arXiv subjects

Qiao Jin

Publications and source records attributed to Qiao Jin.

At least 37 records · Page 2Linked to original sources

arXiv2026

SemanticVocoder: Bridging Audio Generation and Audio Understanding via Semantic Latents

Recent audio generation models typically rely on Variational Autoencoders (VAEs) and perform generation within the VAE latent space. Although VAEs excel at compression and reconstruction, their latents inherently encode low-level acoustic details rather than semantically discriminative information, leading to entangled event semantics and complicating the training of generative models. To address these issues, we discard VAE acoustic latents and introduce semantic encoder latents, thereby proposing SemanticVocoder, a generative vocoder that directly synthesizes waveforms from semantic latents. Equipped with SemanticVocoder, our text-to-audio generation model achieves a Frechet Distance of 12.823 and a Frechet Audio Distance of 1.709 on the AudioCaps test set, as the introduced semantic latents exhibit superior discriminability compared to acoustic VAE latents. Beyond improved generation performance, it also serves as a promising attempt towards unifying audio understanding and generation within a shared semantic space. Generated samples are available at https://zeyuxie29.github.io/SemanticVocoder/.

cs.SD↗

arXiv2026

CT-Bench: A Benchmark for Multimodal Lesion Understanding in Computed Tomography

Artificial intelligence (AI) can automatically delineate lesions on computed tomography (CT) and generate radiology report content, yet progress is limited by the scarcity of publicly available CT datasets with lesion-level annotations. To bridge this gap, we introduce CT-Bench, a first-of-its-kind benchmark dataset comprising two components: a Lesion Image and Metadata Set containing 20,335 lesions from 7,795 CT studies with bounding boxes, descriptions, and size information, and a multitask visual question answering benchmark with 2,850 QA pairs covering lesion localization, description, size estimation, and attribute categorization. Hard negative examples are included to reflect real-world diagnostic challenges. We evaluate multiple state-of-the-art multimodal models, including vision-language and medical CLIP variants, by comparing their performance to radiologist assessments, demonstrating the value of CT-Bench as a comprehensive benchmark for lesion analysis. Moreover, fine-tuning models on the Lesion Image and Metadata Set yields significant performance gains across both components, underscoring the clinical utility of CT-Bench.

cs.CV↗

arXiv2026

Benchmarking Retrieval-Augmented Generation for Chemistry

Retrieval-augmented generation (RAG) has emerged as a powerful framework for enhancing large language models (LLMs) with external knowledge, particularly in scientific domains that demand specialized and dynamic information. Despite its promise, the application of RAG in the chemistry domain remains underexplored, primarily due to the lack of high-quality, domain-specific corpora and well-curated evaluation benchmarks. In this work, we introduce ChemRAG-Bench, a comprehensive benchmark designed to systematically assess the effectiveness of RAG across a diverse set of chemistry-related tasks. The accompanying chemistry corpus integrates heterogeneous knowledge sources, including scientific literature, the PubChem database, PubMed abstracts, textbooks, and Wikipedia entries. In addition, we present ChemRAG-Toolkit, a modular and extensible RAG toolkit that supports five retrieval algorithms and eight LLMs. Using ChemRAG-Toolkit, we demonstrate that RAG yields a substantial performance gain -- achieving an average relative improvement of 17.4% over direct inference methods. We further conduct in-depth analyses on retriever architectures, corpus selection, and the number of retrieved passages, culminating in practical recommendations to guide future research and deployment of RAG systems in the chemistry domain. The code and data is available at https://chemrag.github.io.

cs.CL↗

arXiv2026

Sticky Help, Bounded Effects: Session-by-Session Analytics of Teacher Interventions in K-12 Classrooms

Teachers' in-the-moment support is a limited resource in technology-supported classrooms, and teachers must decide whom to help and when during ongoing student work. However, less is known about how students' prior help history (whether they were helped earlier) and their engagement states (e.g., idle, struggle) shape teachers' decisions, and whether observed learning benefits associated with teacher help extend beyond the current class session. To address these questions, we first conducted interviews with nine K-12 mathematics teachers to identify candidate decision factors for teacher help. We then analyzed 1.4 million student-system interactions from 339 students across 14 classes in the MATHia intelligent tutoring system by linking teacher-logged help events with fine-grained engagement states. Mixed-effects models show that students who received help earlier were more likely to receive additional help later, even after accounting for current engagement state. Cross-lagged panel analyses further show that teacher help recurred across sessions, whereas idle behavior did not receive sustained attention over time. Finally, help coincided with immediate learning within sessions, but did not predict skill acquisition in later sessions, as estimated by additive factor modeling. These findings suggest that teacher help is "sticky" in that it recurs for previously supported students, while its measurable learning benefits in our data are largely session-bound. We discuss implications for designing real-time analytics that track attention coverage and highlight under-visited students to support a more equitable and effective allocation of teacher attention.

cs.CY↗

arXiv2026

Secure Text Entry using a Virtual Radial Keyboard with Dynamically Resized Keys and Non-Intrusive Randomization

As virtual reality (VR) becomes more widely adopted, secure and efficient text entry is an increasingly critical need. In this paper, we identify a vulnerability in a state-of-the-art secure VR text entry method and introduce a novel virtual radial keyboard designed to achieve a balance between security with usability. Keys are arranged alphabetically in a circular layout, with each key selected by controller rotation and dynamically expanding to facilitate precise selection. A randomized rotation mechanism shifts the keyboard after each keystroke, preserving relative key positions while disrupting absolute spatial mappings to protect against inference attacks. We conducted a within-subject study (N=30) comparing our method with the prior secure technique and a standard QWERTY keyboard. Results showed that the radial keyboard significantly improves resistance to keystroke prediction attacks while incurring a tradeoff in entry speed and subjective workload due to the unfamiliar non-QWERTY layout. However, both quantitative trends and qualitative feedback indicate strong potential for performance improvements with practice. We also discuss design implications, possible interface refinements, and directions for future work, including layout variations and visual enhancements.

cs.HC↗

arXiv2025

DeepEvidence: Empowering Biomedical Discovery with Deep Knowledge Graph Research

Biomedical knowledge graphs (KGs) encode vast, heterogeneous information spanning literature, genes, pathways, drugs, diseases, and clinical trials, but leveraging them collectively for scientific discovery remains difficult. Their structural differences, continual evolution, and limited cross-resource alignment require substantial manual integration, limiting the depth and scale of knowledge exploration. We introduce DeepEvidence, an AI-agent framework designed to perform Deep Research across various heterogeneous biomedical KGs. Unlike generic Deep Research systems that rely primarily on internet-scale text, DeepEvidence incorporates specialized knowledge-graph tooling and coordinated exploration strategies to systematically bridge heterogeneous resources. At its core is an orchestrator that directs two complementary agents: Breadth-First ReSearch (BFRS) for broad, multi-graph entity search, and Depth-First ReSearch (DFRS) for multi-hop, evidence-focused reasoning. An internal, incrementally built evidence graph provides a structured record of retrieved entities, relations, and supporting evidence. To operate at scale, DeepEvidence includes unified interfaces for querying diverse biomedical APIs and an execution sandbox that enables programmatic data retrieval, extraction, and analysis. Across established deep-reasoning benchmarks and four key stages of the biomedical discovery lifecycle: drug discovery, pre-clinical experimentation, clinical trial development, and evidence-based medicine, DeepEvidence demonstrates substantial gains in systematic exploration and evidence synthesis. These results highlight the potential of knowledge-graph-driven Deep Research to accelerate biomedical discovery.

cs.IR↗

arXiv2025

Observation of square-like moire lattice and quasicrystalline order in twisted rock-salt nitrides

Twistronics, which exploits moire modulation of lattice and electronic structures in twisted bilayers, has emerged as a powerful approach to engineer novel quantum states. Recent efforts have expanded beyond two dimensional van der Waals (vdWs) crystals to more complex, strongly correlated materials, where interfacial moire effects can dominate physical properties. Here we demonstrate a generalizable route to fabricate twisted bilayers of transition metal nitrides with vdWs like interfaces, using freestanding CrN membranes as a model system. Twisted bilayer CrN (tCrN) is realized by employing cubic alkaline earth metal monoxides as sacrificial layers, enabling the assembly of clean, controllable interfaces. Electron ptychography reveals well defined, periodic square moire superlattices in tCrN. For a twist angle of 16.3 degree, we identify a nearly commensurate moire lattice with coincident Cr columns, whereas at 45 degree we uncover localized octagonal quasicrystalline order with clear self-similarity. These results establish a practical platform for twisted TMNs and open avenues to explore moire-induced atomic configurations and emergent correlated phenomena in nitride based heterostructures.

cond-mat.mtrl-sci↗

arXiv2025

Developing Large Language Models for Clinical Research Using One Million Clinical Trials

Developing artificial intelligence (AI) for clinical research requires a comprehensive data foundation that supports model training and rigorous evaluation. Here, we introduce TrialPanorama, a large-scale structured resource that aggregates 1.6M clinical trial records from fifteen global registries and links them with biomedical ontologies and associated literature. To demonstrate its utility, we build a pipeline that constructs 152K training and testing samples for eight key clinical research tasks. Three tasks support systematic review workflows, including study search, study screening, and evidence summarization. Five tasks focus on trial design and optimization, including arm design, eligibility criteria design, endpoint selection, sample size estimation, and trial completion assessment and rationalization. Benchmarking cutting-edge large language models (LLMs) reveals that generic LLMs have limited capability in clinical reasoning. In contrast, an 8B LLM we developed on TrialPanorama using supervised finetuning and reinforcement learning wins over the 70B generic counterparts in all eight tasks, with a relative improvement of 73.7%, 67.6%, 38.4%, 37.8%, 26.5%, 20.7%, 20.0%, 18.1%, and 5.2%, respectively. We envision that TrialPanorama provides a solid foundation for future scaling of AI for clinical research.

cs.AI↗

arXiv2025

GenLARP: Enabling Immersive Live Action Role-Play through LLM-Generated Worlds and Characters

We introduce GenLARP, a virtual reality (VR) system that transforms personalized stories into immersive live action role-playing (LARP) experiences. GenLARP enables users to act as both creators and players, allowing them to design characters based on their descriptions and live in the story world. Generative AI and agents powered by Large Language Models (LLMs) enrich these experiences.

cs.HC↗

arXiv2025

Gene-R1: Reasoning with Data-Augmented Lightweight LLMs for Gene Set Analysis

The gene set analysis (GSA) is a foundational approach for uncovering the molecular functions associated with a group of genes. Recently, LLM-powered methods have emerged to annotate gene sets with biological functions together with coherent explanatory insights. However, existing studies primarily focus on proprietary models, which have been shown to outperform their open-source counterparts despite concerns over cost and data privacy. Furthermore, no research has investigated the application of advanced reasoning strategies to the GSA task. To address this gap, we introduce Gene-R1, a data-augmented learning framework that equips lightweight and open-source LLMs with step-by-step reasoning capabilities tailored to GSA. Experiments on 1,508 in-distribution gene sets demonstrate that Gene-R1 achieves substantial performance gains, matching commercial LLMs. On 106 out-of-distribution gene sets, Gene-R1 performs comparably to both commercial and large-scale LLMs, exhibiting robust generalizability across diverse gene sources.

q-bio.GN↗

arXiv2025

Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy

AI scientists powered by large language models have demonstrated substantial promise in autonomously conducting experiments and facilitating scientific discoveries across various disciplines. While their capabilities are promising, these agents also introduce novel vulnerabilities that require careful consideration for safety. However, there has been limited comprehensive exploration of these vulnerabilities. This perspective examines vulnerabilities in AI scientists, shedding light on potential risks associated with their misuse, and emphasizing the need for safety measures. We begin by providing an overview of the potential risks inherent to AI scientists, taking into account user intent, the specific scientific domain, and their potential impact on the external environment. Then, we explore the underlying causes of these vulnerabilities and provide a scoping review of the limited existing works. Based on our analysis, we propose a triadic framework involving human regulation, agent alignment, and an understanding of environmental feedback (agent regulation) to mitigate these identified risks. Furthermore, we highlight the limitations and challenges associated with safeguarding AI scientists and advocate for the development of improved models, robust benchmarks, and comprehensive regulations.

cs.CY↗

arXiv2025

T-SVG: Text-Driven Stereoscopic Video Generation

The advent of stereoscopic videos has opened new horizons in multimedia, particularly in extended reality (XR) and virtual reality (VR) applications, where immersive content captivates audiences across various platforms. Despite its growing popularity, producing stereoscopic videos remains challenging due to the technical complexities involved in generating stereo parallax. This refers to the positional differences of objects viewed from two distinct perspectives and is crucial for creating depth perception. This complex process poses significant challenges for creators aiming to deliver convincing and engaging presentations. To address these challenges, this paper introduces the Text-driven Stereoscopic Video Generation (T-SVG) system. This innovative, model-agnostic, zero-shot approach streamlines video generation by using text prompts to create reference videos. These videos are transformed into 3D point cloud sequences, which are rendered from two perspectives with subtle parallax differences, achieving a natural stereoscopic effect. T-SVG represents a significant advancement in stereoscopic content creation by integrating state-of-the-art, training-free techniques in text-to-video generation, depth estimation, and video inpainting. Its flexible architecture ensures high efficiency and user-friendliness, allowing seamless updates with newer models without retraining. By simplifying the production pipeline, T-SVG makes stereoscopic video generation accessible to a broader audience, demonstrating its potential to revolutionize the field.

cs.CV↗

arXiv2025

MedCite: Can Language Models Generate Verifiable Text for Medicine?

Existing LLM-based medical question-answering systems lack citation generation and evaluation capabilities, raising concerns about their adoption in practice. In this work, we introduce \name, the first end-to-end framework that facilitates the design and evaluation of citation generation with LLMs for medical tasks. Meanwhile, we introduce a novel multi-pass retrieval-citation method that generates high-quality citations. Our evaluation highlights the challenges and opportunities of citation generation for medical tasks, while identifying important design choices that have a significant impact on the final citation quality. Our proposed method achieves superior citation precision and recall improvements compared to strong baseline methods, and we show that evaluation results correlate well with annotation results from professional experts.

cs.CL↗

arXiv2025

Knowledge-guided Contextual Gene Set Analysis Using Large Language Models

Gene set analysis (GSA) is a foundational approach for interpreting genomic data of diseases by linking genes to biological processes. However, conventional GSA methods overlook clinical context of the analyses, often generating long lists of enriched pathways with redundant, nonspecific, or irrelevant results. Interpreting these requires extensive, ad-hoc manual effort, reducing both reliability and reproducibility. To address this limitation, we introduce cGSA, a novel AI-driven framework that enhances GSA by incorporating context-aware pathway prioritization. cGSA integrates gene cluster detection, enrichment analysis, and large language models to identify pathways that are not only statistically significant but also biologically meaningful. Benchmarking on 102 manually curated gene sets across 19 diseases and ten disease-related biological mechanisms shows that cGSA outperforms baseline methods by over 30%, with expert validation confirming its increased precision and interpretability. Two independent case studies in melanoma and breast cancer further demonstrate its potential to uncover context-specific insights and support targeted hypothesis generation.

q-bio.GN↗

arXiv2025

Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning

Cell type annotation is a key task in analyzing the heterogeneity of single-cell RNA sequencing data. Although recent foundation models automate this process, they typically annotate cells independently, without considering batch-level cellular context or providing explanatory reasoning. In contrast, human experts often annotate distinct cell types for different cell clusters based on their domain knowledge. To mimic this workflow, we introduce the CellPuzzles task, where the objective is to assign unique cell types to a batch of cells. This benchmark spans diverse tissues, diseases, and donor conditions, and requires reasoning across the batch-level cellular context to ensure label uniqueness. We find that off-the-shelf large language models (LLMs) struggle on CellPuzzles, with the best baseline (OpenAI's o1) achieving only 19.0% batch-level accuracy. To fill this gap, we propose Cell-o1, a 7B LLM trained via supervised fine-tuning on distilled reasoning traces, followed by reinforcement learning with batch-level rewards. Cell-o1 achieves state-of-the-art performance, outperforming o1 by over 73% and generalizing well across contexts. Further analysis of training dynamics and reasoning behaviors provides insights into batch-level annotation performance and emergent expert-like reasoning. Code and data are available at https://github.com/ncbi-nlp/cell-o1.

cs.CL↗

arXiv2025

Advancing Antiferromagnetic Nitrides via Metal Alloy Nitridation

Nitride materials, valued for their structural stability and exceptional physical properties, have garnered significant interest in both fundamental research and technological applications. The fabrication of high-quality nitride thin films is essential for advancing their use in microelectronics and spintronics. Yet, achieving single-crystal nitride thin films with excellent structural integrity remains a challenge. Here, we introduce a straightforward yet innovative metallic alloy nitridation technique for the synthesis of stable single-crystal nitride thin films. By subjecting metal alloy thin films to a controlled nitridation process, nitrogen atoms integrate into the lattice, driving structural transformations while preserving high epitaxial quality. Combining nanoscale magnetic imaging with a diamond nitrogen-vacancy (NV) probe, X-ray magnetic linear dichroism, and comprehensive transport measurements, we confirm that the nitridated films exhibit a robust antiferromagnetic character with a zero net magnetic moment. This work not only provides a refined and reproducible strategy for the fabrication of nitride thin films but also lays a robust foundation for exploring their burgeoning device applications.

cond-mat.mtrl-sci↗

arXiv2025

Benchmarking large language models for biomedical natural language processing applications and recommendations

The rapid growth of biomedical literature poses challenges for manual knowledge curation and synthesis. Biomedical Natural Language Processing (BioNLP) automates the process. While Large Language Models (LLMs) have shown promise in general domains, their effectiveness in BioNLP tasks remains unclear due to limited benchmarks and practical guidelines. We perform a systematic evaluation of four LLMs, GPT and LLaMA representatives on 12 BioNLP benchmarks across six applications. We compare their zero-shot, few-shot, and fine-tuning performance with traditional fine-tuning of BERT or BART models. We examine inconsistencies, missing information, hallucinations, and perform cost analysis. Here we show that traditional fine-tuning outperforms zero or few shot LLMs in most tasks. However, closed-source LLMs like GPT-4 excel in reasoning-related tasks such as medical question answering. Open source LLMs still require fine-tuning to close performance gaps. We find issues like missing information and hallucinations in LLM outputs. These results offer practical insights for applying LLMs in BioNLP.

cs.CL↗

arXiv2025

A single-phase epitaxially grown ferroelectric perovskite nitride

The integration of ferroelectrics with semiconductors is crucial for developing functional devices, such as field-effect transistors, tunnel junctions, and nonvolatile memories. However, the synthesis of high-quality single-crystalline ferroelectric nitride perovskites has been limited, hindering a comprehensive understanding of their switching dynamics and potential applications. Here we report the synthesis and characterizations of epitaxial single-phase ferroelectric cerium tantalum nitride (CeTaN3) on both oxides and semiconductors. The polar symmetry of CeTaN3 was confirmed by observing the atomic displacement of central ions relative to the center of the TaN6 octahedra, as well as through optical second harmonic generation. We observed switchable ferroelectric domains in CeTaN3 films using piezo-response force microscopy, complemented by the characterization of square-like polarization-electric field hysteresis loops. The remanent polarization of CeTaN3 reaches approximately 20 uC/cm2 at room temperature, consistent with theoretical calculations. This work establishes a vital link between ferroelectric nitride perovskites and their practical applications, paving the way for next-generation information and energy-storage devices with enhanced performance, scalability, and manufacturability.

cond-mat.mtrl-sci↗