arXiv Computer Vision
Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jul 1
Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models
arXiv:2606. 31699v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated features can serve as controllable intervention points.
arXiv AI
Sep 4
EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders
EraseSAE is a framework for surgical concept erasure in text-to-video diffusion models. It uses a Partitioned Convolutional Sparse Autoencoder to decompose activations into interpretable sparse features, a contrastive attribution mechanism to isolate concept-specific kernels, and timestep‑resolved masks to confine erasure to active regions. Experiments show precise removal with minimal quality loss, outperforming existing methods.
Hugging Face Trending Papers
Sep 3
EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders
EraseSAE introduces a surgical concept erasure method for text-to-video diffusion models, using sparse autoencoders to decompose activations into interpretable, monosemantic features. The framework employs a contrastive attribution mechanism to isolate concept-specific kernels and applies timestep-resolved masks during inference to remove target concepts while preserving unrelated content. Experiments show that EraseSAE achieves precise, robust concept removal with minimal quality loss, outperforming existing methods.
arXiv Computer Vision
Sep 7
FailSAE: Towards Interpretable Failure Prediction for Vision-Language Models via Sparse Autoencoders
The paper introduces FailSAE, a method that uses Sparse Autoencoders to predict failures in vision‑language models (VLMs) such as CLIP. By treating failure prediction as a classification over sparse SAE latent activations and employing a three‑stage training pipeline, the approach yields higher prediction accuracy than existing confidence‑score or auxiliary‑classifier baselines. Analysis shows that the SAE captures class‑specific concepts and reveals a shift toward ambiguous or style‑related concepts during failures, offering insights for runtime failure recovery.
arXiv Computation and Language
Aug 25
DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning
DynHD is a method for detecting hallucinations in diffusion large language models (D‑LLMs) by focusing on token‑level uncertainty and its evolution during the denoising process. It introduces a semantic‑aware evidence construction module that filters out non‑informative structural tokens and highlights uncertainty in informative tokens, and a reference evidence generator that models the expected trajectory of uncertainty, enabling a deviation‑based detector to identify hallucinations. Experiments show DynHD outperforms existing baselines while being more efficient across various benchmarks and backbone models.
arXiv Machine Learning
Jul 28
To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion
arXiv:2607. 23492v1 Announce Type: cross Abstract: Concept erasure techniques (CETs) edit text-to-image diffusion models to erase undesired targets such as NSFW content or copyrighted styles, while preserving model utility on benign concepts.