paper-with-me

홈 › Papers

Concept Reachability in Diffusion Models: Beyond Dataset Constraints

2025-05-25 · Marta Aparicio Rodriguez, Xenia Miscouridou, Anastasia Borovykh

Despite significant advances in quality and complexity of the generations in text-to-image models, prompting does not always lead to the desired outputs. Controlling model behaviour by directly steering intermediate model activations has emerged as a viable alternative allowing to reach concepts in latent space that may otherwise remain inaccessible by prompt. In this work, we introduce a set of experiments to deepen our understanding of concept reachability. We design a training data setup with three key obstacles: scarcity of concepts, underspecification of concepts in the captions, and data biases with tied concepts. Our results show: (i) concept reachability in latent space exhibits a distinct phase transition, with only a small number of samples being sufficient to enable reachability, (ii) where in the latent space the intervention is performed critically impacts reachability, showing that certain concepts are reachable only at certain stages of transformation, and (iii) while prompting ability rapidly diminishes with a decrease in quality of the dataset, concepts often remain reliably reachable through steering. Model providers can leverage this to bypass costly retraining and dataset curation and instead innovate with user-facing control mechanisms.

📄 PDF Abstract BibTeX arXiv:2505.19313

Code (1)

martaaparod/concept_reachability 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion

2026-02-24 · Sathwik Karnik, Juyeop Kim, Sanmi Koyejo, Jong-Seok Lee 외 arxiv

Text-to-image diffusion models often memorize training data, revealing a fundamental failure to generalize beyond the training set. Current mitigation strategies typically sacrifice image quality or prompt alignment to r…

Reinforcement Learning

Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning

2026-03-08 · Janaka Chathuranga Brahmanage, Akshat Kumar arxiv

Sequential decision making using Markov Decision Process underpins many realworld applications. Both model-based and model free methods have achieved strong results in these settings. However, real-world tasks must balan…

Reinforcement LearningDecision Making

Data-Driven Reachability Analysis via Diffusion Models with PAC Guarantees

2026-03-31 · Yanliang Huang, Peng Xie, Wenyuan Wu, Zhuoqi Zeng 외 arxiv

We present a data-driven framework for reachability analysis of nonlinear dynamical systems that requires no explicit model. A denoising diffusion probabilistic model learns the time-evolving state distribution of a dyna…

Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control

2026-06-23 · Sabrina Bodmer, René Zurbrügg, Tifanny Portela, Hao Ma 외 arxiv

Diffusion models sample effectively from high-dimensional, multimodal distributions, but their outputs may violate deployment constraints. For task-space robot policies, generated grasps, waypoints, or trajectories can b…

$λ$-Reachability: Geometric-Horizon Safety Bellman Equations for Humanoid Safety

2026-06-14 · Rui Chen, Shangtao Li, Yifan Sun, Changliu Liu arxiv

We introduce $λ$-Reachability, a scalable approach to Hamilton--Jacobi safety analysis for high-dimensional robotic systems. Unlike prior discounted formulations that rely on fixed one-step Bellman updates, $λ$-Reachabil…

Collision Avoidance