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.
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.
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.
Ensuring robust and real-time obstacle avoidance is critical for the safe operation of autonomous robots in dynamic, real-world environments. This paper proposes a neural network framework for predicting the time and collision position of an unmanned aerial vehicle with a dynamic object, using RGB and event-based vision sensors. The proposed architecture consists of two separate encoder branches, one for each modality, followed by fusion by self-attention to improve prediction accuracy. To facilitate benchmarking, we leverage the ABCD [8] dataset collected that enables detailed comparisons of single-modality and fusion-based approaches. At the same prediction throughput of 50Hz, the experimental results show that the fusion-based model offers an improvement in prediction accuracy over single-modality approaches of 1% on average and 10% for distances beyond 0.5m, but comes at the cost of +71% in memory and + 105% in FLOPs. Notably, the event-based model outperforms the RGB model by 4% for position and 26% for time error at a similar computational cost, making it a competitive alternative. Additionally, we evaluate quantized versions of the event-based models, applying 1- to 8-bit quantization to assess the trade-offs between predictive performance and computational efficiency. These findings highlight the trade-offs of multi-modal perception using RGB and event-based cameras in robotic applications.
We challenge the dominant focus on neural scaling laws and advocate for a paradigm shift toward downscaling in the development of large language models (LLMs). While scaling laws have provided critical insights into performance improvements through increasing model and dataset size, we emphasize the significant limitations of this approach, particularly in terms of computational inefficiency, environmental impact, and deployment constraints. To address these challenges, we propose a holistic framework for downscaling LLMs that seeks to maintain performance while drastically reducing resource demands. This paper outlines practical strategies for transitioning away from traditional scaling paradigms, advocating for a more sustainable, efficient, and accessible approach to LLM development.
Many works have succeeded in reconstructing Gaussian human avatars from multi-view videos. However, they either struggle to capture pose-dependent appearance details with a single MLP, or rely on a computationally intensive neural network to reconstruct high-fidelity appearance but with rendering performance degraded to non-real-time. We propose a novel Gaussian human avatar representation that can reconstruct high-fidelity pose-dependence appearance with details and meanwhile can be rendered in real time. Our Gaussian avatar is empowered by spatially distributed MLPs which are explicitly located on different positions on human body. The parameters stored in each Gaussian are obtained by interpolating from the outputs of its nearby MLPs based on their distances. To avoid undesired smooth Gaussian property changing during interpolation, for each Gaussian we define a set of Gaussian offset basis, and a linear combination of basis represents the Gaussian property offsets relative to the neutral properties. Then we propose to let the MLPs output a set of coefficients corresponding to the basis. In this way, although Gaussian coefficients are derived from interpolation and change smoothly, the Gaussian offset basis is learned freely without constraints. The smoothly varying coefficients combined with freely learned basis can still produce distinctly different Gaussian property offsets, allowing the ability to learn high-frequency spatial signals. We further use control points to constrain the Gaussians distributed on a surface layer rather than allowing them to be irregularly distributed inside the body, to help the human avatar generalize better when animated under novel poses. Compared to the state-of-the-art method, our method achieves better appearance quality with finer details while the rendering speed is significantly faster under novel views and novel poses.
The intrinsic alignments (IA) of galaxies, a key contaminant in weak lensing analyses, arise from correlations in galaxy shapes driven by tidal interactions and galaxy formation processes. Accurate IA modeling is essential for robust cosmological inference, but current approaches rely on perturbative methods that break down on nonlinear scales or on expensive simulations. We introduce IAEmu, a neural network-based emulator that predicts the galaxy position-position ($\xi$), position-orientation ($\omega$), and orientation-orientation ($\eta$) correlation functions and their uncertainties using mock catalogs based on the halo occupation distribution (HOD) framework. Compared to simulations, IAEmu achieves ~3% average error for $\xi$ and ~5% for $\omega$, while capturing the stochasticity of $\eta$ without overfitting. The emulator provides both aleatoric and epistemic uncertainties, helping identify regions where predictions may be less reliable. We also demonstrate generalization to non-HOD alignment signals by fitting to IllustrisTNG hydrodynamical simulation data. As a fully differentiable neural network, IAEmu enables $\sim$10,000$\times$ speed-ups in mapping HOD parameters to correlation functions on GPUs, compared to CPU-based simulations. This acceleration facilitates inverse modeling via gradient-based sampling, making IAEmu a powerful surrogate model for galaxy bias and IA studies with direct applications to Stage IV weak lensing surveys.
This article presents a method for estimating the dynamic driving states (position, velocity, acceleration and heading) from noisy measurement data. The proposed approach is effective with both complete and partial observations, producing refined trajectory signals with kinematic consistency, ensuring that velocity is the integral of acceleration and position is the integral of velocity. Additionally, the method accounts for the constraint that vehicles can only move in the direction of their orientation. The method is implemented as a configurable python library that also enables trajectory estimation solely based on position data. Regularization is applied to prevent extreme state variations. A key application is enhancing recorded trajectory data for use as reference inputs in machine learning models. At the end, the article presents the results of the method along with a comparison to ground truth data.
This paper proposes an innovative technique for representing multidimensional datasets using icons inspired by Chernoff faces. Our approach combines classical projection techniques with the explicit assignment of selected data dimensions to avatar (facial) features, leveraging the innate human ability to interpret facial traits. We introduce a semantic division of data dimensions into intuitive and technical categories, assigning the former to avatar features and projecting the latter into a four-dimensional (or higher) spatial embedding. The technique is implemented as a plugin for the open-source dpVision visualization platform, enabling users to interactively explore data in the form of a swarm of avatars whose spatial positions and visual features jointly encode various aspects of the dataset. Experimental results with synthetic test data and a 12-dimensional dataset of Portuguese Vinho Verde wines demonstrate that the proposed method enhances interpretability and facilitates the analysis of complex data structures.
Euclidean E(3) equivariant neural networks that employ scalar fields on position-orientation space M(3) have been effectively applied to tasks such as predicting molecular dynamics and properties. To perform equivariant convolutional-like operations in these architectures one needs Euclidean invariant kernels on M(3) x M(3). In practice, a handcrafted collection of invariants is selected, and this collection is then fed into multilayer perceptrons to parametrize the kernels. We rigorously describe an optimal collection of 4 smooth scalar invariants on the whole of M(3) x M(3). With optimal we mean that the collection is independent and universal, meaning that all invariants are pertinent, and any invariant kernel is a function of them. We evaluate two collections of invariants, one universal and one not, using the PONITA neural network architecture. Our experiments show that using a collection of invariants that is universal positively impacts the accuracy of PONITA significantly.
Recently, 3D Gaussian Splatting (3DGS) has emerged as a prominent framework for novel view synthesis, providing high fidelity and rapid rendering speed. However, the substantial data volume of 3DGS and its attributes impede its practical utility, requiring compression techniques for reducing memory cost. Nevertheless, the unorganized shape of 3DGS leads to difficulties in compression. To formulate unstructured attributes into normative distribution, we propose a well-structured tri-plane to encode Gaussian attributes, leveraging the distribution of attributes for compression. To exploit the correlations among adjacent Gaussians, K-Nearest Neighbors (KNN) is used when decoding Gaussian distribution from the Tri-plane. We also introduce Gaussian position information as a prior of the position-sensitive decoder. Additionally, we incorporate an adaptive wavelet loss, aiming to focus on the high-frequency details as iterations increase. Our approach has achieved results that are comparable to or surpass that of SOTA 3D Gaussians Splatting compression work in extensive experiments across multiple datasets. The codes are released at https://github.com/timwang2001/TC-GS.
Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often undermines their previously established safety alignment. To mitigate the degradation of model safety during fine-tuning, we introduce LookAhead Tuning, which comprises two simple, low-resource, and effective data-driven methods that modify training data by previewing partial answer prefixes. Both methods aim to preserve the model's inherent safety mechanisms by minimizing perturbations to initial token distributions. Comprehensive experiments demonstrate that LookAhead Tuning effectively maintains model safety without sacrificing robust performance on downstream tasks. Our findings position LookAhead Tuning as a reliable and efficient solution for the safe and effective adaptation of LLMs. Code is released at https://github.com/zjunlp/LookAheadTuning.
Movable antennas offer new potential for wireless communication by introducing degrees of freedom in antenna positioning, which has recently been explored for improving sum rates. In this paper, we aim to fully leverage the capabilities of movable antennas (MAs) by assuming that both the transmitter and receiver can optimize their antenna positions in multi-user multiple-input multiple-output (MU-MIMO) communications. Recognizing that WMMSE beamforming is a highly effective method for maximizing the MU-MIMO sum rate, we modify it to integrate antenna position optimization for MA systems, which we refer to as flexible WMMSE (F-WMMSE) beamforming. Importantly, we reformulate the subproblems within WMMSE to develop regularized sparse optimization frameworks to achieve joint beamforming (antenna coefficient optimization) and element movement (antenna position optimization). We then propose a regularized least squares-based simultaneous orthogonal matching pursuit (RLS-SOMP) algorithm to address the resulting sparse optimization problem. To enhance practical applications, the low-complexity implementation of the proposed framework is developed based on the pre-calculations and matrix inverse lemma. The overall F-WMMSE algorithm converges similarly to WMMSE, and our findings indicate that F-WMMSE achieves a significant sum rate improvement compared to traditional WMMSE, exceeding 20% under appropriate simulation conditions
Lung cancer is a leading cause of cancer-related deaths globally. PET-CT is crucial for imaging lung tumors, providing essential metabolic and anatomical information, while it faces challenges such as poor image quality, motion artifacts, and complex tumor morphology. Deep learning-based models are expected to address these problems, however, existing small-scale and private datasets limit significant performance improvements for these methods. Hence, we introduce a large-scale PET-CT lung tumor segmentation dataset, termed PCLT20K, which comprises 21,930 pairs of PET-CT images from 605 patients. Furthermore, we propose a cross-modal interactive perception network with Mamba (CIPA) for lung tumor segmentation in PET-CT images. Specifically, we design a channel-wise rectification module (CRM) that implements a channel state space block across multi-modal features to learn correlated representations and helps filter out modality-specific noise. A dynamic cross-modality interaction module (DCIM) is designed to effectively integrate position and context information, which employs PET images to learn regional position information and serves as a bridge to assist in modeling the relationships between local features of CT images. Extensive experiments on a comprehensive benchmark demonstrate the effectiveness of our CIPA compared to the current state-of-the-art segmentation methods. We hope our research can provide more exploration opportunities for medical image segmentation. The dataset and code are available at https://github.com/mj129/CIPA.
Although Multimodal Large Language Models (MLLMs) excel at various image-related tasks, they encounter challenges in precisely aligning coordinates with spatial information within images, particularly in position-aware tasks such as visual grounding. This limitation arises from two key factors. First, MLLMs lack explicit spatial references, making it difficult to associate textual descriptions with precise image locations. Second, their feature extraction processes prioritize global context over fine-grained spatial details, leading to weak localization capability. To address this issue, we introduce VPP-LLaVA, an MLLM equipped with Visual Position Prompt (VPP) to improve its grounding capability. VPP-LLaVA integrates two complementary mechanisms. The global VPP overlays learnable, axis-like embeddings onto the input image to provide structured spatial cues. The local VPP focuses on fine-grained localization by incorporating position-aware queries, which suggests probable object locations. We also introduce a VPP-SFT dataset with 0.6M samples, consolidating high-quality visual grounding data into a compact format for efficient model training. Training on this dataset with VPP enhances the model's performance, achieving state-of-the-art results on standard grounding benchmarks despite using fewer training samples compared to other MLLMs like MiniGPT-v2, which rely on much larger datasets ($\sim$21M samples). The code and VPP-SFT dataset will be available at https://github.com/WayneTomas/VPP-LLaVA upon acceptance.
Co-optimization of both vehicle speed and gear position via model predictive control (MPC) has been shown to offer benefits for fuel-efficient autonomous driving. However, optimizing both the vehicle's continuous dynamics and discrete gear positions may be too computationally intensive for a real-time implementation. This work proposes a learning-based MPC scheme to address this issue. A policy is trained to select and fix the gear positions across the prediction horizon of the MPC controller, leaving a significantly simpler continuous optimization problem to be solved online. In simulation, the proposed approach is shown to have a significantly lower computation burden and a comparable performance, with respect to pure MPC-based co-optimization.
Agentic workflows invoked by Large Language Models (LLMs) have achieved remarkable success in handling complex tasks. However, optimizing such workflows is costly and inefficient in real-world applications due to extensive invocations of LLMs. To fill this gap, this position paper formulates agentic workflows as computational graphs and advocates Graph Neural Networks (GNNs) as efficient predictors of agentic workflow performances, avoiding repeated LLM invocations for evaluation. To empirically ground this position, we construct FLORA-Bench, a unified platform for benchmarking GNNs for predicting agentic workflow performances. With extensive experiments, we arrive at the following conclusion: GNNs are simple yet effective predictors. This conclusion supports new applications of GNNs and a novel direction towards automating agentic workflow optimization. All codes, models, and data are available at https://github.com/youngsoul0731/Flora-Bench.
In this paper, we propose a novel approach for air drawing that uses image processing techniques to draw on the screen by moving fingers in the air. This approach benefits a wide range of applications such as sign language, in-air drawing, and 'writing' in the air as a new way of input. The approach starts with preparing ROI (Region of Interest) background images by taking a running average in initial camera frames and later subtracting it from the live camera frames to get a binary mask image. We calculate the pointer's position as the top of the contour on the binary image. When drawing a circle on the canvas in that position, it simulates the drawing. Furthermore, we combine the pre-trained Tesseract model for OCR purposes. To address the false contours, we perform hand detection based on the haar cascade before performing the background subtraction. In an experimental setup, we achieved a latency of only 100ms in air drawing. The code used to this research are available in GitHub as https://github.com/q-viper/Contour-Based-Writing
Real-world instructions with multiple constraints pose a significant challenge to existing large language models (LLMs). An observation is that the LLMs exhibit dramatic performance fluctuation when disturbing the order of the incorporated constraints. Yet, none of the existing works has systematically investigated this position bias problem in the field of multi-constraint instruction following. To bridge this gap, we design a probing task where we quantitatively measure the difficulty distribution of the constraints by a novel Difficulty Distribution Index (CDDI). Through the experimental results, we find that LLMs are more performant when presented with the constraints in a ``hard-to-easy'' order. This preference can be generalized to LLMs with different architecture or different sizes of parameters. Additionally, we conduct an explanation study, providing an intuitive insight into the correlation between the LLM's attention and constraint orders. Our code and dataset are publicly available at https://github.com/meowpass/PBIF.
Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiotemporal structure of video frames. Existing adaptations, such as RoPE-3D, attempt to encode spatial and temporal dimensions separately but suffer from two major limitations: positional bias in attention distribution and disruptions in video-text transitions. To overcome these issues, we propose Video Rotary Position Embedding (VRoPE), a novel positional encoding method tailored for Video-LLMs. Specifically, we introduce a more balanced encoding strategy that mitigates attention biases, ensuring a more uniform distribution of spatial focus. Additionally, our approach restructures positional indices to ensure a smooth transition between video and text tokens. Extensive experiments on different models demonstrate that VRoPE consistently outperforms previous RoPE variants, achieving significant improvements in video understanding, temporal reasoning, and retrieval tasks. Code will be available at https://github.com/johncaged/VRoPE.