#Machine learning

Articles (7)

• 🇺🇸 Modelling and Simulation of Neuromorphic Datasets for Anomaly Detection in Computer Vision — 02/03/2026 [USA]

  arXiv:2602.23514v1 Announce Type: cross Abstract: Limitations on the availability of Dynamic Vision Sensors (DVS) present a fundamental challenge to researchers of neuromorphic computer vision applic...

  Related: #Neuromorphic vision, #Event‑based computer vision, #Dynamic Vision Sensors, #Dataset simulation
• 🇺🇸 From Bias to Balance: Fairness-Aware Paper Recommendation for Equitable Peer Review — 27/02/2026 [USA]

  arXiv:2602.22438v1 Announce Type: cross Abstract: Despite frequent double-blind review, systemic biases related to author demographics still disadvantage underrepresented groups. We start from a simp...

  Related: #Algorithmic fairness, #Academic publishing
• 🇺🇸 Enhancing Action and Ingredient Modeling for Semantically Grounded Recipe Generation — 19/02/2026 [USA]

  arXiv:2602.15862v1 Announce Type: cross Abstract: Recent advances in Multimodal Large Language Models (MLMMs) have enabled recipe generation from food images, yet outputs often contain semantically i...

  Related: #Multimodal language models, #Natural language generation, #Food technology, #Semantic validation
• 🇺🇸 RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language Models — 16/02/2026 [USA]

  arXiv:2510.19698v2 Announce Type: replace Abstract: Large Language Models (LLMs) can propose rules in natural language, sidestepping the need for a predefined predicate space in traditional rule lear...

  Related: #AI research, #Rule-based systems
• 🇺🇸 What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis — 16/02/2026 [USA]

  arXiv:2602.12395v1 Announce Type: cross Abstract: Reinforcement learning (RL) with verifiable rewards has become a standard post-training stage for boosting visual reasoning in vision-language models...

  Related: #AI research, #Visual reasoning
• 🇺🇸 GPT-5.3-Codex System Card — 05/02/2026 [USA]

  GPT‑5.3-Codex is the most capable agentic coding model to date, combining the frontier coding performance of GPT‑5.2-Codex with the reasoning and professional knowledge capabilities of GPT‑5.2.

  Related: #AI advancement, #Coding technology
• 🇺🇸 Quantifying non deterministic drift in large language models — 29/01/2026 [USA]

  arXiv:2601.19934v1 Announce Type: cross Abstract: Large language models (LLMs) are widely used for tasks ranging from summarisation to decision support. In practice, identical prompts do not always p...

  Related: #AI reliability, #Technology