Search Results for author:
Found 31 papers, 14 papers with code
BreakGPT: A Large Language Model with Multi-stage Structure for Financial Breakout Detection
To address these issues, we introduce BreakGPT, the first large language model for financial breakout detection.
ChemLLM: A Chemical Large Language Model
ChemLLM beats GPT-3. 5 on all three principal tasks in chemistry, i. e., name conversion, molecular caption, and reaction prediction, and surpasses GPT-4 on two of them.
The Information of Large Language Model Geometry
This paper investigates the information encoded in the embeddings of large language models (LLMs).
Large Language Model Evaluation via Matrix Entropy
Large language models (LLMs) have revolutionized the field of natural language processing, extending their strong capabilities into multi-modal domains.
TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
In recent years, multimodal large language models (MLLMs) such as GPT-4V have demonstrated remarkable advancements, excelling in a variety of vision-language tasks.
TransMed: Large Language Models Enhance Vision Transformer for Biomedical Image Classification
Our solution secures the 1st place in the MedFMC challenge.
AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering
By using instance-specific rules as prompt, GPT-4, as an automatic evaluator, can achieve a stable evaluation accuracy of around 97. 0\%, comparable to the 94. 9\% - 97. 5\% accuracy of a human evaluator.
Understanding Grokking Through A Robustness Viewpoint
Recently, an interesting phenomenon called grokking has gained much attention, where generalization occurs long after the models have initially overfitted the training data.
OTMatch: Improving Semi-Supervised Learning with Optimal Transport
In this paper, we present a new approach called OTMatch, which leverages semantic relationships among classes by employing an optimal transport loss function.
Information Flow in Self-Supervised Learning
In this paper, we provide a comprehensive toolbox for understanding and enhancing self-supervised learning (SSL) methods through the lens of matrix information theory.
InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4
To achieve this, we first propose several metrics to access the quality of multimodal instruction data.
FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?
Few-shot learning aims to train models that can be generalized to novel classes with only a few samples.
Rethinking Weak Supervision in Helping Contrastive Learning
Therefore, to explore the mechanical differences between semi-supervised and noisy-labeled information in helping contrastive learning, we establish a unified theoretical framework of contrastive learning under weak supervision.
Matrix Information Theory for Self-Supervised Learning
Inspired by this framework, we introduce Matrix-SSL, a novel approach that leverages matrix information theory to interpret the maximum entropy encoding loss as matrix uniformity loss.
Ranked #1 on
Contrastive Learning
on imagenet-1k
ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations
Moreover, we show that contrastive learning fails to learn domain-invariant features, which limits its transferability.
When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method
In this paper, to handle the problem and address the limitations of prior works, we propose a representation calibration method RCAL.
Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding
Contrastive learning, especially self-supervised contrastive learning (SSCL), has achieved great success in extracting powerful features from unlabeled data.
Towards the Generalization of Contrastive Self-Supervised Learning
It reveals that the generalization ability of contrastive self-supervised learning is related to three key factors: alignment of positive samples, divergence of class centers, and concentration of augmented data.
Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis
Pretext-based self-supervised learning learns the semantic representation via a handcrafted pretext task over unlabeled data and then uses the learned representation for downstream tasks, which effectively reduces the sample complexity of downstream tasks under Conditional Independence (CI) condition.
Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method
To this end, we analyze the working mechanism of GCN with causal graph, estimating the causal effect of a node's local structure for the prediction.
New Interpretations of Normalization Methods in Deep Learning
In recent years, a variety of normalization methods have been proposed to help train neural networks, such as batch normalization (BN), layer normalization (LN), weight normalization (WN), group normalization (GN), etc.
Locally Differentially Private (Contextual) Bandits Learning
We study locally differentially private (LDP) bandits learning in this paper.
Boosting Few-Shot Learning With Adaptive Margin Loss
Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples.
Ranked #1 on
Few-Shot Image Classification
on ImageNet (1-shot)
Meta-Learning PAC-Bayes Priors in Model Averaging
In this paper, we mainly consider the scenario in which we have a common model set used for model averaging instead of selecting a single final model via a model selection procedure to account for this model's uncertainty to improve the reliability and accuracy of inferences.
GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction
Then, in order to better capture the complicated non-linearity of graph data, we present a novel GraphAIR framework which models the neighborhood interaction in addition to neighborhood aggregation.
DARTS+: Improved Differentiable Architecture Search with Early Stopping
Therefore, we propose a simple and effective algorithm, named "DARTS+", to avoid the collapse and improve the original DARTS, by "early stopping" the search procedure when meeting a certain criterion.
Few-Shot Learning with Global Class Representations
In this paper, we propose to tackle the challenging few-shot learning (FSL) problem by learning global class representations using both base and novel class training samples.
Community Exploration: From Offline Optimization to Online Learning
We introduce the community exploration problem that has many real-world applications such as online advertising.
Modeling Local Dependence in Natural Language with Multi-channel Recurrent Neural Networks
In this paper, we propose an improved variant of RNN, Multi-Channel RNN (MC-RNN), to dynamically capture and leverage local semantic structure information.
Combinatorial Pure Exploration with Continuous and Separable Reward Functions and Its Applications (Extended Version)
Each decision has a reward according to the distributions of arms.
Multi-Round Influence Maximization (Extended Version)
In this paper, we study the Multi-Round Influence Maximization (MRIM) problem, where influence propagates in multiple rounds independently from possibly different seed sets, and the goal is to select seeds for each round to maximize the expected number of nodes that are activated in at least one round.
Social and Information Networks
