每天自动聚合 AI 领域最新动态
Recent video generation models can produce highly realistic videos from natural language instructions, with visual qu...
Streaming video LLMs must retain evidence before its relevance to future tasks is known and respond when sufficient e...
Vision language model (VLM) agents can control robots through visual feedback and action primitives, but repeated mod...
Group Relative Policy Optimization (GRPO) is widely used to train reasoning language models, where it computes advant...
Video Large Language Models (VideoLLMs) receive frames in sequential order and interpret how visual content evolves a...
Backdoor attacks can be implanted in Large Language Models (LLMs) during training, causing unwanted behaviour when a ...
Generalization in large language models (LLMs) is the ability to produce consistent and semantically stable outputs w...
Predicting the future evolution of a scene is a fundamental capability for world modeling. Recent work has shown that...
Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities, yet whether they truly capture the...
Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidl...
Web text makes up the majority of pretraining data and is increasingly AI-generated. After applying FineWeb quality f...
Length scaling during reinforcement-learning (RL) post-training is often viewed as a sign of improved reasoning abili...