Search Results for author:
Found 27 papers, 11 papers with code
LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Models
Our results show that LightPure can outperform existing methods by up to 10x in terms of latency while achieving higher accuracy and robustness for various attack scenarios.
Enhancing Group Fairness in Federated Learning through Personalization
Personalized Federated Learning (FL) algorithms collaboratively train customized models for each client, enhancing the accuracy of the learned models on the client's local data (e. g., by clustering similar clients, or by fine-tuning models locally).
Can LLMs Reason in the Wild with Programs?
To investigate this, we introduce the task of reasoning in the wild, where an LLM is tasked to solve a reasoning problem of unknown type by identifying the subproblems and their corresponding formalisms, and writing a program to solve each subproblem, guided by a tactic.
Towards Hierarchical Multi-Agent Workflows for Zero-Shot Prompt Optimization
Specifically, we include a hierarchy of LLMs, first constructing a prompt with precise instructions and accurate wording in a hierarchical manner, and then using this prompt to generate the final answer to the user query.
LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
To address such limitations, we propose a novel Language Model-based Optimal Differential Privacy (LMO-DP) mechanism, which takes the first step to enable the tight composition of accurately fine-tuning (large) language models with a sub-optimal DP mechanism, even in strong privacy regimes (e. g., $0. 1\leq \epsilon<3$).
SketchQL Demonstration: Zero-shot Video Moment Querying with Sketches
In this paper, we will present SketchQL, a video database management system (VDBMS) for retrieving video moments with a sketch-based query interface.
Quantifying Multilingual Performance of Large Language Models Across Languages
Besides, the experiments show that there is a strong correlation between the LLM's performance in different languages and the proportion of those languages in its pre-training corpus.
Generalization Error Bounds for Learning under Censored Feedback
We then use this CDF error bound to provide a bound on the generalization error guarantees of a classifier trained on such non-IID data.
MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
Firstly, their effectiveness in tackling complex mathematical problems is somewhat constrained.
Ranked #1 on
Math Word Problem Solving
on MATH
Not All Federated Learning Algorithms Are Created Equal: A Performance Evaluation Study
(3) However, algorithms such as FedDyn and SCAFFOLD are more prone to catastrophic failures without the support of additional techniques such as gradient clipping.
Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity
We show that subsets that closely preserve the cross-covariance of the images and captions of the full data provably achieve a superior generalization performance.
Prompt Mining for Language-based Human Mobility Forecasting
Specifically, the framework includes a prompt generation stage based on the information entropy of prompts and a prompt refinement stage to integrate mechanisms such as the chain of thought.
When is Tree Search Useful for LLM Planning? It Depends on the Discriminator
In this paper, we examine how large language models (LLMs) solve multi-step problems under a language agent framework with three components: a generator, a discriminator, and a planning method.
Large Language Models Can Learn Temporal Reasoning
Instead of reasoning over the original context, we adopt a latent representation, temporal graph (TG) that enhances the learning of TR.
TEILP: Time Prediction over Knowledge Graphs via Logical Reasoning
We first convert TKGs into a temporal event knowledge graph (TEKG) which has a more explicit representation of time in term of nodes of the graph.
Investigating the Impact of Weight Sharing Decisions on Knowledge Transfer in Continual Learning
Through this lens we demonstrate how task complexity and similarity influence the optimal weight sharing decisions, giving insights into the relationships between tasks and helping inform decision making in similar CL methods.
Beyond Detection: Unveiling Fairness Vulnerabilities in Abusive Language Models
This work investigates the potential of undermining both fairness and detection performance in abusive language detection.
Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation
Translating natural language sentences to first-order logic (NL-FOL translation) is a longstanding challenge in the NLP and formal logic literature.
Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings
Pretrained machine learning models need to be adapted to distribution shifts when deployed in new target environments.
Text-to-SQL Error Correction with Language Models of Code
Thus, we propose a novel representation for SQL queries and their edits that adheres more closely to the pre-training corpora of language models of code.
Mitigating Group Bias in Federated Learning: Beyond Local Fairness
While many mitigation strategies have been proposed in centralized learning, many of these methods are not directly applicable in federated learning, where data is privately stored on multiple clients.
When Fairness Meets Privacy: Fair Classification with Semi-Private Sensitive Attributes
Thus, it is essential to ensure fairness in machine learning models.
Temporal Inductive Logic Reasoning over Hypergraphs
Inductive logic reasoning is a fundamental task in graph analysis, which aims to generalize patterns from data.
Visual Question Answering based on Formal Logic
To achieve this, we take a symbolic reasoning based approach using the framework of formal logic.
Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programming
Most importantly, it allows for incorporating expert knowledge into the learning, and hence leading to much faster learning and better generalization compared to the standard deep reinforcement learning.
Inductive Logic Programming via Differentiable Deep Neural Logic Networks
In particular, we show that our proposed method outperforms the state of the art ILP solvers in classification tasks for Mutagenesis, Cora and IMDB datasets.
Learning Algorithms via Neural Logic Networks
In particular, we propose a new framework for learning the inductive logic programming (ILP) problems by exploiting the explicit representational power of NLN.
