Rotary Position Embedding (RoPE) is an efficient position encoding approach and is widely utilized in numerous large language models (LLMs). Recently, a lot of methods have been put forward to further expand the context window based on RoPE. The core concept of those methods is to predefine or search for a set of factors to rescale the base frequencies of RoPE. Nevertheless, it is quite a challenge for existing methods to predefine an optimal factor due to the exponential search space. In view of this, we introduce PSC (Phase Shift Calibration), a small module for calibrating the frequencies predefined by existing methods. With the employment of PSC, we demonstrate that many existing methods can be further enhanced, like PI, YaRN, and LongRoPE. We conducted extensive experiments across multiple models and tasks. The results demonstrate that (1) when PSC is enabled, the comparative reductions in perplexity increase as the context window size is varied from 16k, to 32k, and up to 64k. (2) Our approach is broadly applicable and exhibits robustness across a variety of models and tasks. The code can be found at https://github.com/WNQzhu/PSC.
Traffic forecasting is a key task in the field of Intelligent Transportation Systems. Recent research on traffic forecasting has mainly focused on combining graph neural networks (GNNs) with other models. However, GNNs only consider short-range spatial information. In this study, we present a novel model termed LSTAN-GERPE (Lightweight Spatio-Temporal Attention Network with Graph Embedding and Rotational Position Encoding). This model leverages both Temporal and Spatial Attention mechanisms to effectively capture long-range traffic dynamics. Additionally, the optimal frequency for rotational position encoding is determined through a grid search approach in both the spatial and temporal attention mechanisms. This systematic optimization enables the model to effectively capture complex traffic patterns. The model also enhances feature representation by incorporating geographical location maps into the spatio-temporal embeddings. Without extensive feature engineering, the proposed method in this paper achieves advanced accuracy on the real-world traffic forecasting datasets PeMS04 and PeMS08.
Modern video generation frameworks based on Latent Diffusion Models suffer from inefficiencies in tokenization due to the Frame-Proportional Information Assumption. Existing tokenizers provide fixed temporal compression rates, causing the computational cost of the diffusion model to scale linearly with the frame rate. The paper proposes the Duration-Proportional Information Assumption: the upper bound on the information capacity of a video is proportional to the duration rather than the number of frames. Based on this insight, the paper introduces VFRTok, a Transformer-based video tokenizer, that enables variable frame rate encoding and decoding through asymmetric frame rate training between the encoder and decoder. Furthermore, the paper proposes Partial Rotary Position Embeddings (RoPE) to decouple position and content modeling, which groups correlated patches into unified tokens. The Partial RoPE effectively improves content-awareness, enhancing the video generation capability. Benefiting from the compact and continuous spatio-temporal representation, VFRTok achieves competitive reconstruction quality and state-of-the-art generation fidelity while using only 1/8 tokens compared to existing tokenizers.
AI automated segmentations for radiation treatment planning (RTP) can deteriorate when applied in clinical cases with different characteristics than training dataset. Hence, we refined a pretrained transformer into a hybrid transformer convolutional network (HTN) to segment cardiac substructures lung and breast cancer patients acquired with varying imaging contrasts and patient scan positions. Cohort I, consisting of 56 contrast-enhanced (CECT) and 124 non-contrast CT (NCCT) scans from patients with non-small cell lung cancers acquired in supine position, was used to create oracle with all 180 training cases and balanced (CECT: 32, NCCT: 32 training) HTN models. Models were evaluated on a held-out validation set of 60 cohort I patients and 66 patients with breast cancer from cohort II acquired in supine (n=45) and prone (n=21) positions. Accuracy was measured using DSC, HD95, and dose metrics. Publicly available TotalSegmentator served as the benchmark. The oracle and balanced models were similarly accurate (DSC Cohort I: 0.80 \pm 0.10 versus 0.81 \pm 0.10; Cohort II: 0.77 \pm 0.13 versus 0.80 \pm 0.12), outperforming TotalSegmentator. The balanced model, using half the training cases as oracle, produced similar dose metrics as manual delineations for all cardiac substructures. This model was robust to CT contrast in 6 out of 8 substructures and patient scan position variations in 5 out of 8 substructures and showed low correlations of accuracy to patient size and age. A HTN demonstrated robustly accurate (geometric and dose metrics) cardiac substructures segmentation from CTs with varying imaging and patient characteristics, one key requirement for clinical use. Moreover, the model combining pretraining with balanced distribution of NCCT and CECT scans was able to provide reliably accurate segmentations under varied conditions with far fewer labeled datasets compared to an oracle model.
Reliable three-dimensional human pose estimation is becoming increasingly important for real-world applications, yet much of prior work has focused solely on the performance within a single dataset. In practice, however, systems must adapt to diverse viewpoints, environments, and camera setups -- conditions that differ significantly from those encountered during training, which is often the case in real-world scenarios. To address these challenges, we present a standardized testing environment in which each method is evaluated on a variety of datasets, ensuring consistent and fair cross-dataset comparisons -- allowing for the analysis of methods on previously unseen data. Therefore, we propose PoseBench3D, a unified framework designed to systematically re-evaluate prior and future models across four of the most widely used datasets for human pose estimation -- with the framework able to support novel and future datasets as the field progresses. Through a unified interface, our framework provides datasets in a pre-configured yet easily modifiable format, ensuring compatibility with diverse model architectures. We re-evaluated the work of 18 methods, either trained or gathered from existing literature, and reported results using both Mean Per Joint Position Error (MPJPE) and Procrustes Aligned Mean Per Joint Position Error (PA-MPJPE) metrics, yielding more than 100 novel cross-dataset evaluation results. Additionally, we analyze performance differences resulting from various pre-processing techniques and dataset preparation parameters -- offering further insight into model generalization capabilities.
Wearable sensors are typically affixed to specific locations on the human body, and their position remains static, only changing unintentionally due to motion artifacts. This static configuration introduces significant limitations. As a result, current systems miss the opportunity to capture dynamic physiological data from diverse body regions. This research investigates the potential of developing movable sensors that adaptively reposition themselves to sample different areas of interest on the body, addressing gaps in spatial coverage. We designed, developed, and fabricated a 3 x 3 matrix platform to support moving sensors from one location to another. We validated the feasibility through simulations on a matrix of up to 9 x 9 locations with up to 16 concurrent sensors and real-world prototype characterization.
Using multimodal sensory data can enhance communications systems by reducing the overhead and latency in beam training. However, processing such data incurs high computational complexity, and continuous sensing results in significant power and bandwidth consumption. This gives rise to a tradeoff between the (multimodal) sensing data acquisition rate and communications performance. In this work, we develop a constrained multimodal sensing-aided communications framework where dynamic sensing and beamforming are performed under a sensing budget. Specifically, we formulate an optimization problem that maximizes the average received signal-to-noise ratio (SNR) of user equipment, subject to constraints on the average number of sensing actions and power budget. Using the Saleh-Valenzuela mmWave channel model, we construct the channel primarily based on position information obtained via multimodal sensing. Stricter sensing constraints reduce the availability of position data, leading to degraded channel estimation and thus lower performance. We apply Lyapunov optimization to solve the problem and derive a dynamic sensing and beamforming algorithm. Numerical evaluations on the DeepSense and Raymobtime datasets show that halving sensing times leads to only up to 7.7% loss in average SNR.
The intricate and multifaceted nature of vision language model (VLM) development, adaptation, and application necessitates the establishment of clear and standardized reporting protocols, particularly within the high-stakes context of healthcare. Defining these reporting standards is inherently challenging due to the diverse nature of studies involving VLMs, which vary significantly from the development of all new VLMs or finetuning for domain alignment to off-the-shelf use of VLM for targeted diagnosis and prediction tasks. In this position paper, we argue that traditional machine learning reporting standards and evaluation guidelines must be restructured to accommodate multiphase VLM studies; it also has to be organized for intuitive understanding of developers while maintaining rigorous standards for reproducibility. To facilitate community adoption, we propose a categorization framework for VLM studies and outline corresponding reporting standards that comprehensively address performance evaluation, data reporting protocols, and recommendations for manuscript composition. These guidelines are organized according to the proposed categorization scheme. Lastly, we present a checklist that consolidates reporting standards, offering a standardized tool to ensure consistency and quality in the publication of VLM-related research.
Vision transformers have demonstrated significant advantages in computer vision tasks due to their ability to capture long-range dependencies and contextual relationships through self-attention. However, existing position encoding techniques, which are largely borrowed from natural language processing, fail to effectively capture semantic-aware positional relationships between image patches. Traditional approaches like absolute position encoding and relative position encoding primarily focus on 1D linear position relationship, often neglecting the semantic similarity between distant yet contextually related patches. These limitations hinder model generalization, translation equivariance, and the ability to effectively handle repetitive or structured patterns in images. In this paper, we propose 2-Dimensional Semantic-Aware Position Encoding ($\text{SaPE}^2$), a novel position encoding method with semantic awareness that dynamically adapts position representations by leveraging local content instead of fixed linear position relationship or spatial coordinates. Our method enhances the model's ability to generalize across varying image resolutions and scales, improves translation equivariance, and better aggregates features for visually similar but spatially distant patches. By integrating $\text{SaPE}^2$ into vision transformers, we bridge the gap between position encoding and perceptual similarity, thereby improving performance on computer vision tasks.
Intra-cardiac Echocardiography (ICE) plays a crucial role in Electrophysiology (EP) and Structural Heart Disease (SHD) interventions by providing high-resolution, real-time imaging of cardiac structures. However, existing navigation methods rely on electromagnetic (EM) tracking, which is susceptible to interference and position drift, or require manual adjustments based on operator expertise. To overcome these limitations, we propose a novel anatomy-aware pose estimation system that determines the ICE catheter position and orientation solely from ICE images, eliminating the need for external tracking sensors. Our approach leverages a Vision Transformer (ViT)-based deep learning model, which captures spatial relationships between ICE images and anatomical structures. The model is trained on a clinically acquired dataset of 851 subjects, including ICE images paired with position and orientation labels normalized to the left atrium (LA) mesh. ICE images are patchified into 16x16 embeddings and processed through a transformer network, where a [CLS] token independently predicts position and orientation via separate linear layers. The model is optimized using a Mean Squared Error (MSE) loss function, balancing positional and orientational accuracy. Experimental results demonstrate an average positional error of 9.48 mm and orientation errors of (16.13 deg, 8.98 deg, 10.47 deg) across x, y, and z axes, confirming the model accuracy. Qualitative assessments further validate alignment between predicted and target views within 3D cardiac meshes. This AI-driven system enhances procedural efficiency, reduces operator workload, and enables real-time ICE catheter localization for tracking-free procedures. The proposed method can function independently or complement existing mapping systems like CARTO, offering a transformative approach to ICE-guided interventions.
Based on the concept that ventral visual stream (VVS) mainly functions for object recognition, current unsupervised task-driven methods model VVS by contrastive learning, and have achieved good brain similarity. However, we believe functions of VVS extend beyond just object recognition. In this paper, we introduce an additional function involving VVS, named relative position (RP) prediction. We first theoretically explain contrastive learning may be unable to yield the model capability of RP prediction. Motivated by this, we subsequently integrate RP learning with contrastive learning, and propose a new unsupervised task-driven method to model VVS, which is more inline with biological reality. We conduct extensive experiments, demonstrating that: (i) our method significantly improves downstream performance of object recognition while enhancing RP predictivity; (ii) RP predictivity generally improves the model brain similarity. Our results provide strong evidence for the involvement of VVS in location perception (especially RP prediction) from a computational perspective.
Occlusion and the scarcity of labeled surgical data are significant challenges in disparity estimation for stereo laparoscopic images. To address these issues, this study proposes a Depth Guided Occlusion-Aware Disparity Refinement Network (DGORNet), which refines disparity maps by leveraging monocular depth information unaffected by occlusion. A Position Embedding (PE) module is introduced to provide explicit spatial context, enhancing the network's ability to localize and refine features. Furthermore, we introduce an Optical Flow Difference Loss (OFDLoss) for unlabeled data, leveraging temporal continuity across video frames to improve robustness in dynamic surgical scenes. Experiments on the SCARED dataset demonstrate that DGORNet outperforms state-of-the-art methods in terms of End-Point Error (EPE) and Root Mean Squared Error (RMSE), particularly in occlusion and texture-less regions. Ablation studies confirm the contributions of the Position Embedding and Optical Flow Difference Loss, highlighting their roles in improving spatial and temporal consistency. These results underscore DGORNet's effectiveness in enhancing disparity estimation for laparoscopic surgery, offering a practical solution to challenges in disparity estimation and data limitations.
Bed-based pressure-sensitive mats (PSMs) offer a non-intrusive way of monitoring patients during sleep. We focus on four-way sleep position classification using data collected from a PSM placed under a mattress in a sleep clinic. Sleep positions can affect sleep quality and the prevalence of sleep disorders, such as apnea. Measurements were performed on patients with suspected sleep disorders referred for assessments at a sleep clinic. Training deep learning models can be challenging in clinical settings due to the need for large amounts of labeled data. To overcome the shortage of labeled training data, we utilize transfer learning to adapt pre-trained deep learning models to accurately estimate sleep positions from a low-resolution PSM dataset collected in a polysomnography sleep lab. Our approach leverages Vision Transformer models pre-trained on ImageNet using masked autoencoding (ViTMAE) and a pre-trained model for human pose estimation (ViTPose). These approaches outperform previous work from PSM-based sleep pose classification using deep learning (TCN) as well as traditional machine learning models (SVM, XGBoost, Random Forest) that use engineered features. We evaluate the performance of sleep position classification from 112 nights of patient recordings and validate it on a higher resolution 13-patient dataset. Despite the challenges of differentiating between sleep positions from low-resolution PSM data, our approach shows promise for real-world deployment in clinical settings
This work presents DLO-Splatting, an algorithm for estimating the 3D shape of Deformable Linear Objects (DLOs) from multi-view RGB images and gripper state information through prediction-update filtering. The DLO-Splatting algorithm uses a position-based dynamics model with shape smoothness and rigidity dampening corrections to predict the object shape. Optimization with a 3D Gaussian Splatting-based rendering loss iteratively renders and refines the prediction to align it with the visual observations in the update step. Initial experiments demonstrate promising results in a knot tying scenario, which is challenging for existing vision-only methods.
Autoregressive models (ARMs), which predict subsequent tokens one-by-one ``from left to right,'' have achieved significant success across a wide range of sequence generation tasks. However, they struggle to accurately represent sequences that require satisfying sophisticated constraints or whose sequential dependencies are better addressed by out-of-order generation. Masked Diffusion Models (MDMs) address some of these limitations, but the process of unmasking multiple tokens simultaneously in MDMs can introduce incoherences, and MDMs cannot handle arbitrary infilling constraints when the number of tokens to be filled in is not known in advance. In this work, we introduce Insertion Language Models (ILMs), which learn to insert tokens at arbitrary positions in a sequence -- that is, they select jointly both the position and the vocabulary element to be inserted. By inserting tokens one at a time, ILMs can represent strong dependencies between tokens, and their ability to generate sequences in arbitrary order allows them to accurately model sequences where token dependencies do not follow a left-to-right sequential structure. To train ILMs, we propose a tailored network parameterization and use a simple denoising objective. Our empirical evaluation demonstrates that ILMs outperform both ARMs and MDMs on common planning tasks. Furthermore, we show that ILMs outperform MDMs and perform on par with ARMs in an unconditional text generation task while offering greater flexibility than MDMs in arbitrary-length text infilling.
Large Vision Language Models (LVLMs) excel in various vision-language tasks. Yet, their robustness to visual variations in position, scale, orientation, and context that objects in natural scenes inevitably exhibit due to changes in viewpoint and environment remains largely underexplored. To bridge this gap, we introduce V$^2$R-Bench, a comprehensive benchmark framework for evaluating Visual Variation Robustness of LVLMs, which encompasses automated evaluation dataset generation and principled metrics for thorough robustness assessment. Through extensive evaluation on 21 LVLMs, we reveal a surprising vulnerability to visual variations, in which even advanced models that excel at complex vision-language tasks significantly underperform on simple tasks such as object recognition. Interestingly, these models exhibit a distinct visual position bias that contradicts theories of effective receptive fields, and demonstrate a human-like visual acuity threshold. To identify the source of these vulnerabilities, we present a systematic framework for component-level analysis, featuring a novel visualization approach for aligned visual features. Results show that these vulnerabilities stem from error accumulation in the pipeline architecture and inadequate multimodal alignment. Complementary experiments with synthetic data further demonstrate that these limitations are fundamentally architectural deficiencies, scoring the need for architectural innovations in future LVLM designs.
Recommender systems are essential for delivering personalized content across digital platforms by modeling user preferences and behaviors. Recently, large language models (LLMs) have been adopted for prompt-based recommendation due to their ability to generate personalized outputs without task-specific training. However, LLM-based methods face limitations such as limited context window size, inefficient pointwise and pairwise prompting, and difficulty handling listwise ranking due to token constraints. LLMs can also be sensitive to position bias, as they may overemphasize earlier items in the prompt regardless of their true relevance. To address and investigate these issues, we propose a hybrid framework that combines a traditional recommendation model with an LLM for reranking top-k items using structured prompts. We evaluate the effects of user history reordering and instructional prompts for mitigating position bias. Experiments on MovieLens-100K show that randomizing user history improves ranking quality, but LLM-based reranking does not outperform the base model. Explicit instructions to reduce position bias are also ineffective. Our evaluations reveal limitations in LLMs' ability to model ranking context and mitigate bias. Our code is publicly available at https://github.com/aminul7506/LLMForReRanking.
Linear Hall sensors are a cost-effective alternative to optical encoders for measuring the rotor positions of actuators, with the main challenge being that they exhibit position-dependent inaccuracies resulting from manufacturing tolerances. This paper develops a data-driven calibration procedure for linear analog Hall sensors that enables accurate online estimates of the rotor angle without requiring expensive external encoders. The approach combines closed-loop data collection with nonlinear identification to obtain an accurate model of the sensor inaccuracies, which is subsequently used for online compensation. Simulation results show that when the flux density model structure is known, measurement errors are reduced to the sensor noise floor, and experiments on an industrial setup demonstrate a factor of 2.6 reduction in the root-mean-square measurement error. These results confirm that Hall sensor inaccuracies can be calibrated even when no external encoder is available, improving their practical applicability.
In this position paper, we advocate for the development of conversational technology that is inherently designed to support and facilitate argumentative processes. We argue that, at present, large language models (LLMs) are inadequate for this purpose, and we propose an ideal technology design aimed at enhancing argumentative skills. This involves re-framing LLMs as tools to exercise our critical thinking skills rather than replacing them. We introduce the concept of \textit{reasonable parrots} that embody the fundamental principles of relevance, responsibility, and freedom, and that interact through argumentative dialogical moves. These principles and moves arise out of millennia of work in argumentation theory and should serve as the starting point for LLM-based technology that incorporates basic principles of argumentation.
Technological advancements have led to the rise of wearable devices with sensors that continuously monitor user activities, generating vast amounts of unlabeled data. This data is challenging to interpret, and manual annotation is labor-intensive and error-prone. Additionally, data distribution is often heterogeneous due to device placement, type, and user behavior variations. As a result, traditional transfer learning methods perform suboptimally, making it difficult to recognize daily activities. To address these challenges, we use a variational autoencoder (VAE) to learn a shared, low-dimensional latent space from available sensor data. This space generalizes data across diverse sensors, mitigating heterogeneity and aiding robust adaptation to the target domain. We integrate contrastive learning to enhance feature representation by aligning instances of the same class across domains while separating different classes. We propose Variational Contrastive Domain Adaptation (VaCDA), a multi-source domain adaptation framework combining VAEs and contrastive learning to improve feature representation and reduce heterogeneity between source and target domains. We evaluate VaCDA on multiple publicly available datasets across three heterogeneity scenarios: cross-person, cross-position, and cross-device. VaCDA outperforms the baselines in cross-position and cross-device scenarios.