Gang Niu

Decoupling the Class Label and the Target Concept in Machine Unlearning

Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms

Rethinking Consistent Multi-Label Classification Under Inexact Supervision

Unlocking the Power of Co-Occurrence in CLIP: A DualPrompt-Driven Method for Training-Free Zero-Shot Multi-Label Classification

Are Large Vision-Language Models Good Annotators for Image Tagging?

Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy Labels

Learning from Label Proportions via Proportional Value Classification

Bilateral Information-aware Test-time Adaptation for Vision-Language Models

Towards Scalable Oversight with Collaborative Multi-Agent Debate in Error Detection

A Closer Look at In-context Learning of LLMs in Simple Classification Tasks

Unsupervised Prompt Learning with Few-shot Examples for Answering Objective Questions

What Is Preference Optimization Doing, How and Why?

Sequence Length Matters in Data Scheduling for Accelerating Language Model Pretraining

From Coefficients to Directions: Rethinking Model Merging with Directional Alignment

CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Vision-Language Model

Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective

Color Blindness Test Images as Seen by Large Vision-Language Models

Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers

Adaptive Localization of Knowledge Negation for Continual LLM Unlearning

Realistic Evaluation of Deep Partial-Label Learning Algorithms

On the Role of Label Noise in the Feature Learning Process

Towards Out-of-Modal Generalization without Instance-level Modal Correspondence

Decoupling the Class Label and the Target Concept in Machine Unlearning

CARPRT: Class-Aware Prompt Reweighting for Pre-Trained Vision-Language Models

On the Cost-Effectiveness of Partially-Annotating Methods for Multi-Label Learning

Learning without Isolation: Pathway Protection for Continual Learning

Learning View-invariant World Models for Visual Robotic Manipulation

The Role of Label Noise in the Feature Learning Process

Exploring the Discriminative Capability of LLMs in In-context Learning

Do We Really Need Parameter-Isolation to Protect Task Knowledge?

On Unsupervised Prompt Learning for Classification with Black-box Language Models