Search Results for author:
Found 5 papers, 1 papers with code
ODIN: Disentangled Reward Mitigates Hacking in RLHF
In this work, we study the issue of reward hacking on the response length, a challenge emerging in Reinforcement Learning from Human Feedback (RLHF) on LLMs.
Reviving Shift Equivariance in Vision Transformers
While the self-attention operator in vision transformers (ViT) is permutation-equivariant and thus shift-equivariant, patch embedding, positional encoding, and subsampled attention in ViT variants can disrupt this property, resulting in inconsistent predictions even under small shift perturbations.
Learning UI-to-Code Reverse Generator Using Visual Critic Without Rendering
We evaluate the UI-to-Code performance using a combination of automated metrics such as MSE, BLEU, IoU, and a novel htmlBLEU score.
RNN-based Online Handwritten Character Recognition Using Accelerometer and Gyroscope Data
We have built a dataset of timestamped gyroscope and accelerometer data gathered during the manual process of handwriting Latin characters, labeled with the character being written; in total, the dataset con-sists of 1500 gyroscope and accelerometer data sequenc-es for 8 characters of the Latin alphabet from 6 different people, and 20 characters, each 1500 samples from Georgian alphabet from 5 different people.
Reproduction Report on "Learn to Pay Attention"
We have successfully implemented the "Learn to Pay Attention" model of attention mechanism in convolutional neural networks, and have replicated the results of the original paper in the categories of image classification and fine-grained recognition.
