Search Results for author:
Found 8 papers, 4 papers with code
Direct Language Model Alignment from Online AI Feedback
Moreover, responses in these datasets are often sampled from a language model distinct from the one being aligned, and since the model evolves over training, the alignment phase is inevitably off-policy.
Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning
Based on our ICL study, (3) we push ICL further and propose new multimodal ICL variants such as; Multitask-ICL, Chain-of-Hindsight-ICL, and Self-Correcting-ICL.
UnIVAL: Unified Model for Image, Video, Audio and Language Tasks
Our model is efficiently pretrained on many tasks, based on task balancing and multimodal curriculum learning.
Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization
In this paper, we introduce a new regularization - named Fishr - that enforces domain invariance in the space of the gradients of the loss: specifically, the domain-level variances of gradients are matched across training domains.
Ranked #30 on
Domain Generalization
on TerraIncognita
MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks
Recent strategies achieved ensembling "for free" by fitting concurrently diverse subnetworks inside a single base network.
Ranked #15 on
Image Classification
on Tiny ImageNet Classification
DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation
Deep ensembles perform better than a single network thanks to the diversity among their members.
CoRe: Color Regression for Multicolor Fashion Garments
That's why in addition to a first color classifier, we include a second regression stage for refinement in our newly proposed architecture.
OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation
Similarly to self-training methods, the predictions of these initial detectors mitigate the missing annotations on the complementary datasets.
