Asia
Reverse Engineering Self-Supervised Learning
Self-supervised learning (SSL) is a powerful tool in machine learning, but understanding the learned representations and their underlying mechanisms remains a challenge.
Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning
In online advertising, for instance, the user's profile is the context, the
ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation
We present ComSL, a speech-language model built atop a composite architecture of public pretrained speech-only and language-only models and optimized data-efficiently for spoken language tasks.
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
In addition, we introduce a reversible mapping to determine the defensive target label.
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
While significant progress has been made in developing autonomous agents for shape assembly, existing datasets have not yet tackled the 4D grounding of assembly instructions in videos, essential for a holistic understanding of assembly in 3D space over time.
Implicit Bias of (Stochastic) Gradient Descent for Rank-1 Linear Neural Network
Unfortunately, even for standard linear networks in regression setting, a comprehensive characterization of the implicit bias is still an open problem.
V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark
We release all the benchmark, making it more efficient and friendly to researchers.
Appendices of On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions
Step 2. The deduction in Step 1 can be iterated repeatedly due to the symmetry of