Yushi Cao

Xu Liu, Yuxuan Liang, Chao Huang et al.

Spatio-temporal graph neural networks (STGNN) have become the most popular solution to traffic forecasting. While successful, they rely on the message passing scheme of GNNs to establish spatial dependencies between nodes, and thus inevitably inherit GNNs' notorious inefficiency. Given these facts, in this paper, we propose an embarrassingly simple yet remarkably effective spatio-temporal learning approach, entitled SimST. Specifically, SimST approximates the efficacies of GNNs by two spatial learning techniques, which respectively model local and global spatial correlations. Moreover, SimST can be used alongside various temporal models and involves a tailored training strategy. We conduct experiments on five traffic benchmarks to assess the capability of SimST in terms of efficiency and effectiveness. Empirical results show that SimST improves the prediction throughput by up to 39 times compared to more sophisticated STGNNs while attaining comparable performance, which indicates that GNNs are not the only option for spatial modeling in traffic forecasting.

Yushi Cao, Zhiming Li, Tianpei Yang et al.

Despite achieving superior performance in human-level control problems, unlike humans, deep reinforcement learning (DRL) lacks high-order intelligence (e.g., logic deduction and reuse), thus it behaves ineffectively than humans regarding learning and generalization in complex problems. Previous works attempt to directly synthesize a white-box logic program as the DRL policy, manifesting logic-driven behaviors. However, most synthesis methods are built on imperative or declarative programming, and each has a distinct limitation, respectively. The former ignores the cause-effect logic during synthesis, resulting in low generalizability across tasks. The latter is strictly proof-based, thus failing to synthesize programs with complex hierarchical logic. In this paper, we combine the above two paradigms together and propose a novel Generalizable Logic Synthesis (GALOIS) framework to synthesize hierarchical and strict cause-effect logic programs. GALOIS leverages the program sketch and defines a new sketch-based hybrid program language for guiding the synthesis. Based on that, GALOIS proposes a sketch-based program synthesis method to automatically generate white-box programs with generalizable and interpretable cause-effect logic. Extensive evaluations on various decision-making tasks with complex logic demonstrate the superiority of GALOIS over mainstream baselines regarding the asymptotic performance, generalizability, and great knowledge reusability across different environments.

Yushi Cao, Yiming Chen, Hongchao Jiang et al.

Predicting future clinical outcomes from electronic health records (EHR) remains challenging due to the complexity and heterogeneity of patient data. LLMs have shown strong potential for such predictive tasks, yet existing approaches mainly focus on enhancing medical knowledge through distillation or RAG while relying on the model's internal ability to interpret contextual information. In this work, we present ReMedi (Reasoner for Medical Clinical Prediction), a framework for improving clinical outcome prediction from EHR. ReMedi generates rationale-answer pairs using a challenging sample regeneration mechanism for complex clinical questions, which leverages ground-truth answers as hints to enhance reasoning for further fine-tuning and preference tuning. ReMedi integrates ground-truth outcome guidance into the preference data construction loop, regenerating rationale-answer variants. By tuning on these rationale-answer pairs, the model improves its predictive performance. Experiments on multiple EHR prediction tasks demonstrate substantial gains of up to 19.9 percent over state-of-the-art baselines in terms of F1 score, underscoring ReMedi's effectiveness in real-world clinical prediction.

Zhiming Li, Junzhe Jiang, Yushi Cao et al.

Deep reinforcement learning (DRL) has revolutionized quantitative trading (Q-trading) by achieving decent performance without significant human expert knowledge. Despite its achievements, we observe that the current state-of-the-art DRL models are still ineffective in identifying the market trends, causing them to miss good trading opportunities or suffer from large drawdowns when encountering market crashes. To address this limitation, a natural approach is to incorporate human expert knowledge in identifying market trends. Whereas, such knowledge is abstract and hard to be quantified. In order to effectively leverage abstract human expert knowledge, in this paper, we propose a universal logic-guided deep reinforcement learning framework for Q-trading, called Logic-Q. In particular, Logic-Q adopts the program synthesis by sketching paradigm and introduces a logic-guided model design that leverages a lightweight, plug-and-play market trend-aware program sketch to determine the market trend and correspondingly adjusts the DRL policy in a post-hoc manner. Extensive evaluations of two popular quantitative trading tasks demonstrate that Logic-Q can significantly improve the performance of previous state-of-the-art DRL trading strategies.

Aishik Nagar, Arun-Kumar Kaliya-Perumal, Yu-Hsuan Han et al.

Inpatient clinical reasoning is a sequential decision under partial observability: the clinician sees the admission so far and must choose the next action whose downstream consequences are not yet visible. Existing clinical-LLM evaluations and RL rewards signals collapse this into closed-form retrieval, clinical journey leakage, or unanchored LLM-as-judge scoring. We introduce CLR-voyance, a framework that reformulates inpatient reasoning as a Partially Observable Markov Decision Process (POMDP) and supervises it with rewards that are simultaneously outcome-grounded and clinician-validated. We instantiate the formulation as CLR-POMDP, which partitions successful patient journeys into a policy-visible past and an oracle-only future. Using the past information, an oracle LLM generates a case-specific query-answer pair, and the first adaptive rubric for clinical reasoning which is verifiable in the future of the patient journey. These rubrics are used for both post-training and evaluation of models for inpatient clinical reasoning. We post-train Qwen3-8B and MedGemma-4B with GRPO followed by model merging, yielding state-of-the-art inpatient clinical reasoning while retaining generalist capabilities. CLR-voyance-8B achieves 84.91% on CLR-POMDP, ahead of frontier medical reasoning models like GPT-5 (77.83%) and MedGemma-27B (66.66%) and has comparable or better performance on existing medical benchmarks. To ensure a clinically meaningful setting, we conduct a large-scale clinician alignment study, where physicians curate per-case rubrics, grade candidate responses, and provide blinded pairwise preferences of model reasoning. This study provides insights on clinical LLM-as-a-judge and clinical preference-model selection, which can inform the community at large. CLR-voyance has been deployed for 6+ months at a partner public hospital, drafting thousands of reasoning-heavy inpatient notes.

Zhiming Li, Yushi Cao, Xiufeng Xu et al.

Large language models (LLMs) have revolutionized many areas (e.g. natural language processing, software engineering, etc.) by achieving state-of-the-art performance on extensive downstream tasks. Aiming to achieve robust and general artificial intelligence, there has been a surge of interest in investigating the reasoning ability of the LLMs. Whereas the textual and numerical reasoning benchmarks adopted by previous works are rather shallow and simple, it is hard to conclude that the LLMs possess strong reasoning ability by merely achieving positive results on these benchmarks. Recent efforts have demonstrated that the LLMs are poor at solving sequential decision-making problems that require common-sense planning by evaluating their performance on the reinforcement learning benchmarks. In this work, we conduct an in-depth assessment of several state-of-the-art LLMs' reasoning ability based on the inductive logic programming (ILP) benchmark, which is broadly recognized as a representative and challenging measurement for evaluating logic program induction/synthesis systems as it requires inducing strict cause-effect logic to achieve robust deduction on independent and identically distributed (IID) and out-of-distribution (OOD) test samples. Our evaluations illustrate that compared with the neural program induction systems which are much smaller in model size, the state-of-the-art LLMs are much poorer in terms of reasoning ability by achieving much lower performance and generalization using either natural language prompting or truth-value matrix prompting.

Hongchao Jiang, Yiming Chen, Yushi Cao et al.

Large Language Models (LLMs) have significantly advanced the state-of-the-art in various coding tasks. Beyond directly answering user queries, LLMs can also serve as judges, assessing and comparing the quality of responses generated by other models. Such an evaluation capability is crucial both for benchmarking different LLMs and for improving response quality through response ranking. However, despite the growing adoption of the LLM-as-a-Judge paradigm, its effectiveness in coding scenarios remains underexplored due to the absence of dedicated benchmarks. To address this gap, we introduce CodeJudgeBench, a benchmark explicitly designed to evaluate the performance of LLM-as-a-Judge models across three critical coding tasks: code generation, code repair, and unit test generation. Through comprehensive benchmarking of 26 LLM-as-a-Judge models, we find that recent thinking models significantly outperform non-thinking models on our carefully designed code judging tasks. Notably, even relatively small thinking models, such as Qwen3-8B, can outperform specially trained LLM-as-a-Judge models up to 70B in size. Nevertheless, all models still exhibit significant randomness in their judgment of coding tasks. For pairwise judging tasks, simply changing the order in which responses are presented can substantially impact accuracy. In addition, when judging code and unit tests written by different LLMs, LLM-as-a-Judge models also show variance in performance. This sensitivity raises concerns about the reliability and consistency of LLM-as-a-Judge in coding scenarios. Lastly, we study optimal prompting strategies for LLM-as-a-Judge. We find that using pair-wise comparison outperforms scalar point-wise judging. Furthermore, retaining comments and reasoning in the full, unprocessed LLM response leads to improved judge performance.

Sarthak Ketanbhai Modi, Zi Pong Lim, Yushi Cao et al.

The process of tuning the size of the hidden layers for autoencoders has the benefit of providing optimally compressed representations for the input data. However, such hyper-parameter tuning process would take a lot of computation and time effort with grid search as the default option. In this paper, we introduce the Self-Organization Regularization for Autoencoders that dynamically adapts the dimensionality of the feature space to the optimal size. Inspired by physics concepts, Self-Organizing Sparse AutoEncoder (SOSAE) induces sparsity in feature space in a structured way that permits the truncation of the non-active part of the feature vector without any loss of information. This is done by penalizing the autoencoder based on the magnitude and the positional index of the feature vector dimensions, which during training constricts the feature space in both terms. Extensive experiments on various datasets show that our SOSAE can tune the feature space dimensionality up to 130 times lesser Floating-point Operations (FLOPs) than other baselines while maintaining the same quality of tuning and performance.

Sarthak Ketanbhai Modi, Zi Pong Lim, Shourya Kuchhal et al.

The rapid growth in complexity and size of modern deep neural networks (DNNs) has increased challenges related to computational costs and memory usage, spurring a growing interest in efficient model compression techniques. Previous state-of-the-art approach proposes using a Torque-inspired regularization which forces the weights of neural modules around a selected pivot point. Whereas, we observe that the pruning effect of this approach is far from perfect, as the post-trained network is still dense and also suffers from high accuracy drop. In this work, we attribute such ineffectiveness to the default linear force application scheme, which imposes inappropriate force on neural module of different distances. To efficiently prune the redundant and distant modules while retaining those that are close and necessary for effective inference, in this work, we propose Exponential Torque Pruning (ETP), which adopts an exponential force application scheme for regularization. Experimental results on a broad range of domains demonstrate that, though being extremely simple, ETP manages to achieve significantly higher compression rate than the previous state-of-the-art pruning strategies with negligible accuracy drop.

Yupeng Cheng, Zi Pong Lim, Sarthak Ketanbhai Modi et al.

Test automation has become increasingly important as the complexity of both design and content in Human Machine Interface (HMI) software continues to grow. Current standard practice uses Optical Character Recognition (OCR) techniques to automatically extract textual information from HMI screens for validation. At present, one of the key challenges faced during the automation of HMI screen validation is the noise handling for the OCR models. In this paper, we propose to utilize adversarial training techniques to enhance OCR models in HMI testing scenarios. More specifically, we design a new adversarial attack objective for OCR models to discover the decision boundaries in the context of HMI testing. We then adopt adversarial training to optimize the decision boundaries towards a more robust and accurate OCR model. In addition, we also built an HMI screen dataset based on real-world requirements and applied multiple types of perturbation onto the clean HMI dataset to provide a more complete coverage for the potential scenarios. We conduct experiments to demonstrate how using adversarial training techniques yields more robust OCR models against various kinds of noises, while still maintaining high OCR model accuracy. Further experiments even demonstrate that the adversarial training models exhibit a certain degree of robustness against perturbations from other patterns.

Zhiming Li, Yanzhou Li, Tianlin Li et al.

Deep learning has introduced significant improvements in many software analysis tasks. Although the Large Language Models (LLMs) based neural code models demonstrate commendable performance when trained and tested within the intra-project independent and identically distributed (IID) setting, they often struggle to generalize effectively to real-world inter-project out-of-distribution (OOD) data. In this work, we show that this phenomenon is caused by the heavy reliance on project-specific shortcuts for prediction instead of ground-truth evidence. We propose a Cond-Idf measurement to interpret this behavior, which quantifies the relatedness of a token with a label and its project-specificness. The strong correlation between model behavior and the proposed measurement indicates that without proper regularization, models tend to leverage spurious statistical cues for prediction. Equipped with these observations, we propose a novel bias mitigation mechanism that regularizes the model's learning behavior by leveraging latent logic relations among samples. Experimental results on two representative program analysis tasks indicate that our mitigation framework can improve both inter-project OOD generalization and adversarial robustness, while not sacrificing accuracy on intra-project IID data.

Yushi Cao, David Berend, Palina Tolmach et al.

Deep learning-based facial recognition systems have experienced increased media attention due to exhibiting unfair behavior. Large enterprises, such as IBM, shut down their facial recognition and age prediction systems as a consequence. Age prediction is an especially difficult application with the issue of fairness remaining an open research problem (e.g., predicting age for different ethnicity equally accurate). One of the main causes of unfair behavior in age prediction methods lies in the distribution and diversity of the training data. In this work, we present two novel approaches for dataset curation and data augmentation in order to increase fairness through balanced feature curation and increase diversity through distribution aware augmentation. To achieve this, we introduce out-of-distribution detection to the facial recognition domain which is used to select the data most relevant to the deep neural network's (DNN) task when balancing the data among age, ethnicity, and gender. Our approach shows promising results. Our best-trained DNN model outperformed all academic and industrial baselines in terms of fairness by up to 4.92 times and also enhanced the DNN's ability to generalize outperforming Amazon AWS and Microsoft Azure public cloud systems by 31.88% and 10.95%, respectively.