Search papers, labs, and topics across Lattice.
7
0
10
Qwen-RobotNav redefines navigation by allowing real-time reconfiguration of strategies, achieving unprecedented flexibility and performance across diverse tasks.
Qwen-RobotManip achieves a 20% relative improvement over the previous state-of-the-art in robotic manipulation, showcasing unprecedented generalization capabilities from diverse, open-source datasets.
Language-driven video generation in Qwen-RobotWorld achieves unprecedented accuracy in predicting robotic actions, outperforming existing models across key benchmarks.
Interactive dialogue can unlock creative potential that static assessments overlook, leading to richer evaluations of creativity in AI contexts.
One model to control them all: Qwen-VLA achieves impressive zero-shot generalization across diverse robotic tasks and embodiments by unifying vision-language-action modeling.
Video LLMs don't just get details wrong, they fundamentally distort motion and fabricate entire events, demanding a new approach to evaluation and mitigation.
Fine-tuning language models on role-specific representations bridges the semantic gap in cognitive diagnosis, substantially boosting performance across diverse educational tasks.
