開発者ツール
B
448 件中 421〜448 件目を表示
-
Distilling neural networks into equations to predict planetary instability
-
Hierarchical Skill Evolution for Coding Agent
-
VaLoP: Value Gradient Lookahead and Pullback for Reward-Guided Diffusion
-
Evolve on Graph: Self-Evolving Knowledge Graph Reasoning without Question Annotations
-
KAPPA: Checking the Proofs in Statistics Papers with Lean 4 and Language Model Agents
-
Agentic Algorithm Design: LLMs that Propose, Formalise, and Prove Runtime Bounds for Evolutionary Algorithms in Lean
-
Linear Probes Transfer from Base to Distilled Language Models despite Rotation
-
Distributed Predictive Flocking for a Swarm of Miniature Vibration-Driven Robots in a Confined Arena
-
Infinity Machine: a self-improving AI agent for research
-
High-resolution tactile observation makes hidden racket-control mechanisms learnable
-
Multi-Fidelity Training Reshapes Uncertainty Decomposition in Atomistic Models
-
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。
-
EXCISE: Locating and Excising Distracting Sentences in Medical Question Answering
-
Balanced Sampling in Stochastic Multi-objective Bandits
-
Explainable Prediction of High-Speed Solar Wind Streams driven by Coronal Holes via Topological Data Analysis
-
Efficient probabilistic weather forecasting at quarter-degree resolution with two-sided transport attention
-
An Algorithmic Account of Few-Shot Concept Induction in Language Models
-
Ranking Function Generation with LLMs for Termination
-
S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning
-
Depth Improves Training-Time Scaling for Difficult Tasks in Deep Linear Networks
-
MATCHA: A Chinese Multi-Disorder Mental Health Dataset with Cross-Lingual Analyses on Social Media
-
Governing Enterprise AI Traffic at Scale: Design and Operation of a Policy-Driven, Multi-Vendor LLM Gateway on Envoy
-
Constraint Learning by Optimizing over Trained Neural Networks: A Pragmatic Tutorial
-
Beyond Words Alone: Disentangling Distributed Evidence for Visually Grounded Cultural Translation
-
GPDPO: Learning from Reward Conflicts via Group Pareto-Dominance Policy Optimization
-
DOJ says presidents should be able to sell secrets on eBay司法省が「大統領は機密情報をeBayで売却できる」と主張と報道Freedom of the Pressの記事は、米司法省が大統領による機密情報のeBayでの売却を認めるべきだと主張していると伝えている。本文の抜粋が取得できていないため、詳細は元記事の確認が必要。
-
GPT-6.1 Sol helps CodeRabbit strengthen security across complex codebasesCodeRabbit、GPT-6.1 Solで複雑なコードの安全性を強化CodeRabbitは、GPT-6.1 Solを使って複雑なコードベースに潜むセキュリティリスクを調べている。同社のセキュリティエージェントは、開発者が検出結果と修正案を確認するのを助ける。
-
The Geometry of Emotion Representations Across Scale, Depth, and Instruction Tuning