マルチモーダル
A
112 件中 91〜112 件目を表示
-
Mining the Nineteenth Century for the Thirteenth: Register-Scale Forced Alignment and HTR Bootstrapping via Legacy Regesta and Antiquarian Editions
-
DocXEval: A Systematic Evaluation of Explainability in Multimodal Document Understanding
-
GPT-6.1 TerraOpenAI、視覚推論とコンピュータ操作に強い高速モデルGPT-6.1 Terraを発表OpenAIが高速で効率的なモデルGPT-6.1 Terraを発表。詳細な視覚推論と精密なコンピュータ操作、より自然な文章力を備え、GPT-5.6 Terraから大きく進化した。Simon Willisonは、AnthropicのSonnetに近い中間的な位置づけで、反復的な自動操作作業に向くと指摘している。
-
Learning Force-Reactive Humanoid Loco-Manipulation
-
Profiling a Frontier Agent with EBench: From Direct Control to Harness with Policy
-
Pretraining Knows What, Simulation Teaches How: Compositional Generalization in a Sim-Trained Robot Agent
-
EEGaze: Multimodal Attention Prediction in Visual Search via EEG-Based Saliency Refinement
-
Explainable Multimodal AI Approach to Reduce Unnecessary Breast Biopsies
-
From Self-Confidence to Statistical Accuracy: Scaling Human-in-the-Loop Evaluation with Direct and LLM-Assisted Auditing
-
EvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy Distillation
-
TrySee: Modular Perception-Enhanced VLM Grounding for Closed-Loop Robot Task Planning in Specialized Domains
-
Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews
-
Provably Efficient Q-learning for Robust Reinforcement Learning
-
From Language to Drives: A Multimodal Framework for Aligning Autonomous Robots with Human Purposes
-
VaLoP: Value Gradient Lookahead and Pullback for Reward-Guided Diffusion
-
ArchiveLens: A Generative Spatial Knowledge Framework for Semantic Reconstruction of Historical Maps
-
KAPPA: Checking the Proofs in Statistics Papers with Lean 4 and Language Model Agents
-
SAP-ViT: A Self-Attributing Patch Vision Transformer for Medical Image Classification
-
Taking Japan-Born AI Products to the World: An Interview with Sakana AI’s VP of GTMSakana AI、GTM責任者に聞く研究発の製品を世界へ届ける戦略Sakana AIは2026年にSakana Chat、Marlin、Fugu、Translateを相次いで発表し、研究開発企業から企業・官公庁向けに製品を届ける段階に入った。9月に本格始動したGTMチームを率いるVP柿島氏は、AWS Japan、SORACOM、Skydioで新技術の事業化を担ってきた人物。インタビューでは、なぜ今Sakana AIなのか、研究由来の製品をどう売るか、仕組みが未整備のチームで働く面白さを語る。
-
Generative Structure from Motion with Native 3D Diffusion
-
GPDPO: Learning from Reward Conflicts via Group Pareto-Dominance Policy Optimization
-
ImgMT: Wikipedia-based Dataset For Evaluating Text-in-Image Translation