New Model Releases A

Showing 271–300 of 315
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    Stemma: Induced Decision Regions Reveal LLM Provenance
    Inference Neural Network Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Policy & Regulation
    Runtime Uncertainty Monitoring for LLM-Based Multi-Agent Systems Using Bayesian Networks
    AI Agents Meta
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    A2TTA: Anchored-and-Agile Test-Time Adaptation for Evolving Traffic Sensor Networks
    Neural Network Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    OmniQEC: discovering practical quantum error-correcting codes by an AI scientist
    Deep Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.LG (Machine Learning) · EN New Model Releases
    DRIFT: Direct-Recursive Intervention-Conditioned Forecasting of ICU Physiological Trajectories
    Retrieval-Augmented Generation (RAG) Reinforcement Learning from Human Feedback (RLHF) Transformer
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    Shieldstral
    Reinforcement Learning Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • Data Center Dynamics · EN New Model Releases extract
    China to launch new cable laying vessel next month, Global Marine Group commissions new vessel
    China and Global Marine to add new subsea cable-laying vessels
    China is set to launch a new cable-laying vessel next month, while Global Marine Group has commissioned its own new ship. The two vessels are expected to debut in 2026 and 2029 respectively, expanding global subsea cable installation capacity.
    Read original (Data Center Dynamics) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    Lowering the implementation barrier of neutral-atom quantum computing with agentic workflows
    Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • Data Center Dynamics · EN New Model Releases extract
    Johnson Controls releases absorption chiller reference design
    Johnson Controls unveils absorption chiller reference design for DCs
    Johnson Controls has released a reference design for an absorption chiller, outlining how data centers can reuse waste heat for cooling. The approach aims to improve energy efficiency and cut cooling costs amid rising thermal management demands.
    Read original (Data Center Dynamics) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Inference & Efficiency
    Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RL
    AI Agents Retrieval-Augmented Generation (RAG) Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    WorkSurface-Bench: Benchmarking Enterprise Agents on Multi-Surface Knowledge Routing
    AI Agents Neural Network Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    From Deterministic to Generative Deep Learning for Urban Air Quality Reconstruction from Sparse Observations
    Deep Learning Machine Learning Retrieval-Augmented Generation (RAG) Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Infrastructure & Hardware
    Rashomon Alignment
    Algorithms & Theory Machine Learning Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.LG (Machine Learning) · EN Developer Tools
    Contextual Deconvolution for Variance-Stable Demand Sensing: Kernel-Modulated Operators in Promotional Retail
    Machine Learning
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    Localized Adaptation Reveals Distinct Learning Signatures in Transformers
    Deep Learning Neural Network Reinforcement Learning Transformer
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    AIriskEval-edu Demo: Auditing of Pedagogical Risks in Educational Explanations
    GPT Llama Neural Network
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Funding & M&A
    Beyond Self-Knowledge: Propagating Uncertainty Across Reasoning and Retrieval in LLMs
    Neural Network Retrieval-Augmented Generation (RAG) Reinforcement Learning Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Multimodal
    Forensic Reproducibility Audit of a Radiology Vision-Language Model Benchmark: From Intended Protocol to Released Artifact
    Claude Computer Vision Meta Neural Network
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.LG (Machine Learning) · EN New Model Releases
    Multi-Scale Structural Features for Continual, Comprehensible Visual Recognition in a Developmental Learning Framework
    Machine Learning Retrieval-Augmented Generation (RAG) Reinforcement Learning
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.LG (Machine Learning) · EN New Model Releases
    AMPBench-MT: A Homology-Controlled Benchmark for Antimicrobial Peptide Potency, Spectrum, and Safety Prediction
    Embeddings Neural Network Reinforcement Learning from Human Feedback (RLHF)
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    Phase Structure in Rotary Attention: A Spectral Framework for Semantic Continuity and Execution-Boundary Governance
    Embeddings Machine Learning Neural Network Transformer
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • ITmedia AI+ · JA New Model Releases extract
    「痺れるほどにミスを繰り返す」Gemini 3.6 Flashは変わった？　公開から1週間、当初のおバカ回答を今検証する
    ITmedia re-tests Google's Gemini 3.6 Flash a week after launch
    Gemini Google
    ITmedia revisits Google's Gemini 3.6 Flash about a week after its release. Just after launch, the model drew attention on X for shaky accuracy, including botched numerical comparisons and an answer about a fictional fish. The piece re-runs those early wrong answers to check whether its behavior has improved.
    Read original (ITmedia AI+) ↗
  • arXiv cs.CL (Computation and Language) · EN Developer Tools
    Memory for Large Language Models
    Neural Network Retrieval-Augmented Generation (RAG)
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Funding & M&A
    CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition
    Neural Network Reinforcement Learning Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    Where Steering Signals Come From: Activation Source Selection in Activation Steering
    Inference Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    VisualPatchWorld: Code World Models as Latent Structured Representations for Planning
    Neural Network Reinforcement Learning
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    A Cross-lingual Comparison of Human and Classification Model Entrainment Behavior in Code-switched Speech Settings
    AI Agents Speech Processing Transformer
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    MyoCardBench: A Real-World Data Benchmark for Evaluating Large Language Models in Clinically Authentic Cardiovascular Care Scenarios
    Gemini GPT Neural Network Retrieval-Augmented Generation (RAG) Reinforcement Learning
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • Simon Willison's Weblog · EN New Model Releases extract
    moonshotai/Kimi-K3
    Moonshot releases weights for Kimi K3, a 2.8-trillion-parameter model
    Retrieval-Augmented Generation (RAG) Reinforcement Learning
    Moonshot AI released the weights for Kimi K3, a 2.8-trillion-parameter LLM that runs to 1.56TB on Hugging Face. With K2 in July 2025 the company added a modified MIT license requiring commercial products with over 100M monthly active users or $20M in monthly revenue to prominently display 'Kimi K2' in their UI. Reported via Simon Willison's link-blog; details past the license clause are truncated in the source excerpt and unconfirmed.
    Read original (Simon Willison's Weblog) ↗
  • Simon Willison's Weblog · EN New Model Releases extract
    An opinionated guide to which AI to use to do stuff
    Simon Willison on Ethan Mollick's updated guide to which AI to use
    AI Agents Claude Gemini Google GPT
    Simon Willison links to Ethan Mollick's evolving guide on which AI to use for tasks. A year ago it centered on chat (ChatGPT, Claude, Gemini); today it emphasizes agentic systems doing the equivalent of hours of human work. Gemini has dropped off Ethan's list, while modes such as ChatGPT Work/Codex and Claude Cowork/Code are explained. Note: the excerpt is truncated at the end, so later details could not be verified.
    Read original (Simon Willison's Weblog) ↗