每天自动聚合 AI 领域最新动态
LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused i...
Generative world renderer AlayaRenderer receives structured world states exported from physics engines and synthesize...
Teaching videos are becoming a major medium for education, creating a growing need for scalable evaluation of their p...
Optimizer state is the largest single line item in the memory budget of mixture-of-experts (MoE) training: on a 6.78B...
Accurate agricultural field boundary delineation at large scale is a foundational task for food security, supply chai...
Multimodal humor in memes, cartoons, and comics remains difficult for AI systems because intended meaning depends on ...
Optical coherence tomography (OCT) imaging is essential for the diagnosis and treatment of retinal diseases. Although...
Current video generation models achieve impressive results in single-shot generation, yet remain limited in cinematic...
Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly. T...
Egocentric videos of human manipulation provide scalable supervision for embodied intelligence, yet existing resource...
Structure-based drug design (SBDD) leverages the 3D structure of protein targets, often complemented by other spatial...
Egocentric devices, such as wearable front-facing cameras, provide a unique perspective for capturing the continuous ...