Shang Wang

TFA is introduced, a reliability-guided, training-free aggregation method requiring neither place labels nor task-specific weight updates that can recover additional retrieval capability from frozen representations, providing a practical baseline for new environments with scarce place supervision.

RIM achieves up to 13.77 percentage points improvement in localization recall while being over 40 times faster than traditional methods.

Stop relying on inaccurate proxies: directly optimizing 3D-IC partitioning for PPA metrics is now practical, yielding significant improvements without increasing runtime.

LLM agents can now selectively forget sensitive information without sacrificing overall performance, thanks to a new framework that translates natural language unlearning requests into actionable prompts.

Dataset distillation, intended to compress data while preserving model performance, actually leaks sensitive information about the original training data and model architecture.