Search Results for author:
Found 33 papers, 8 papers with code
Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective
In this paper, we aim to establish a simple, effective, and theoretically grounded benchmark for rigorously probing abstract reasoning in Large Language Models (LLMs).
Improving LLM Interpretability and Performance via Guided Embedding Refinement for Sequential Recommendation
The fast development of Large Language Models (LLMs) offers growing opportunities to further improve sequential recommendation systems.
Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness
In this study, we first explore the feasibility of training SNNs that generalize across different time steps.
Uncertainty Quantification for LLM-Based Survey Simulations
Additionally, the selected sample size quantifies the degree of misalignment between the LLM and the target human population.
Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Boostrapping
Modern foundation models often undergo iterative ``bootstrapping'' in their post-training phase: a model generates synthetic data, an external verifier filters out low-quality samples, and the high-quality subset is used for further fine-tuning.
Black-box Optimization with Simultaneous Statistical Inference for Optimal Performance
In practice, decision-makers often face the dual tasks of optimization and statistical inference for the optimal performance, in order to achieve it with a high reliability.
UTF:Undertrained Tokens as Fingerprints A Novel Approach to LLM Identification
Our method has minimal overhead and impact on model's performance, and does not require white-box access to target model's ownership identification.
Can LLMs "Reason" in Music? An Evaluation of LLMs' Capability of Music Understanding and Generation
Yet scant research explores the details of how these LLMs perform on advanced music understanding and conditioned generation, especially from the multi-step reasoning perspective, which is a critical aspect in the conditioned, editable, and interactive human-computer co-creation process.
Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models
We identify three types of relationship co-occurrences that lead to hallucinations: relationship-relationship, subject-relationship, and relationship-object.
AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models
Evaluating the alignment capabilities of large Vision-Language Models (VLMs) is essential for determining their effectiveness as helpful assistants.
Large Language Model Enhanced Machine Learning Estimators for Classification
Pre-trained large language models (LLM) have emerged as a powerful tool for simulating various scenarios and generating output given specific instructions and multimodal input.
OccTransformer: Improving BEVFormer for 3D camera-only occupancy prediction
This technical report presents our solution, "occTransformer" for the 3D occupancy prediction track in the autonomous driving challenge at CVPR 2023.
ChatMusician: Understanding and Generating Music Intrinsically with LLM
It is based on continual pre-training and finetuning LLaMA2 on a text-compatible music representation, ABC notation, and the music is treated as a second language.
Rethinking Personalized Federated Learning with Clustering-based Dynamic Graph Propagation
Subsequently, we design a precise personalized model distribution strategy to allow clients to obtain the most suitable model from the server side.
Assessing Prompt Injection Risks in 200+ Custom GPTs
In the rapidly evolving landscape of artificial intelligence, ChatGPT has been widely used in various applications.
Causal inference with Machine Learning-Based Covariate Representation
Utilizing covariate information has been a powerful approach to improve the efficiency and accuracy for causal inference, which support massive amount of randomized experiments run on data-driven enterprises.
Best Arm Identification with Fairness Constraints on Subpopulations
The BAICS problem aims at correctly identify, with high confidence, the arm with the largest expected reward from all arms that satisfy subpopulation constraints.
SMARTQUERY: An Active Learning Framework for Graph Neural Networks through Hybrid Uncertainty Reduction
Graph neural networks have achieved significant success in representation learning.
Adaptive Data Fusion for Multi-task Non-smooth Optimization
We study the problem of multi-task non-smooth optimization that arises ubiquitously in statistical learning, decision-making and risk management.
Forecast-based Multi-aspect Framework for Multivariate Time-series Anomaly Detection
Today's cyber-world is vastly multivariate.
Multi-Centroid Representation Network for Domain Adaptive Person Re-ID
First, we present a Domain-Specific Contrastive Learning (DSCL) mechanism to fully explore intradomain information by comparing samples only from the same domain.
Contrastive Learning
Domain Adaptive Person Re-Identification
+2
Event2Graph: Event-driven Bipartite Graph for Multivariate Time-series Anomaly Detection
Modeling inter-dependencies between time-series is the key to achieve high performance in anomaly detection for multivariate time-series data.
Adversarial Example Detection Using Latent Neighborhood Graph
We present the first graph-based adversarial detection method that constructs a Latent Neighborhood Graph (LNG) around an input example to determine if the input example is adversarial.
Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions
Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers.
Lee at SemEval-2020 Task 5: ALBERT Model Based on the Maximum Ensemble Strategy and Different Data Sampling Methods for Detecting Counterfactual Statements
Our methods achieved a F1 score of 0. 85 in subtask A.
Warren at SemEval-2020 Task 4: ALBERT and Multi-Task Learning for Commonsense Validation
This paper describes our system in subtask A of SemEval 2020 Shared Task 4.
GroupIM: A Mutual Information Maximization Framework for Neural Group Recommendation
We study the problem of making item recommendations to ephemeral groups, which comprise users with limited or no historical activities together.
Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Study
While feasible, digital attacks have limited applicability in attacking deployed systems, including face recognition systems, where an adversary typically has access to the input and not the transmission channel.
YNU-junyi in BioNLP-OST 2019: Using CNN-LSTM Model with Embeddings for SeeDev Binary Event Extraction
We participated in the BioNLP 2019 Open Shared Tasks: binary relation extraction of SeeDev task.
Occlusion-guided compact template learning for ensemble deep network-based pose-invariant face recognition
The compact face representation is not sensitive to the number of patches that are used to construct the facial template and is more suitable for incorporating the information from different view angles for image-set based face recognition.
Convolutional Point-set Representation: A Convolutional Bridge Between a Densely Annotated Image and 3D Face Alignment
The method relies on Convolutional Point-set Representation (CPR), a carefully designed matrix representation to summarize different layers of information encoded in the set of detected points in the annotated image.
Facial 3D Model Registration Under Occlusions With SensiblePoints-based Reinforced Hypothesis Refinement
The visual clues extracted from the fiducial points, non-fiducial points, and facial contour are jointly employed to verify the hypotheses.
GoDP: Globally optimized dual pathway system for facial landmark localization in-the-wild
Facial landmark localization is a fundamental module for pose-invariant face recognition.
