Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
Bibliometric analysis of 7,120 Arabic NLP papers (1960–2026) identifies research trends, topic evolution, and gaps via BERTopic and social network analysis.
Characterizes low-resource language underperformance in LLMs via representational geometry, finding degeneration in final layers.
AI factories are interconnected systems where fleet economics depend on how efficiently the entire stack converts power and capital into completed agent tasks.... AI factories are interconnected systems where fleet economics depend on how efficiently the entire stack converts…
VIALS benchmark reveals frontier vision-language models fail on biotech artifact interpretation (gel blots, microscopy, flow cytometry) from real experimental workflows.
Study shows generation, critique, and revision stages in LLM self-refinement have asymmetric computational requirements; smaller models sufficient for some stages.
Analysis of prompt-model interaction fixed-point structure independent of task performance metrics.
Rank-calibrated multi-stream anomaly detector for operational telemetry using copula dependence and AR(1) innovations.
AI factories are power-constrained industrial systems. The question is no longer how many GPUs fit in a data center, but how much AI output each available... AI factories are power-constrained industrial systems. The question is no longer how many GPUs fit in a data center, but…
SRL-MPC combines RL with MPC for shape-aware navigation of heterogeneous robots in dense crowds without geometry simplification.
IAR: three-stage post-training framework (inject, align, recover) for internalizing bounded document corpora into LLM parametric knowledge.
Transfer learning framework for nonparametric regression using deep ReLU networks with group-specific offsets and L2 error bounds.
Empirical evaluation framework audits cross-lingual fairness in LLM watermarking with calibrated thresholds and threshold-independent quality metrics across languages.
Simon Willison discusses productivity metrics for AI coding agents, arguing lines of code can meaningfully measure agent output despite conventional skepticism.
Geometric iterative retrieval improves neural audio codec resynthesis from RVQ tokens by treating layer hierarchy as natural continuous decomposition.
Frontier LLMs saturate on accuracy; precision (output consistency) rather than capability now determines practical advantage, reframing the metrics.
Learning Random Geometric Graphs via probabilistic metric spaces for generic multivariate dataset representation.
Fuzzy accuracy metric addresses label subjectivity in Fitzpatrick skin tone classification from PPG signals, improving 40-55% accuracy.
Two large-scale surveys (N≈2,800 each) reveal asymmetric user acceptance of autonomous LLM agents in dating platforms: users accept delegation and reception differently.
Small language models for invoice GL categorization analyzed via embedding geometry for interpretability and cost reduction.
LLM hidden state manifolds organize as small-world networks enabling multi-hop reasoning; bypasses attention artifacts via geometric analysis.
Collective Counterfactual Planning formalizes multi-agent coordination where representational geometry constrains perception and goal verification.
Probing study reveals six frozen LLMs encode geometric constraints in hidden states but fail to steer behavior using them.
Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to the wrong same-class instance. Generic visual-question-answering accuracy marks the response as wrong, while object-hallucination metrics may regard both the…
High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent state, leaving retrieved evidence functionally irrelevant. We call this failure mode query dominance. To address it, we introduce \textbf{GRIP} (Grounded Reasoning via…
Large Language Models (LLMs) are increasingly being deployed in cybersecurity operations to assist cybersecurity analysts with rapid decision-making against emerging threats. However, there is a main criteria that must be met when using LLMs in cybersecurity, that is, trust in…
Physical design algorithms operate within tightly coupled, multi-stage optimization flows, where stage-local gains may vanish or induce downstream degradation. Existing program-evolution frameworks often rely on stage-local objectives or undifferentiated multi-metric feedback…
The language-model head maps a hidden state of width D to a vocabulary of size V, so its transpose can return at most D independent directions to the Transformer. Godey and Artzi argue that this severe projection is a harmful optimization bottleneck. We separate the geometry…
This paper presents Chronocooked, a reinforcement learning (RL) benchmark suite for studying implicit interval timing in RL agents. Inspired by Overcooked, the suite comprises cooking scenarios that require temporal decision making. The tasks and reward functions are designed…
We study the Random Quadratic Form (RQF) on a sphere in the presence of random Brownian forcing. We show that the forcing does not effectively change the law of the process but affects the synchronization properties of the system. While the RQF without forcing exhibits partial…
We present QuantumPhaseNet, a gauge-covariant geometric and quantum-spectral extension of Transformer representations. Context-dependent semantic states are modeled as complex amplitudes; a covariant phase rate induces a semantic wavelength used as a proxy for conceptual scale…