開発者ツール
B
439 件中 331〜360 件目を表示
-
QD-PINN:A Physics-Informed Neural Network Approach to Bayesian Quickest Detection in High-Dimensional Diffusions
-
PerceptRL: Making Visual Perception Rewardable in MLLMs from Answers to Interactions
-
Autonomous fixed-wing interception using reinforcement learning
-
What Carries Forward? Pretraining Disclosure Across Language Model Releases
-
Concordat: Typed Sessions for LLM Agents
-
M4Bench: Evaluating Procedural Specification for Clinical EHR Derivation Agents
-
ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents
-
Multi-Agent Reinforcement Learning of Co-Adaptive Hip Exoskeleton Control (MARL-Exo) for Metabolic Energy Reduction
-
Representing the Unseen: Rethinking Visual Imagination for Spatial Reasoning
-
FeatureArc: Benchmarking Coding Agents on Evolving Features
-
Nidec anounces 3.2MW in-row CDUNidec、3.2MWのインロークーリング用CDUを発表Nidecが3.2MWのインロウ型CDU（冷却液分配装置）を発表した。新製品は来年に量産に入る予定。
-
Beyond the Readout: A Latent Numerical Frame Shared Across Modality and Operation
-
Displacement Moments and Path-Terminal Separation in Brownian Interpolant Sampling
-
Constraining the Commit Boundary: A DIO/ODI-Informed Authorization Guardrail for Agentic Entity Resolution
-
Clearing the FoG: Training KG Agents to Retrieve the Evidence Behind Their Answers
-
An end-to-end framework for uncertainty-aware validation of generative models
-
Game-Theoretic Solvers with Bayesian Opponent Modeling and Moral Rhetoric Framing for GLEE
-
Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data
-
Euclidean Crowding-Driven Adaptive Euclidean-Hyperbolic Graph Learning
-
The Geometry of Manifold Learning: Singular foliations via Deep Learning models
-
Retell uses OpenAI models to help power 100M monthly callsRetell、OpenAIモデルで月間1億件の通話を支える音声エージェントのRetellでは、GPT-6 Astraが同社のベンチマークで首位になったと紹介されている。また、Codexの活用により、従業員1人あたりの年間売上ランレートが160万ドルに達したという。
-
3 Ways to Boost MoE Inference on NVIDIA DGX SparkNVIDIA、DGX Spark上でMoE推論を高速化する3つの方法を紹介NVIDIAの開発者ブログが、DGX SparkでMoE(専門家混合)モデルの推論を速くする3つの方法を解説した。トークン生成を速めるには、まず推論性能を何が制約しているかを見極めることが出発点だとし、Inclusion AIのLing-3.0-flashをバッチサイズ1で評価した結果を例に検討している。
-
Aligning Institutional Power and Operational Ability
-
Normative Deviation Modeling for EEG-based Depression Detection
-
CoS-VQ: Coordinated Shared-Scale Vector Quantization for Large Language Models
-
WCC: A Learning-Based Framework for Deciding When to Apply Cooperative Coevolution in Large-Scale Optimization
-
UCVE: Graph Structured Retrieval for Compliance Validation
-
ReForest: Interpretability Meets Reasoning in Isolation Forest
-
Multi-Label Agreement: A Flexible Framework for Inter-Annotator Reliability
-
Modeling Preference Dependencies with Directed Acyclic Graphs for Narrative-Driven Recommendation