Comba: Improving Bilinear RNNs with Closed-loop Control

A new framework named throttLL'eM has been introduced to optimize energy consumption during Large Language Model (LLM) inference by utilizing GPU frequency scaling while adhering to Service-Level Objectives (SLOs). This approach addresses the growing energy demands associated with LLMs, which are heavily reliant on GPUs for processing. The framework incorporates machine learning to predict future cache usage and batch sizes, allowing for efficient performance management.

A novel framework named Frequency-Aware Mamba (FAMamba) has been introduced to enhance traffic image restoration under adverse weather conditions, addressing a significant challenge in intelligent transportation systems. This architecture leverages frequency guidance alongside sequence modeling, featuring components like the Dual-Branch Feature Extraction Block and the Prior-Guided Block for improved texture detail recovery.

PanFoMa has been introduced as a lightweight hybrid neural network model designed to enhance pan-cancer research by addressing challenges in learning efficient single-cell representations and establishing a comprehensive evaluation benchmark. This model integrates the capabilities of Transformers and state-space models, enabling effective transcriptome modeling and capturing complex gene interactions.

A novel approach to motion capture using a deformable state space model has been developed, allowing AI to accurately track occluded motion, such as hands hidden behind objects. This advancement addresses the limitations of traditional computer vision systems that struggle with occlusions, leading to improved animation and robotic control.

A new study has introduced AbscessHeNe, a dataset of 4,926 contrast-enhanced CT slices specifically focused on head and neck abscesses, which are critical for timely diagnosis and treatment. This dataset aims to enhance the development of semantic segmentation models that can accurately identify abscess boundaries and assess deep neck space involvement.

A new dataset named MasHeNe has been introduced, comprising 3,779 contrast-enhanced CT slices that include both tumors and cysts, complete with pixel-level annotations. This initiative aims to fill the gap in existing public datasets that primarily focus on malignant lesions in head and neck imaging. The Windowing-Enhanced Mamba with Frequency integration (WEMF) model has been proposed, achieving a Dice score of 70.4, marking it as the top performer among evaluated methods.

DF-Mamba, a new framework for 3D hand pose estimation, addresses the challenges of severe occlusions in hand interactions by leveraging deformable state space modeling to enhance visual feature extraction beyond traditional convolutional methods. This innovation aims to improve the accuracy of hand pose estimation in complex scenarios where hands overlap or are partially obscured.