Multimodal

A
Showing 91–111 of 111
  • arXiv cs.CL (Computation and Language) · EN Inference & Efficiency
    Mining the Nineteenth Century for the Thirteenth: Register-Scale Forced Alignment and HTR Bootstrapping via Legacy Regesta and Antiquarian Editions
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Multimodal
    DocXEval: A Systematic Evaluation of Explainability in Multimodal Document Understanding
    Meta Transformer
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • Simon Willison's Weblog · EN New Model Releases
    GPT-6.1 Terra
    OpenAI launches GPT-6.1 Terra, fast model for visual reasoning, computer use
    Anthropic GPT Neural Network OpenAI
    OpenAI introduced GPT-6.1 Terra, a fast, efficient model emphasizing detailed visual reasoning, precise computer use and clearer writing, a significant step up from GPT-5.6 Terra. Simon Willison notes it sits where Sonnet does in Anthropic's lineup, and suits repetitive automated computer-use tasks.
    Read original (Simon Willison's Weblog) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Multimodal
    Learning Force-Reactive Humanoid Loco-Manipulation
    Neural Network
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Multimodal
    Profiling a Frontier Agent with EBench: From Direct Control to Harness with Policy
    Computer Vision GPT Machine Learning Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Training & Fine-tuning
    Pretraining Knows What, Simulation Teaches How: Compositional Generalization in a Sim-Trained Robot Agent
    Computer Vision Fine-tuning GPT Neural Network Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    EEGaze: Multimodal Attention Prediction in Visual Search via EEG-Based Saliency Refinement
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Multimodal
    Explainable Multimodal AI Approach to Reduce Unnecessary Breast Biopsies
    Computer Vision Embeddings Neural Network Reinforcement Learning Transformer
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.CL (Computation and Language) · EN Inference & Efficiency
    From Self-Confidence to Statistical Accuracy: Scaling Human-in-the-Loop Evaluation with Direct and LLM-Assisted Auditing
    Inference Machine Learning
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Inference & Efficiency
    EvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy Distillation
    Neural Network Retrieval-Augmented Generation (RAG) Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    TrySee: Modular Perception-Enhanced VLM Grounding for Closed-Loop Robot Task Planning in Specialized Domains
    Fine-tuning Neural Network Reinforcement Learning Robotics
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.CL (Computation and Language) · EN Multimodal
    Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews
    GPT Neural Network
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Multimodal
    Provably Efficient Q-learning for Robust Reinforcement Learning
    AI Agents Algorithms & Theory Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Multimodal
    From Language to Drives: A Multimodal Framework for Aligning Autonomous Robots with Human Purposes
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Training & Fine-tuning
    VaLoP: Value Gradient Lookahead and Pullback for Reward-Guided Diffusion
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Inference & Efficiency
    ArchiveLens: A Generative Spatial Knowledge Framework for Semantic Reconstruction of Historical Maps
    Computer Vision Quantization Retrieval-Augmented Generation (RAG)
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Developer Tools
    KAPPA: Checking the Proofs in Statistics Papers with Lean 4 and Language Model Agents
    AI Agents Claude Software Engineering
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Infrastructure & Hardware
    SAP-ViT: A Self-Attributing Patch Vision Transformer for Medical Image Classification
    Embeddings Neural Network Retrieval-Augmented Generation (RAG) Reinforcement Learning Transformer
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • Sakana AI Blog (ja) · EN New Model Releases
    Taking Japan-Born AI Products to the World: An Interview with Sakana AI’s VP of GTM
    Sakana AI's GTM chief on taking research-born products global
    Neural Network Reinforcement Learning Robotics
    In 2026 Sakana AI launched Sakana Chat, Marlin, Fugu and Translate, shifting from an R&D firm to delivering products to companies and government agencies. Its GTM team started in earnest in September under VP Hidekazu Kakishima, who previously helped launch new tech at AWS Japan, SORACOM and Skydio. The interview covers why Sakana AI and why now, how to sell research-born products, and what it is like to build a team with few established systems.
    Read original (Sakana AI Blog (ja)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Multimodal
    Generative Structure from Motion with Native 3D Diffusion
    Computer Vision Neural Network Transformer
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.CL (Computation and Language) · EN Developer Tools
    GPDPO: Learning from Reward Conflicts via Group Pareto-Dominance Policy Optimization
    Reinforcement Learning Reinforcement Learning from Human Feedback (RLHF)
    Read original (arXiv cs.CL (Computation and Language)) ↗