arXiv subjects

Han Deng

Publications and source records attributed to Han Deng.

11 recordsLinked to original sources

arXiv2026

LabOSBench: Benchmarking Computer Use Agents for Scientific Instrument Control

Current computer-use benchmarks primarily focus on software operation tasks in virtualized systems, whereas scientific instrumentation scenarios require coordinated control over complex interfaces, and feedback-driven parameter adjustment. However, directly evaluating agents on physical high-precision instruments is impractical due to high cost, safety risks, limited accessibility, and difficulty in ensuring reproducible evaluation. This motivates the need for a simulated yet realistic testbed that preserves the operational challenges of scientific instruments while enabling scalable and safe benchmarking. To this end, we introduce LabOSBench, a challenging benchmark for multimodal GUI agents built on a suite of web-based scientific-instrument simulators. Operating directly via a browser, LabOSBench avoids resource-heavy OS virtualization while supporting flexible task configuration and execution-based evaluation. Specifically, LabOSBench constructs 96 subtasks across eight instrument simulators, covering workflows from sample loading, alignment, parameter tuning, and data acquisition to result inspection. We evaluate general-purpose vision-language models, specialized GUI agent models, and advanced agentic frameworks at both subtask and end-to-end levels. Our experiments reveal that while existing agents can complete many structured GUI subtasks, they still struggle with feedback-driven operations and long-horizon workflow execution. Overall, LabOSBench provides a reproducible, low-cost testbed for advancing computer-using agents toward scientific-instrument control.

cs.AI↗

arXiv2026

Owl-AuraID 1.0: An Intelligent System for Autonomous Scientific Instrumentation and Scientific Data Analysis

Scientific discovery increasingly depends on high-throughput characterization, yet automation is hindered by proprietary GUIs and the limited generalizability of existing API-based systems. We present Owl-AuraID, a software-hardware collaborative embodied agent system that adopts a GUI-native paradigm to operate instruments through the same interfaces as human experts. Its skill-centric framework integrates Type-1 (GUI operation) and Type-2 (data analysis) skills into end-to-end workflows, connecting physical sample handling with scientific interpretation. Owl-AuraID demonstrates broad coverage across ten categories of precision instruments and diverse workflows, including multimodal spectral analysis, microscopic imaging, and crystallographic analysis, supporting modalities such as FTIR, NMR, AFM, and TGA. Overall, Owl-AuraID provides a practical, extensible foundation for autonomous laboratories and illustrates a path toward evolving laboratory intelligence through reusable operational and analytical skills. The code are available at https://github.com/OpenOwlab/AuraID.

cs.AI↗

arXiv2025

SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence

We introduce SciEvalKit, a unified benchmarking toolkit designed to evaluate AI models for science across a broad range of scientific disciplines and task capabilities. Unlike general-purpose evaluation platforms, SciEvalKit focuses on the core competencies of scientific intelligence, including Scientific Multimodal Perception, Scientific Multimodal Reasoning, Scientific Multimodal Understanding, Scientific Symbolic Reasoning, Scientific Code Generation, Science Hypothesis Generation and Scientific Knowledge Understanding. It supports six major scientific domains, spanning from physics and chemistry to astronomy and materials science. SciEvalKit builds a foundation of expert-grade scientific benchmarks, curated from real-world, domain-specific datasets, ensuring that tasks reflect authentic scientific challenges. The toolkit features a flexible, extensible evaluation pipeline that enables batch evaluation across models and datasets, supports custom model and dataset integration, and provides transparent, reproducible, and comparable results. By bridging capability-based evaluation and disciplinary diversity, SciEvalKit offers a standardized yet customizable infrastructure to benchmark the next generation of scientific foundation models and intelligent agents. The toolkit is open-sourced and actively maintained to foster community-driven development and progress in AI4Science.

cs.AI↗

arXiv2025

SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines

We present a scientific reasoning foundation model that aligns natural language with heterogeneous scientific representations. The model is pretrained on a 206B-token corpus spanning scientific text, pure sequences, and sequence-text pairs, then aligned via SFT on 40M instructions, annealed cold-start bootstrapping to elicit long-form chain-of-thought, and reinforcement learning with task-specific reward shaping, which instills deliberate scientific reasoning. It supports four capability families, covering up to 103 tasks across workflows: (i) faithful translation between text and scientific formats, (ii) text/knowledge extraction, (iii) property prediction, (iv) property classification, (v) unconditional and conditional sequence generation and design. Compared with specialist systems, our approach broadens instruction coverage, improves cross-domain generalization, and enhances fidelity. We detail data curation and training and show that cross-discipline learning strengthens transfer and downstream reliability. The model, instruct tuning datasets and the evaluation code are open-sourced at https://huggingface.co/SciReason and https://github.com/open-sciencelab/SciReason.

cs.CL↗

arXiv2025

Optimal Feedback Schemes for Dirty Paper Channels With State Estimation at the Receiver

In the literature, it has been shown that feedback does not increase the optimal rate-distortion region of the dirty paper channel with state estimation at the receiver (SE-R). On the other hand, it is well-known that feedback helps to construct low-complexity coding schemes in Gaussian channels, such as the elegant Schalkwijk-Kailath (SK) feedback scheme. This motivates us to explore capacity-achieving SK-type schemes in dirty paper channels with SE-R and feedback. In this paper, we first propose a capacity-achieving feedback scheme for the dirty paper channel with SE-R (DPC-SE-R), which combines the superposition coding and the classical SK-type scheme. Then, we extend this scheme to the dirty paper multiple-access channel with SE-R and feedback, and also show the extended scheme is capacity-achieving. Finally, we discuss how to extend our scheme to a noisy state observation case of the DPC-SE-R. However, the capacity-achieving SK-type scheme for such a case remains unknown.

cs.IT↗

arXiv2025

CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming

Competitive programming benchmarks are widely used in scenarios such as programming contests and large language model assessments. However, the growing presence of duplicate or highly similar problems raises concerns not only about competition fairness, but also about the validity of competitive programming as a benchmark for model evaluation. In this paper, we propose a new problem, similar question retrieval, to tackle this issue. Due to the lack of both data and models, solving this problem is challenging. To this end, we introduce CPRet, a retrieval-oriented benchmark suite for competitive programming, covering four retrieval tasks: two code-centric (i.e., Text-to-Code, Code-to-Code) and two newly proposed problem-centric tasks (i.e., Problem-to-Duplicate, Simplified-to-Full) built from a combination of automatically crawled problem-solution data and manually curated annotations. Our contribution includes both high-quality training data and temporally separated test sets for reliable evaluation. Besides, we further develop two task-specialized retrievers based on this dataset: CPRetriever-Code, trained with a novel Group-InfoNCE loss for problem-code alignment, and CPRetriever-Prob, fine-tuned for identifying problem-level similarity. Both models achieve strong results and are open-sourced for local use. Finally, we analyze LiveCodeBench and find that high-similarity problems inflate model pass rates and reduce differentiation, underscoring the need for similarity-aware evaluation in future benchmarks. Github: https://github.com/coldchair/CPRet Online Demo: https://www.cpret.online/

cs.SE↗

arXiv2024

STT: Stateful Tracking with Transformers for Autonomous Driving

Tracking objects in three-dimensional space is critical for autonomous driving. To ensure safety while driving, the tracker must be able to reliably track objects across frames and accurately estimate their states such as velocity and acceleration in the present. Existing works frequently focus on the association task while either neglecting the model performance on state estimation or deploying complex heuristics to predict the states. In this paper, we propose STT, a Stateful Tracking model built with Transformers, that can consistently track objects in the scenes while also predicting their states accurately. STT consumes rich appearance, geometry, and motion signals through long term history of detections and is jointly optimized for both data association and state estimation tasks. Since the standard tracking metrics like MOTA and MOTP do not capture the combined performance of the two tasks in the wider spectrum of object states, we extend them with new metrics called S-MOTA and MOTPS that address this limitation. STT achieves competitive real-time performance on the Waymo Open Dataset.

cs.RO↗

arXiv2023

Review on Decarbonizing the Transportation Sector in China: Overview, Analysis, and Perspectives

This review identifies challenges and effective strategies to decarbonize China's rapidly growing transportation sector, currently the third largest carbon emitter, considering China's commitment to peak carbon emissions by 2030 and achieve carbon neutrality by 2060. Key challenges include rising travel demand, unreached peak car ownership, declining bus ridership, gaps between energy technology research and practical application, and limited institutional capacity for decarbonization. This review categorizes current decarbonization measures, strategies, and policies in China's transportation sector using the "Avoid, Shift, Improve" framework, complemented by a novel strategic vector of "Institutional Capacity & Technology Development" to capture broader development perspectives. This comprehensive analysis aims to facilitate informed decision-making and promote collaborative strategies for China's transition to a sustainable transportation future.

econ.GN↗

arXiv2022

Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking

Monocular image-based 3D perception has become an active research area in recent years owing to its applications in autonomous driving. Approaches to monocular 3D perception including detection and tracking, however, often yield inferior performance when compared to LiDAR-based techniques. Through systematic analysis, we identified that per-object depth estimation accuracy is a major factor bounding the performance. Motivated by this observation, we propose a multi-level fusion method that combines different representations (RGB and pseudo-LiDAR) and temporal information across multiple frames for objects (tracklets) to enhance per-object depth estimation. Our proposed fusion method achieves the state-of-the-art performance of per-object depth estimation on the Waymo Open Dataset, the KITTI detection dataset, and the KITTI MOT dataset. We further demonstrate that by simply replacing estimated depth with fusion-enhanced depth, we can achieve significant improvements in monocular 3D perception tasks, including detection and tracking.

cs.CV↗

arXiv2021

SkullEngine: A Multi-stage CNN Framework for Collaborative CBCT Image Segmentation and Landmark Detection

We propose a multi-stage coarse-to-fine CNN-based framework, called SkullEngine, for high-resolution segmentation and large-scale landmark detection through a collaborative, integrated, and scalable JSD model and three segmentation and landmark detection refinement models. We evaluated our framework on a clinical dataset consisting of 170 CBCT/CT images for the task of segmenting 2 bones (midface and mandible) and detecting 175 clinically common landmarks on bones, teeth, and soft tissues.

eess.IV↗

arXiv2017

On the Capacity Requirement for Arbitrary End-to-End Deadline and Reliability Guarantees in Multi-hop Networks

It has been shown that it is impossible to achieve both stringent end-to-end deadline and reliability guarantees in a large network without having complete information of all future packet arrivals. In order to maintain desirable performance in the presence of uncertainty of future packet arrivals, common practice is to add redundancy by increasing link capacities. This paper studies the amount of capacity needed to provide stringent performance guarantees. We propose a low-complexity online algorithm and prove that it only requires a small amount of redundancy to guarantee both end-to-end deadline and reliability. Further, we show that in large networks with very high reliability requirements, the redundancy needed by our policy is at most twice as large as a theoretical lower bound. Also, for practical implementation, we propose a fully distributed protocol based on the previous centralized policy. Without adding redundancy, we further propose a low-complexity order-optimal online policy for the network. Simulation results also show that our policy achieves much better performance than other state-of-the-art policies.

cs.PF↗