Deep Learning
Long-form factuality in large language models Jerry Wei 1 Chengrun Y ang 1 Xinying Song 1 Yifeng Lu
To benchmark a model's long-form factuality in open domains, we first use GPT -4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE).
Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces
However, training EBMs on data in discrete or mixed state spaces poses significant challenges due to the lack of robust and fast sampling methods. In this work, we propose to train discrete EBMs with Energy Discrepancy, a loss function which only requires the evaluation of the energy function at data points and their perturbed counterparts, thus eliminating the need for Markov chain Monte Carlo.
GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition
The creation of large-scale image datasets has enabled advances in the performance of computer vision models.
Temporal Continual Learning with Prior Compensation for Human Motion Prediction
To better preserve prior information, we introduce the Prior Compensation Factor (PCF). We incorporate it into the model training to compensate for the lost prior information. Furthermore, we derive a more reasonable optimization objective through theoretical derivation.
Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading Qi Bi
Disease grading is a crucial task in medical image analysis.
Spike-driven Transformer Man Y ao
Key, and V alue are mask and addition.
Riemannian Residual Neural Networks
Recent methods in geometric deep learning have introduced various neural networks to operate over data that lie on Riemannian manifolds.
