Spotlight Others

X-Ray: A novel 3D representation generating complete object surfaces from a single image!

T2IScoreScore objectively evaluates text-to-image prompt faithfulness metrics using semantic error graphs, revealing that simpler metrics surprisingly outperform complex, computationally expensive one…

Voxel Mamba: a group-free 3D object detection method using state space models, achieving higher accuracy and efficiency by overcoming limitations of serialization-based Transformers.

Voila-A enhances vision-language models by aligning their attention with user gaze, improving real-world application effectiveness and interpretability.

VMamba: a vision backbone achieving linear time complexity using Visual State Space (VSS) blocks and 2D Selective Scan (SS2D) for efficient visual representation.

VLMs learn to generate their own memories by abstracting experiences from noisy demonstrations and human feedback, significantly boosting in-context learning performance.

EVE, a groundbreaking encoder-free vision-language model, rivals encoder-based counterparts using a fraction of the data and resources, demonstrating efficient, transparent training for pure decoder-o…

Stable deep learning on graphs achieved using novel unitary group convolutions, preventing over-smoothing and enhancing model robustness.

Enhance deep neural network privacy and trustworthiness with unified gradient-based machine unlearning, leveraging remain geometry for efficient forgetting and performance preservation.

Simulation-free Neural SDE training via Trajectory Flow Matching unlocks scalability and stability for modeling complex real-world time series, particularly in clinical settings.

TrackIME enhances video point tracking by cleverly pruning the search space, resulting in improved accuracy and efficiency.

Universal Mesh Movement Network (UM2N) revolutionizes mesh movement for PDE solvers, enabling zero-shot adaptation to diverse problems and significantly accelerating simulations with improved accuracy…

UniKE: A unified multimodal editing method achieves superior reliability, generality, and locality by disentangling knowledge into semantic and truthfulness spaces, enabling enhanced collaboration bet…

EVORATE quantifies evolving patterns in sequential data, enabling better model selection and temporal analysis for improved machine learning.

Hybrid neural networks, combining digital feedforward and analog energy-based blocks, are trained end-to-end via a novel BP-EP gradient chaining algorithm, achieving state-of-the-art results on ImageN…

This paper introduces efficient algorithms for learning under arbitrary covariate shift, addressing limitations of prior approaches by enabling classifiers to abstain from predictions in high-shift sc…

Alchemist, a novel automated labeling system, reduces data annotation costs by 500x compared to LLMs while improving accuracy by an average of 12.9%.

TFG: A unified, training-free framework for boosting diffusion model performance by efficiently searching its algorithm-agnostic design space.

TextCtrl: a novel diffusion-based scene text editing method using prior guidance control, achieving superior style fidelity and accuracy with a new real-world benchmark dataset, ScenePair.

Text2CAD: AI generates CAD models from text prompts!