Search papers, labs, and topics across Lattice.
University of Electronic Science and Technology, Huazhong University of Science and Technology
4
0
10
Decoupling semantic reasoning from real-time control allows robots to master complex tasks with unprecedented stability and generalization.
Only a subset of design interactions in heterogeneous LLM inference are binding constraints, revealing critical insights for optimizing deployment strategies.
Forget specialized architectures: StepAudio 2.5 proves a single audio-language foundation, shaped by RLHF, can dominate ASR, TTS, and real-time dialogue simultaneously.
MLLMs still struggle with real-world document understanding, but a new benchmark and reinforcement learning approach can significantly improve their ability to extract structured information from receipts.
