Brian Lu

Brian Lu, Hongyu Zhao, Shuo Sun et al.

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for post-training large language models (LLMs) on complex reasoning tasks. Yet, the conditions under which RLVR yields robust generalization remain poorly understood. This paper provides an empirical study of RLVR generalization in the setting of probabilistic inference over causal graphical models. This setting offers two natural axes along which to examine generalization: (i) the level of the probabilistic query -- associational, interventional, or counterfactual -- and (ii) the structural complexity of the query, measured by the size of its relevant subgraph. We construct datasets of causal graphs and queries spanning these difficulty axes and fine-tune Qwen-2.5-Instruct models using RLVR or supervised fine-tuning (SFT). We vary both the model scale (3B-32B) and the query level included in training. We find that RLVR yields stronger within-level and across-level generalization than SFT, but only for specific combinations of model size and training query level. Further analysis shows that RLVR's effectiveness depends on the model's initial reasoning competence. With sufficient initial competence, RLVR improves an LLM's marginalization strategy and reduces errors in intermediate probability calculations, producing substantial accuracy gains, particularly on more complex queries. These findings show that RLVR can improve specific causal reasoning subskills, with its benefits emerging only when the model has sufficient initial competence.

Shepard Xia, Brian Lu, Jason Eisner

A hallmark of intelligence is the ability to flesh out underspecified situations using "common sense." We propose to extract that common sense from large language models (LLMs), in a form that can feed into probabilistic inference. We focus our investigation on $\textit{guesstimation}$ questions such as "How much are Airbnb listings in Newark, NJ?" Formulating a sensible answer without access to data requires drawing on, and integrating, bits of common knowledge about how $\texttt{Price}$ and $\texttt{Location}$ may relate to other variables, such as $\texttt{Property Type}$. Our framework answers such a question by synthesizing an $\textit{ad hoc}$ probabilistic model. First we prompt an LLM to propose a set of random variables relevant to the question, followed by moment constraints on their joint distribution. We then optimize the joint distribution $p$ within a log-linear family to maximize the overall constraint satisfaction. Our experiments show that LLMs can successfully be prompted to propose reasonable variables, and while the proposed numerical constraints can be noisy, jointly optimizing for their satisfaction reconciles them. When evaluated on probabilistic questions derived from three real-world tabular datasets, we find that our framework performs comparably to a direct prompting baseline in terms of total variation distance from the dataset distribution, and is similarly robust to noise.

Eric Modesitt, Haicheng Yin, Williams Huang Wang et al.

The task of Electroencephalogram (EEG) analysis is paramount to the development of Brain-Computer Interfaces (BCIs). However, to reach the goal of developing robust, useful BCIs depends heavily on the speed and the accuracy at which BCIs can understand neural dynamics. In response to that goal, this paper details the integration of pre-trained Vision Transformers (ViTs) with Temporal Convolutional Networks (TCNet) to enhance the precision of EEG regression. The core of this approach lies in harnessing the sequential data processing strengths of ViTs along with the superior feature extraction capabilities of TCNet, to significantly improve EEG analysis accuracy. In addition, we analyze the importance of how to construct optimal patches for the attention mechanism to analyze, balancing both speed and accuracy tradeoffs. Our results showcase a substantial improvement in regression accuracy, as evidenced by the reduction of Root Mean Square Error (RMSE) from 55.4 to 51.8 on EEGEyeNet's Absolute Position Task, outperforming existing state-of-the-art models. Without sacrificing performance, we increase the speed of this model by an order of magnitude (up to 4.32x faster). This breakthrough not only sets a new benchmark in EEG regression analysis but also opens new avenues for future research in the integration of transformer architectures with specialized feature extraction methods for diverse EEG datasets.

Brian Lu, Dennis Pham, Ti-Chiun Chang et al.

We report the development of a knowledge representation and reasoning (KRR) system built on hybrid SHACL-SKOS ontologies for globally harmonized system (GHS) material Safety Data Sheets (SDS) to enhance chemical safety communication and regulatory compliance. SDS are comprehensive documents containing safety and handling information for chemical substances. Thus, they are an essential part of workplace safety and risk management. However, the vast number of Safety Data Sheets from multiple organizations, manufacturers, and suppliers that produce and distribute chemicals makes it challenging to centralize and access SDS documents through a single repository. To accomplish the underlying issues of data exchange related to chemical shipping and handling, we construct SDS related controlled vocabulary and conditions validated by SHACL, and knowledge systems of similar domains linked via SKOS. The resulting hybrid ontologies aim to provide standardized yet adaptable representations of SDS information, facilitating better data sharing, retrieval, and integration across various platforms. This paper outlines our SHACL-SKOS system architectural design and showcases our implementation for an industrial application streamlining the generation of a composite shipping cover sheet.

Yao Zheng, Shekh Md Mahmudul Islam, Yanjun Pan et al.

The increasingly sophisticated at-home screening systems for obstructive sleep apnea (OSA), integrated with both contactless and contact-based sensing modalities, bring convenience and reliability to remote chronic disease management. However, the device pairing processes between system components are vulnerable to wireless exploitation from a non-compliant user wishing to manipulate the test results. This work presents SIENNA, an insider-resistant context-based pairing protocol. SIENNA leverages JADE-ICA to uniquely identify a user's respiration pattern within a multi-person environment and fuzzy commitment for automatic device pairing, while using friendly jamming technique to prevents an insider with knowledge of respiration patterns from acquiring the pairing key. Our analysis and test results show that SIENNA can achieve reliable (> 90% success rate) device pairing under a noisy environment and is robust against the attacker with full knowledge of the context information.