This paper introduces Align4D, a framework for generating coherent video-3D pairs using any-modal input, achieving state-of-the-art quality and consistency in X-to-4D generation.

This paper proposes KroQuant, a post-training quantization method for diffusion transformers using learned Kronecker-structured invertible transforms, which reduces parameters, improves speed, and mai…

The paper proposes VRPO, a reinforcement learning-based optimization strategy that replaces static alignment losses in diffusion models, significantly improving both convergence and image fidelity.

The paper proposes a novel render-free framework that conditions video diffusion models directly on compressed 3D human mesh tokens, enabling robust 3D-aware human motion control without relying on re…

This paper introduces Spatially Conditioned Diffusion Policy (SCDP), a single-camera manipulation system that uses end-effector trajectories as visual attention anchors.

The paper demonstrates that high detection performance against obfuscated prompts does not guarantee representational robustness, identifying a phenomenon called latent embedding collapse.

This paper investigates the phenomenon of 'copying' in Distribution Matching Distillation (DMD), finding that high-dimensional distillation causes student models to spontaneously reproduce the teacher…

This paper explores how different components of the Transformer feedforward block architecture impact rank preservation across depth during initialization.

The paper introduces SynCity 3000, a framework for generating large, coherent 3D scenes using a convolutional generator, addressing the scarcity of 3D scene data for training.

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…

The paper demonstrates that off-the-shelf image diffusion models, like Stable Diffusion, can be repurposed to generate synthetic structured data, posing a threat of ground truth drift in closed eviden…

The study demonstrates that robust, domain-invariant representations of synthetic deception can be rapidly entrenched in LLMs using modest fine-tuning, detectable by linear probes even in early layers…

This paper introduces DDC, a Dead-Direction Conditioner that keeps a deep network's optimization on the symmetry quotient by conditioning the optimizer's state in the orbit decomposition of a $G$-inva…

The paper proposes SafeDIG, a robust safety steering framework that adapts Diffusion Transformers for text-to-image generation by treating safety control as position-aware sparse feature transfer, ens…

The paper proposes AEGIS, a novel diffusion-guided method for injecting adversarial perturbations into the latent space to create generalizable and robust defenses against advanced facial deepfake man…

The paper proposes using geometric metrics, specifically eigenspace alignment, to monitor the structural integrity of large behavioral populations, demonstrating its effectiveness in detecting network…

The paper introduces MDM-VGB, a reward-guided sampler for Masked Diffusion Models, which extends the Jerrum-Sinclair backtracking Markov chain to a masked-state graph for effective high-reward generat…