每天自动聚合 AI 领域最新动态
Training-free in-context segmentation enables new object categories to be introduced at inference time from a single ...
Plasma diagnostic models for tokamak fusion devices are almost universally evaluated on clean, complete sensor data. ...
We introduce Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a ...
Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing v...
🙌 OpenHands: AI-Driven Development（⭐81227）
A striking feature of the human visual system is that it ingests visual information through a series of local foveate...
Recent generalizable 3D Gaussian Splatting models have advanced long-sequence novel view synthesis (NVS), but at the ...
CAD-to-image alignment aims to estimate an object's 9D pose (rotation, translation, and anisotropic scale) from a sin...
In this paper we introduce token time continuous diffusion (TTCD), a new diffusion language model which (a) operates ...
Embodied cognition requires agents to connect high-level task reasoning with the physical states to be achieved. We i...
Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streami...
Validating autonomous driving systems requires diverse, regulation-compliant test scenarios. In simulation-based test...