Oral Others

VASA-1: Real-time, lifelike talking faces generated from a single image and audio!

Revolutionizing machine learning, Schedule-Free optimization achieves state-of-the-art results without needing learning rate schedules, simplifying training and improving efficiency.

Stochastic Taylor Derivative Estimator (STDE) drastically accelerates the optimization of neural networks involving high-dimensional, high-order differential operators by efficiently amortizing comput…

ScaleGMNs, a new framework, enhances neural network processing by incorporating scaling symmetries, boosting performance across various tasks and datasets.

RG-SAN achieves state-of-the-art 3D referring expression segmentation by leveraging spatial awareness and rule-guided weak supervision, significantly improving accuracy and handling of ambiguous descr…

NeuroClips: groundbreaking fMRI-to-video reconstruction, achieving high-fidelity smooth video up to 6s at 8FPS by decoding both high-level semantics and low-level perception flows.

MeshFormer: High-quality 3D mesh generation from sparse views in seconds, using transformers and 3D convolutions.

MDAgents: An adaptive multi-agent LLM framework boosts medical decision-making accuracy by dynamically adjusting collaboration structures based on task complexity.

GIC: Novel hybrid framework leverages 3D Gaussian representation for accurate physical property estimation from visual observations, achieving state-of-the-art performance.

FlipClass dynamically updates the teacher model in a teacher-student framework to align with the student’s attention, resolving learning inconsistencies and significantly improving generalized categor…

SGRL, a novel graph contrastive learning framework, significantly boosts performance by leveraging the inherent ‘representation scattering’ mechanism and integrating graph topology, outperforming exis…

E2E-MFD: A novel end-to-end multimodal fusion detection algorithm achieves state-of-the-art performance by synchronously optimizing image fusion and object detection.

DenoiseRep: A novel denoising model enhances feature discrimination in computer vision tasks by integrating feature extraction and denoising within a single backbone, achieving impressive improvements…

DeAR: A novel framework lets LLMs solve complex problems with human-like iterative reasoning.

DapperFL enhances federated learning by introducing a model fusion pruning module and domain adaptive regularization to improve performance and reduce model size for heterogeneous edge devices.

Can AI understand humor? A new benchmark, YESBUT, reveals that even state-of-the-art models struggle with the nuanced humor of juxtaposed comics, highlighting the need for improved AI in understandin…

Convolutional Differentiable Logic Gate Networks achieve state-of-the-art accuracy on CIFAR-10 with 29x fewer gates than existing models, demonstrating highly efficient deep learning inference.

CAT3D: Generate high-quality 3D scenes from as little as one image using a novel multi-view diffusion model, outperforming existing methods in speed and quality.

Cambrian-1: Open, vision-centric multimodal LLMs achieve state-of-the-art performance using a novel spatial vision aggregator and high-quality data.

Bayesian-guided Label Mapping (BLM) enhances visual reprogramming!