每天自动聚合 AI 领域最新动态
Scaling vision-language-action (VLA) models is constrained by scarce action-labeled demonstrations and incompatible c...
Can LLM agents carry a hard real-world problem from raw data to a system that holds its own against people? We study ...
Rubric-based rewards enable effective reinforcement learning on non-verifiable tasks. However, because these rewards ...
Spatial audio authoring coordinates source decisions with soundfield synthesis. For editing, plans specify what to ch...
Recursive self-improvement (RSI), in which a system also improves the way it improves, is a long-standing aspiration ...
Feed-forward models accurately estimate camera motion and 3D geometry from short video windows. However, computationa...
Critic-free methods are widely used in reinforcement learning with verifiable rewards (RLVR) for long chain-of-though...
While Multimodal Large Language Models (MLLMs) excel at zero-shot reasoning, their spatial capabilities are primarily...
Hallucination detection is increasingly important for evaluating and deploying large language models. However, existi...
Mixture-of-experts (MoE) transformers, the standard backbone for modern large-scale deep learning, employ conditional...
Large-scale AI training increasingly relies on massive video datasets with random temporal sampling patterns. However...
Embodied agents are expected to accomplish real-world goals by deciding for themselves how and when to interact with ...