開発者ツール B

Asymmetric Communication: Large Language Models and Language Games

LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation Learning

ConMem: Contribution-Aware Memory for Long-Horizon Manufacturing Inspection Logs

Information Bottleneck Learning for Faithful Time Series Forecasting Explanations

Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training

MIND: Lightweight and Effective Memory Injection Defense for LLM Agents via Intent-Aware Information Bottleneck

PCAP-LM: An LLM-Native Text Representation for TLS Bulk Traffic Analysis

Meteosat Third Generation imagery improves CNN-based SSI retrieval

PerturbMap: Cross-Context Transfer of Single-Cell Perturbation Responses

Diversifying Personalized Research Ideation against AI-Induced Homogenization

On a joint simultaneous learning of relevant feature subsets and subspaces in regression-like problems

Chem World: A Large-Scale Benchmark and Physics-Informed Framework for Trustworthy Chemical Property Prediction

LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models

Group-Reflective Self-Distillation for Agentic Reinforcement Learning

Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs

Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale

Stimulus-Evoked Network Dynamics in Human Cortical Organoids: From a Graph-Computational Framework to Repeated-Stimulation Depression

Learning features from Newton's algorithm: a way to accelerate nonlinear parametrized PDE solvers

Enhancing Irregular Time Series Forecasting with Continuous-Time Modeling Framework

Flux-OPD: On-Policy Distillation with Evolving Contexts

Building a User Foundation Model for the Open Web

Generalization and Trade-off in Adversarial Training: An RKHS Perspective via Kernel Integral Operators

It's All Just Vectorization: einx, a Universal Notation for Tensor Operations

What Makes Graph Unified? Principles and Generative Sliding-Window Transformer for Graph Foundation Models

Google will expand age checks on Android worldwide till the end of the year

AutoPref: Automatic Discovery of Task-Specific Preference Objectives for Neural Combinatorial Optimization

Complementary Matrix-Gated QKAN Fast-Weight Programmers for Quantum Dynamics Forecasting

TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

Harnessing the Potential of Optimizing Data Mixtures via Bayesian Domain Reweighting

IFHierBench: Hierarchical Instruction Following for Large Language Models