United States

We describe the development of a one-credit course to promote AI literacy at the University of Texas at Austin. In response to a call for the rapid deployment of class that would serve a broad audience in Fall of 2023, we designed a 14-week seminar-style course that incorporated an interdisciplinary group of speakers who lectured on topics ranging from the fundamentals of AI to societal concerns including disinformation and employment. University students, faculty, and staff, and even community members outside of the University were invited to enroll in this online offering: The Essentials of AI for Life and Society. We collected feedback from course participants through weekly reflections and a final survey. Satisfyingly, we found that attendees reported gains in their AI literacy. We sought critical feedback through quantitative and qualitative analysis, which uncovered challenges in designing a course for this general audience. We utilized the course feedback to design a three-credit version of the course that is being offered in Fall of 2024. The lessons we learned and our plans for this new iteration may serve as a guide to instructors designing AI courses for a broad audience.

AAAI 2025

The Essentials of AI for Life and Society: An AI Literacy Course for the University Community

technical paper

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

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-25 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.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

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-25 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.



Model counting is task of counting the number of satisfying assignments of a Boolean formula. Since counting is intractable in general, most applications use $(\varepsilon, \delta)$-approximations, where the output is within a $(1+\varepsilon)$-factor of the count with  probability at least $1-\delta$. 
Many demanding applications make thousands of counting queries, and the state-of-the-art approximate counter, ApproxMC, makes hundreds of calls to SAT solvers to answer a single approximate counting query.
The sheer number of SAT calls, poses a significant challenge to the existing approaches. 

In this work, we propose an approximation scheme, RealMC, that is tailored to such demanding applications with low time limits. Compared to ApproxMC, RealMC makes 14$\times$ fewer SAT calls while providing the same guarantees as ApproxMC in the constant-factor regime. In an evaluation over 2,247 instances, RealMC solved 271 more and achieved a $2\times$ speedup against ApproxMC.

Towards Real-Time Approximate Counting

Image-guided object assembly represents a burgeoning research topic in computer vision. This paper introduces a novel task: translating multi-view images of a structural 3D model (for example, one constructed with building blocks drawn from a 3D-object library) into a detailed sequence of assembly instructions executable by a robotic arm. Fed with multi-view images of the target 3D model for replication, the model designed for this task must address several sub-tasks, including recognizing individual components used in constructing the 3D model, estimating the geometric pose of each component, and deducing a feasible assembly order adhering to physical rules. Establishing accurate 2D-3D correspondence between multi-view images and 3D objects is technically challenging. To tackle this, we propose an end-to-end model known as the Neural Assembler. This model learns an object graph where each vertex represents recognized components from the images, and the edges specify the topology of the 3D model, enabling the derivation of an assembly plan. We establish benchmarks for this task and conduct comprehensive empirical evaluations of Neural Assembler and alternative solutions. Our experiments clearly demonstrate the superiority of Neural Assembler.

Neural Assembler: Learning to Generate Fine-Grained Robotic Assembly Instructions from Multi-View Images

Due to the communication bottleneck in distributed and decentralized federated learning applications, algorithms using compressed communication have attracted significant attention. The Error Feedback (EF) is a widely-studied compression framework for convergence with biased compressors such as top-$k$ sparsification. Although various improvements have been obtained in recent years, the theoretical guarantee for EF-type framework is still limited. Previous works either 1) rely on strong assumptions such as bounded gradient/dissimilarity assumptions, thus can not deal with arbitrary data heterogeneity and also slow the convergence speed, or 2) can not enjoy linear speedup in the number of clients. In this work, we propose a new EFSkip framework which removes the strong assumptions to allow arbitrary data heterogeneity and enjoys linear speedup for significantly improving upon previous results. In particular, EFSkip achieves the complexity result $O(\frac{\sigma^2}{n\epsilon^4} + \frac{1}{\epsilon^2})$ while previous EF21 only obtains $O(\frac{\sigma^2}{\delta^3\epsilon^4} + \frac{1}{\delta\epsilon^2})$, i.e., EFSkip enjoys the linear speedup in the number of clients $n$ (reducing the result linearly using more clients) and also removes the compression factor $\delta$ (matching the result without compression). We also show that EFSkip enjoys linear speedup and achieves faster convergence for nonconvex problems satisfying Polyak-Lojasiewicz (PL) condition. Finally, the deep learning experiments validate the theoretical results and confirm the practical superiority of EFSkip. We believe that the new EFSkip framework will have a large impact on the communication- and computation-efficient distributed and decentralized federated learning.

EFSkip: A New Error Feedback with Linear Speedup for Compressed Federated Learning with Arbitrary Data Heterogeneity

Dynamic graphs exhibit the intricate and intertwined spatio-temporal evolutionary patterns, widely existing in real-world scenarios. Nevertheless, the structure incompleteness, noise, and redundancy result in poor robustness for the prevailing Dynamic Graph Neural Networks (DGNNs). Dynamic Graph Structure Learning (DGSL) offers promising insight into optimizing graph structures. However, aside from encountering unacceptable quadratic complexity, it overly relies on the heuristic priors, making it difficult to discover underlying predictive patterns. How to efficiently refine dynamic structures, capture intrinsic dependencies, and learn robust representations for downstream tasks is still under-explored. In this work, we propose the **REDGSL**, an **E**fficient **D**ynamic **G**raph **S**tructure **L**earning framework for **R**obust graph representations. To accelerate the spatio-temporal structure learning, we propose a kernelized dynamic message-passing operator that reduces the quadratic time complexity to linear. To capture global intrinsic dynamics, we establish the dynamic graph as a self-contained system with State Space Model. By discretizing the system states with the cross-snapshot graph adjacency, we enable the long-distance dependencies capturing with the selective snapshot scan. To endow learned dynamic structures more expressive with informativeness, we propose the self-supervised Principle of Relevant Information for DGSL to regularize the most relevant yet least redundant information, enhancing global robustness. Extensive experiments demonstrate the superiority of the efficiency and robustness of our REDGSL compared with the state-of-the-art baselines against adversarial attacks.

DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models

The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied robots. Although reinforcement learning methods can largely ease human effort, designing reward functions for real-world tasks, especially high-dimensional robotic control, is challenging due to complex relationships among joints and tasks. Recent advancements in the aid of large language models (LLMs) enable automatic reward function design. However, current approaches evaluate reward functions by re-training policies from scratch placing an undue burden on the reward function, expecting it to be effective at every stage of the policy improvement process, from initiation to convergence. We argue for a more practical strategy in robotic autonomy, focusing on refining existing policies with policy-dependent reward functions rather than seeking a universal reward function. To this end, we propose a novel reward-policy co-evolution framework where the reward function and the learned policy benefit from each other's progressive on-the-fly improvements, resulting in more efficient and higher-performing skill acquisition. 
Specifically, the reward evolution process translates the robot's previous best reward function, descriptions of tasks and environment into text inputs. These inputs are used to query LLMs to generate a dynamic amount of reward function candidates, ensuring continuous improvement through each evolutionary round. For policy evolution, our method generates new policy populations by hybridizing historically optimal and random policies. Through an improved Bayesian optimization, our approach efficiently and robustly identifies the most capable and plastic reward-policy combination, which then proceeds to the next round of co-evolution.
Despite using less data, our approach demonstrates an average normalized improvement of $95.3$\% across various high-dimensional robotic skill learning tasks.

Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution

In recent years, with the advancements in brain science, spiking neural networks (SNNs) have garnered significant attention. SNNs can generate spikes that mimic the function of neurons transmission in humans brain, thereby significantly reducing computational costs by the event-driven nature during training. While deep SNNs have shown impressive performance on classification tasks, they still face challenges in more complex tasks such as object detection. In this paper, we propose SpikingYOLOX, extending the structure of the original YOLOX by introducing signed spiking neurons and fast Fourier convolution (FFC). The designed ternary signed spiking neurons could generate three kinds of spikes to obtain more robust features in the deep layer of the backbone. Meanwhile, we integrate FFC with SNN modules to enhance object detection performance, because its global receptive field is beneficial to the object detection task. Extensive experiments demonstrate that the proposed SpikingYOLOX achieves state-of-the-art performance among other SNN-based object detection methods.

SpikingYOLOX: Improved YOLOX Object Detection with Fast Fourier Convolution and Spiking Neural Networks

Recent works have explored the use of counting queries coupled with Description Logic ontologies.
The answer of such a query in a particular model of a knowledge base is either an integer or $\infty$, and its spectrum is the set of its answers over all models.
While it is unclear how to compute and manipulate such a set in general, we identify a class of counting queries whose spectra can be effectively represented.
Further focusing on atomic counting queries, we pinpoint the possible shapes of a spectrum when the ontology is formulated in $ALCIF$: they are essentially the subsets of $\mathbb{N} \cup \{ \infty\}$ closed under addition.
For most sublogics of $ALCIF$, we show that possible spectra enjoy simpler shapes, being $[ m, \infty]$ or variations thereof.
To obtain our results, we refine constructions used for finite model reasoning in those DLs and notably rely on a cycle-reversion technique for the Horn fragment of $ALCIF$.
We also study the data complexity of computing the proposed effective representation and establish the $FP^{NP[log]}$-completeness of this task under several settings.

Spectra of Cardinality Queries over Description Logic Knowledge Bases

LiDAR-based 3D object detection is crucial for autonomous driving. However, due to the quality deterioration of LiDAR point clouds, it suffers from performance degradation in adverse weather conditions. Fusing LiDAR with the weather-robust 4D radar sensor is expected to solve this problem; however, it faces challenges of significant differences in terms of data quality and the degree of degradation in adverse weather. To address these issues, we introduce L4DR, a weather-robust 3D object detection method that effectively achieves LiDAR and 4D Radar fusion. Our L4DR proposes Multi-Modal Encoding (MME) and Foreground-Aware Denoising (FAD) modules to reconcile sensor gaps, which is the first exploration of the complementarity of early fusion between LiDAR and 4D radar. Additionally, we design an Inter-Modal and IntraModal ({IM} 2 ) parallel feature extraction backbone coupled with a Multi-Scale Gated Fusion (MSGF) module to counteract the varying degrees of sensor degradation under adverse weather conditions. Experimental evaluation on a VoD dataset with simulated fog proves that L4DR is more adaptable to changing weather conditions. It delivers a significant performance increase under different fog levels, improving the 3D mAP by up to 20.0% over the traditional LiDAR-only approach. Moreover, the results on the K-Radar dataset validate the consistent performance improvement of L4DR in real-world adverse weather conditions.

L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection

Diffusion-based models have been recently shown to be high-quality data generators. However, its performance severely degrades when training on non-stationary changing data distributions in an online manner, which is because of catastrophic forgetting. In this paper, we propose to enable the diffusion model with a novel Dynamic Expansion Memory Unit (DEMU) approach that adaptively creates new memory buffers to preserve the information deemed critical for the training of the model. Having a selective memory buffering unit is essential for training diffusion networks, which are expensive to train, especially when deployed in resource constrained environments. A Maximum Mean Discrepancy (MMD) based expansion mechanism, that evaluates probabilistic distances between each previously defined memory buffers and the newly given data, as an expansion signal, is employed for ensuring the learning of a diversity of information. A novel memory compaction approach is proposed to automatically remove statistically overlapping memory units through a graph relationship evaluation, is employed for preventing the limitless expansion of DEMU. In addition, we propose a new model expansion mechanism to automatically add new diffusion models as experts in a mixture system, which enhances the multi-domain image generation performance. Comprehensive results show that the proposed approach performs better than the state-of-the-art.

Lifelong Scalable Generative System via Online Maximum Mean Discrepancy

Responsible AI (RAI) is the science and practice of ensuring the design, development, use, and oversight of AI are socially sustainable---benefiting diverse stakeholders while controlling the risks. Achieving this goal requires active engagement and participation from the broader public. This paper introduces "We are AI: Taking Control of Technology," a public education course that brings the topics of AI and RAI to the general audience in a peer-learning setting. 

We outline the goals behind the course's development, discuss the multi-year iterative process that shaped its creation, and summarize its content. We also discuss two offerings of "We are AI" to an active and engaged group of librarians and professional staff at New York University, highlighting successes and areas for improvement. The course materials, including a multilingual comic book series by the same name, are publicly available and can be used independently. By sharing our experience in creating and teaching "We are AI", we aim to introduce these resources to the community of AI educators, researchers, and practitioners, supporting their public education efforts.

Premium content

Next from AAAI 2025

Towards Real-Time Approximate Counting

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES