N.C.
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
"\^{I}n\c{t}elegi Rom\^ane\c{s}te?'' A Recipe for Romanian Vision-Language Models
arXiv:2605.31401v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) largely follow the text-only LLM trajectory, excelling on English benchmarks but sharply degrading on low-resource languages, where neither large-scale image-text corpora nor culturally grounded evaluations exist. We present a systematic study of building a language-specific VLM for Romanian, covering the full pipeline from data construction to architectural choices. We translate established English VLM...
The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size
arXiv:2606.02646v1 Announce Type: cross Abstract: Inference-time multi-agent LLM scaling lacks a shared unit: counting nominal agents conflates cost with independent evidence. We derive a two-parameter scaling law $R(N) = N_\text{eff}/N = 1/(1+c(N-1)N^{-\beta})$ where the regime exponent $\beta$ classifies any configuration into one of three asymptotic regimes -- hard-ceiling at $1/c$ ($\beta = 0$), sublinear at $N^\beta/c$ ($0 0.99$; only $(c, \beta)$ shifts. On free-form math, dense peer...
The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size
arXiv:2606.02646v1 Announce Type: new Abstract: Inference-time multi-agent LLM scaling lacks a shared unit: counting nominal agents conflates cost with independent evidence. We derive a two-parameter scaling law $R(N) = N_\text{eff}/N = 1/(1+c(N-1)N^{-\beta})$ where the regime exponent $\beta$ classifies any configuration into one of three asymptotic regimes -- hard-ceiling at $1/c$ ($\beta = 0$), sublinear at $N^\beta/c$ ($0 0.99$; only $(c, \beta)$ shifts. On free-form math, dense peer...
Deterministic Monotone Min-Plus Product and Convolution
arXiv:2605.07150v2 Announce Type: replace Abstract: The Monotone Min-Plus Product problem is a useful primitive that has seen many algorithmic applications over the past decade. In this problem, we are given two $n\times n$ integer matrices $A$ and $B$, where each row of $B$ is a monotone non-decreasing sequence of integers from $\{1,\dots,n\}$, and the goal is to compute their Min-Plus product, defined as the $n\times n$ matrix $C$ with $C_{i,j} = \min_{k}\{A_{i,k} + B_{k,j}\}$. The fastest...
Bounds for Single-Error-Correcting Analog Codes
arXiv:2606.03011v1 Announce Type: new Abstract: We study single-error correction for analog codes over $\mathbb{R}$. A key performance measure is the parameter $\Gamma_2(\mathcal{C})$, which quantifies the minimum separation required between large outlying errors that need to be located/corrected and bounded tolerable perturbations. We prove that every real linear $[n,n-2]$ code $\mathcal{C}$ satisfies \[ \Gamma_2(\mathcal{C})\ge \frac{1}{\sin^2(\pi/2n)}. This resolves Roth's open problem on...
Infinite sequences with optimal diaphony, periodic $L_2$-discrepancy, and beyond
arXiv:2606.05482v1 Announce Type: new Abstract: We investigate the periodic $L_2$-discrepancy of infinite sequences $\S_d$ in $[0,1)^d$ and its analytic counterpart, the diaphony. We prove that infinite order-2 digital sequences over $\mathbb{F}_2$ attain the optimal order $L_{2,N}^{{\rm per}}(\S_d) \le C_d (\log N)^{d/2}/N$ for all $N \in \mathbb{N}\setminus \{1\}$, matching known lower bounds for infinitely many $N \in \mathbb{N}$.
"I've Seen How This Goes": Characterizing Diversity via Progressive Conditional Surprise
arXiv:2606.01811v1 Announce Type: new Abstract: Measuring the diversity of creative outputs is central to evaluating post-training mode collapse, comparing decoding strategies, and quantifying creative behavior in both AI and human writing. We propose a new approach to measuring diversity using in-context learning, of which the ``Decan'' metric, $D_{Ca_n} = C \times a_n$, is the working instance we evaluate: a per-byte score read off the per-token log-probabilities of a base model $\theta$...
Tomography of quantum states with bounded extent
arXiv:2606.07425v1 Announce Type: cross Abstract: We give a general framework for tomography of states that have bounded-extent with respect to a structured class of states. Let $\textsf{C}$ be a family of $n$-qubit states such that: $(i)$ $\textsf{C}$ is succinctly representable and $(ii)$ there is a weak agnostic learner of $\textsf{C}$. We give a tomography protocol for an unknown state $|\psi\rangle$ that is promised to admit a decomposition of the form $|\psi\rangle = \sum_i c_i...
Counting Distinct (Non-)Crossing Substrings in Optimal Time
Announce Type: replace Abstract: Let $w$ be a string of length $n$. The problem of counting factors crossing a position -- Problem 64 from the textbook ``125 Problems in Text Algorithms'' [Crochemore, Lecroq, and Rytter, 2021] -- asks to count the number $\mathcal{C}(w,k)$ (resp. $\mathcal{N}(w,k)$) of distinct substrings in $w$ that have occurrences containing (resp.
Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling
arXiv:2605.18838v3 Announce Type: replace Abstract: Scaling laws predict loss from compute but not how capabilities interact. We measure the coupling between reasoning and truthfulness across 63 base models from 16 families and find a regime change invisible to loss curves: below a family-dependent critical scale N_c, capabilities anticorrelate (r = -0.989, p = 4 x 10^{-5} nonparametric permutation test); above it, they cooperate.