Posters

DISCEDIT efficiently identifies and edits discriminative neural network components for structured pruning and class unlearning, achieving high sparsity and forgetting rates without needing training da…

DisC-GS enhances Gaussian Splatting for real-time novel view synthesis by accurately rendering image discontinuities and boundaries, improving visual quality.

Director3D generates realistic 3D scenes and camera trajectories from text descriptions using a three-stage pipeline: Cinematographer, Decorator, and Detailer.

New sub-optimality bounds for gradient descent leverage directional smoothness, a localized gradient variation measure, achieving tighter convergence guarantees and adapting to optimization paths.

Direct3D: Revolutionizing image-to-3D generation with a scalable, native 3D diffusion model achieving state-of-the-art quality.

Direct Unlearning Optimization (DUO) robustly removes unsafe content from text-to-image models by using paired image data and output-preserving regularization, effectively defending against adversaria…

D-PBEMO: A novel framework for preference-based multi-objective optimization using clustering-based stochastic dueling bandits to directly leverage human feedback, improving efficiency and managing co…

Boosting personalized image generation! Direct Consistency Optimization (DCO) fine-tunes text-to-image models, ensuring subject consistency and prompt fidelity, even when merging separately customized…

DiPEx: a novel self-supervised prompt expansion method dramatically boosts class-agnostic object detection by progressively learning non-overlapping hyperspherical prompts, surpassing existing methods…

DiP-GO: A novel pruning method accelerates diffusion models via few-step gradient optimization, achieving a 4.4x speedup on Stable Diffusion 1.5 without accuracy loss.

DINTR: A novel diffusion-based object tracker surpasses existing methods by using efficient interpolation, achieving superior performance across diverse benchmarks.

DiMSUM: A novel diffusion model boosts image generation by unifying spatial and frequency information, achieving superior results and faster training.

Dimension-free private mean estimation is achieved for anisotropic data, breaking the curse of dimensionality in privacy-preserving high-dimensional analysis.

DIGRAF, a novel graph-adaptive activation function, significantly boosts Graph Neural Network performance by dynamically adapting to graph structure, offering consistent superior results across divers…

DigiRL: Autonomous RL trains robust in-the-wild device-control agents by offline-to-online RL, surpassing prior methods.

DiffusionPDE uses generative diffusion models to solve PDEs accurately, even with highly incomplete observations, outperforming state-of-the-art methods.

DiffusionFake enhances deepfake detection by cleverly reversing the image generation process, enabling detectors to learn more robust features and significantly improve cross-domain generalization.

DiffusionBlend++ learns a 3D image prior via position-aware diffusion score blending, achieving state-of-the-art 3D CT reconstruction with superior efficiency.

Diffusion4D: Fast, consistent 4D content generation via a novel 4D-aware video diffusion model, surpassing existing methods in efficiency and 4D geometry consistency.

Diffusion-Reward Adversarial Imitation Learning (DRAIL) enhances Generative Adversarial Imitation Learning by integrating diffusion models, resulting in more stable and smoother reward functions for s…