Deep Learning
MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning
To address this gap, we set up a new task: M ulti-E vent C ausal D iscovery (MECD), which aims to uncover causal relationships among events that distribute chronologically in long videos.
One-Step Effective Diffusion Network for Real-World Image Super-Resolution
We finetune the pre-trained diffusion network with trainable layers to adapt it to complex image degradations.
GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts
To bridge this gap, we propose GeSS, a comprehensive benchmark designed for evaluating the performance of GDL models in scientific scenarios with distribution shifts.
ConStat: Performance-Based Contamination Detection in Large Language Models Jasper Dekoninck 1, Mark Niklas Mรผller 1,2, Martin Vechev 1 Department of Computer Science 1
Public benchmarks play an essential role in the evaluation of large language models.
Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
We use decision trees to convey this reasoning information, as they can be easily represented in natural language, effectively providing knowledge from prior experiments ( i.e., the impact of the generated features on performance) to
Unraveling the Gradient Descent Dynamics of Transformers
By analyzing the loss landscape of a single Transformer layer using Softmax and Gaussian attention kernels, our work provides concrete answers to these questions.
Intrinsic Self-Supervision for Data Quality Audits
Benchmark datasets in computer vision often contain off-topic images, near duplicates, and label errors, leading to inaccurate estimates of model performance.
