Deep Learning
Visual Harmfulness Recognition (Supplementary Material) Chen Y eh
Please refer to table 1. The harmful keywords are with red and the unharmful keywords are withgreen background color.
T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition Chen Y eh 1 Y ou-Ming Chang 1 Wei-Chen Chiu 1 Ning Y u
Warning: This paper contains inappropriate/harmful visual contents. While widespread access to the Internet and the rapid advancement of generative models boost people's creativity and productivity, the risk of encountering inappropriate or harmful content also increases.
Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search
To this end, we present a formulation of synthesis planning with starting material constraints.
Fractal Patterns May Illuminate the Success of Next-Token Prediction
Nature and geometry furnish us with many such patterns, such as coastlines, snowflakes, the Cantor set and the Kuch curve.
Compositional Generalization Across Distributional Shifts with Sparse Tree Operations
Work partially completed while at Microsoft Research.
Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning
However, enabling human trust and control over FL systems requires understanding the evolving behaviour of clients, whether beneficial or detrimental for the training, which still represents a key challenge in the current literature.
NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention
We leverage this unique capability to propose NoMAD-Attention, an efficient attention algorithm that replaces MAD operations with in-register lookups.
AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection Y ujin Wang
Image Signal Processors (ISPs) play a fundamental role in camera systems.
Context-Aware Testing: A New Paradigm for Model Testing with Large Language Models
The predominant de facto paradigm of testing ML models relies on either using only held-out data to compute aggregate evaluation metrics or by assessing the performance on different subgroups.