Spatial crowdsourcing (SC) services, such as ridesharing and food delivery, are increasingly shaping people's daily lives. A key issue in SC is online task assignment, which involves assigning tasks to appropriate workers in real time. Most existing studies focus on task assignment within independent platforms but still face the limitation of spatial-temporal imbalance between tasks and workers. Recently, aggregation platforms (e.g., AMap's ride-hailing) have emerged, enabling tasks to be completed by workers from multiple cooperating platforms. However, effectively incentivizing these cooperating platforms to deliver high-quality services remains an open challenge. In this paper, we study a novel Aggregative Online Task Assignment (AOTA) problem, where the aggregation platform assigns tasks to suitable cooperating providers with the goal of maximizing overall quality-aware social welfare. To address the AOTA problem, we design an efficient Context-aware Online Bidding Task Assignment (COBTA) framework, which integrates a reverse sealed Vickrey auction to promote truthful bidding for public tasks among platforms. COBTA employs an exploration-exploitation strategy for efficient and effective public task assignment and leverages a multi-agent reinforcement learning method to enable cooperating platforms to make adaptive bid-or-not decisions based on their internal status. Extensive experiments on three real-world datasets validate the effectiveness and efficiency of our proposed solution.

Collaborative spatial crowdsourcing leverages distributed workers' collective intelligence to accomplish spatial tasks. A central challenge is to efficiently assign suitable workers to collaborate on these tasks. Although mainstream reinforcement learning (RL) methods have proven effective in task allocation, they face two key obstacles: delayed reward feedback and non-stationary data distributions, both hindering optimal allocation and collaborative efficiency. To address these limitations, we propose CAFE (credit assignment and fine-tuning enhanced), a novel multi-agent RL framework for spatial crowdsourcing. CAFE introduces a credit assignment mechanism that distributes rewards based on workers' contributions and spatiotemporal constraints, coupled with bi-level meta-optimization to jointly optimize credit assignment and RL policy. To handle non-stationary spatial task distributions, CAFE employs an adaptive fine-tuning procedure that efficiently adjusts credit assignment parameters while preserving collaborative knowledge. Experiments on two real-world datasets validate the effectiveness of our framework, demonstrating superior performance in terms of task completion and equitable reward redistribution.

The rapid growth of e-commerce has intensified the demand for efficient urban logistics. Electric Vehicles (EVs), with their eco-friendly and high-efficiency features, have emerged as a promising solution for improving urban logistics efficiency. However, due to their limited battery capacity, EVs often require recharging during operations, and improper charging decisions may lead to delivery delays, resulting in a loss of platform revenue. In this paper, we explore a novel EV Charging-Aware Task Assignment (ECTA) problem in urban logistics scenarios, where the objective is to maximize platform revenue by ensuring timely task completion while meeting the charging needs of EVs. To address this challenge, we present e-Charge, an efficient two-stage framework that enables real-time optimization of two continuous processes: task assignment and charging decision. For task assignment, which focuses on matching tasks to suitable EVs, we construct a hybrid weight model that incorporates charging penalties to calculate matching weights for EVs in both active and charging states, thus improving task assignment quality. Additionally, we implement an effective vehicle selection strategy to expedite the matching process, ensuring the efficiency of task assignment. For charging decision, which focuses on determining when and where EVs should be charged, we propose a multi-agent reinforcement learning (MARL) approach to dynamically select the charging timing for EVs. To further enhance decision-making quality, we devise a hierarchical communication graph that enables better collaboration between EVs and facilitates adaptive charging decisions. Finally, extensive experiments demonstrate thate-Chargesignificantly outperforms compared methods, achieving higher revenue and task completion ratio across a wide range of parameter settings.

Recent studies show that large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others.We discovered that such a contrary is due to LLM's bias in evaluating their own output.In this paper, we formally define LLM's self-bias -the tendency to favor its own generation -using two statistics.We analyze six LLMs (GPT-4, GPT-3.5, Gemini, LLaMA2, Mixtral and DeepSeek) on translation, constrained text generation, and mathematical reasoning tasks.We find that self-bias is prevalent in all examined LLMs across multiple languages and tasks.Our analysis reveals that while the self-refine pipeline improves the fluency and understandability of model outputs, it further amplifies self-bias.To mitigate such biases, we discover that larger model size and external feedback with accurate assessment can significantly reduce bias in the self-refine pipeline, leading to actual performance improvement in downstream tasks.The code and data are released at https://github. com/xu1998hz/llm_self_bias.

Various heuristic objectives for modeling hand-object interaction have been proposed in past work. However, due to the lack of a cohesive framework, these objectives often possess a narrow scope of applicability and are limited by their efficiency or accuracy. In this paper, we propose HANDYPRIORS, a unified and general pipeline for pose estimation in human-object interaction scenes by leveraging recent advances in differentiable physics and rendering. Our approach employs rendering priors to align with input images and segmentation masks along with physics priors to mitigate penetration and relative-sliding across frames. Furthermore, we present two alternatives for hand and object pose estimation. The optimization-based pose estimation achieves higher accuracy, while the filtering-based tracking, which utilizes the differentiable priors as dynamics and observation models, executes faster. We demonstrate that HANDYPRIORS attains comparable or superior results in the pose estimation task, and that the differentiable physics module can predict contact information for pose refinement. We also show that our approach generalizes to perception tasks, including robotic hand manipulation and human-object pose estimation in the wild.

Video transformers are slow to train due to extremely large numbers of input tokens, even though many video tokens are repeated over time. Existing methods to remove uninformative tokens either have significant overhead, negating any speedup, or require tuning for different datasets and examples. We present Run-Length Tokenization (RLT), a simple approach to speed up video transformers inspired by run-length encoding for data compression. RLT efficiently finds and removes `runs' of patches that are repeated over time before model inference, then replaces them with a single patch and a positional encoding to represent the resulting token's new length. Our method is content-aware, requiring no tuning for different datasets, and fast, incurring negligible overhead. RLT yields a large speedup in training, reducing the wall-clock time to fine-tune a video transformer by 30% while matching baseline model performance. RLT also works without training, increasing model throughput by 35% with only 0.1% drop in accuracy. RLT speeds up training at 30 FPS by more than 100%, and on longer video datasets, can reduce the token count by up to 80\%. Our project page is at rccchoudhury.github.io/projects/rlt.

Top- k Publish/Subscribe (TkPS) service is widely studied in spatial database, with various cache-based methods proposed to address its efficiency challenge in top- k result maintenance. These methods require in-depth exploration of relationships between cache updates and different factors (e.g., data distribution) to optimize cache performance. However, there is currently no system available that assists developers in conducting comprehensive cache analyses within TkPS services. We therefore introduce Catcher , a multi-functional cache analysis system designed for TkPS services. It not only enables users to intuitively analyze the entire maintenance process of top- k results but also aids in identifying bottlenecks and potential optimization spaces of caches. Catcher provides two user-friendly interfaces that allow users to employ simple and easy-to-use consoles to perform statistical analysis. Furthermore, Catcher offers the real-time evaluation of cache-based methods, providing users with instant analysis. We have demonstrated the usability of Catcher on real-world datasets. A short video of our demonstration can be found at https://youtu.be/qI81HoypB0w.

With the rapid development of wireless networks and smart devices, spatial crowdsourcing (SC) has become increasingly prevalent. The key issue in SC is efficiently assigning spatial tasks, such as parcel and food delivery, to mobile workers in order to maximize platform utility. Existing works mainly focus on task assignment based on real-time spatio-temporal constraints of workers and tasks, neglecting the influence of future spatio-temporal distributions of tasks on current assignments. In this paper, we propose a novel problem in SC calledPrediction-aware Task Assignment (PTA), where the platform adaptively assigns spatial tasks to workers by considering their current and future spatio-temporal constraints to maximize overall platform revenue. To address this problem, we introduce a two-stage framework composed of task prediction and task assignment. In the task prediction stage, we develop a powerfulBilateral Spatial-Temporal Graph Convolutional Network (BSTGCNet)to predict the time and location where potential tasks may appear in the future. In the task assignment stage, we present aDeep Reinforcement Learning (DRL)approach to dynamically partition tasks into batches based on the current and future status of tasks, and conduct bipartite graph matching for spatial tasks and workers in a batch-wise manner. Finally, extensive experiments on real-world datasets validate the effectiveness and efficiency of our proposed solution.

Multi-finger grasping relies on high quality training data, which is hard to obtain: human data is hard to transfer and synthetic data relies on simplifying assumptions that reduce grasp quality. By making grasp simulation differentiable, and contact dynamics amenable to gradient-based optimization, we accelerate the search for high-quality grasps with fewer limiting assumptions. We present Grasp'D-1M: a large-scale dataset for multi-finger robotic grasping, synthesized with Fast-Grasp'D, a novel differentiable grasping simulator. Grasp'D-1M contains one million training examples for three robotic hands (three, four and five-fingered), each with multimodal visual inputs (RGB+depth+segmentation, available in mono and stereo). Grasp synthesis with Fast-Grasp'D is 10x faster than GraspIt! [1] and 20x faster than the prior Grasp'D differentiable simulator [2]. Generated grasps are more stable and contact-rich than GraspIt! grasps, regardless of the distance threshold used for contact generation. We validate the usefulness of our dataset by retraining an existing vision-based grasping pipeline [3] on Grasp'D-1M, and showing a dramatic increase in model performance, predicting grasps with 30% more contact, a 33% higher epsilon metric, and 35% lower simulated displacement. Additional details at fast-graspd.github.io.

The wide adoption of GPS-enabled smart devices has greatly promoted spatial crowdsourcing, where the core issue is how to assign tasks to workers efficiently and with high quality. In this paper, we build a novel visual analysis system for spatial crowdsourcing, namely AMRAS, which can not only intuitively present the task allocation for workers under different time window scales to users (e.g., data analysts and managers) in real-time, but also help users analyze task assignment decision model and its learning process. AMRAS has the following novel features. First, AMRAS provides two user-friendly interfaces that allow users to employ simple and easy-to-use console to perform statistical analysis. Secondly, AMRAS provides three powerful visualization tools, such as the visualization of assignment results, assignment process, and assignment decision model, which not only allow users to intuitively analyze the whole process of task assignment, but also help users discover the computational bottleneck of their task assignment solution. Finally, AMRAS enables online access to real-time data, providing users with instant assignment and instant analysis. We have implemented and deployed AMRAS on Alibaba Cloud and demonstrated its usability and efficiency in real-world datasets. The demonstration video of AMRAS has been uploaded to Google Drive.