Search Results for author:
Found 20 papers, 7 papers with code
Findings of the WOAH 5 Shared Task on Fine Grained Hateful Memes Detection
We present the results and main findings of the shared task at WOAH 5 on hateful memes detection.
High Resolution and Fast Face Completion via Progressively Attentive GANs
Face completion is a challenging task with the difficulty level increasing significantly with respect to high resolution, the complexity of "holes" and the controllable attributes of filled-in fragments.
Modality-specific Distillation
In this paper, we propose modality-specific distillation (MSD) to effectively transfer knowledge from a teacher on multimodal datasets.
Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder
We prove that SAEs can serve as a good alternative to diversity measure and design our method to be scalable for potential industrial large-scale pruning, and we will also release our trained SAEs for use by the broader community.
Unveiling User Satisfaction and Creator Productivity Trade-Offs in Recommendation Platforms
In this work, we demonstrate, both theoretically and empirically, that a purely relevance-driven policy with low exploration strength boosts short-term user satisfaction but undermines the long-term richness of the content pool.
The Perfect Blend: Redefining RLHF with Mixture of Judges
However, RLHF has limitations in multi-task learning (MTL) due to challenges of reward hacking and extreme multi-objective optimization (i. e., trade-off of multiple and/or sometimes conflicting objectives).
M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning
Instruction tuning has emerged as an effective strategy for achieving zero-shot generalization by finetuning pretrained models on diverse multimodal tasks.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #3 on
Question Answering
on PeerQA
On the Equivalence of Graph Convolution and Mixup
We establish this equivalence mathematically by demonstrating that graph convolution networks (GCN) and simplified graph convolution (SGC) can be expressed as a form of Mixup.
Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales
Existing metrics like task performance of the LM generating the rationales, or similarity between generated and gold rationales are not good indicators of their human utility.
COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation
However, the bias inherent in user written text, often used for PTG model training, can inadvertently associate different levels of linguistic quality with users' protected attributes.
AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning
Fine-tuning large pre-trained language models on downstream tasks is apt to suffer from overfitting when limited training data is available.
FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationales
Following how humans communicate, free-text rationales aim to use natural language to explain neural language model (LM) behavior.
ER-Test: Evaluating Explanation Regularization Methods for Language Models
to align with human rationales (Which input tokens would humans focus on?).
Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem
Without the use of a knowledge base or candidate sets, our model sets a new state of the art in two benchmark datasets of entity linking: COMETA in the biomedical domain, and AIDA-CoNLL in the news domain.
BARACK: Partially Supervised Group Robustness With Guarantees
Theoretically, we provide generalization bounds for our approach in terms of the worst-group performance, which scale with respect to both the total number of training points and the number of training points with group labels.
UNIREX: A Unified Learning Framework for Language Model Rationale Extraction
An extractive rationale explains a language model's (LM's) prediction on a given task instance by highlighting the text inputs that most influenced the prediction.
MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding
The idea aims at mimicking a teacher's modality-specific predictions by introducing auxiliary loss terms for each modality.
Towards Controllable and Interpretable Face Completion via Structure-Aware and Frequency-Oriented Attentive GANs
The proposed frequency-oriented attentive module (FOAM) encourages GANs to attend to only finer details in the coarse-to-fine progressive training, thus enabling progressive attention to face structures.
High Resolution Face Completion with Multiple Controllable Attributes via Fully End-to-End Progressive Generative Adversarial Networks
It is a challenging task with the difficulty level increasing significantly with respect to high resolution, the complexity of "holes" and the controllable attributes of filled-in fragments.
