NEGATE: Constrained Semantic Guidance for Linguistic Negation in Text-to-Video Diffusion

TL;DR

This paper introduces a training-free, structured approach to model linguistic negation in diffusion-based text-to-video generation, improving negation handling without retraining and extending to video dynamics.

Contribution

It presents a novel, unified, training-free framework for modeling linguistic negation as a semantic guidance constraint in diffusion models, applicable to images and videos.

Findings

Achieves robust negation compliance in generated videos

Preserves visual fidelity and structural coherence

Extends negation modeling beyond representation-level evaluation

Abstract

Negation is a fundamental linguistic operator, yet it remains inadequately modeled in diffusion-based generative systems. In this work, we present a formal treatment of linguistic negation in diffusion-based generative models by modeling it as a structured feasibility constraint on semantic guidance within diffusion dynamics. Rather than introducing heuristics or retraining model parameters, we reinterpret classifier-free guidance as defining a semantic update direction and enforce negation by projecting the update onto a convex constraint set derived from linguistic structure. This novel formulation provides a unified framework for handling diverse negation phenomena, including object absence, graded non-inversion semantics, multi-negation composition, and scope-sensitive disambiguation. Our approach is training-free, compatible with pretrained diffusion backbones, and naturally extends from image generation to temporally evolving video trajectories. In addition, we introduce a structured negation-centric benchmark suite that isolates distinct linguistic failure modes in generative systems, to further research in this area. Experiments demonstrate that our method achieves robust negation compliance while preserving visual fidelity and structural coherence, establishing the first unified formulation of linguistic negation in diffusion-based generative models beyond representation-level evaluation.