Developer Tools

B
Showing 181–210 of 326
  • ITmedia AI+ · JA Agents & Tool Use
    その.envのAPIキーが、AIエージェントを「内通者」に変える――“人間前提のやり方”は破綻した
    That API key in .env can turn your AI agent into an insider threat
    AI Agents
    As AI agents spread, the credentials behind them, API keys and tokens, are multiplying. The article argues that key management designed around human users breaks down once always-on agents act autonomously, and that a single key left in a .env file can make an agent an insider.
    Read original (ITmedia AI+) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science
    Gemini Google Inference Machine Learning Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.LG (Machine Learning) · EN Developer Tools
    A Chosen Future Can Still Be Rewritten: Causal Writability in Video Models
    Reinforcement Learning
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.CL (Computation and Language) · EN Training & Fine-tuning
    Disentangling Representation Evolution in Transformers through Directional Decomposition
    Deep Learning Machine Learning Neural Network Retrieval-Augmented Generation (RAG) Transformer
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Multimodal
    Discovery Foundation Models: Toward Open-Ended Discovery Intelligence
    Neural Network Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Inference & Efficiency
    Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States
    Llama Reinforcement Learning
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Developer Tools
    Verifiable by Construction: Claim-Level Evaluation of Verbatim Citation in Clinical Question Answering
    Claude Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale
    AI Agents Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses
    AI Agents Algorithms & Theory Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Safety & Evaluation
    Recurrent GraphNeural NetworkswithSet-BasedAggregation
    Neural Network Retrieval-Augmented Generation (RAG)
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Industry Adoption
    Pilot Early, Commit Late: A Real-Options Model of Enterprise AI Adoption under Rapid Technological Progress
    Deep Learning Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.LG (Machine Learning) · EN Inference & Efficiency
    Bridging Control, Inference, Transport, and Thermodynamics: From Theory to Applications in Learning
    Inference Machine Learning Neural Network Reinforcement Learning
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Training & Fine-tuning
    LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys
    Llama Retrieval-Augmented Generation (RAG) Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Training & Fine-tuning
    LongAgent: History-Guided Agentic Search for Longitudinal Outcome Prediction
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.LG (Machine Learning) · EN New Model Releases
    Task-Directed Residual AddUNet:Perfect-Reconstruction Routing for Full-Rate Representations
    Neural Network Reinforcement Learning
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Training & Fine-tuning
    K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations
    GPT Retrieval-Augmented Generation (RAG) Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.CL (Computation and Language) · EN Inference & Efficiency
    Learning to Coach for Experiential Learning
    Inference Neural Network
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.LG (Machine Learning) · EN Inference & Efficiency
    Proportional-Fair Resource Allocation and Dual-Threshold Early-Exit Inference for Secure Cooperative Multi-Layer Edge Intelligence
    Inference Meta Neural Network Reinforcement Learning
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • NVIDIA Developer Blog · EN Infrastructure & Hardware
    Accelerating Dropless MoE Training in JAX with NVIDIA Transformer Engine
    NVIDIA boosts JAX dropless MoE training 10x with Transformer Engine
    DeepSeek Mistral Mixture of Experts (MoE) NVIDIA Transformer
    NVIDIA details Transformer Engine optimizations for dropless MoE training in JAX: grouped GEMM for ragged expert shapes, MXFP8 quantization, and fused dispatch/combine via NCCL EP. DeepSeek-V3 671B throughput rose from 103 to 1,068 TFLOPS/GPU (10.4x), with 97% scaling efficiency at 1,024 GPUs.
    Read original (NVIDIA Developer Blog) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    Per-Matrix Optimality Is Not Enough: Three-Level Optimization for Low-Rank LLM Compression
    Llama Neural Network Software Engineering Transformer
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Safety & Evaluation
    CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering
    Retrieval-Augmented Generation (RAG) Software Engineering
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.LG (Machine Learning) · EN Safety & Evaluation
    Sharp Rates and a One-Line Correction for Spectral Representation Learning
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Training & Fine-tuning
    AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery
    AI Agents Deep Learning Machine Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.LG (Machine Learning) · EN Developer Tools
    Accelerating Transfer-Learning-Based Autotuning with Predictive LLVM IR Performance Ranking
    Machine Learning Retrieval-Augmented Generation (RAG)
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Agents & Tool Use
    Delegating Authorization to Misaligned Agents: Coalitional Alignment and Safe Control
    AI Agents Neural Network Retrieval-Augmented Generation (RAG)
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    When Should a World Model Move? Loss-Conditioned State Execution
    Retrieval-Augmented Generation (RAG) Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Training & Fine-tuning
    Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and Consolidation
    Retrieval-Augmented Generation (RAG) Reinforcement Learning Software Engineering
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.LG (Machine Learning) · EN New Model Releases
    MoveBench: A Benchmark for Global-Scale Wildlife Movement Forecasting
    Deep Learning
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    EvoOntology: A Self-Evolving Ontology Layer for Data Agents
    AI Agents Model Context Protocol (MCP)
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Multimodal
    Transfer Learning for Socioeconomic Estimation in Forced-Displacement Settings
    Machine Learning Retrieval-Augmented Generation (RAG) Reinforcement Learning Transformer
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗