The paper proposes Neighbor-Aware Localized Concept Erasure (NLCE), a training-free framework that effectively removes specific concepts from text-to-image models while minimizing the unintended degra…

CoreUnlearn introduces a novel framework that disentangles and removes undesirable concepts from text-guided diffusion models by targeting specific, erasure-critical components of the concept embeddin…

The paper introduces GEM, an effective concept erasure framework for Rectified Flow Transformers, by unifying trajectory-based unlearning with classic teacher-guided flow matching.

The paper introduces TICoE, a text-image collaborative framework that achieves precise and faithful concept removal from text-to-image generative models, surpassing existing methods in both precision…

AnchorSteer introduces a framework that achieves high-fidelity, structure-preserving music editing by decoupling semantic concept injection from structural constraints.

The paper proposes Hydra, a framework to stabilize and control the injection of multiple, conflicting backdoor triggers into text-to-image diffusion models, ensuring high attack reliability while main…

The paper proposes a unified, constrained optimization framework using KL divergence and likelihood constraints to achieve effective and principled unlearning in diffusion models.

Mind-Omni introduces a unified multi-task framework that models the interplay between brain, vision, and language signals using a discrete diffusion paradigm, achieving state-of-the-art performance ac…

LoRA-Key introduces a user-centric watermarking framework that attaches a recoverable ownership key to LoRA modules via a standalone Watermark LoRA, providing lightweight, plug-and-play copyright prot…

EvoGens is an evolution-inspired framework that treats scientific idea generation as an evolutionary search, significantly boosting the novelty and diversity of generated research ideas compared to ex…

This paper provides the first integrated analysis of model dememorization, unifying unlearnability and unlearning methods, and offering theoretical guarantees on dememorization depth.

The paper introduces Staged Executable Inverse Graphics (SEIG), an agentic framework that uses general-purpose Vision-Language Models (VLMs) to reconstruct editable 3D scenes directly into executable…

The paper demonstrates that the location and nature of state encoding in sequence models are not fixed architectural traits but are highly dependent on the specific task, showing that the encoding pro…

This paper systematically investigates unlearnable examples (UEs) across diverse training paradigms, finding that existing UEs fail under pretraining-finetuning (PF) settings, and proposes Shallow Sem…

The paper proposes a local perturbation theory showing that cross-domain interference in multi-domain RL occurs via a low-dimensional shared conflict subspace, which can be selectively mitigated by sh…

The paper proposes a novel global sketch-based watermarking technique for diffusion language models that controls the entire sequence's statistics, offering an order-agnostic and context-independent a…

The paper introduces a theoretically grounded evaluation framework for watermarking generative models, proposing a novel method (SSB) that allows for systematic design across all security-robustness-f…

The paper compares anchorless methods for diversifying LLM-generated idea pools against traditional anchor-dependent methods, finding that semantic direction stratification offers the best balance of…

The paper introduces IDEAFix, a systematic evaluation framework designed to analyze how structured prompting and task design influence the divergent thinking and originality of idea generation in LLMs…