arXiv subjects

Jiahuan Zhang

Publications and source records attributed to Jiahuan Zhang.

15 recordsLinked to original sources

arXiv2026

InfraOcc: An Infrastructure Occupancy Benchmark with Static-to-Dynamic Reasoning

Fixed-viewpoint infrastructure sensors repeatedly observe the same traffic space, making roadside 3D occupancy structurally different from ego-vehicle perception: a near-persistent static scaffold is overlaid with sparse, short-lived dynamic events. Existing occupancy benchmarks and methods, however, are built around moving ego vehicles and neither measure nor exploit this structure, instead treating occupancy as flat one-shot voxel classification. We address this gap from both data and model perspectives. We build InfraOcc, to our knowledge, the first real-world infrastructure-side semantic occupancy benchmark, with dense voxel annotations for 290 multi-modal sequences in a fixed roadside frame, a static-dynamic decoupled annotation pipeline, unified camera-only, LiDAR-only, and multi-modal evaluation, and diagnostics for static and dynamic occupancy. InfraOcc shows that static infrastructure fills 97.3% of occupied voxels and persists across frames, whereas dynamic participants have a median occupied-frame ratio of only 1.8% per location, revealing a structural static-dynamic asymmetry beyond semantic long-tailedness. We further propose ProSD-Occ, which reformulates occupancy as progressive static-to-dynamic evidence reasoning: it explains persistent layout, exposes residual dynamic evidence under static-confidence guidance, and recomposes static, dynamic, and free-space evidence into a unified field. ProSD-Occ ranks first in overall, dynamic, static, and geometric occupancy on every track, e.g., a 23.5% relative camera-only dynamic-mIoU gain over the strongest baseline and 65.87 multi-modal overall mIoU, establishing fixed-viewpoint roadside occupancy as a distinct problem with its own reasoning paradigm. The benchmark and code will be publicly available at https://github.com/yanglei18/InfraOcc

cs.CV↗

arXiv2026

ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog

Despite growing automation, turning a paper into a coherent poster, talk video, and blog piece often remains a labor-intensive last mile. Recent systems increasingly generate multiple dissemination formats, but a practical workflow must also keep the outputs editable in native tools and bound into one navigable deliverable for revision and reuse. We present ResearchStudio-Reel, a native-editable dissemination workspace that binds its three artifacts into one interactive deliverable at the experience level, implemented as five skills executable in Claude Code and Codex: one shared extractor, three editable artifact generators, and one interactive convergence layer. A shared asset bundle feeds a PowerPoint poster and video deck, plus a bilingual Word blog; rather than re-rendering the paper into a fourth format, Paper2Reel converges these already-produced artifacts at the experience level, binding poster regions, video segments, and blog passages into one interactive viewer. Artifact-specific release checks make this delivery contract testable, and Paper2Poster additionally uses a measured-fill loop. On the Paper2Poster benchmark, our Claude Code configuration achieves the best scores among automated systems on all three aesthetic sub-criteria and the best or tied-best scores on two of three information sub-criteria. Under two VLMjudges, it exceeds the authors' posters in average aesthetics (3.56 vs. 3.03) and wins on overall quality on 74 and 95 of the 100 papers under the two judges. The full pipeline additionally packages the native-editable source artifacts and their aligned viewer. Project is available at https://aka.ms/ResearchStudio

cs.CV↗

arXiv2026

OracleAnalyser: Analysing Implicit Semantics of Oracle Bone Scripts through MLLMs with Post-training

With the advancement of artificial intelligence, research on oracle bone scripts has entered a new era. However, existing methods and benchmarks remain largely confined to recognition tasks, overlooking the equally crucial aspect of oracle bone analysis. To address this gap, we propose OracleAnalyser, a reasoning framework for oracle bone analysis based on post-training techniques. Specifically, we fine-tune Qwen2.5-VL-3B-Instruct through multiple post-training stages and introduce a new preference optimization algorithm, Stable Focal Preference Optimization (SFPO), tailored to the characteristics of oracle bone datasets. In addition, we release both an oracle bone reasoning dataset and an oracle bone preference dataset, and further construct a new benchmark to evaluate models' analytical capabilities for oracle bone scripts. Extensive experiments validate the superior analytical performance of OracleAnalyser, which achieves remarkable results with only 3B parameters, surpassing models with substantially larger scales.

cs.CV↗

arXiv2026

CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage

Modern 3D visual learning relies on observations sampled from metric 3D assets, yet existing scans, meshes, point clouds, simulations, and reconstructions do not directly provide a sparse, comparable, and geometry-consistent panoramic training interface. Dense trajectories duplicate nearby views, source-specific rendering policies yield heterogeneous annotations, and sparse heuristics may miss important regions or introduce depth-inconsistent observations. We study how to convert 3D assets into sparse panoramic RGB-D-pose data that preserves complete scene coverage with low redundancy and auditable provenance. We propose COVER (Coverage-Oriented Viewpoint curation with ERP Range-depth warping), a training-free ERP viewpoint curator that projects geometry observed from selected views into candidate ERP probes, scores incremental coverage, and penalizes depth conflicts. Under bounded proxy error, its greedy coverage proxy preserves the standard coverage-style approximation behavior up to an additive error term. Using COVER, we build CM-EVS (Coverage-curated Metric ERP View Set), a panoramic RGB-D-pose dataset with 36,373 curated ERP frames from 1,275 indoor scenes across Blender indoor, HM3D, and ScanNet++, complemented by outdoor panoramas from TartanGround and OB3D re-encoded into the same schema. Each frame provides full-sphere RGB, metric range depth, calibrated pose; COVER-produced indoor frames include per-step provenance logs. With a median of only 25 frames per indoor scene, CM-EVS covers all 13 unified room types while maintaining compact scene-level coverage. Experiments show that COVER improves the coverage-conflict trade-off, making CM-EVS a sparse, compact, and auditable RGB-D-pose resource for geometry-consistent panoramic 3D learning.

cs.CV↗

arXiv2026

DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving

Multimodal Large Language Models (MLLMs) are rapidly becoming the intelligence brain of end-to-end autonomous driving systems. A key challenge is to assess whether MLLMs can truly understand and follow complex real-world traffic rules. However, existing benchmarks mainly focus on single-rule scenarios like traffic sign recognition, neglecting the complexity of multi-rule concurrency and conflicts in real driving. Consequently, models perform well on simple tasks but often fail or violate rules in real world complex situations. To bridge this gap, we propose DriveCombo, a text and vision-based benchmark for compositional traffic rule reasoning. Inspired by human drivers' cognitive development, we propose a systematic Five-Level Cognitive Ladder that evaluates reasoning from single-rule understanding to multi-rule integration and conflict resolution, enabling quantitative assessment across cognitive stages. We further propose a Rule2Scene Agent that maps language-based traffic rules to dynamic driving scenes through rule crafting and scene generation, enabling scene-level traffic rule visual reasoning. Evaluations of 14 mainstream MLLMs reveal performance drops as task complexity grows, particularly during rule conflicts. After splitting the dataset and fine-tuning on the training set, we further observe substantial improvements in both traffic rule reasoning and downstream planning capabilities. These results highlight the effectiveness of DriveCombo in advancing compliant and intelligent autonomous driving systems.

cs.CV↗

arXiv2025

Image Denoising Using Global and Local Circulant Representation

The proliferation of imaging devices and countless image data generated every day impose an increasingly high demand on efficient and effective image denoising. In this paper, we establish a theoretical connection between principal component analysis (PCA) and the Haar transform under circulant representation, and present a computationally simple denoising algorithm. The proposed method, termed Haar-tSVD, exploits a unified tensor singular value decomposition (t-SVD) projection combined with Haar transform to efficiently capture global and local patch correlations. Haar-tSVD operates as a one-step, parallelizable plug-and-play denoiser that eliminates the need for learning local bases, thereby striking a balance between denoising speed and performance. Besides, an adaptive noise estimation scheme is introduced to improve robustness according to eigenvalue analysis of the circulant structure. To further enhance the performance under severe noise conditions, we integrate deep neural networks with Haar-tSVD based on the established Haar-PCA relationship. Experimental results on various denoising datasets demonstrate the efficiency and effectiveness of proposed method for noise removal. Our code is publicly available at https://github.com/ZhaomingKong/Haar-tSVD.

cs.CV↗

arXiv2025

CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving

End-to-end planning methods are the de facto standard of the current autonomous driving system, while the robustness of the data-driven approaches suffers due to the notorious long-tail problem (i.e., rare but safety-critical failure cases). In this work, we explore whether recent diffusion-based video generation methods (a.k.a. world models), paired with structured 3D layouts, can enable a fully automated pipeline to self-correct such failure cases. We first introduce an agent to simulate the role of product manager, dubbed PM-Agent, which formulates data requirements to collect data similar to the failure cases. Then, we use a generative model that can simulate both data collection and annotation. However, existing generative models struggle to generate high-fidelity data conditioned on 3D layouts. To address this, we propose DriveSora, which can generate spatiotemporally consistent videos aligned with the 3D annotations requested by PM-Agent. We integrate these components into our self-correcting agentic system, CorrectAD. Importantly, our pipeline is an end-to-end model-agnostic and can be applied to improve any end-to-end planner. Evaluated on both nuScenes and a more challenging in-house dataset across multiple end-to-end planners, CorrectAD corrects 62.5% and 49.8% of failure cases, reducing collision rates by 39% and 27%, respectively.

cs.CV↗

arXiv2025

Efficient Image Denoising Using Global and Local Circulant Representation

The advancement of imaging devices and countless image data generated everyday impose an increasingly high demand on efficient and effective image denoising. In this paper, we present a computationally simple denoising algorithm, termed Haar-tSVD, aiming to explore the nonlocal self-similarity prior and leverage the connection between principal component analysis (PCA) and the Haar transform under circulant representation. We show that global and local patch correlations can be effectively captured through a unified tensor-singular value decomposition (t-SVD) projection with the Haar transform. This results in a one-step, highly parallelizable filtering method that eliminates the need for learning local bases to represent image patches, striking a balance between denoising speed and performance. Furthermore, we introduce an adaptive noise estimation scheme based on a CNN estimator and eigenvalue analysis to enhance the robustness and adaptability of the proposed method. Experiments on different real-world denoising tasks validate the efficiency and effectiveness of Haar-tSVD for noise removal and detail preservation. Datasets, code and results are publicly available at https://github.com/ZhaomingKong/Haar-tSVD.

eess.IV↗

arXiv2025

Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models

Humans naturally possess the spatial reasoning ability to form and manipulate images and structures of objects in space. There is an increasing effort to endow Vision-Language Models (VLMs) with similar spatial reasoning capabilities. However, it remains unclear whether these models truly understand and manipulate spatial objects or not. To address this question, we propose a new evaluation framework aimed at assessing the performance of VLMs in spatial deformation reasoning tasks. Specifically, we construct a benchmark for spatial deformation reasoning from 2D to 3D. Leveraging our data engine, we can generate unlimited evaluation problem pairs with infinite steps, without any data leakage. We explore whether the model can effectively perform spatial deformation reasoning from two directions: forward reasoning (given the operations, find the final state) and reverse reasoning (given the final state, determine the operations). We adopt a ladder competition format, using the number of deformation steps as the level classification criterion, with the goal of exploring the boundaries of the model's deformation reasoning capabilities. Interestingly, the benchmarking results reveal that almost no model demonstrates plausible spatial deformation reasoning abilities. Furthermore, even after applying targeted training and mainstream reasoning enhancement methods, the models are still unable to perform well on 3D spatial deformation reasoning.

cs.CV↗

arXiv2025

SR-LLM: Rethinking the Structured Representation in Large Language Model

Structured representations, exemplified by Abstract Meaning Representation (AMR), have long been pivotal in computational linguistics. However, their role remains ambiguous in the Large Language Models (LLMs) era. Initial attempts to integrate structured representation into LLMs via a zero-shot setting yielded inferior performance. We hypothesize that such a decline stems from the structure information being passed into LLMs in a code format unfamiliar to LLMs' training corpora. Consequently, we propose SR-LLM, an innovative framework with two settings to explore a superior way of integrating structured representation with LLMs from training-free and training-dependent perspectives. The former integrates structural information through natural language descriptions in LLM prompts, whereas its counterpart augments the model's inference capability through fine-tuning on linguistically described structured representations. Performance improvements were observed in widely downstream datasets, with particularly notable gains of 3.17% and 12.38% in PAWS. To the best of our knowledge, this work represents the pioneering demonstration that leveraging structural representations can substantially enhance LLMs' inference capability. We hope that our work sheds light and encourages future research to enhance the reasoning and interoperability of LLMs by structure data.

cs.CL↗

arXiv2024

LangCell: Language-Cell Pre-training for Cell Identity Understanding

Cell identity encompasses various semantic aspects of a cell, including cell type, pathway information, disease information, and more, which are essential for biologists to gain insights into its biological characteristics. Understanding cell identity from the transcriptomic data, such as annotating cell types, has become an important task in bioinformatics. As these semantic aspects are determined by human experts, it is impossible for AI models to effectively carry out cell identity understanding tasks without the supervision signals provided by single-cell and label pairs. The single-cell pre-trained language models (PLMs) currently used for this task are trained only on a single modality, transcriptomics data, lack an understanding of cell identity knowledge. As a result, they have to be fine-tuned for downstream tasks and struggle when lacking labeled data with the desired semantic labels. To address this issue, we propose an innovative solution by constructing a unified representation of single-cell data and natural language during the pre-training phase, allowing the model to directly incorporate insights related to cell identity. More specifically, we introduce $\textbf{LangCell}$, the first $\textbf{Lang}$uage-$\textbf{Cell}$ pre-training framework. LangCell utilizes texts enriched with cell identity information to gain a profound comprehension of cross-modal knowledge. Results from experiments conducted on different benchmarks show that LangCell is the only single-cell PLM that can work effectively in zero-shot cell identity understanding scenarios, and also significantly outperforms existing models in few-shot and fine-tuning cell identity understanding scenarios.

q-bio.GN↗

arXiv2024

DeepCRE: Transforming Drug R&D via AI-Driven Cross-drug Response Evaluation

The fields of therapeutic application and drug research and development (R&D) both face substantial challenges, i.e., the therapeutic domain calls for more treatment alternatives, while numerous promising pre-clinical drugs have failed in clinical trials. One of the reasons is the inadequacy of Cross-drug Response Evaluation (CRE) during the late stages of drug R&D. Although in-silico CRE models bring a promising solution, existing methodologies are restricted to early stages of drug R&D, such as target and cell-line levels, offering limited improvement to clinical success rates. Herein, we introduce DeepCRE, a pioneering AI model designed to predict CRE effectively in the late stages of drug R&D. DeepCRE outperforms the existing best models by achieving an average performance improvement of 17.7% in patient-level CRE, and a 5-fold increase in indication-level CRE, facilitating more accurate personalized treatment predictions and better pharmaceutical value assessment for indications, respectively. Furthermore, DeepCRE has identified a set of six drug candidates that show significantly greater effectiveness than a comparator set of two approved drugs in 5/8 colorectal cancer organoids. This demonstrates the capability of DeepCRE to systematically uncover a spectrum of drug candidates with enhanced therapeutic effects, highlighting its potential to transform drug R&D.

cs.AI↗

arXiv2023

Towards Unified AI Drug Discovery with Multiple Knowledge Modalities

In recent years, AI models that mine intrinsic patterns from molecular structures and protein sequences have shown promise in accelerating drug discovery. However, these methods partly lag behind real-world pharmaceutical approaches of human experts that additionally grasp structured knowledge from knowledge bases and unstructured knowledge from biomedical literature. To bridge this gap, we propose KEDD, a unified, end-to-end, and multimodal deep learning framework that optimally incorporates both structured and unstructured knowledge for vast AI drug discovery tasks. The framework first extracts underlying characteristics from heterogeneous inputs, and then applies multimodal fusion for accurate prediction. To mitigate the problem of missing modalities, we leverage multi-head sparse attention and a modality masking mechanism to extract relevant information robustly. Benefiting from integrated knowledge, our framework achieves a deeper understanding of molecule entities, brings significant improvements over state-of-the-art methods on a wide range of tasks and benchmarks, and reveals its promising potential in assisting real-world drug discovery.

cs.LG↗

arXiv2023

BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine

Foundation models (FMs) have exhibited remarkable performance across a wide range of downstream tasks in many domains. Nevertheless, general-purpose FMs often face challenges when confronted with domain-specific problems, due to their limited access to the proprietary training data in a particular domain. In biomedicine, there are various biological modalities, such as molecules, proteins, and cells, which are encoded by the language of life and exhibit significant modality gaps with human natural language. In this paper, we introduce BioMedGPT, an open multimodal generative pre-trained transformer (GPT) for biomedicine, to bridge the gap between the language of life and human natural language. BioMedGPT allows users to easily ``communicate'' with diverse biological modalities through free text, which is the first of its kind. BioMedGPT aligns different biological modalities with natural language via a large generative language model, namely, BioMedGPT-LM. We publish BioMedGPT-10B, which unifies the feature spaces of molecules, proteins, and natural language via encoding and alignment. Through fine-tuning, BioMedGPT-10B outperforms or is on par with human and significantly larger general-purpose foundation models on the biomedical QA task. It also demonstrates promising performance in the molecule QA and protein QA tasks, which could greatly accelerate the discovery of new drugs and therapeutic targets. In addition, BioMedGPT-LM-7B is the first large generative language model based on Llama2 in the biomedical domain, therefore is commercial friendly. Both BioMedGPT-10B and BioMedGPT-LM-7B are open-sourced to the research community. In addition, we publish the datasets that are meticulously curated for the alignment of multi-modalities, i.e., PubChemQA and UniProtQA. All the models, codes, and datasets are available at \url{https://github.com/PharMolix/OpenBioMed}.

cs.CE↗

arXiv2023

Large-Scale Cell Representation Learning via Divide-and-Conquer Contrastive Learning

Single-cell RNA sequencing (scRNA-seq) data is a potent tool for comprehending the "language of life" and can provide insights into various downstream biomedical tasks. Large-scale language models (LLMs) are starting to be used for cell representation learning. However, current LLM-based cell representation learning methods depend solely on the BERT architecture, causing an anisotropic embedding space that leads to inefficient semantic representation. Contrastive learning alleviates this problem by distributing the embeddings uniformly. As a larger batch size in contrastive learning results in better representation, the practical application of contrastive learning in cell representation learning is hampered by the high dimensionality of scRNA-seq data and the large parameter volume of LLMs. To address the batch size limitation, we propose a novel divide-and-conquer contrastive learning approach to decouple the batch size from the GPU memory size for cell representation learning. Based on our divide-and-conquer contrastive learning approach, we introduce Single-Cell Language Model CellLM, a large-scale cell representation learning model to handle high-dimensional scRNA-seq data with tens of thousands of genes. CellLM has over 50 million parameters trained with 2 million scRNA-seq data and makes the first attempt to learn cell language models from both normal cells and cancer cells. CellLM achieves new state-of-the-art (SOTA) results in all evaluated downstream tasks: including a 71.8 F_1-score for cell type annotation (a 3.0% absolute improvement over scBERT), an average F_1-score of 88.9 for single-cell drug sensitivity prediction in a few-shot scenario (an 8.3% absolute improvement), and a 93.4 Pearson's correlation for single-omics cell line drug sensitivity prediction (a 6.2% absolute improvement).

cs.CE↗