Search papers, labs, and topics across Lattice.
Beijing Institute of Technology
5
0
9
Aco2 enables quadrotors to autonomously adapt to diverse payloads in real-time, eliminating the need for manual calibration or system identification.
Current vision-language models falter in ultra-resolution reasoning, with errors primarily stemming from evidence grounding and local perception.
Learning-based congestion controllers are surprisingly more robust to adversarial attacks than traditional algorithms, and these attacks can be used to train even better controllers.
By unifying specialized detectors with MLLMs in an agentic framework, Echo-{\alpha} achieves state-of-the-art ultrasound interpretation, suggesting a path to more accurate, interpretable, and transferable medical AI.
Ditch the deep stacks: a dual-stream architecture for learned data compression unlocks state-of-the-art compression ratios and throughput while slashing latency and memory usage.
