Intelligence Artificielle - Blog

🧠

Intelligence Artificielle

A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts

arXiv:2608.23626v1 Announce Type: new Abstract: Foundation models for astronomy are trained on survey pixels together with the catalogue products derived from those pixels. Those catalogues are incomplete at a measurable rate, and a model trained on both inherits that incompleteness as a systematic. We audit AION-1, a 39-modality transformer trained on more than 200 million…

--

Équipe

2 min

Lire l'article

🧠

Intelligence Artificielle

LLM Agents Perform Controlled Experiments Using Simulation Models

arXiv:2608.23622v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong capabilities in reasoning, planning, and tool use, but many scientific and engineering tasks require more than plausible text and code generation. They require understanding how a system responds to intervention, which in practice depends on controlled experimentation. In this work,…

--

Équipe

1 min

Lire l'article

🧠

Intelligence Artificielle

ESQ-Bench: A Multi-Tier Enterprise Oracle Benchmark for Evaluating NL2SQL Dialect Generalization and Silent Semantic Divergence

arXiv:2608.23569v1 Announce Type: new Abstract: State-of-the-art Natural Language to SQL (NL2SQL) models report execution accuracy exceeding 89 percent on established benchmarks such as Spider and BIRD. However, these benchmarks rely on simplified academic schemas and open-source SQL dialects that do not reflect the complexity of enterprise database environments. We introduce…

--

Équipe

1 min

Lire l'article

🧠

Intelligence Artificielle

RENDER: Controlling Reader-Facing Evidence in LLM Memory Evaluation

arXiv:2608.23568v1 Announce Type: new Abstract: Memory and RAG evaluations often treat the answering model's input as an implementation detail, even though systems may render the same history as a memory entry, summary, typed record, or raw excerpt. We introduce RENDER, a benchmark control that fixes the conversation while varying the reader-facing artifact. RENDER combines a…

--

Équipe

1 min

Lire l'article

🤖

Intelligence Artificielle

Generalist lève 200 M$ pour accélérer les cerveaux dans la robotique

Generalist n'a pas attendu longtemps avant de retourner sur le marché. La start-up spécialisée dans l’IA appliquée à (...)

--

Équipe

1 min

Lire l'article

🧠

Intelligence Artificielle

Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding

arXiv:2608.21415v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases from their training data, resulting in biased behavior when processing portraits from different social groups. Existing debiasing approaches typically compare token probabilities…

--

Équipe

1 min

Lire l'article

Restez à la pointe de la tech

A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts

LLM Agents Perform Controlled Experiments Using Simulation Models

ESQ-Bench: A Multi-Tier Enterprise Oracle Benchmark for Evaluating NL2SQL Dialect Generalization and Silent Semantic Divergence

RENDER: Controlling Reader-Facing Evidence in LLM Memory Evaluation

Generalist lève 200 M$ pour accélérer les cerveaux dans la robotique

Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding