on Temperate Terrestrial Exoplanets
Janina Hansen, Daniel Angerhausen, Sascha P. Quanz, Derek Vance, Bj\"orn S. Konrad, Emily O. Garvin, Eleonora Alei, Jens Kammerer, Felix A. Dannert
https://arxiv.org/abs/2…

Detecting Atmospheric CO2 Trends as Population-Level Signatures for Long-Term Stable Water Oceans and Biotic Activity on Temperate Terrestrial Exoplanets
Identifying key observables is essential for enhancing our knowledge of exoplanet habitability and biospheres, as well as improving future mission capabilities. While currently challenging, future observatories such as the Large Interferometer for Exoplanets (LIFE) will enable atmospheric observations of a diverse sample of temperate terrestrial worlds. Using thermal emission spectra that represent conventional predictions of atmospheric CO2 variability across the Habitable Zone (HZ), we assess…

Potemkin Understanding in Large Language Models
Marina Mancoridis, Bec Weeks, Keyon Vafa, Sendhil Mullainathan
https://arxiv.org/abs/2506.21521 https://arxiv.org/pdf/2506.21521 https://arxiv.org/html/2506.21521
arXiv:2506.21521v1 Announce Type: new
Abstract: Large language models (LLMs) are regularly evaluated using benchmark datasets. But what justifies making inferences about an LLM's capabilities based on its answers to a curated set of questions? This paper first introduces a formal framework to address this question. The key is to note that the benchmarks used to test LLMs -- such as AP exams -- are also those used to test people. However, this raises an implication: these benchmarks are only valid tests if LLMs misunderstand concepts in ways that mirror human misunderstandings. Otherwise, success on benchmarks only demonstrates potemkin understanding: the illusion of understanding driven by answers irreconcilable with how any human would interpret a concept. We present two procedures for quantifying the existence of potemkins: one using a specially designed benchmark in three domains, the other using a general procedure that provides a lower-bound on their prevalence. We find that potemkins are ubiquitous across models, tasks, and domains. We also find that these failures reflect not just incorrect understanding, but deeper internal incoherence in concept representations.
toXiv_bot_toot

The Pythagoras number of fields of transcendence degree $1$ over $\mathbb{Q}$
Olivier Benoist
https://arxiv.org/abs/2506.21380 https://

The Pythagoras number of fields of transcendence degree $1$ over $\mathbb{Q}$
We show that any sum of squares in a field of transcendence degree $1$ over $\mathbb{Q}$ is a sum of $5$ squares, answering a question of Pop and Pfister. We deduce this result from a representation theorem, in $k(C)$, for quadratic forms of rank $\geq 5$ with coefficients in $k$, where $C$ is a curve over a number field $k$.

Connections between hyperlinearity, stability and character rigidity for higher rank lattices
Alon Dogon, Itamar Vigdorovich
https://arxiv.org/abs/2506.20843

Connections between hyperlinearity, stability and character rigidity for higher rank lattices
Let $Γ$ be an irreducible lattice in a semisimple Lie group of real rank at least $2$. Suppose that $Γ$ has property (T;FD), that is, its finite dimensional representations have a uniform spectral gap. We show that if $Γ$ is (flexibly) Hilbert--Schmidt stable then: $(a)$ infinite central extensions $\widetildeΓ$ of $Γ$ are not hyperlinear, and $(b)$ every character of $Γ$ is either finite-dimensional or induced from the center (character rigidity). As a consequence, a positive answer to t…