Hao Li

Jiankun Li, Hao Li, Jiangjiang Liu et al. · baidu

Deep learning-based models are widely deployed in autonomous driving areas, especially the increasingly noticed end-to-end solutions. However, the black-box property of these models raises concerns about their trustworthiness and safety for autonomous driving, and how to debug the causality has become a pressing concern. Despite some existing research on the explainability of autonomous driving, there is currently no systematic solution to help researchers debug and identify the key factors that lead to the final predicted action of end-to-end autonomous driving. In this work, we propose a comprehensive approach to explore and analyze the causality of end-to-end autonomous driving. First, we validate the essential information that the final planning depends on by using controlled variables and counterfactual interventions for qualitative analysis. Then, we quantitatively assess the factors influencing model decisions by visualizing and statistically analyzing the response of key model inputs. Finally, based on the comprehensive study of the multi-factorial end-to-end autonomous driving system, we have developed a strong baseline and a tool for exploring causality in the close-loop simulator CARLA. It leverages the essential input sources to obtain a well-designed model, resulting in highly competitive capabilities. As far as we know, our work is the first to unveil the mystery of end-to-end autonomous driving and turn the black box into a white one. Thorough close-loop experiments demonstrate that our method can be applied to end-to-end autonomous driving solutions for causality debugging. Code will be available at https://github.com/bdvisl/DriveInsight.

Hao Li, Gopi Krishnan Rajbahadur, Cor-Paul Bezemer

Bindings for machine learning frameworks (such as TensorFlow and PyTorch) allow developers to integrate a framework's functionality using a programming language different from the framework's default language (usually Python). In this paper, we study the impact of using TensorFlow and PyTorch bindings in C#, Rust, Python and JavaScript on the software quality in terms of correctness (training and test accuracy) and time cost (training and inference time) when training and performing inference on five widely used deep learning models. Our experiments show that a model can be trained in one binding and used for inference in another binding for the same framework without losing accuracy. Our study is the first to show that using a non-default binding can help improve machine learning software quality from the time cost perspective compared to the default Python binding while still achieving the same level of correctness.

Yuhan Peng, Junwen Dong, Yuzhi Zeng et al.

Graph neural networks face two fundamental challenges rooted in the linear structure of Euclidean vector spaces: (1) Current architectures represent geometry through vectors (directions, gradients), yet many tasks require matrix-valued representations that capture relationships between directions-such as how atomic orientations covary in a molecule. These second-order representations are naturally captured by points on the symmetric positive definite matrices (SPD) manifold; (2) Standard message passing applies shared transformations across edges. Sheaf neural networks address this via edge-specific transformations, but existing formulations remain confined to vector spaces and therefore cannot propagate matrix-valued features. We address both challenges by developing the first sheaf neural network operates natively on the SPD manifold. Our key insight is that the SPD manifold admits a Lie group structure, enabling well-posed analogs of sheaf operators without projecting to Euclidean space. Theoretically, we prove that SPD-valued sheaves are strictly more expressive than Euclidean sheaves: they admit consistent configurations (global sections) that vector-valued sheaves cannot represent, directly translating to richer learned representations. Empirically, our sheaf convolution transforms effectively rank-1 directional inputs into full-rank matrices encoding local geometric structure. Our dual-stream architecture achieves SOTA on 6/7 MoleculeNet benchmarks, with the sheaf framework providing consistent depth robustness.

Hao Li, Cor-Paul Bezemer, Ahmed E. Hassan

Foundation models (FMs) such as large language models (LLMs) have significantly impacted many fields, including software engineering (SE). The interaction between SE and FMs has led to the integration of FMs into SE practices (FM4SE) and the application of SE methodologies to FMs (SE4FM). While several literature surveys exist on academic contributions to these trends, we are the first to provide a practitioner's view. We analyze 155 FM4SE and 997 SE4FM blog posts from leading technology companies, leveraging an FM-powered surveying approach to systematically label and summarize the discussed activities and tasks. We observed that while code generation is the most prominent FM4SE task, FMs are leveraged for many other SE activities such as code understanding, summarization, and API recommendation. The majority of blog posts on SE4FM are about model deployment & operation, and system architecture & orchestration. Although the emphasis is on cloud deployments, there is a growing interest in compressing FMs and deploying them on smaller devices such as edge or mobile devices. We outline eight future research directions inspired by our gained insights, aiming to bridge the gap between academic findings and real-world applications. Our study not only enriches the body of knowledge on practical applications of FM4SE and SE4FM but also demonstrates the utility of FMs as a powerful and efficient approach in conducting literature surveys within technical and grey literature domains. Our dataset, results, code and used prompts can be found in our online replication package at https://github.com/SAILResearch/fmse-blogs.

James Jewitt, Hao Li, Bram Adams et al.

Hidden license conflicts in the open-source AI ecosystem pose serious legal and ethical risks, exposing organizations to potential litigation and users to undisclosed risk. However, the field lacks a data-driven understanding of how frequently these conflicts occur, where they originate, and which communities are most affected. We present the first end-to-end audit of licenses for datasets and models on Hugging Face, as well as their downstream integration into open-source software applications, covering 364 thousand datasets, 1.6 million models, and 140 thousand GitHub projects. Our empirical analysis reveals systemic non-compliance in which 35.5% of model-to-application transitions eliminate restrictive license clauses by relicensing under permissive terms. In addition, we prototype an extensible rule engine that encodes almost 200 SPDX and model-specific clauses for detecting license conflicts, which can solve 86.4% of license conflicts in software applications. To support future research, we release our dataset and the prototype engine. Our study highlights license compliance as a critical governance challenge in open-source AI and provides both the data and tools necessary to enable automated, AI-aware compliance at scale.

Hao Li, Haoxiang Zhang, Ahmed E. Hassan

The future of software engineering--SE 3.0--is unfolding with the rise of AI teammates: autonomous, goal-driven systems collaborating with human developers. Among these, autonomous coding agents are especially transformative, now actively initiating, reviewing, and evolving code at scale. This paper introduces AIDev, the first large-scale dataset capturing how such agents operate in the wild. Spanning over 456,000 pull requests by five leading agents--OpenAI Codex, Devin, GitHub Copilot, Cursor, and Claude Code--across 61,000 repositories and 47,000 developers, AIDev provides an unprecedented empirical foundation for studying autonomous teammates in software development. Unlike prior work that has largely theorized the rise of AI-native software engineering, AIDev offers structured, open data to support research in benchmarking, agent readiness, optimization, collaboration modeling, and AI governance. The dataset includes rich metadata on PRs, authorship, review timelines, code changes, and integration outcomes--enabling exploration beyond synthetic benchmarks like SWE-bench. For instance, although agents often outperform humans in speed, their PRs are accepted less frequently, revealing a trust and utility gap. Furthermore, while agents accelerate code submission--one developer submitted as many PRs in three days as they had in three years--these are structurally simpler (via code complexity metrics). We envision AIDev as a living resource: extensible, analyzable, and ready for the SE and AI communities. Grounding SE 3.0 in real-world evidence, AIDev enables a new generation of research into AI-native workflows and supports building the next wave of symbiotic human-AI collaboration. The dataset is publicly available at https://github.com/SAILResearch/AI_Teammates_in_SE3. > AI Agent, Agentic AI, Coding Agent, Agentic Coding, Software Engineering Agent

Hao Li, Xue Yang, Zhaokai Wang et al.

Many reinforcement learning environments (e.g., Minecraft) provide only sparse rewards that indicate task completion or failure with binary values. The challenge in exploration efficiency in such environments makes it difficult for reinforcement-learning-based agents to learn complex tasks. To address this, this paper introduces an advanced learning system, named Auto MC-Reward, that leverages Large Language Models (LLMs) to automatically design dense reward functions, thereby enhancing the learning efficiency. Auto MC-Reward consists of three important components: Reward Designer, Reward Critic, and Trajectory Analyzer. Given the environment information and task descriptions, the Reward Designer first design the reward function by coding an executable Python function with predefined observation inputs. Then, our Reward Critic will be responsible for verifying the code, checking whether the code is self-consistent and free of syntax and semantic errors. Further, the Trajectory Analyzer summarizes possible failure causes and provides refinement suggestions according to collected trajectories. In the next round, Reward Designer will further refine and iterate the dense reward function based on feedback. Experiments demonstrate a significant improvement in the success rate and learning efficiency of our agents in complex tasks in Minecraft, such as obtaining diamond with the efficient ability to avoid lava, and efficiently explore trees and animals that are sparse in the plains biome.

Ahmed E. Hassan, Hao Li, Dayi Lin et al.

Agentic Software Engineering (SE 3.0) represents a new era where intelligent agents are tasked not with simple code generation, but with achieving complex, goal-oriented SE objectives. To harness these new capabilities while ensuring trustworthiness, we must recognize a fundamental duality within the SE field in the Agentic SE era, comprising two symbiotic modalities: SE for Humans and SE for Agents. This duality demands a radical reimagining of the foundational pillars of SE (actors, processes, tools, and artifacts) which manifest differently across each modality. We propose two purpose-built workbenches to support this vision. The Agent Command Environment (ACE) serves as a command center where humans orchestrate and mentor agent teams, handling outputs such as Merge-Readiness Packs (MRPs) and Consultation Request Packs (CRPs). The Agent Execution Environment (AEE) is a digital workspace where agents perform tasks while invoking human expertise when facing ambiguity or complex trade-offs. This bi-directional partnership, which supports agent-initiated human callbacks and handovers, gives rise to new, structured engineering activities (i.e., processes) that redefine human-AI collaboration, elevating the practice from agentic coding to true agentic software engineering. This paper presents the Structured Agentic Software Engineering (SASE) vision, outlining several of the foundational pillars for the future of SE. The paper culminates in a research roadmap that identifies a few key challenges and opportunities while briefly discussing the resulting impact of this future on SE education. Our goal is not to offer a definitive solution, but to provide a conceptual scaffold with structured vocabulary to catalyze a community-wide dialogue, pushing the SE community to think beyond its classic, human-centric tenets toward a disciplined, scalable, and trustworthy agentic future.

Yan Li, Changyao Tian, Renqiu Xia et al.

We propose AdapTok, an adaptive temporal causal video tokenizer that can flexibly allocate tokens for different frames based on video content. AdapTok is equipped with a block-wise masking strategy that randomly drops tail tokens of each block during training, and a block causal scorer to predict the reconstruction quality of video frames using different numbers of tokens. During inference, an adaptive token allocation strategy based on integer linear programming is further proposed to adjust token usage given predicted scores. Such design allows for sample-wise, content-aware, and temporally dynamic token allocation under a controllable overall budget. Extensive experiments for video reconstruction and generation on UCF-101 and Kinetics-600 demonstrate the effectiveness of our approach. Without additional image data, AdapTok consistently improves reconstruction quality and generation performance under different token budgets, allowing for more scalable and token-efficient generative video modeling.

Hao Li, Gopi Krishnan Rajbahadur, Dayi Lin et al.

In software engineering, deep learning models are increasingly deployed for critical tasks such as bug detection and code review. However, overfitting remains a challenge that affects the quality, reliability, and trustworthiness of software systems that utilize deep learning models. Overfitting can be (1) prevented (e.g., using dropout or early stopping) or (2) detected in a trained model (e.g., using correlation-based approaches). Both overfitting detection and prevention approaches that are currently used have constraints (e.g., requiring modification of the model structure, and high computing resources). In this paper, we propose a simple, yet powerful approach that can both detect and prevent overfitting based on the training history (i.e., validation losses). Our approach first trains a time series classifier on training histories of overfit models. This classifier is then used to detect if a trained model is overfit. In addition, our trained classifier can be used to prevent overfitting by identifying the optimal point to stop a model's training. We evaluate our approach on its ability to identify and prevent overfitting in real-world samples. We compare our approach against correlation-based detection approaches and the most commonly used prevention approach (i.e., early stopping). Our approach achieves an F1 score of 0.91 which is at least 5% higher than the current best-performing non-intrusive overfitting detection approach. Furthermore, our approach can stop training to avoid overfitting at least 32% of the times earlier than early stopping and has the same or a better rate of returning the best model.

Hao Li, Filipe R. Cogo, Cor-Paul Bezemer

Cargo, the software packaging manager of Rust, provides a yank mechanism to support release-level deprecation, which can prevent packages from depending on yanked releases. Most prior studies focused on code-level (i.e., deprecated APIs) and package-level deprecation (i.e., deprecated packages). However, few studies have focused on release-level deprecation. In this study, we investigate how often and how the yank mechanism is used, the rationales behind its usage, and the adoption of yanked releases in the Cargo ecosystem. Our study shows that 9.6% of the packages in Cargo have at least one yanked release, and the proportion of yanked releases kept increasing from 2014 to 2020. Package owners yank releases for other reasons than withdrawing a defective release, such as fixing a release that does not follow semantic versioning or indicating a package is removed or replaced. In addition, we found that 46% of the packages directly adopted at least one yanked release and the yanked releases propagated through the dependency network, which leads to 1.4% of the releases in the ecosystem having unresolved dependencies.