Yue Li

TailSieve achieves up to 2.59x speedup in LLM rollouts by intelligently routing long-tail requests, transforming how we handle high-concurrency decoding.

DFL-C not only ensures global model consistency in decentralized federated learning but also outperforms existing solutions in the face of Byzantine attacks.

Newer LLMs may ace build tasks, but they struggle with delivering correct app behaviors, especially when specifications are involved.

Achieving a Macro F1 score of 0.8626 while detecting unknown attacks at a mere 1% false positive rate reveals a new standard for explainable and effective intrusion detection.

Super-resolution techniques can significantly erase small white matter lesions in MRI scans, challenging assumptions about their reliability in clinical settings.

Hard prompt compressors can leave critical context gaps, leading to a staggering 60% of examples suffering from referential dangling, which severely impacts accuracy in multi-hop question answering.