This week, researchers from USC Viterbi—including the Thomas Lord Department of Computer Science, the Information Sciences Institute, the Ming Hsieh Department of Electrical and Computer Engineering and the Department of Aerospace and Mechanical Engineering—are presenting their latest research at the 39th Annual AAAI Conference on Artificial Intelligence (AAAI-25) in Philadelphia, Pennsylvania, from February 25 to March 4, 2025.

AAAI is one of the largest academic conferences in the world that promotes research in artificial intelligence, fostering scientific exchange within researchers across AI and affiliated disciplines. 

From deploying AI-powered robots to address worker shortages in manufacturing, to detecting state-sponsored misinformation campaigns across social media platforms, the research explores how artificial intelligence can solve real-world challenges.

Accepted papers with USC affiliation (USC authors highlighted)

Main Technical Track

Counterfactual Online Learning for Open-Loop Monte-Carlo Planning

Authors: Thomy Phan, Shao-Hung Chan, Sven Koenig

Abstract: Monte-Carlo Tree Search (MCTS) is a popular approach to online planning under uncertainty. While MCTS uses statistical sampling via multi-armed bandits to avoid exhaustive search in complex domains, common closed-loop approaches typically construct enormous search trees to consider a large number of potential observations and actions. On the other hand, open-loop approaches offer better memory efficiency by ignoring observations but are generally not competitive with closed-loop MCTS in terms of performance – even with commonly integrated human knowledge. In this paper, we propose Counterfactual Open-loop Reasoning with Ad hoc Learning (CORAL) for open-loop MCTS, using a causal multi-armed bandit approach with unobserved confounders (MABUC). CORAL consists of two online learning phases that are conducted during the open-loop search. In the first phase, observational values are learned based on preferred actions. In the second phase, counterfactual values are learned with MABUCs to make a decision via an intent policy obtained from the observational values. We evaluate CORAL in four POMDP benchmark scenarios and compare it with closed-loop and open-loop alternatives. In contrast to standard open-loop MCTS, CORAL achieves competitive performance compared with closed-loop algorithms while constructing significantly smaller search trees.

Anytime Multi-Agent Path Finding with an Adaptive Delay-Based Heuristic

Authors: Thomy Phan, Benran Zhang, Shao-Hung Chan, Sven Koenig

Abstract: Anytime multi-agent path finding (MAPF) is a promising approach to scalable path optimization in multi-agent systems. MAPF-LNS, based on Large Neighborhood Search (LNS), is the current state-of-the-art approach where a fast initial solution is iteratively optimized by destroying and repairing selected paths of the solution. Current MAPF-LNS variants commonly use an adaptive selection mechanism to choose among multiple destroy heuristics. However, to determine promising destroy heuristics, MAPF-LNS requires a considerable amount of exploration time. As common destroy heuristics are non-adaptive, any performance bottleneck caused by these heuristics cannot be overcome via adaptive heuristic selection alone, thus limiting the overall effectiveness of MAPF-LNS in terms of solution cost. In this paper, we propose Adaptive Delay-based Destroy-and-Repair Enhanced with Success-based Self-Learning (ADDRESS) as a single-destroy-heuristic variant of MAPF-LNS. ADDRESS applies restricted Thompson Sampling to the top-K set of the most delayed agents to select a seed agent for adaptive LNS neighborhood generation. We evaluate ADDRESS in multiple maps from the MAPF benchmark set and demonstrate cost improvements by at least 50% in large-scale scenarios with up to a thousand agents, compared with the original MAPF-LNS and other state-of-the-art methods.

Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks

Authors: Shengbin Yue, Siyuan Wang, Wei Chen, Xuanjing Huang, Zhongyu Wei

Abstract: Recent advancements in Large Language Models (LLMs) have led to significant breakthroughs in various natural language processing tasks. However, generating factually consistent responses in knowledge-intensive scenarios remains a challenge due to issues such as hallucination, difficulty in acquiring long-tailed knowledge, and limited memory expansion. This paper introduces SMART, a novel multi-agent framework that leverages external knowledge to enhance the interpretability and factual consistency of LLM-generated responses. SMART comprises four specialized agents, each performing a specific sub-trajectory action to navigate complex knowledge-intensive tasks. We propose a multi-agent co-training paradigm, Long-Short Trajectory Learning, which ensures synergistic collaboration among agents while maintaining fine-grained execution by each agent. Extensive experiments on five knowledge-intensive tasks demonstrate SMART’s superior performance compared to widely adopted knowledge internalization and knowledge enhancement methods. Our framework can extend beyond knowledge-intensive tasks to more complex scenarios.

Our code is available at https://github.com/yueshengbin/SMART.

Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning

Authors: Rishabh Agrawal, Nathan Dahlin, Rahul Jain, Ashutosh Nayyar

Abstract: Imitation learning (IL) is notably effective for robotic tasks where directly programming behaviors or defining optimal control costs is challenging. In this work, we address a scenario where the imitator relies solely on observed behavior and cannot make environmental interactions during learning. It does not have additional supplementary datasets beyond the expert’s dataset nor any information about the transition dynamics. Unlike state-of-the-art (SOTA) IL methods, this approach tackles the limitations of conventional IL by operating in a more constrained and realistic setting. Our method uses the Markov balance equation and introduces a novel conditional density estimation-based imitation learning framework. It employs conditional normalizing flows for transition dynamics estimation and aims at satisfying a balance equation for the environment. Through a series of numerical experiments on Classic Control and MuJoCo environments, we demonstrate consistently superior empirical performance compared to many SOTA IL algorithms.

Revisiting CAD Model Generation by Learning Raster Sketch

Authors: Pu Li, Wenhao Zhang, Jianwei Guo, Jinglu Chen, Dong-Ming Yan

Abstract: The integration of deep generative networks into generating Computer-Aided Design (CAD) models has garnered increasing attention over recent years. Traditional methods often rely on discrete sequences of parametric line/curve segments to represent sketches. Differently, we introduce RECAD, a novel framework that generates Raster sketches and 3D Extrusions for CAD models. Representing sketches as raster images offers several advantages over discrete sequences: 1) it breaks the limitations on the types and numbers of lines/curves, providing enhanced geometric representation capabilities; 2) it enables interpolation within a continuous latent space; and 3) it allows for more intuitive user control over the output. Technically, RECAD employs two diffusion networks: the first network generates extrusion boxes conditioned on the number and types of extrusions, while the second network produces sketch images conditioned on these extrusion boxes. By combining these two networks, RECAD effectively generates sketch-and-extrude CAD models, offering a more robust and intuitive approach to CAD model generation. Experimental results indicate that RECAD achieves strong performance in unconditional generation, while also demonstrating effectiveness in conditional generation and output editing.

Bridge Program

(KEYNOTE) Integrating AI with OR for Responsible Decision-Making in Homeless Services Provision: Transparency, Robustness, and Fairness

Keynote speaker: Phebe Vayanos

Embodied AI for Smart Robotic Cells in Manufacturing Applications

Author: Satyandra K. Gupta

Abstract: Many manufacturing companies are facing an acute shortage of qualified workers. Deploying robotic cells is a potential solution to address this challenge. Historically robots have been deployed only in mass production applications in manufacturing. A large fraction of manufacturing is classified as high-mix manufacturing where a large variety of products are produced. Manually programming robots is not a viable solution in high-mix manufacturing applications. Robotic cells need to be powered by embodied AI to make them useful in high-mix manufacturing applications. This paper aims to build a bridge between smart manufacturing and AI communities to enable AI researchers to develop methods and tools that can be successfully deployed to realize smart robotic cells for high-mix manufacturing applications. This paper highlights key requirements for developing embodied AI for powering robotic cells for high-mix manufacturing applications. It also makes the case for approaches that combine model-based and data-driven methods to meet the needs of embodied AI in manufacturing applications and describes the role of generative AI approaches in smart manufacturing applications. Finally, it describes how AI can be used to enhance digital twins and augment human-machine interfaces in manufacturing applications.

Distributional MIPLIB: a Multi-Domain Library for Advancing ML-Guided MILP Methods

Authors: Weimin Huang, Taoan Huang, Aaron Ferber and Bistra Dilkina

AI For Social Impact

Aligning Time-series by Local Trends: Applications in Public Health

Author: Ajitesh Srivastava

Abstract: Individual models of infectious diseases or trajectories coming from different simulations may vary considerably, making it challenging for public communication and supporting policy-making. Therefore, it is common in public health to first create a consensus across multiple models and simulations through ensembling. However, current methods are limited to mean and median ensembles that perform aggregation of scale (cases, hospitalizations, deaths) along the time axis, which often misrepresents the underlying trajectories — e.g., they underrepresent the peak. Instead, we wish to create an ensemble that represents aggregation simultaneously over both time and scale and thus better preserves the properties of the trajectories. This is particularly useful for public health where time-series have a sequence of meaningful local trends that are ordered, e.g., a surge to an increase to a peak to a decrease. We propose a novel alignment method DTW+SBA, which combines a representation of local trends along with dynamic time warping barycenter averaging. We prove key properties of this method that ensure appropriate alignment based on local trends. We demonstrate on real multi-model outputs that our approach preserves the properties of underlying trajectories. We also show that our alignment leads to a more sensible clustering of epidemic trajectories.

IOHunter: Graph Foundation Model to Uncover Online Information Operations

Authors: Marco Minici, Luca Luceri, Francesco Fabbri, Emilio Ferrara

Abstract: Social media platforms have become vital spaces for public discourse, serving as modern agorás where a wide range of voices influence societal narratives. However, their open nature also makes them vulnerable to exploitation by malicious actors, including state-sponsored entities, who can conduct information operations (IOs) to manipulate public opinion. The spread of misinformation, false news, and misleading claims threatens democratic processes and societal cohesion, making it crucial to develop methods for the timely detection of inauthentic activity to protect the integrity of online discourse. In this work, we introduce a methodology designed to identify users orchestrating information operations, a.k.a. IO drivers, across various influence campaigns. Our framework, named IOHunter, leverages the combined strengths of Language Models and Graph Neural Networks to improve generalization in supervised, scarcely-supervised, and cross-IO contexts. Our approach achieves state-of-the-art performance across multiple sets of IOs originating from six countries, significantly surpassing existing approaches. This research marks a step toward developing Graph Foundation Models specifically tailored for the task of IO detection on social media platforms.

Dynamics-Based Feature Augmentation of Graph Neural Networks for Variant Emergence Prediction

Authors: Majd Al Aawar, Srikar Mutnuri, Mansooreh Montazerin, Ajitesh Srivastava

Abstract: During the COVID-19 pandemic, a major driver of new surges has been the emergence of new variants. When a new variant emerges in one or more countries, other nations monitor its spread in preparation for its potential arrival. The impact of the new variant and the timings of epidemic peaks in a country highly depend on when the variant arrives. The current methods for predicting the spread of new variants rely on statistical modeling, however, these methods work only when the new variant has already arrived in the region of interest and has a significant prevalence. Can we predict when a variant existing elsewhere will arrive in a given region? To address this question, we propose a variant-dynamics-informed Graph Neural Network (GNN) approach. First, we derive the dynamics of variant prevalence across pairs of regions (countries) that apply to a large class of epidemic models. The dynamics motivate the introduction of certain features in the GNN. We demonstrate that our proposed dynamics-informed GNN outperforms all the baselines, including the currently pervasive framework of Physics-Informed Neural Networks (PINNs). To advance research in this area, we introduce a benchmarking tool to assess a user defined model’s prediction performance across 87 countries and 36 variants.

New Faculty Highlights

Community-Aware Variational Autoencoder for Continuous Dynamic Networks

Authors: Junwei Cheng, Chaobo He, Pengxing Feng, Weixiong Liu, Kunlin Han, Yong Tang

Abstract: Variational autoencoder performs well in community detection on static networks, but it is difficult to directly extend to continuous dynamic networks. The main reason is that traditional methods mainly rely on adjacency structures to complete the inference and generation processes. However, continuous dynamic networks cannot be described by this structure because the inherent timeliness and causality information of the network would be lost. To address this issue, we propose a novel variational autoencoder, CT-VAE, for community detection in continuous dynamic networks, along with its scalable variant, CT-CAVAE. By conceptualizing node interactions as event streams and adopting the Hawkes process to capture temporal dynamics and causality, and incorporating them into the inference process, CT-VAE can effectively extend the traditional inference approach to continuous dynamic networks. Additionally, in the generation phase, CT-VAE combines pseudo-labeling and compact constraint strategies to facilitate the reconstruction process of non-adjacent structures. For the scalable variant, CT-CAVAE, end-to-end community detection is achieved by cleverly combining Gaussian mixture distribution. Extensive experimental results demonstrate that the proposed CT-VAE and CT-CAVAE achieve more favorable performance compared with the state-of-the-art baselines.

Efficient Robot Learning via Interaction with Humans

Author: Erdem Bıyık

Abstract: In many human-robot collaboration and multi-agent tasks, it is vital to model the partners and estimate their objectives to efficiently collaborate/interact with them. While learning from demonstrations is the most common approach for this, it is very data-hungry, which we cannot afford in many settings including robotics, and demonstrations are unreliable in a surprisingly large number of domains, including those we think humans perform reasonably well, e.g., driving. In this talk, I will start with introducing comparison-based feedback and explain why it does not suffer from most of the problems that demonstrations have, but is still data-hungry. To address this problem, I will propose comparative language based feedback and active learning techniques, which will result in (1) a new type of human feedback, and (2) an active querying algorithm that optimizes the information the AI agent will elicit from the human. I will conclude the talk by discussing what other types of human feedback exist, e.g., interventions or hand gestures, and how we can incorporate them into the existing learning algorithms.

Axioms for AI Alignment from Human Feedback

Authors: Luise Ge, Daniel Halpern, Evi Micha, Ariel D. Procaccia, Itai Shapira, Yevgeniy Vorobeychik, Junlin Wu

Abstract: In the context of reinforcement learning from human feedback (RLHF), the reward function is generally derived from maximum likelihood estimation of a random utility model based on pairwise comparisons made by humans. The problem of learning a reward function is one of preference aggregation that, we argue, largely falls within the scope of social choice theory. From this perspective, we can evaluate different aggregation methods via established axioms, examining whether these methods meet or fail well-known standards. We demonstrate that both the Bradley-Terry-Luce Model and its broad generalizations fail to meet basic axioms. In response, we develop novel rules for learning reward functions with strong axiomatic guarantees. A key innovation from the standpoint of social choice is that our problem has a linear structure, which greatly restricts the space of feasible rules and leads to a new paradigm that we call linear social choice.

Workshops

Risk and Response in Large Language Models: Evaluating Key Threat Categories

Authors: Bahareh Harandizade, Abel Salinas and Fred Morstatter

Abstract: This paper explores the pressing issue of risk assessment in Large Language Models (LLMs) as they become increasingly prevalent in various applications. Focusing on how reward models, which are designed to fine-tune pretrained LLMs to align with human values, perceive and categorize different types of risks, we delve into the challenges posed by the subjective nature of preference-based training data. By utilizing the Anthropic Red-team dataset, we analyze major risk categories, including Information Hazards, Malicious Uses, and Discrimination/Hateful content. Our findings indicate that LLMs tend to consider Information Hazards less harmful, a finding confirmed by a specially developed regression model. Additionally, our analysis shows that LLMs respond less stringently to Information Hazards compared to other risks. The study further reveals a significant vulnerability of LLMs to jailbreaking attacks in Information Hazard scenarios, highlighting a critical security concern in LLM risk assessment and emphasizing the need for improved AI safety measures.

Knowledge Graph Analysis of Legal Understanding and Violations in LLMs

Authors: Abel Salinas and Fred Morstatter

Risk and Response in Large Language Models: Evaluating Key Threat Categories

Authors: Elan Markowitz, Anil Ramakrishna, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, Aram Galstyan

Mixed-feature logistic regression robust to distribution shifts

Authors: Qingshi Sun, Nathan Justin, Andres Gomez, Phebe Vayanos

Logistic regression models are widely used in the social and behavioral sciences and in high-stakes domains, due to their simplicity and interpretability properties. At the same time, such domains are permeated by distribution shifts, where the distribution generating the data changes between training and deployment. In this paper, we study a distributionally robust logistic regression problem that seeks the model that will perform best against adversarial realizations of the data distribution drawn from a suitably constructed Wasserstein ambiguity set. Our model and solution approach differ from prior work in that we can capture settings where the likelihood of distribution shifts can vary across features, significantly broadening the applicability of our model relative to the state-of-the-art. We propose a graph-based solution approach that can be integrated into off-the-shelf optimization solvers. We evaluate the performance of our model and algorithms on numerous publicly available datasets. Our solution achieves a 38x speed-up relative to the state-of-the-art. Additionally, compared to the state-of-the-art, our model reduces average calibration error by up to 36.19% and worst-case calibration error by up to 41.70%, while increasing the average area under the ROC curve (AUC) by up to 23.06% and worst-case AUC by up to 33.42%.

Published on February 26th, 2025

Last updated on February 28th, 2025