Performance Analysis
Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos
Procedural activities are sequences of key-steps aimed at achieving specific goals. They are crucial to build intelligent agents able to assist users effectively.
Learning De-Biased Representations for Remote-Sensing Imagery
It is an unsupervised learning approach that can diversify minor class features based on the shared attributes with major classes, where the attributes are obtained by a simple step of clustering.
Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions
Both component functions are in expectation forms, i.e.,
Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection Geng Y u
The code is publicly available at: https://github.com/tmlr-group/SCT .
Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when combating deepfake or harmful content.
FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling
To overcome the limitations of autoregressive methods (e.g., error accumulation), recent works