開発者ツール
B
439 件中 151〜180 件目を表示
-
OCCAMS: A Multi-Task Learning-Based Investigation of the CMB Power Spectra
-
Bridging Neural Representations and Symbolic Semantics in Audio Classification
-
Retrieving from Your Own Mistakes: On-Policy Training of Embedding Models for Multi-Hop Retrieval-Augmented Generation
-
SCARL: Sequence Confidence-Aligned Reinforcement Learning
-
Continuous-Action World Models: Learning Cross-Embodiment Spatiotemporal Dynamics Priors
-
Deep Learning Based Behavioral Drift Modeling for Continuous Biometric Authentication
-
Beyond Selected Breakthroughs: Evaluating Language Models on Randomly Sampled Mathematical Conjectures
-
Agentic LLM reasoning in pediatric diabetes outcome prediction from multimodal medical records
-
The Athlete as a Scientist of One: Agentic Bayesian Experimental Design for Individualized Physiology from Consumer Wearables
-
Is It the Curriculum or Just the Easy Start? Benchmarking Unsupervised Environment Design on Quadrupeds
-
Your LR Schedule May Not Be Principled: Effective Learning Rate Scheduling in Weight-Normalized Training
-
A Unified Hessian-Guided Framework for Post-Training Quantization
-
Multistep and Multivariate Time Series Explainability with GradientSHAP: A Wind Power Case Study
-
Factorized Representations of Concurrent Temporal Variables in Pretrained Language Models
-
Radiology Guideline-derived Decision Graph for Efficient Clinical Decision Support
-
Decision and System One models in rheumatology: accuracy and calibration on specialty-training examination questions and diagnostic case vignettes
-
Causal-prior-constrained deep learning for rapid-intensification warning of western North Pacific tropical cyclones
-
TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents
-
From MS/MS evidence to adaptive spectroscopic characterization: Reinforcement learning guided by candidate molecular structures
-
Learned Terminal Costs for Short-Horizon Model Predictive Control of Autonomous Trucks in Interactive Highway Traffic
-
Statistical Analysis of Synthetic Data with Verification: A Linear Regression Framework
-
Mobilizing the Archive: Bitext Extraction at Scale from Archival Documents for Extremely Low-resource Languages
-
EpiAgent: Epistemic Self-Play for LLM Agents
-
Unlocking Tensor Core Performance for Machine Learning Interatomic PotentialsNVIDIA、機械学習原子間ポテンシャルのTensor Core高速化を解説原子スケールのシミュレーションは、化学反応や相転移、機械的破壊など分子や材料の振る舞いを理解するために使われる。NVIDIAの開発者ブログは、機械学習原子間ポテンシャル(MLIP)の計算でTensor Coreの性能を引き出す方法を取り上げている。
-
Towards Full-Text Scholarly Argument Mining using Entity-Anchored Claim Extraction
-
One Vector or Many? Clustered Optimal-Transport Steering under Quantization
-
Can LLMs Ignore What They Know? Measuring Knowledge Leakage in Persona-Based User Simulation
-
Prompts and probabilities in the linguistic assessment of language models: Evidence from semantic focus-sensitivity
-
Surprise Alone Learns Lies: Evidence-Gated Continual Learning for LLMs from Streaming Claims
-
Qwenputer: a fully functioning, deterministic RISC-V CPU inside Qwen3.5Qwen3.5の内部で動く決定論的RISC-V CPU「Qwenputer」Lobstersで共有されたブログ記事で、題名によれば、LLMのQwen3.5の内部で決定論的に動作するRISC-V CPUを実現したとするプロジェクト「Qwenputer」を紹介している。本文は取得できておらず、実装方法や性能の詳細は未確認。