Search papers, labs, and topics across Lattice.
Zhejiang University Q Qualcomm AI Research
2
0
6
Android agents can now learn much faster by squeezing more value out of each emulator interaction, thanks to a novel "Single State Multiple Actions" training paradigm.
MLLMs often fail at multimodal emotion recognition due to premature commitment to data priors, but a new architecture, HyDRA, uses reinforcement learning to synthesize evidence-grounded rationales and significantly outperforms strong baselines, especially in ambiguous scenarios.
