arXiv
Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning
Building socially calibrated large language models, which can learn from others without simply yielding to them, requ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Unsupervised Consensus-Based Anomaly Detection for Spatiotemporal Malaria Incidence in Ghana
A consensus anomaly detection framework was applied to monthly malaria surveillance data from Ghana (2014-2023) to id...
arXiv
Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity
Faithful explanations of time-series classifiers should identify subsequences that are not only sufficient to preserv...
arXiv
Synthetic data generation framework for quality control automation in gravure printing
Quality control in printing, particularly in rotogravure printing, still depends on slow, costly, and subjective manu...
arXiv
Barzilai-Borwein Fails Superlinear Convergence on an Open Set of Quadratics for Every Dimension $n\geq 4$
Barzilai--Borwein (BB) method has shown strong practical performance in continuous optimization, yet its convergence ...
arXiv
GraphVid: Interactive Graph-Controllable Video Generation
Controllable video generation remains challenging due to the difficulty of specifying precise multi-object interactio...
arXiv
3D-Aware VLMs with Implicit and Explicit Geometries
Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when h...
HuggingFace
ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders
The recent emergence of vibe-coding workflows is changing what coding agents are expected to do. Instead of merely co...
HuggingFace
Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers
Multi-agent interactive world models should not only generate consistent observations, but also maintain world states...
HuggingFace
TableVerse: A Large-scale Tabletop Dataset with Real-world Grounded Layouts for Generalizable Manipulation
The development of generalizable robotic manipulation policies is inherently bounded by the availability of large-sca...
HuggingFace
NVIDIA-labs OO Agents: Native Python Object-Oriented Agents
Traditional agent development is split across prompt templates, tool schemas, callback code, and workflow graphs. We ...
HuggingFace
Predictive Divergence Masks for LLM RL
Reinforcement learning for large language models (LLMs) typically relies on trust-region masks to stabilize off-polic...