Search papers, labs, and topics across Lattice.
School of Computer Science, Shanghai Jiao Tong University
6
0
10
11
Current multimodal agents fail to consistently pass CAPTCHA tests, revealing fundamental limitations in their ability to replace humans in automated workflows.
MLLMs excel at single-hop tasks but falter dramatically in open-world scenarios, revealing critical gaps in their reasoning capabilities.
Mobile-using agents can now achieve 17% higher task success rates offline and 26% higher success rates in real-world dynamic experiments, all while significantly reducing unnecessary human intervention.
Poisoned training data leaves a unique fingerprint in the spectral entropy of LLM gradients, enabling backdoor detection even at extreme poison ratios where clustering-based defenses fail.
Self-evolving agents can now learn more efficiently in resource-constrained environments by explicitly structuring experience into a tool graph memory that facilitates planning and tool reuse.
Pinpoint exactly which client leaked your federated model with a black-box watermark that's robust to fine-tuning, pruning, and quantization.
