Machine Unlearning

CAP: Controllable Alignment Prompting for Unlearning in LLMs ACL 2026 CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization ACL 2026 Controlling Path Dependence in Gradient Ascent Unlearning through Forget-Set Ordering UAI 2026 CRISP: Persistent Concept Unlearning via Sparse Autoencoders ACL 2026 Disentangling the Effects of Unlearning in Measuring Parametric Faithfulness of Chain-of-Thought ACL 2026 Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models CVPR 2026 Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models ACL 2026 Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens ACL 2026 Grokked Models are Better Unlearners UAI 2026 JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification ACL 2026 LOKA: Conflict-Aware LLM Knowledge Update with Adaptive Knowledge Memory ACL 2026 LOTUS: Evolving Multimodal Unlearning via Hyperbolic Entailment and Lorentz Transport ACL 2026 Machine Unlearning via Adaptive Gradient Reweighting and Multi-stage Objective Optimization CVPR 2026 Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning ACL 2026 pH-Strips for Selective Forgetting: A Blunt but Fast Diagnostic Baseline for Machine Unlearning CVPR 2026 POUR: A Provably Optimal Method for Unlearning Representation via Neural Collapse CVPR 2026 REMIND: Memorization and Unlearning in LLMs Through the Lens of Input Loss Landscapes ACL 2026 Roots Beneath the Cut: Uncovering the Risk of Concept Revival in Pruning-Based Unlearning for Diffusion Models CVPR 2026 SANER: Switchable Adapter with Non-parametric Enhanced Routing for Person De-Reidentification CVPR 2026 Selective Amnesia using Contrastive Subnet Erasure for Class Level Unlearning in Vision Models CVPR 2026 Selective Span-Level Unlearning for Large Language Models ACL 2026 SGPVT: Self-Generated Proximal Visual Tokens for Mitigating Proximal Collateral Damage in MLLM Unlearning ACL 2026 SineProject: Machine Unlearning for Stable Vision-Language Alignment CVPR 2026 Stake the Points: Structure-Faithful Instance Unlearning CVPR 2026 TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models CVPR 2026