Tootfinder

MaXIFE: Multilingual and Cross-lingual Instruction Following Evaluation
Yile Liu, Ziwei Ma, Xiu Jiang, Jinglu Hu, Jing Chang, Liang Li
https://arxiv.org/abs/2506.01776

MaXIFE: Multilingual and Cross-lingual Instruction Following Evaluation
With the rapid adoption of large language models (LLMs) in natural language processing, the ability to follow instructions has emerged as a key metric for evaluating their practical utility. However, existing evaluation methods often focus on single-language scenarios, overlooking the challenges and differences present in multilingual and cross-lingual contexts. To address this gap, we introduce MaXIFE: a comprehensive evaluation benchmark designed to assess instruction-following capabilities a…

A Hierarchical and Evolvable Benchmark for Fine-Grained Code Instruction Following with Multi-Turn Feedback
Guoliang Duan, Mingwei Liu, Yanlin Wang, Chong Wang, Xin Peng, Zibin Zheng
https://arxiv.org/abs/2507.00699

A Hierarchical and Evolvable Benchmark for Fine-Grained Code Instruction Following with Multi-Turn Feedback
Large language models (LLMs) have advanced significantly in code generation, yet their ability to follow complex programming instructions with layered and diverse constraints remains underexplored. Existing benchmarks often prioritize functional correctness, overlooking the nuanced requirements found in real-world development. We introduce MultiCodeIF, a comprehensive benchmark designed to evaluate instruction-following in code generation across multiple dimensions: constraint type, hierarchica…

Microsoft's FY 2025 report excludes the names of rivals, breaking from a common industry practice; its last report designated 25 companies as competitors (Jordan Novet/CNBC)
https://www.cnbc.com/2025/07/31/microsoft-competitors-filings.html

Microsoft ends tradition of naming competitors in regulatory filings
Apple, Meta and Nvidia still mention their rivals in annual reports. It's a practice that Alphabet, Amazon and Tesla gave up years ago.

Designer Meg Lewis on separating who you're told to be from who you really are – The Creative Independent https://thecreat…

Designer Meg Lewis on separating who you're told to be from who you really are – The Creative Independent
Designer Meg Lewis discusses following what's enjoyable, leaving doors open to possibility, and recapturing the impulsive creativity of childhood.

Social World Models
Xuhui Zhou, Jiarui Liu, Akhila Yerukola, Hyunwoo Kim, Maarten Sap
https://arxiv.org/abs/2509.00559 https://arxiv.org/pdf/2509.00559

Social World Models
Humans intuitively navigate social interactions by simulating unspoken dynamics and reasoning about others' perspectives, even with limited information. In contrast, AI systems struggle to automatically structure and reason about these implicit social contexts. In this paper, we introduce a novel structured social world representation formalism (S3AP), designed to help AI systems reason more effectively about social dynamics. Following a POMDP-driven design, S3AP represents social interactions …

LHS in LHS: A new expansion strategy for Latin hypercube sampling in simulation design
Matteo Boschini, Davide Gerosa, Alessandro Crespi, Matteo Falcone
https://arxiv.org/abs/2509.00159

LHS in LHS: A new expansion strategy for Latin hypercube sampling in simulation design
Latin Hypercube Sampling (LHS) is a prominent tool in simulation design, with a variety of applications in high-dimensional and computationally expensive problems. LHS allows for various optimization strategies, most notably to ensure space-filling properties. However, LHS is a single-stage algorithm that requires a priori knowledge of the targeted sample size. In this work, we present LHS in LHS, a new expansion algorithm for LHS that enables the addition of new samples to an existing LHS-dist…

Heute wird's 34 °C bei uns, und dieser Zettel lag im Briefkasten...
"Ich habe heute leider kein Wasser 💧 für dich"
#Wasser

Faster Algorithm for Second (s,t)-mincut and Breaking Quadratic barrier for Dual Edge Sensitivity for (s,t)-mincut
Surender Baswana, Koustav Bhanja, Anupam Roy
https://arxiv.org/abs/2507.01366

Faster Algorithm for Second (s,t)-mincut and Breaking Quadratic barrier for Dual Edge Sensitivity for (s,t)-mincut
We study (s,t)-cuts of second minimum capacity and present the following algorithmic and graph-theoretic results. 1. Vazirani and Yannakakis [ICALP 1992] designed the first algorithm for computing an (s,t)-cut of second minimum capacity using $O(n^2)$ maximum (s,t)-flow computations. For directed integer-weighted graphs, we significantly improve this bound by designing an algorithm that computes an $(s,t)$-cut of second minimum capacity using $O(\sqrt{n})$ maximum (s,t)-flow computations w.h.…

Filing: Apple sues Di Liu, a former senior product designer who worked on the Vision Pro, for allegedly stealing trade secrets and taking them to Snap (Ethan Baron/SiliconValley.com)
https://www.siliconvalley.com/2025/06/30/apple-san-jos…

Apple claims San Jose engineer stole trade secrets, took them to rival
Allegations of theft of Apple’s trade secrets in recent years have led to criminal and civil court cases.

This https://arxiv.org/abs/2503.07792 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Efficient Neural Clause-Selection Reinforcement
Clause selection is arguably the most important choice point in saturation-based theorem proving. Framing it as a reinforcement learning (RL) task is a way to challenge the human-designed heuristics of state-of-the-art provers and to instead automatically evolve -- just from prover experiences -- their potentially optimal replacement. In this work, we present a neural network architecture for scoring clauses for clause selection that is powerful yet efficient to evaluate. Following RL principle…