每天自动聚合 AI 领域最新动态
On-policy distillation (OPD) transfers teacher capabilities by supervising trajectories sampled from the student's ow...
Real-world image search queries are multimodal and compositional: ``find this shirt in pink'' specifies an entity to ...
Small language models are usually built like large ones and then squeezed onto a CPU afterwards. We did the opposite:...
Semantic vision encoders have become a central visual interface for multimodal understanding and semantic conditionin...
Take three frontier mixture-of-experts models (Alibaba, OpenAI, NVIDIA; 3.6-4.0B active parameters each) and fine-tun...
Current dexterous grasp planners primarily optimize for physical stability, focusing on whether an object can be gras...
Multifingered grasping is a crucial robotic skill, but current deep-learning grasp planners often struggle to general...
Modern LLM agents are often improved by modifying prompts, tools, or workflows manually, while the executable scaffol...
LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched ...
Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coheren...
Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-a...
We introduce TinyCast, an attention-free zero-shot forecaster that emits a predictive distribution from 146,505 param...