每天自动聚合 AI 领域最新动态
Multimodal Large Language Models (MLLMs) demonstrate strong performance on standard visual question answering benchma...
Midway through an ordinary pretraining run, a small language model learns the pronoun-gender rule: cued with a girl's...
AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems...
The laser welding full-penetration is of critical importance, as it constitutes one of the fundamental factors in ach...
A central goal of safety research is determining whether a model is misaligned. Prior work has largely focused on det...
Supervised deep learning has been widely used for weld penetration state classification; however, its performance oft...
Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings rema...
On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student, with...
Most Vision-Language-Action (VLA) models build on a Vision-Language Model (VLM) backbone by attaching an action modul...
Unified multi-modal large language models (MLLMs) have achieved strong text-to-image generation quality, but still st...
While Large Language Models (LLMs) have substantially advanced text-to-code synthesis, many real programming tasks sp...
Autoregressive video diffusion with causal diffusion transformers has emerged as a major paradigm for real-time strea...