Search Results for author:
Found 41 papers, 15 papers with code
Unlabeled Data or Pre-trained Model: Rethinking Semi-Supervised Learning and Pretrain-Finetuning
Therefore, a question naturally occurs: \emph{When the labeled data is scarce in the target tasks, should we exploit unlabeled data or pre-trained models?}
Curriculum Abductive Learning
Abductive Learning (ABL) integrates machine learning with logical reasoning in a loop: a learning model predicts symbolic concept labels from raw inputs, which are revised through abduction using domain knowledge and then fed back for retraining.
LIFT+: Lightweight Fine-Tuning for Long-Tail Learning
The fine-tuning paradigm has emerged as a prominent approach for addressing long-tail learning tasks in the era of foundation models.
Micro Text Classification Based on Balanced Positive-Unlabeled Learning
In real-world text classification tasks, negative texts often contain a minimal proportion of negative content, which is especially problematic in areas like text quality control, legal risk screening, and sensitive information interception.
LawGPT: Knowledge-Guided Data Generation and Its Application to Legal LLM
To address these limitations, we study data generation for legal reasoning to improve the legal reasoning performance of open-source LLMs with the help of proprietary LLMs.
Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models
The integration of slow-thinking mechanisms into large language models (LLMs) offers a promising way toward achieving Level 2 AGI Reasoners, as exemplified by systems like OpenAI's o1.
Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning
In this paper, we present the first theoretical error decomposition analysis of these techniques, breaking down their error into estimation error and model error.
Contrast-Aware Calibration for Fine-Tuned CLIP: Leveraging Image-Text Alignment
Vision-language models (VLMs), such as CLIP, have demonstrated exceptional generalization capabilities and can quickly adapt to downstream tasks through prompt fine-tuning.
TabFSBench: Tabular Benchmark for Feature Shifts in Open Environment
TabFSBench evaluates impacts of four distinct feature-shift scenarios on four tabular model categories across various datasets and assesses the performance of large language models (LLMs) and tabular LLMs in the tabular benchmark for the first time.
Vision-Language Model Selection and Reuse for Downstream Adaptation
The proposal is highly computationally efficient and growable since the model labeling process is completed target task independent and the ability could grow with the number of candidate VLMs.
Robust Semi-Supervised Learning in Open Environments
Conventional SSL studies typically assume close environments where important factors (e. g., label, feature, distribution) between labeled and unlabeled data are consistent.
ChinaTravel: A Real-World Benchmark for Language Agents in Chinese Travel Planning
Recent advances in LLMs, particularly in language reasoning and tool integration, have rapidly sparked the real-world development of Language Agents.
You Only Submit One Image to Find the Most Suitable Generative Model
In this paper, we propose a novel setting called Generative Model Identification (GMI), which aims to enable the user to identify the most appropriate generative model(s) for the user's requirements from a large number of candidate models efficiently.
Fully Test-time Adaptation for Tabular Data
To this end, we propose the Fully Test-time Adaptation for Tabular data, namely FTAT, which enables FTTA methods to robustly optimize the label distribution of predictions, adapt to shifted covariate distributions, and suit a variety of tasks and models effectively.
Learning for Long-Horizon Planning via Neuro-Symbolic Abductive Imitation
In contrast, traditional symbolic planning excels in long-horizon tasks through logical reasoning over human-defined symbolic spaces but struggles to handle observations beyond symbolic states, such as high-dimensional visual inputs encountered in real-world scenarios.
RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models
To further improve generation quality and alignment with user-specific information, we design a pipeline for data collection and create a specialized dataset for personalized training of MLLMs.
Vision-Language Models are Strong Noisy Label Detectors
The proposed framework establishes a noisy label detector by learning positive and negative textual prompts for each class.
Enabling Small Models for Zero-Shot Selection and Reuse through Model Label Learning
In this paper, we attempt to demonstrate that by constructing a model hub and aligning models with their functionalities using model labels, new tasks can be solved in a zero-shot manner by effectively selecting and reusing models in the hub.
Offline Imitation Learning with Model-based Reverse Augmentation
Specifically, we build a reverse dynamic model from the offline demonstrations, which can efficiently generate trajectories leading to the expert-observed states in a self-paced style.
Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model
For efficient adaptation, we treat the CLIP model as a black box and leverage the extracted features to obtain visual and textual prototypes for prediction.
LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model
Large language models (LLMs), including both proprietary and open-source models, have showcased remarkable capabilities in addressing a wide range of downstream tasks.
Robustness Assessment of Mathematical Reasoning in the Presence of Missing and Contradictory Conditions
To further study this problem, we develop a benchmark called Problems with Missing and Contradictory conditions (PMC) and introduce two novel metrics to evaluate the performance of few-shot prompting methods in these scenarios.
DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection
In this paper, we explore a problem setting called Open-world Prompt Tuning (OPT), which involves tuning prompts on base classes and evaluating on a combination of base and new classes.
Investigating the Limitation of CLIP Models: The Worst-Performing Categories
Contrastive Language-Image Pre-training (CLIP) provides a foundation model by integrating natural language into visual concepts, enabling zero-shot recognition on downstream tasks.
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
The fine-tuning paradigm in addressing long-tail learning tasks has sparked significant interest since the emergence of foundation models.
Ranked #1 on
Long-tail Learning
on CIFAR-100-LT (ρ=100)
(using extra training data)
Fine-Grained Image Classification
Long-tail learning with class descriptors
A Survey on Extreme Multi-label Learning
Multi-label learning has attracted significant attention from both academic and industry field in recent decades.
USB: A Unified Semi-supervised Learning Benchmark for Classification
We further provide the pre-trained versions of the state-of-the-art neural models for CV tasks to make the cost affordable for further tuning.
LAMDA-SSL: Semi-Supervised Learning in Python
The second part shows the usage of LAMDA-SSL by abundant examples in detail.
Robust Deep Semi-Supervised Learning: A Brief Introduction
Semi-supervised learning (SSL) is the branch of machine learning that aims to improve learning performance by leveraging unlabeled data when labels are insufficient.
STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data
However, in many real-world applications, it is desirable to have SSL algorithms that not only classify the samples drawn from the same distribution of labeled data but also detect out-of-distribution (OOD) samples drawn from an unknown distribution.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Prototypical Classifier for Robust Class-Imbalanced Learning
Deep neural networks have been shown to be very powerful methods for many supervised learning tasks.
Dash: Semi-Supervised Learning with Dynamic Thresholding
In this work we develop a simple yet powerful framework, whose key idea is to select a subset of training examples from the unlabeled data when performing existing SSL methods so that only the unlabeled examples with pseudo labels related to the labeled data will be used to train models.
Robust Long-Tailed Learning under Label Noise
To overcome this limitation, we establish a new prototypical noise detection method by designing a distance-based metric that is resistant to label noise.
Ranked #27 on
Image Classification
on mini WebVision 1.0
NGC: A Unified Framework for Learning with Open-World Noisy Data
The existence of noisy data is prevalent in both the training and testing phases of machine learning systems, which inevitably leads to the degradation of model performance.
Ranked #19 on
Image Classification
on mini WebVision 1.0
Improving Tail Label Prediction for Extreme Multi-label Learning
Extreme multi-label learning (XML) works to annotate objects with relevant labels from an extremely large label set.
Weakly Supervised Learning Meets Ride-Sharing User Experience Enhancement
For example, in user experience enhancement from Didi, one of the largest online ride-sharing platforms, the ride comment data contains severe label noise (due to the subjective factors of passengers) and severe label distribution bias (due to the sampling bias).
Reliable Weakly Supervised Learning: Maximize Gain and Maintain Safeness
We guide the optimization of label quality through a small amount of validation data, and to ensure the safeness of performance while maximizing performance gain.
Deep learning based automatic segmentation of lumbosacral nerves on non-contrast CT for radiographic evaluation: a pilot study
Pixel accuracy, IoU, and Dice score are used to assess the segmentation performance of lumbosacral structures.
Convex and Scalable Weakly Labeled SVMs
In this paper, we study the problem of learning from weakly labeled data, where labels of the training examples are incomplete.
Nyström Method vs Random Fourier Features: A Theoretical and Empirical Comparison
Both random Fourier features and the Nyström method have been successfully applied to efficient kernel learning.
