Cover Image

Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kwon, JuneHyoung, Kim, MiHyeon, Lee, Eunju, Yun, JungMin, Lim, Byeonggeuk, Kim, YoungBin
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias
by: Kwon, JuneHyoung, et al.
Published: (2026)

Position on LLM-Assisted Peer Review: Addressing Reviewer Gap through Mentoring and Feedback
by: Yun, JungMin, et al.
Published: (2026)

Erase Persona, Forget Lore: Benchmarking Multimodal Copyright Unlearning in Large Vision Language Models
by: Kwon, JuneHyoung, et al.
Published: (2026)

See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias
by: Kwon, JuneHyoung, et al.
Published: (2025)

Rank-O-ToM: Unlocking Emotional Nuance Ranking to Enhance Affective Theory-of-Mind
by: Kim, JiHyun, et al.
Published: (2025)

HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning
by: Lee, Eunju, et al.
Published: (2026)

Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation
by: Kwon, JuneHyoung, et al.
Published: (2024)

Aligning with Your Own Voice: Self-Corrected Preference Learning for Hallucination Mitigation in LVLMs
by: Lim, Byeonggeuk, et al.
Published: (2026)

VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought
by: Lim, Byeonggeuk, et al.
Published: (2026)

Query, Decompose, Compress: Structured Query Expansion for Efficient Multi-Hop Retrieval
by: Yun, JungMin, et al.
Published: (2026)

Medal Matters: Probing LLMs' Failure Cases Through Olympic Rankings
by: Choi, Juhwan, et al.
Published: (2024)

VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks
by: Choi, Juhwan, et al.
Published: (2024)

Beyond Single-User Dialogue: Assessing Multi-User Dialogue State Tracking Capabilities of Large Language Models
by: Song, Sangmin, et al.
Published: (2025)

UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation
by: Choi, Juhwan, et al.
Published: (2024)

SUMMPILOT: Bridging Efficiency and Customization for Interactive Summarization System
by: Yun, JungMin, et al.
Published: (2026)

GPTs Are Multilingual Annotators for Sequence Generation Tasks
by: Choi, Juhwan, et al.
Published: (2024)

Colorful Cutout: Enhancing Image Data Augmentation with Curriculum Learning
by: Choi, Juhwan, et al.
Published: (2024)

Structural analysis of the peptidoglycan DL‐endopeptidase CwlO complexed with its inhibitory protein IseA
by: Sudarshan Tandukar, et al.
Published: (2024)

Adverb Is the Key: Simple Text Data Augmentation with Adverb Deletion
by: Choi, Juhwan, et al.
Published: (2024)

Remembering the Stages, Forgetting the Person: Who Really Was Graham Wallas?
by: Kyung Hee Kim
Published: (2026)

Revisiting Early-Learning Regularization When Federated Learning Meets Noisy Labels
by: Kim, Taehyeon, et al.
Published: (2024)

Forget and Explain: Transparent Verification of GNN Unlearning
by: Ahsan, Imran, et al.
Published: (2025)

Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation
by: Choi, Juhwan, et al.
Published: (2024)

Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluation
by: Hwang, Yerin, et al.
Published: (2025)

Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning
by: Paramonov, Kirill, et al.
Published: (2025)

Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning
by: Yang, Nakyeong, et al.
Published: (2025)

Exploring the Impact of Collegiate Experiences on Academic Success and Retention for Non‐Traditional Students at Community Colleges: A Machine Learning Approach
by: JoHyun Kim, et al.
Published: (2025)

DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation
by: Jang, Soojin, et al.
Published: (2024)

Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting
by: Jang, Jinhyeok, et al.
Published: (2025)

Remembering and Forgetting the Ancient City
Published: (2022)

Dipeptidic Proline‐Derived Thiourea Organocatalysts for Asymmetric Michael addition Reactions between Aldehydes and Nitroolefins
by: Hyoung Min Yeo, et al.
Published: (2024)

Riemannian Geometric-based Meta Learning
by: Park, JuneYoung, et al.
Published: (2025)

Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens
by: Koh, Seunghee, et al.
Published: (2026)

Graph Memory Learning: Imitating Lifelong Remembering and Forgetting of Brain Networks
by: Miao, Jiaxing, et al.
Published: (2024)

Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
by: Kim, Minkuk, et al.
Published: (2024)

Revisit What You See: Revealing Visual Semantics in Vision Tokens to Guide LVLM Decoding
by: Cho, Beomsik, et al.
Published: (2025)

Chiral-odd generalized parton distributions in the large-$N_{c}$ limit of QCD: Next-to-leading-order contributions
by: Kim, June-Young
Published: (2025)

Tensor-polarized parton density in the $N \to Δ$ transition from the large-$N_c$ light-cone wave function
by: Kim, June-Young
Published: (2025)

Robust Extraction of Electron Energy Probability Function via Neural Network-Based Smoothing
by: Kim, June Young
Published: (2025)

Revisiting Softmax Masking: Stop Gradient for Enhancing Stability in Replay-based Continual Learning
by: Kim, Hoyong, et al.
Published: (2023)