Posters

Unlocking the speed and efficiency of Mixture-of-Expert models, this research unveils novel optimization techniques, achieving dramatic improvements in inference throughput and resource usage.

Dynamic NLOS imaging gets a speed boost! New ST-Mamba method leverages temporal consistency across frames for high-resolution video reconstruction, overcoming speed limitations of traditional methods.

Boost survival prediction accuracy with CSD-iPOT: a novel post-processing method achieving superior marginal & conditional calibration without sacrificing discrimination.

Boosting 3D human pose estimation: Biomechanical Pose Generator and Binary Depth Coordinates enhance accuracy and scalability.

ConSurv: a novel contrastive learning approach for survival analysis enhances discrimination without sacrificing calibration by employing weighted sampling and aligning well with the assumption that p…

LeHaCE: a novel framework for evaluating object hallucination in LVLMs, improving evaluation stability and fairness by accounting for instruction-induced image description length variations.

Shallow ReLU neural networks face topological training obstructions due to gradient flow confinement on disconnected quadric hypersurfaces.

New topology-based complexity measures reliably predict deep learning model generalization, outperforming existing methods and offering practical computational efficiency.

TopoLogic uses lane geometry and query similarity to improve lane topology reasoning in autonomous driving, significantly outperforming existing methods.

TopoFR enhances face recognition by aligning topological structures between input and latent spaces. Using persistent homology, it preserves crucial data structure info, overcoming overfitting. A har…

ToMe: a novel training-free method dramatically improves semantic binding in text-to-image synthesis by intelligently merging related tokens, ensuring accurate alignment between generated images and t…

A new dual-learning model resolves the paradox of perceptual learning, showing how task-based and feature-based learning interact to produce both specific and transferable improvements in sensory perc…

This paper introduces novel metrics for visual emotion recognition evaluation, considering the psychological distance between emotions to better reflect human perception, improving the assessment of m…

This paper introduces an innovative iterative prompting method for estimating epistemic uncertainty in LLMs, enabling reliable detection of hallucinations.

TinyTTA enables efficient test-time adaptation on memory-constrained edge devices using a novel self-ensemble and early-exit strategy, improving accuracy and reducing memory usage.

TinyLUT achieves 10x lower memory consumption and superior accuracy in image restoration on edge devices using innovative separable mapping and dynamic discretization of LUTs.

Tiny Time Mixers (TTMs) achieve state-of-the-art zero/few-shot multivariate time series forecasting, outperforming existing benchmarks while drastically reducing computational requirements.

TimeXer empowers transformers for superior time series forecasting by cleverly integrating exogenous variables, achieving state-of-the-art results on diverse benchmarks.

Terra, a novel time-varying low-rank adapter, enables effective cross-domain fine-tuning of diffusion models by creating a continuous parameter manifold, facilitating efficient knowledge sharing and g…

TIME-FFM: a Federated Foundation Model empowers time series forecasting using pre-trained Language Models, tackling data scarcity and privacy concerns for superior few-shot and zero-shot predictions.