EoS-FM: Can an Ensemble of Specialist Models act as a Generalist Feature Extractor?

SignRoundV2 has been introduced as a post-training quantization framework aimed at improving the efficiency of deploying Large Language Models (LLMs) while minimizing performance degradation typically associated with low-bit quantization. This framework employs a fast sensitivity metric and a lightweight pre-tuning search to optimize layer-wise bit allocation and quantization scales, achieving competitive accuracy even at extremely low-bit levels.

OnSight Pathology has introduced a platform-agnostic computational pathology software that enhances real-time histopathological analysis through AI-driven insights, addressing the challenges of subjective interpretation and the need for specialized expertise in surgical tissue examination.

Recent advancements in diffusion models have led to the introduction of Refa\c{c}ade, a novel method for Object Retexture, which allows for the transfer of local textures from a reference object to a target object in images or videos. This method addresses the limitations of existing approaches by enhancing controllability and precision in texture transfer through innovative designs, including a texture remover trained on 3D mesh renderings.

OmniScaleSR has been introduced as a novel approach to arbitrary-scale super-resolution (ASSR), addressing the limitations of traditional super-resolution methods that only function at fixed scales. This model utilizes a scale-controlled diffusion prior to enhance the realism and detail in generated images, overcoming challenges faced by existing diffusion-based models that lack explicit scale control.

Large Language Models (LLMs) are being explored for their zero-shot multilingual capabilities, particularly in the context of information retrieval from Electronic Health Records (EHRs) in Italian healthcare. This research highlights the potential of LLMs to enhance the extraction of critical information from complex clinical texts, addressing limitations of traditional NLP methods.

A new framework for recognizing Parkinsonian gait patterns has been developed, utilizing a multimodal approach that fuses RGB and Depth (RGB-D) data. This system employs dual YOLOv11-based encoders and a Multi-Scale Local-Global Extraction module to enhance gait analysis, particularly in challenging conditions such as low lighting or occlusion.

A new memory-efficient optimization strategy for the VANICP point cloud registration algorithm has been proposed, enabling its lightweight execution on embedded GPUs with limited hardware resources. This strategy addresses the high memory demands of the original implementation, which hindered its deployment in resource-constrained environments.

The introduction of 4DLangVGGT, a Transformer-based framework for 4D language grounding, marks a significant advancement in the construction of 4D language fields, essential for applications in embodied AI and augmented/virtual reality. This framework integrates geometric perception and language alignment, addressing limitations of existing methods that rely on scene-specific Gaussian splatting.