Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments
As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to f...
每天自动聚合 AI 领域最新动态
As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to f...
The prevalent dual-branch paradigm, i.e., training a side network to encode visual conditions and fusing its intermed...
Earth Observation (EO) forecasting aims to predict future Earth surface dynamics from satellite observations under ch...
Reasoning capability has advanced rapidly in large language models (LLMs), leading to an increasing size of key-value...
Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings rema...
ABACUS is a unified vision-language model that handles object counting, crowd counting, referring-expression counting...
We present a conceptual framework for analyzing dialogue in collaborative problem-solving contexts, with an emphasis ...
AI nudification uses generative models to create synthetic non-consensual sexually explicit imagery (SNEACI) of real ...
Building persistent embodied agents in unstructured environments demands unified orchestration of heterogeneous tools...
Recently, a few works have made early attempts to study test-time scaling for embodied tasks. However, two major chal...
Earth Observation (EO) forecasting aims to predict future Earth surface dynamics from satellite observations under ch...
Mechanistic epidemiological models are widely used to support infectious disease forecasting and public-health decisi...