Copertina

Understanding Machine Unlearning Through the Lens of Mode Connectivity

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cheng, Jiali, Amiri, Hadi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MultiDelete for Multimodal Machine Unlearning
di: Cheng, Jiali, et al.
Pubblicazione: (2023)

Toward Understanding Unlearning Difficulty: A Mechanistic Perspective and Circuit-Guided Difficulty Metric
di: Cheng, Jiali, et al.
Pubblicazione: (2026)

Do Students Debias Like Teachers? On the Distillability of Bias Mitigation Methods
di: Cheng, Jiali, et al.
Pubblicazione: (2025)

Tool Unlearning for Tool-Augmented LLMs
di: Cheng, Jiali, et al.
Pubblicazione: (2025)

Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs
di: Pan, Zhiyu, et al.
Pubblicazione: (2026)

Linguistic Blind Spots of Large Language Models
di: Cheng, Jiali, et al.
Pubblicazione: (2025)

FairFlow: Mitigating Dataset Biases through Undecided Learning
di: Cheng, Jiali, et al.
Pubblicazione: (2025)

A Comparative Study of Machine Unlearning Techniques for Image and Text Classification Models
di: Safa, Omar M., et al.
Pubblicazione: (2024)

Towards Reversible Model Merging For Low-rank Weights
di: Alipour, Mohammadsajad, et al.
Pubblicazione: (2025)

Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU
di: Vidal, Àlex Pujol, et al.
Pubblicazione: (2025)

$\nabla τ$: Gradient-based and Task-Agnostic machine Unlearning
di: Trippa, Daniel, et al.
Pubblicazione: (2024)

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models
di: Tian, Bozhong, et al.
Pubblicazione: (2024)

Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
di: Fang, Xianya, et al.
Pubblicazione: (2026)

DOCCI: Descriptions of Connected and Contrasting Images
di: Onoe, Yasumasa, et al.
Pubblicazione: (2024)

Deep Learning-Based Digitization of Overlapping ECG Images with Open-Source Python Code
di: Karbasi, Reza, et al.
Pubblicazione: (2025)

VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety
di: Palaskar, Shruti, et al.
Pubblicazione: (2025)

Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study
di: Crivoi, Carla, et al.
Pubblicazione: (2025)

Benchmarking the Thinking Mode of Multimodal Large Language Models in Clinical Tasks
di: Hong, Jindong, et al.
Pubblicazione: (2025)

One-Shot Machine Unlearning with Mnemonic Code
di: Yamashita, Tomoya, et al.
Pubblicazione: (2023)

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging
di: Xu, Haoming, et al.
Pubblicazione: (2025)

Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data
di: Zhang, Yuhui, et al.
Pubblicazione: (2024)

MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning
di: Cheng, Jiali, et al.
Pubblicazione: (2024)

Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Tasks
di: Hoehing, Nils, et al.
Pubblicazione: (2025)

Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI
di: Spartalis, Christoforos N., et al.
Pubblicazione: (2025)

Language-Image Models with 3D Understanding
di: Cho, Jang Hyun, et al.
Pubblicazione: (2024)

Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images
di: Bonato, Jacopo, et al.
Pubblicazione: (2024)

Understanding the Effects of Distractors on Reasoning Vision-Language Models
di: Bae, Jiyun, et al.
Pubblicazione: (2025)

Rethinking Genomic Modeling Through Optical Character Recognition
di: Xiang, Hongxin, et al.
Pubblicazione: (2026)

Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
di: Campbell, Declan, et al.
Pubblicazione: (2024)

MobileCLIP2: Improving Multi-Modal Reinforced Training
di: Faghri, Fartash, et al.
Pubblicazione: (2025)

CoUn: Empowering Machine Unlearning via Contrastive Learning
di: Khalil, Yasser H., et al.
Pubblicazione: (2025)

Privacy-Preserving Debiasing using Data Augmentation and Machine Unlearning
di: Pan, Zhixin, et al.
Pubblicazione: (2024)

Can Large Language Models Understand Symbolic Graphics Programs?
di: Qiu, Zeju, et al.
Pubblicazione: (2024)

Physical Property Understanding from Language-Embedded Feature Fields
di: Zhai, Albert J., et al.
Pubblicazione: (2024)

Rerouting Connection: Hybrid Computer Vision Analysis Reveals Visual Similarity Between Indus and Tibetan-Yi Corridor Writing Systems
di: Reddy, Ooha Lakkadi
Pubblicazione: (2025)

ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models
di: Lee, Jewon, et al.
Pubblicazione: (2025)

MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding
di: Zuo, Yuxin, et al.
Pubblicazione: (2025)

Transferring Textual Preferences to Vision-Language Understanding through Model Merging
di: Li, Chen-An, et al.
Pubblicazione: (2025)

Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Models
di: Miyai, Atsuyuki, et al.
Pubblicazione: (2024)

LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation
di: Lee, Suhyeon, et al.
Pubblicazione: (2023)