Singapore

Electric bicycles (e-bikes) have become the dominant mode of transportation in China’s urban instant delivery industry. However, many riders lack the experience to navigate complex traffic networks and diverse road conditions, leading to reduced delivery efficiency. To address this issue, we present Talking Trails, an e-bike delivery route planning system built upon an LLM-enhanced spatiotemporal trajectory model. Trained on millions of real-world delivery trajectories, fused with spatiotemporal and semantic data information, the model achieves a top-5 rider displacement prediction accuracy of 95\% and a route optimization rate of 82.1\%. In practice, we augment the core planner with an LLM-driven semantic layer that translates high-level user intent into executable tasks, then pair it with a battery-swap module that continuously validates route feasibility so the vehicle never runs out of charge mid-mission. Currently serving tens of thousands of riders, the system is projected to reduce average delivery mileage by 17\% and lower annual carbon emissions by 3978 tons. Overall, Talking Trails significantly improves delivery efficiency, offering a scalable and sustainable solution for instant delivery operations.

AAAI 2026

Talking Trails: LLM-Enhanced Spatiotemporal Trajectory Modeling for E-Bike Delivery Route Planning

e-bike route planning

semantic-enhanced modeling

spatiotemporal trajectory model

instant delivery

 **RTSS 2021** has successfully concluded. Hope you have enjoyed it, and look forward to seeing you next year in person.
    Announcement for the Awards:
 * Best Paper Award goes to: Monte Carlo Response-Time Analysis, Sergey Bozhko, Georg von der Brüggen, and Björn Brandenburg
 * Best Student Paper Award goes to: Automatic Energy-Hotspot Detection and Elimination in Real-Time Deeply Embedded Systems, Mohsen Shekarisaz, Lothar Thiele, and Mehdi Kargahi.
 * Best Solution Award for Industry Session goes to: Toward Real-Time Guaranteed Scheduling for Autonomous Driving Systems. Jinghao Sun, Tianyi Wang, Kailu Duan, Bin Lu, Jiankang Ren, Zhishan Guo, and Guozhen Tan.



IEEE RTSS 2021

The IEEE Real-Time Systems Symposium (RTSS) is the premier conference in the field of real-time systems, and is a venue for researchers and practitioners to showcase innovations covering all aspects of real-time systems, including theory, design, analysis, implementation, evaluation, and experience. 

technical paper

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.<br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

Phase transitions in condensed matter systems traditionally require prior knowledge of order parameters for identification. We present Prometheus, a variational autoencoder framework for unsupervised discovery of phase transitions and order parameters in the two-dimensional Ising model without prior physical knowledge. Our approach combines convolutional neural networks with beta-variational autoencoders to learn compressed representations that naturally separate ordered and disordered phases. Experimental validation demonstrates automatic discovery of the order parameter with 0.85 correlation to theoretical magnetization and critical temperature detection within 0.27% of the theoretical value, achieving 89% improvement over principal component analysis while requiring no supervision.

Prometheus: Unsupervised Discovery of Phase Transitions and Order Parameters in the 2D Ising Model Using Variational Autoencoders (Student Abstract)

Transformer models have achieved remarkable success across diverse deep learning fields, including natural language processing (NLP) and computer vision (CV). One drawback of these models is that the computational cost of the softmax attention, the core component of the transformer, exhibits quadratic complexity in both time and memory. As data scales up various attempts have been reported to overcome this bottleneck. The objective of this study is to propose a novel attention mechanism, “Cumulant Attention,” that systematically balances efficiency and accuracy. This proposal introduces a statistical-mechanics perspective and a reliable approximation based on cumulant expansion into the attention layer. The low-order variant reduces computational complexity to linear order, similar to the linear attention, while keeping nonlinearity of the softmax attention. We evaluate several variants on CV tasks, including image classification with ViT on ImageNet-100 and video classification with ViViT on UCF-101. Experimental results demonstrate that the cumulant attention outperforms the linear attention and achieves accuracy comparable to the softmax attention. These findings validate the effectiveness of our approach and highlight future directions, including scaling to larger models, extending to other modalities, and optimizing implementations for GPU hardware.

Cumulant Attention in Vision Transformers (Student Abstract)

We propose Tailored ViT Slimming (TVS), a budget-aware multi-dimensional pruning framework for Vision Transformers. TVS injects learnable masks into MHSA and MLP modules and applies adaptive non-convex sparsity regularization to achieve maximal utilization of parameters under strict module-wise budgets. In addition, by retaining scaled masks after pruning, TVS avoids abrupt accuracy drops and provides stable initialization for fine-tuning. On ImageNet-1k with DeiT-S and DeiT-B, TVS consistently outperforms prior ViT compression methods. This result empirically shows that the non-convex sparsity regularizer is effective not only in CNNs but also in ViTs.

Tailored ViT Slimming: Budget-Aware Multi-Dimensional Sparsity Regularization for Vision Transformers Pruning (Student Abstract)

Deep learning approaches to object detection have achieved reliable detection of specific object classes in images. However, extending a model’s detection capability to new object classes requires large amounts of annotated training data, which is costly and time-consuming to acquire, especially for long-tailed classes with insufficient representation in existing datasets. We compare four different methods of generating synthetic data to finetune object detection models on novel object categories, particularly when limited data is available in the form of object-centric data (multi-view images or 3D models). Our approaches are based on simple image processing techniques, 3D rendering, and image generation models, each varying in complexity and image realism. We assess the ability of models finetuned using synthetic data to generalize to novel object classes in real-world data, and we achieve significant performance boosts in our data-constrained experimental setting.

Object-Centric Data Synthesis for Category-level Object Detection (Student Abstract)

Word Sense Disambiguation (WSD) has been a central challenge since the earliest proposals for Machine Translation (MT), most famously Weaver's 1949 memorandum. Classical systems treated WSD as an explicit task, grounded in lexical resources and annotated data. Recently, however, Large Language Models (LLMs) have blurred the boundary between disambiguation and general language understanding, leading some to suggest that WSD might be obsolete. This paper surveys the role of WSD in the LLM era, drawing on recent studies of encoder-based sense separation and disambiguation, and decoder-based definition selection and generation, as well as multilingual evaluation. Closed-source instruction-tuned LLMs now achieve performance comparable to specialized WSD systems, yet systematic weaknesses remain: non-predominant senses are often misclassified and disambiguation biases in MT persist. We argue that WSD is not "dead" but redefined as a diagnostic lens for assessing lexical-semantic competence, robustness, and interpretability in LLMs.

Is Word Sense Disambiguation Dead in the LLM Era?

Continuous cardiac monitoring during sleep is vital for detecting silent arrhythmia and other nocturnal cardiac events. While electrocardiogram (ECG) is the clinical gold standard, its reliance on electrodes and physical contact makes it intrusive for daily long-term use. Millimeter-wave (mmWave) radar offers a compelling non-contact alternative by capturing cardiac-induced chest-wall micro-vibrations. Existing radar-to-ECG methods often rely on direct waveform regression, assuming posture-stable mappings that break under natural sleep movements and obscure true cardiac rhythms. Inspired by the modality-invariant perception observed in speech and vision, we introduce mmJEPA-ECG, a physiology-guided framework for reconstructing clinical ECGs by anchoring radar sensing to invariant cardiac dynamics. It addresses two fundamental challenges: (i) disentangling robust cardiac representations from posture-induced artifacts, and (ii) generalizing ECG reconstruction across individuals under signal ambiguity. To address these challenges, Physiology-Oriented Self-Supervised Pretraining builds on a Joint Embedding Predictive Architecture (JEPA) with domain-informed masking and heart rate consistency to extract posture-robust cardiac embeddings. Conditional Diffusion-based ECG Reconstruction then generates personalized ECG waveforms through a hierarchical conditional diffusion process by spectral fidelity and denoising constraints. Extensive experiments on both public and self-collected multi-subject datasets demonstrate that our method outperforms state-of-the-art across waveform and rhythm metrics, halving R-R peak errors even under posture shifts and arrhythmic conditions. Codes and dataset are released at https://github.com/lanyangyang/mmJEPA-ECG.

mmJEPA-ECG: Cross-Posture Robust Contactless Electrocardiogram Monitoring via Millimeter Wave Radar Sensing

Distributed multi-stage image compression—where visual content traverses multiple processing nodes under varying quality requirements—poses challenges. Progressive methods enable bitstream truncation but underutilize available compute resources; successive compression repeats costly pixel-domain operations and suffers cumulative quality loss and inefficiency; fixed-parameter models lack post-encoding flexibility. In this work, we developed the Hierarchical Cascade Framework (HCF) that achieves high rate-distortion performance and better computational efficiency through direct latent-space transformations across network nodes in distributed multi-stage image compression system. Under HCF, we introduced policy-driven quantization control to optimize rate–distortion trade-offs, and established the edge quantization principle through differential entropy analysis. The configuration based on this principle demonstrates up to 0.6dB PSNR gains over other configurations. When comprehensively evaluated on the Kodak, CLIC, and CLIC2020-mobile datasets, HCF outperforms successive-compression methods by up to 5.56% BD-Rate in PSNR on CLIC, while saving up to 97.8% FLOPs, 96.5% GPU memory, and 90.0% execution time. It also outperforms state-of-the-art progressive compression methods by up to 12.64% BD-Rate on Kodak and enables retraining-free cross-quality adaptation with 7.13-10.87% BD-Rate reductions on CLIC2020-mobile.

HCF: Hierarchical Cascade Framework for Distributed Multi-Stage Image Compression

Recent advances have focused on training high-performance spiking neural networks (SNNs) by leveraging surrogate gradient (SG) learning to estimate the derivatives of non-differentiable spiking activity. However, the distribution of neuronal membrane potentials varies across timesteps and progressively deviates toward both sides of the firing threshold during training. When threshold and SG remain fixed, this may lead to imbalanced spike firing rates and diminished gradient signals, which prevent SNNs from performing well. To address these issues, we propose a novel dual-stage synergistic learning algorithm that achieves forward adaptive thresholding and backward dynamic SG. In forward propagation, we adaptively adjust thresholds based on the distribution of membrane potential dynamics (MPD) at each timestep, which enriches neuronal diversity and effectively balances firing rates across layers. In backward propagation, drawing from the association between MPD and SG, we dynamically optimize the SG driven by thresholds to enhance gradient estimation through spatio-temporal alignment, effectively mitigating gradient information loss. Experimental results demonstrate that our method achieves significant performance improvements. Moreover, it allows neurons to fire stable proportions of spikes at each timestep and increases the proportion of neurons that obtain gradients in deeper layers. Code is available at Supplementary Materials.

DS-ATGO: Dual-Stage Synergistic Learning via Forward Adaptive Threshold and Backward Gradient Optimization for Spiking Neural Networks

Alignment is crucial for text-to-image (T2I) models to ensure that the generated images faithfully capture user intent while maintaining safety and fairness. Direct Preference Optimization (DPO) has emerged as a key alignment technique for large language models (LLMs), and its influence is now extending to T2I systems. This paper introduces **DPO-Kernels** for T2I models, a novel extension of DPO that enhances alignment across three key dimensions: *(i) Hybrid Loss*, which integrates embedding-based objectives with the traditional probability-based loss to improve optimization; *(ii) Kernelized Representations*, leveraging Radial Basis Function (RBF), Polynomial, and Wavelet kernels to enable richer feature transformations, ensuring better separation between safe and unsafe inputs; and *(iii) Divergence Selection*, expanding beyond DPO’s default Kullback–Leibler (KL) regularizer by incorporating alternative divergence measures such as Wasserstein and Rényi divergences to enhance stability and robustness in alignment training. We introduce **DETONATE**, the first large-scale benchmark of its kind, comprising approximately 100K curated image pairs, categorized as chosen and rejected. This benchmark encapsulates three critical axes of social bias and discrimination: *Race*, *Gender*, and *Disability*. The prompts are sourced from the hate speech datasets, while the images are generated using state-of-the-art T2I models, including Stable Diffusion 3.5 Large (SD-3.5), Stable Diffusion XL (SD-XL), and Midjourney. Furthermore, to evaluate alignment beyond surface metrics, we introduce the **Alignment Quality Index (AQI)**: a novel geometric measure that quantifies latent space separability of safe/unsafe image activations, revealing hidden model vulnerabilities. While alignment techniques often risk overfitting, we empirically demonstrate that DPO-Kernels preserve strong generalization bounds using the theory of Heavy-Tailed Self-Regularization (HT-SR). To foster further research, we publicly release DETONATE along with the complete codebase for DPO-Kernels.

DETONATE – A Benchmark for Text-to-Image Alignment and Kernelized Direct Preference Optimization

Artificial neural networks are popular for computer vision as they often give state-of-the-art
performance, but are difficult to interpret because of their complexity. This black box modeling is especially troubling when the application concerns human well-being such as in medical image analysis or autonomous driving. In this work, we propose a technique called routing path visualization for capsule networks, which reveals how much of each region in an image is routed to each capsule. In turn, this technique can be used to interpret the entity that a given capsule detects, and speculate how the network makes a prediction. We demonstrate our new visualization technique on several real world datasets. Experimental results suggest that routing path visualization can precisely localize the predicted class from an image, even though the capsule networks are trained using just images and their respective class labels, without additional information defining the location of the class in the image.

Downloads

Next from AAAI 2026

Prometheus: Unsupervised Discovery of Phase Transitions and Order Parameters in the 2D Ising Model Using Variational Autoencoders (Student Abstract)

Similar lecture

Concurrent Order Dispatch for Instant Delivery with Time-Constrained Actor-Critic Reinforcement Learning