Rhyme-aware Chinese lyric generator based on GPT

Neural language representation models such as GPT, pre-trained on large-scale corpora, can effectively capture rich semantic patterns from plain text and be fine-tuned to consistently improve natural language generation performance. However, existing pre-trained language models used to generate lyrics rarely consider rhyme information, which is crucial in lyrics. Using a pre-trained model directly results in poor performance. To enhance the rhyming quality of generated lyrics, we incorporate integrated rhyme information into our model, thereby improving lyric generation performance.

Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models

Automatic code generation has been a longstanding research topic. With the advancement of general-purpose large language models (LLMs), the ability to code stands out as one important measure to the model's reasoning performance. Usually, a two-stage training paradigm is implemented to obtain a Code LLM, namely the pretraining and the fine-tuning. Within the fine-tuning, supervised fine-tuning (SFT), and reinforcement learning (RL) are often used to improve the model's zero-shot ability. A large number of work has been conducted to improve the model's performance on code-related benchmarks with either modifications to the algorithm or refinement of the dataset. However, we still lack a deep insight into the correlation between SFT and RL. For instance, what kind of dataset should be used to ensure generalization, or what if we abandon the SFT phase in fine-tuning. In this work, we make an attempt to understand the correlation between SFT and RL. To facilitate our research, we manually craft 100 basis python functions, called atomic functions, and then a synthesizing pipeline is deployed to create a large number of synthetic functions on top of the atomic ones. In this manner, we ensure that the train and test sets remain distinct, preventing data contamination. Through comprehensive ablation study, we find: (1) Both atomic and synthetic functions are indispensable for SFT's generalization, and only a handful of synthetic functions are adequate; (2) Through RL, the SFT's generalization to target domain can be greatly enhanced, even with the same training prompts; (3) Training RL from scratch can alleviate the over-fitting issue introduced in the SFT phase.

Exploring Mathematical Extrapolation of Large Language Models with Synthetic Data

Large Language Models (LLMs) have shown excellent performance in language understanding, text generation, code synthesis, and many other tasks, while they still struggle in complex multi-step reasoning problems, such as mathematical reasoning. In this paper, through a newly proposed arithmetical puzzle problem, we show that the model can perform well on multi-step reasoning tasks via fine-tuning on high-quality synthetic data. Experimental results with the open-llama-3B model on three different test datasets show that not only the model can reach a zero-shot pass@1 at 0.44 on the in-domain dataset, it also demonstrates certain generalization capabilities on the out-of-domain datasets. Specifically, this paper has designed two out-of-domain datasets in the form of extending the numerical range and the composing components of the arithmetical puzzle problem separately. The fine-tuned models have shown encouraging performance on these two far more difficult tasks with the zero-shot pass@1 at 0.33 and 0.35, respectively.

M3H: Multimodal Multitask Machine Learning for Healthcare

Recent breakthroughs in AI are poised to fundamentally enhance our study and understanding of healthcare. The development of an integrated many-to-many framework that leverages multiple data modality inputs for the analytical modeling of multiple medical tasks, is critical for a unified understanding of modern medicine. In this work, we introduce M3H, an explainable Multimodal Multitask Machine Learning for Healthcare framework that consolidates learning from diverse multimodal inputs across a broad spectrum of medical task categories and machine learning problem classes. The modular design of the framework ensures its generalizable data processing, task definition, and rapid model prototyping, applicable to both clinical and operational healthcare settings. We evaluate the M3H framework by validating models trained from four modalities (tabular, time-series, language, and vision) on 41 medical tasks across 4 machine learning problem classes. Our results demonstrate that M3H consistently produces multitask models that outperform canonical single-task models (by 1.1- 37.2%) across 37 disease diagnoses from 16 medical departments, three hospital operation forecasts, and one patient phenotyping task: spanning ML problem classes of supervised binary classification, multiclass classification, regression, and clustering. Additionally, the framework introduces a novel attention mechanism to balance self-exploitation (focus on learning source task), and cross-exploration (encourage learning from other tasks). Furthermore, M3H provides explainability insights on how joint learning of additional tasks impacts the learning of source task using a proposed TIM score, shedding light into the dynamics of task interdependencies. Its adaptable architecture facilitates the customization and integration, establishing it as a robust and scalable candidate solution for future AI-driven healthcare systems.

Towards Stable Machine Learning Model Retraining via Slowly Varying Sequences

Retraining machine learning models remains an important task for real-world machine learning model deployment. Existing methods focus largely on greedy approaches to find the best-performing model without considering the stability of trained model structures across different retraining evolutions. In this study, we develop a mixed integer optimization algorithm that holistically considers the problem of retraining machine learning models across different data batch updates. Our method focuses on retaining consistent analytical insights - which is important to model interpretability, ease of implementation, and fostering trust with users - by using custom-defined distance metrics that can be directly incorporated into the optimization problem. Importantly, our method shows stronger stability than greedily trained models with a small, controllable sacrifice in model performance in a real-world production case study. Finally, important analytical insights, as demonstrated using SHAP feature importance, are shown to be consistent across retraining iterations.

SNE-RoadSegV2: Advancing Heterogeneous Feature Fusion and Fallibility Awareness for Freespace Detection

Feature-fusion networks with duplex encoders have proven to be an effective technique to solve the freespace detection problem. However, despite the compelling results achieved by previous research efforts, the exploration of adequate and discriminative heterogeneous feature fusion, as well as the development of fallibility-aware loss functions remains relatively scarce. This paper makes several significant contributions to address these limitations: (1) It presents a novel heterogeneous feature fusion block, comprising a holistic attention module, a heterogeneous feature contrast descriptor, and an affinity-weighted feature recalibrator, enabling a more in-depth exploitation of the inherent characteristics of the extracted features, (2) it incorporates both inter-scale and intra-scale skip connections into the decoder architecture while eliminating redundant ones, leading to both improved accuracy and computational efficiency, and (3) it introduces two fallibility-aware loss functions that separately focus on semantic-transition and depth-inconsistent regions, collectively contributing to greater supervision during model training. Our proposed heterogeneous feature fusion network (SNE-RoadSegV2), which incorporates all these innovative components, demonstrates superior performance in comparison to all other freespace detection algorithms across multiple public datasets. Notably, it ranks the 1st on the official KITTI Road benchmark.

Robust Regression over Averaged Uncertainty

We propose a new formulation of robust regression by integrating all realizations of the uncertainty set and taking an averaged approach to obtain the optimal solution for the ordinary least-squared regression problem. We show that this formulation surprisingly recovers ridge regression and establishes the missing link between robust optimization and the mean squared error approaches for existing regression problems. We first prove the equivalence for four uncertainty sets: ellipsoidal, box, diamond, and budget, and provide closed-form formulations of the penalty term as a function of the sample size, feature size, as well as perturbation protection strength. We then show in synthetic datasets with different levels of perturbations, a consistent improvement of the averaged formulation over the existing worst-case formulation in out-of-sample performance. Importantly, as the perturbation level increases, the improvement increases, confirming our method's advantage in high-noise environments. We report similar improvements in the out-of-sample datasets in real-world regression problems obtained from UCI datasets.

TabText: a Systematic Approach to Aggregate Knowledge Across Tabular Data Structures

Processing and analyzing tabular data in a productive and efficient way is essential for building successful applications of machine learning in fields such as healthcare. However, the lack of a unified framework for representing and standardizing tabular information poses a significant challenge to researchers and professionals alike. In this work, we present TabText, a methodology that leverages the unstructured data format of language to encode tabular data from different table structures and time periods efficiently and accurately. We show using two healthcare datasets and four prediction tasks that features extracted via TabText outperform those extracted with traditional processing methods by 2-5%. Furthermore, we analyze the sensitivity of our framework against different choices for sentence representations of missing values, meta information and language descriptiveness, and provide insights into winning strategies that improve performance.

Integrated multimodal artificial intelligence framework for healthcare applications

Artificial intelligence (AI) systems hold great promise to improve healthcare over the next decades. Specifically, AI systems leveraging multiple data sources and input modalities are poised to become a viable method to deliver more accurate results and deployable pipelines across a wide range of applications. In this work, we propose and evaluate a unified Holistic AI in Medicine (HAIM) framework to facilitate the generation and testing of AI systems that leverage multimodal inputs. Our approach uses generalizable data pre-processing and machine learning modeling stages that can be readily adapted for research and deployment in healthcare environments. We evaluate our HAIM framework by training and characterizing 14,324 independent models based on MIMIC-IV-MM, a multimodal clinical database (N=34,537 samples) containing 7,279 unique hospitalizations and 6,485 patients, spanning all possible input combinations of 4 data modalities (i.e., tabular, time-series, text and images), 11 unique data sources and 12 predictive tasks. We show that this framework can consistently and robustly produce models that outperform similar single-source approaches across various healthcare demonstrations (by 6-33%), including 10 distinct chest pathology diagnoses, along with length-of-stay and 48-hour mortality predictions. We also quantify the contribution of each modality and data source using Shapley values, which demonstrates the heterogeneity in data type importance and the necessity of multimodal inputs across different healthcare-relevant tasks. The generalizable properties and flexibility of our Holistic AI in Medicine (HAIM) framework could offer a promising pathway for future multimodal predictive systems in clinical and operational healthcare settings.

Simulating LIDAR Point Cloud for Autonomous Driving using Real-world Scenes and Traffic Flows

We present a LIDAR simulation framework that can automatically generate 3D point cloud based on LIDAR type and placement. The point cloud, annotated with ground truth semantic labels, is to be used as training data to improve environmental perception capabilities for autonomous driving vehicles. Different from previous simulators, we generate the point cloud based on real environment and real traffic flow. More specifically we employ a mobile LIDAR scanner with cameras to capture real world scenes. The input to our simulation framework includes dense 3D point cloud and registered color images. Moving objects (such as cars, pedestrians, bicyclists) are automatically identified and recorded. These objects are then removed from the input point cloud to restore a static background (e.g., environment without movable objects). With that we can insert synthetic models of various obstacles, such as vehicles and pedestrians in the static background to create various traffic scenes. A novel LIDAR renderer takes the composite scene to generate new realistic LIDAR points that are already annotated at point level for synthetic objects. Experimental results show that our system is able to close the performance gap between simulation and real data to be 1 ~ 6% in different applications, and for model fine tuning, only 10% ~ 20% extra real data could help to outperform the original model trained with full real dataset.