Search Results for author:
Found 27 papers, 15 papers with code
A Foundational Generative Model for Breast Ultrasound Image Analysis
Additionally, we characterized the scaling effect of using generated data which was as effective as the collected real-world data for training diagnostic models.
A Federated Approach to Few-Shot Hate Speech Detection for Marginalized Communities
In this paper, we aim to provide marginalized communities living in societies where the dominant language is low-resource with a privacy-preserving tool to protect themselves from hate speech on the internet by filtering offensive content in their native languages.
Reducing Hallucinations in Vision-Language Models via Latent Space Steering
Unlike in large language models (LLMs), hallucination in LVLMs often arises from misalignments between visual inputs and textual outputs.
Geometric Trajectory Diffusion Models
In this work, we propose geometric trajectory diffusion models (GeoTDM), the first diffusion model for modeling the temporal distribution of 3D geometric trajectories.
LangSAMP: Language-Script Aware Multilingual Pretraining
However, this removal increases the burden on token embeddings to encode all language-specific information, which may hinder the model's ability to produce more language-neutral representations.
How Transliterations Improve Crosslingual Alignment
However, we also show that better alignment does not always yield better downstream performance, suggesting that further research is needed to clarify the connection between alignment and performance.
TFG: Unified Training-Free Guidance for Diffusion Models
Given an unconditional diffusion model and a predictor for a target property of interest (e. g., a classifier), the goal of training-free guidance is to generate samples with desirable target properties without additional training.
Exploring the Role of Transliteration in In-Context Learning for Low-resource Languages Written in Non-Latin Scripts
Inspired by recent work that leverages transliteration in encoder-only models, we investigate whether transliteration is also effective in improving LLMs' performance for low-resource languages written in non-Latin scripts.
TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data
TransMI can create strong baselines for data that is transliterated into a common script by exploiting an existing mPLM and its tokenizer without any training.
Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM).
DOF: Accelerating High-order Differential Operators with Forward Propagation
Solving partial differential equations (PDEs) efficiently is essential for analyzing complex physical systems.
Selecting Large Language Model to Fine-tune via Rectified Scaling Law
The ever-growing ecosystem of LLMs has posed a challenge in selecting the most appropriate pre-trained model to fine-tune amidst a sea of options.
TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models
As a consequence, mPLMs are faced with a script barrier: representations from different scripts are located in different subspaces, which can result in crosslingual transfer involving languages of different scripts performing suboptimally.
MoSECroT: Model Stitching with Static Word Embeddings for Crosslingual Zero-shot Transfer
In this paper, we introduce MoSECroT Model Stitching with Static Word Embeddings for Crosslingual Zero-shot Transfer), a novel and challenging task that is especially relevant to low-resource languages for which static word embeddings are available.
In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
On a new query, instead of adding demonstrations to the prompt, we shift the latent states of the LLM using the ICV.
Forward Laplacian: A New Computational Framework for Neural Network-based Variational Monte Carlo
Neural network-based variational Monte Carlo (NN-VMC) has emerged as a promising cutting-edge technique of ab initio quantum chemistry.
Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective
By using circuit complexity theory, we first give impossibility results showing that bounded-depth Transformers are unable to directly produce correct answers for basic arithmetic/equation tasks unless the model size grows super-polynomially with respect to the input length.
A study of conceptual language similarity: comparison and evaluation
An interesting line of research in natural language processing (NLP) aims to incorporate linguistic typology to bridge linguistic diversity and assist the research of low-resource languages.
Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs
ColexNet's nodes are concepts and its edges are colexifications.
A Crosslingual Investigation of Conceptualization in 1335 Languages
The resulting measure for the conceptual similarity of two languages is complementary to standard genealogical, typological, and surface similarity measures.
Taxi1500: A Multilingual Dataset for Text Classification in 1500 Languages
While natural language processing tools have been developed extensively for some of the world's languages, a significant portion of the world's over 7000 languages are still neglected.
Discovering Latent Knowledge in Language Models Without Supervision
Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we train them to generate text that humans rate highly, they may output errors that human evaluators can't detect.
Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise
This opens a promising strategy to first train a feature learner rather than a classifier, and then perform linear probing (last layer retraining) in the test environment.
On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness
Generalization in Reinforcement Learning (RL) aims to learn an agent during training that generalizes to the target environment.
Towards a Theoretical Framework of Out-of-Distribution Generalization
We also introduce a new concept of expansion function, which characterizes to what extent the variance is amplified in the test domains over the training domains, and therefore give a quantitative meaning of invariant features.
Out-of-Distribution Generalization Analysis via Influence Function
One of the definitions of OOD accuracy is worst-domain accuracy.
Risk Variance Penalization
The key of the out-of-distribution (OOD) generalization is to generalize invariance from training domains to target domains.
