Image de couverture de livre

BrokenBind: Universal Modality Exploration beyond Dataset Boundaries

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Huang, Zhuo, Chen, Runnan, Han, Bo, Niu, Gang, Sugiyama, Masashi, Liu, Tongliang
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents
par: Tran, Quan M., et autres
Publié: (2026)

Towards Scalable Oversight with Collaborative Multi-Agent Debate in Error Detection
par: Chen, Yongqiang, et autres
Publié: (2025)

Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
par: Cai, Xin-Qiang, et autres
Publié: (2025)

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
par: Wang, Qizhou, et autres
Publié: (2024)

Decoupling the Class Label and the Target Concept in Machine Unlearning
par: Zhu, Jianing, et autres
Publié: (2024)

What Is Preference Optimization Doing, and Why?
par: Wang, Yue, et autres
Publié: (2025)

A Fast Algorithm for the Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit
par: Nakamura, Shintaro, et autres
Publié: (2023)

BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
par: Zhang, Jingfeng, et autres
Publié: (2023)

Thompson Exploration with Best Challenger Rule in Best Arm Identification
par: Lee, Jongyeong, et autres
Publié: (2023)

When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
par: Hong, Ziming, et autres
Publié: (2025)

Rethinking Consistent Multi-Label Classification Under Inexact Supervision
par: Wang, Wei, et autres
Publié: (2025)

Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical
par: Wang, Wei, et autres
Publié: (2023)

Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought
par: Zhang, Zhen-Yu, et autres
Publié: (2024)

Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning
par: Xiao, Jia-Hao, et autres
Publié: (2024)

AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editing
par: Hong, Ziming, et autres
Publié: (2025)

Offline Reinforcement Learning from Datasets with Structured Non-Stationarity
par: Ackermann, Johannes, et autres
Publié: (2024)

Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning
par: Huang, Zhuo, et autres
Publié: (2026)

MeGU: Machine-Guided Unlearning with Target Feature Disentanglement
par: Wang, Haoyu, et autres
Publié: (2026)

In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement
par: Zhang, Zhen-Yu, et autres
Publié: (2024)

Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms
par: Wang, Wei, et autres
Publié: (2025)

Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
par: Yang, Puning, et autres
Publié: (2025)

Balancing Similarity and Complementarity for Federated Learning
par: Yan, Kunda, et autres
Publié: (2024)

Data-dependent Exploration for Online Reinforcement Learning from Human Feedback
par: Zhang, Zhen-Yu, et autres
Publié: (2026)

Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation
par: Xu, Jie, et autres
Publié: (2025)

Accurate Forgetting for Heterogeneous Federated Continual Learning
par: Wuerkaixi, Abudukelimu, et autres
Publié: (2025)

Realistic Evaluation of Deep Partial-Label Learning Algorithms
par: Wang, Wei, et autres
Publié: (2025)

Label Distribution Learning with Biased Annotations by Learning Multi-Label Representation
par: Kou, Zhiqiang, et autres
Publié: (2025)

Multi-Player Approaches for Dueling Bandits
par: Raveh, Or, et autres
Publié: (2024)

Riemannian Langevin Dynamics: Strong Convergence of Geometric Euler-Maruyama Scheme
par: Zhan, Zhiyuan, et autres
Publié: (2026)

VEC-SBM: Optimal Community Detection with Vectorial Edges Covariates
par: Braun, Guillaume, et autres
Publié: (2024)

Enriching Disentanglement: From Logical Definitions to Quantitative Metrics
par: Zhang, Yivan, et autres
Publié: (2023)

Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples
par: Yuan, Suqin, et autres
Publié: (2025)

On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
par: Lin, Runqi, et autres
Publié: (2023)

Practical estimation of the optimal classification error with soft labels and calibration
par: Ushio, Ryota, et autres
Publié: (2025)

The Survival Bandit Problem
par: Riou, Charles, et autres
Publié: (2022)

VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
par: Cai, Xin-Qiang, et autres
Publié: (2026)

Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training
par: Xie, Ming-Kun, et autres
Publié: (2024)

From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium
par: Yi, Xie, et autres
Publié: (2025)

From Coefficients to Directions: Rethinking Model Merging with Directional Alignment
par: Chen, Zhikang, et autres
Publié: (2025)

Reinforcement Learning with Options and State Representation
par: Ghriss, Ayoub, et autres
Publié: (2024)