Li Pan

Xinjie Shen, Mufei Li, Pan Li · gatech

The deployment of Large Language Models (LLMs) in embodied agents creates an urgent need to measure their privacy awareness in the physical world. Existing evaluation methods, however, are confined to natural language based scenarios. To bridge this gap, we introduce EAPrivacy, a comprehensive evaluation benchmark designed to quantify the physical-world privacy awareness of LLM-powered agents. EAPrivacy utilizes procedurally generated scenarios across four tiers to test an agent's ability to handle sensitive objects, adapt to changing environments, balance task execution with privacy constraints, and resolve conflicts with social norms. Our measurements reveal a critical deficit in current models. The top-performing model, Gemini 2.5 Pro, achieved only 59\% accuracy in scenarios involving changing physical environments. Furthermore, when a task was accompanied by a privacy request, models prioritized completion over the constraint in up to 86\% of cases. In high-stakes situations pitting privacy against critical social norms, leading models like GPT-4o and Claude-3.5-haiku disregarded the social norm over 15\% of the time. These findings, demonstrated by our benchmark, underscore a fundamental misalignment in LLMs regarding physically grounded privacy and establish the need for more robust, physically-aware alignment. Codes and datasets will be available at https://github.com/Graph-COM/EAPrivacy.

Yinan Huang, Siqi Miao, Pan Li

Machine learning on graphs has recently found extensive applications across domains. However, the commonly used Message Passing Neural Networks (MPNNs) suffer from limited expressive power and struggle to capture long-range dependencies. Graph transformers offer a strong alternative due to their global attention mechanism, but they come with great computational overheads, especially for large graphs. In recent years, State Space Models (SSMs) have emerged as a compelling approach to replace full attention in transformers to model sequential data. It blends the strengths of RNNs and CNNs, offering a) efficient computation, b) the ability to capture long-range dependencies, and c) good generalization across sequences of various lengths. However, extending SSMs to graph-structured data presents unique challenges due to the lack of canonical node ordering in graphs. In this work, we propose Graph State Space Convolution (GSSC) as a principled extension of SSMs to graph-structured data. By leveraging global permutation-equivariant set aggregation and factorizable graph kernels that rely on relative node distances as the convolution kernels, GSSC preserves all three advantages of SSMs. We demonstrate the provably stronger expressiveness of GSSC than MPNNs in counting graph substructures and show its effectiveness across 11 real-world, widely used benchmark datasets. GSSC achieves the best results on 6 out of 11 datasets with all significant improvements compared to the state-of-the-art baselines and second-best results on the other 5 datasets. Our findings highlight the potential of GSSC as a powerful and scalable model for graph machine learning. Our code is available at https://github.com/Graph-COM/GSSC.

Mufei Li, Viraj Shitole, Eli Chien et al. · gatech

Directed acyclic graphs (DAGs) serve as crucial data representations in domains such as hardware synthesis and compiler/program optimization for computing systems. DAG generative models facilitate the creation of synthetic DAGs, which can be used for benchmarking computing systems while preserving intellectual property. However, generating realistic DAGs is challenging due to their inherent directional and logical dependencies. This paper introduces LayerDAG, an autoregressive diffusion model, to address these challenges. LayerDAG decouples the strong node dependencies into manageable units that can be processed sequentially. By interpreting the partial order of nodes as a sequence of bipartite graphs, LayerDAG leverages autoregressive generation to model directional dependencies and employs diffusion models to capture logical dependencies within each bipartite graph. Comparative analyses demonstrate that LayerDAG outperforms existing DAG generative models in both expressiveness and generalization, particularly for generating large-scale DAGs with up to 400 nodes-a critical scenario for system benchmarking. Extensive experiments on both synthetic and real-world flow graphs from various computing platforms show that LayerDAG generates valid DAGs with superior statistical properties and benchmarking performance. The synthetic DAGs generated by LayerDAG enhance the training of ML-based surrogate models, resulting in improved accuracy in predicting performance metrics of real-world DAGs across diverse computing platforms.

Mufei Li, Dongqi Fu, Limei Wang et al. · gatech

Modern long-context large language models (LLMs) perform well on synthetic "needle-in-a-haystack" (NIAH) benchmarks, but such tests overlook how noisy contexts arise from biased retrieval and agentic workflows. We argue that haystack engineering is necessary to construct noisy long contexts that faithfully capture key real-world factors -- distraction from heterogeneous biased retrievers and cascading errors in agentic workflows -- to test models' long-context robustness. We instantiate it through HaystackCraft, a new NIAH benchmark built on the full English Wikipedia hyperlink network with multi-hop questions. HaystackCraft evaluates how heterogeneous retrieval strategies (e.g., sparse, dense, hybrid, and graph-based) affect distractor composition, haystack ordering, and downstream LLM performance. HaystackCraft further extends NIAH to dynamic, LLM-dependent settings that simulate agentic operations, where models refine queries, reflect on their past reasonings, and decide when to stop. Experiments with 15 long-context models show that (1) while stronger dense retrievers can introduce more challenging distractors, graph-based reranking simultaneously improves retrieval effectiveness and mitigates more harmful distractors; (2) in agentic tests, even advanced models like Gemini 2.5 Pro and GPT-5 suffer cascading failures from self-generated distractors or struggle to perform early stops. These results highlight persistent challenges in agentic long-context reasoning and establish HaystackCraft as a valuable testbed for future progress.

Pan Li, Alexander Tuzhilin

Cross domain recommender systems have been increasingly valuable for helping consumers identify useful items in different applications. However, existing cross-domain models typically require large number of overlap users, which can be difficult to obtain in some applications. In addition, they did not consider the duality structure of cross-domain recommendation tasks, thus failing to take into account bidirectional latent relations between users and items and achieve optimal recommendation performance. To address these issues, in this paper we propose a novel cross-domain recommendation model based on dual learning that transfers information between two related domains in an iterative manner until the learning process stabilizes. We develop a novel latent orthogonal mapping to extract user preferences over multiple domains while preserving relations between users across different latent spaces. Furthermore, we combine the dual learning method with the metric learning approach, which allows us to significantly reduce the required common user overlap across the two domains and leads to even better cross-domain recommendation performance. We test the proposed model on two large-scale industrial datasets and six domain pairs, demonstrating that it consistently and significantly outperforms all the state-of-the-art baselines. We also show that the proposed model works well with very few overlap users to obtain satisfying recommendation performance comparable to the state-of-the-art baselines that use many overlap users.