arXiv subjects

Jiang Bian

Publications and source records attributed to Jiang Bian.

At least 19 recordsLinked to original sources

arXiv2026

MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching

Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluation benchmarks. Existing general-purpose benchmarks (e.g., MMLU and HELM) primarily assess broad knowledge and reasoning capabilities, but fail to capture critical domain requirements such as exercise safety, physiological appropriateness, personalization, and actionable coaching quality. This gap is particularly concerning in fitness and health applications, where incorrect or unsafe recommendations can lead to physical harm. To address this limitation, we introduce MoveBench, the first comprehensive benchmarking framework specifically designed for evaluating LLMs in sports and health coaching. The proposed benchmark integrates heterogeneous task formats, including multiple-choice questions (MCQs) and open-ended question answering (OpenQA), grounded in real-world user scenarios and paired with structured rubrics emphasizing safety compliance, scientific validity, and training logic. Through large-scale evaluation of 15 diverse LLMs on 809 questions with 5,012 rubric-level criteria, our results reveal substantial performance variability, particularly in safety awareness, structured program design, and personalization capability, highlighting a critical gap between knowing and doing. Our work establishes a foundational evaluation standard for sports and health LLM applications and provides a reproducible framework for advancing safe, reliable, and context-aware AI-driven coaching systems. Open resources are available at https://github.com/SatoSakula/MoveBench.

cs.AI↗

arXiv2026

Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey

This survey examines evaluation methods for large language model (LLM)-based agents in multi-turn conversational settings. Using a PRISMA-inspired framework, we systematically reviewed nearly 250 scholarly sources, capturing the state of the art from various venues of publication, and establishing a solid foundation for our analysis. Our study offers a structured approach by developing two interrelated taxonomy systems: one that defines \emph{what to evaluate} and another that explains \emph{how to evaluate}. The first taxonomy identifies key components of LLM-based agents for multi-turn conversations and their evaluation dimensions, including task completion, response quality, user experience, memory and context retention, as well as planning and tool integration. These components ensure that the performance of conversational agents is assessed in a holistic and meaningful manner. The second taxonomy system focuses on the evaluation methodologies. It categorizes approaches into annotation-based evaluations, automated metrics, hybrid strategies that combine human assessments with quantitative measures, and self-judging methods utilizing LLMs. This framework not only captures traditional metrics derived from language understanding, such as BLEU and ROUGE scores, but also incorporates advanced techniques that reflect the dynamic, interactive nature of multi-turn dialogues.

cs.CL↗

arXiv2026

Exploring Post-Training Alignment of Small Language Models for Biomedical Data-to-Text Generation: A Case Study of Medication Leaflet

Translating structured biomedical information into accurate, patient-friendly narratives remains a challenging biomedical data-to-text (D2T) task. While small language models (SLMs) are attractive for healthcare applications because of their lower computational cost, easier deployment, and improved data governance, the impact of post-training alignment on biomedical D2T generation has not been systematically studied. In this work, we compare four alignment methods: supervised fine-tuning (SFT), direct preference optimization (DPO), odds ratio preference optimization (ORPO), and group relative policy optimization (GRPO), using Qwen-2.5 models for medication leaflet generation. We further introduce FDALeaflets, a dataset derived from OpenFDA drug labels, to evaluate cross-regulatory generalization in a zero-shot setting. Selected aligned SLMs outperform GPT-5 on several reference-based metrics, whereas GPT-5 achieves better hallucination and adequacy scores on FDALeaflets under LLM-as-judge evaluation. Among RL-free alignment methods, ORPO achieves the best in-domain semantic performance, reaching a semantic textual similarity (STS) score of 0.9752. GRPO achieves the highest FDALeaflets STS (0.9407), exceeding GPT-5 (0.9295). These findings show that post-training alignment is a key factor in improving both semantic fidelity and generalization for biomedical D2T generation, while clinical safety and patient readability require human verification.

cs.CL↗

arXiv2026

Exploring Recurrent-Depth Language Models for Multitask Clinical Text Processing

Clinical natural language processing includes diverse tasks such as information extraction, classification, and question answering. Developing one model for all tasks could simplify deployment and improve knowledge transfer. We evaluated whether small recurrent-depth language models can meet this need through joint fine-tuning and compared their performance with standard transformers. We fine-tuned Ouro1.4B-Thinking, Ouro-2.6B-Thinking, HRM-Text-1B, Qwen3-1.7B, and Qwen3-8B on 9 datasets covering information extraction, classification, inference, and question answering, and evaluated them on four additional datasets excluded from training. Across these 13 datasets, Ouro-1.4B-Thinking achieved higher performances than Qwen3-1.7B on 11 datasets; Ouro-2.6BThinking was competitive with Qwen3-8B on most tasks. Ouro models showed the largest gains on inference and question answering, whereas HRM-Text-1B showed mixed results. These findings support further study of recurrent-depth models for clinical tasks through controlled experiments to isolate architectural effects and investigate how recurrent computation influences reasoning, knowledge acquisition, and generalization.

cs.CL↗

arXiv2026

SceneReVis: A Self-Reflective Vision-Grounded Framework for 3D Indoor Scene Synthesis via Multi-Turn RL

Current one-pass 3D scene synthesis methods often suffer from spatial hallucinations, such as collisions, due to a lack of deliberative reasoning. To bridge this gap, we introduce SceneReVis, a vision-grounded self-reflection framework that employs an iterative "diagnose-and-act" loop to explicitly intercept and resolve spatial conflicts using multi-modal feedback. To support this step-wise paradigm, we construct SceneChain-12k, a large-scale dataset of causal construction trajectories derived through a novel reverse engineering pipeline. We further propose a two-stage training recipe that transitions from Supervised Fine-Tuning to Agentic Reinforcement Learning, evolving the model into an active spatial planner. Extensive experiments demonstrate that SceneReVis achieves state-of-the-art performance in high-fidelity generation and goal-oriented optimization, with improved transfer to underrepresented room categories in the dataset and promising potential for extension to out-of-distribution room types.

cs.CV↗

arXiv2026

MedFeat: Model-Aware and Explainability-Driven Feature Engineering with LLMs for Tabular Prediction

In clinical tabular prediction, classical machine learning models with feature engineering often outperform neural methods. LLMs are increasingly used to automate this process, acting as domain experts that propose diverse feature transformations to boost downstream performance. However, the feature generation process of existing LLM-based methods is agnostic to the downstream learner: the LLM receives no signal about which features currently drive predictions or where the model's representational capacity falls short, so proposals are neither targeted to promising regions of the feature space nor tailored to the learner's inductive bias. This shortcoming is amplified in healthcare data, which simultaneously exhibits class imbalance, heterogeneous feature spaces, and strict interpretability requirements. In this paper, we propose MedFeat, the first feature engineering framework inspired by the workflow of machine learning practitioners, leveraging model-awareness and feature importance signals to iteratively guide feature discovery for clinical tabular learning. We evaluate MedFeat on a broad range of challenging real-world clinical tasks and show that it statistically significantly outperforms state-of-the-art baselines, with an average F1 improvement of more than 10% over the baseline across models with distinct inductive biases.

cs.LG↗

arXiv2026

Low latency global carbon budget reveals strong land sink recovery in 2025

The atmospheric CO2 growth rate fell sharply in 2025, from a record 3.76 $\pm$ 0.09 ppm yr-1 in 2024 to 2.06 $\pm$ 0.09 ppm yr-1 (NOAA marine boundary layer observations), below the 2015-2022 mean of 2.47 ppm yr-1, even as fossil CO2 emissions rose by 0.7% to 10.38 GtC yr-1. Here we present a low-latency global and regional carbon budget for 2025, combining three dynamic global vegetation models (DGVMs) and ocean model emulators with four atmospheric inversions constrained by OCO-2 satellite retrievals. The global net land sink reached 2.36 $\pm$ 0.16 GtC yr-1 in 2025 (DGVMs: 2.04 $\pm$ 0.24; inversions: 2.68 $\pm$ 0.20 GtC yr-1), strengthening by 2.81 $\pm$ 0.31 GtC yr-1 from 2024 and exceeding the 2015-2022 mean by 0.71 $\pm$ 0.13 GtC yr-1. Ocean uptake (3.11 $\pm$ 0.36 GtC yr-1) remained similar to 2024, making the land sink rebound the dominant driver of the slowdown in CO2 growth. Tropical lands shifted from net sources in 2024 to net sinks in 2025, with enhanced uptake across much of Africa and northern Eurasia, and land flux anomalies covaried with GRACE terrestrial water storage. Where the sink had weakened substantially in 2023-2024, about 80% of the area showed some recovery, with overall recovery of 87.3% (DGVMs) to 99.5% (inversions). Recovery exceeded 100% in the tropics but remained incomplete in the northern extratropics, indicating a strong but spatially uneven rebound of the land carbon sink.

physics.ao-ph↗

arXiv2026

MW-Nowcast: Six-hour ensemble nowcasting of extreme precipitation

Extending reliable nowcasting of extreme precipitation could provide critical additional time for warnings and emergency response during high-impact events such as flash floods. Radar-based generative machine-learning models have enabled skilful hyperlocal precipitation nowcasting, but accurate prediction of intense precipitation remains confined to the first few hours. Because storm-scale structure is predictable for longer than individual cells, a natural strategy is to predict that structure while generatively modelling only the uncertain local growth, decay, reorganisation and initiation of storms. Here we present Microsoft Weather Nowcast (MW-Nowcast), a six-hour ensemble radar nowcasting model that jointly learns a deterministic predictor to capture organised precipitation structure shared across ensemble members, and a generator to produce diverse local residuals around this shared prediction. Across independent test data from the United States, Europe and China, MW-Nowcast achieves higher detection skill than leading methods for heavy and extreme precipitation throughout the 6 h horizon. For the most intense rainfall, MW-Nowcast doubles the available warning time across all three regions, delivering 6 h forecasts with skill previously limited to 3 h for the leading generative baseline. A cost-loss decision analysis shows that MW-Nowcast retains substantial value for a broad range of applications even at 4-6 h, where alternative methods offer little benefit. These additional hours can give forecasters and emergency managers the time to warn and act before extreme rainfall strikes, helping to protect lives and property.

physics.ao-ph↗

arXiv2026

FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity

While the overall inference latency of Video Diffusion Transformers (DiTs) can be substantially reduced through model distillation, per-step inference latency remains a critical bottleneck. Existing acceleration paradigms primarily exploit redundancy across the denoising trajectory; however, we identify a limitation where these step-wise strategies encounter diminishing returns in few-step regimes. In such scenarios, fewer intermediate states can limit opportunities for feature reuse or predictive modeling, motivating complementary forms of acceleration. To overcome this, we propose Frame Interleaved Sparsity DiT (FIS-DiT), a training-free and operator-agnostic framework that shifts the optimization focus from the temporal trajectory to the latent frame dimension. Our approach is motivated by an intrinsic duality within this dimension: the existence of frame-wise sparsity that permits reduced computation, coupled with a structural consistency that calls for maintaining coverage of frame positions in the global spatiotemporal context. Leveraging this insight, we implement Frame Interleaved Sparsity (FIS) as an execution strategy that manipulates frame subsets across the model hierarchy, refreshing all latent positions without requiring full-scale block computation. Empirical evaluations on Wan 2.2 and HunyuanVideo 1.5 demonstrate that FIS-DiT reaches 2.4$\times$ speedup while maintaining comparable performance on VBench, providing a scalable and robust pathway toward real-time high-definition video generation.

cs.CV↗

arXiv2026

RefAdapt-DiT: Adaptive Joint Attention for Reference-Conditioned Diffusion Transformers

Diffusion Transformers (DiTs) have become the standard backbone for high-quality generative modeling, yet deploying them in conditional generation tasks remains computationally prohibitive because bidirectional joint attention repeatedly processes large reference streams. While existing optimization schemes mitigate generic temporal redundancy, they typically rely on coarse-grained static reuse and overlook the distinct dynamics of references and targets. Specifically, we observe that reference representations often evolve slowly along the generation trajectory, while the target often assigns little attention mass to them; reference drift and this target-to-reference exposure jointly shape how strongly stale reference states affect the target. To exploit these patterns, we introduce \RefAdapt, a training-free framework for adaptive control of joint attention between references and targets. Instead of rigid static strategies, \RefAdapt combines consecutive target-Q change with previously observed target-to-reference attention mass to control reference computation adaptively at block granularity. Under ultra-few-step settings, \RefAdapt enables speedups of up to $2.097\times$ on 4-step MiniMax H3 and $3.54\times$ on 8-step Qwen Image Edit, while maintaining comparable visual quality.

cs.CV↗

arXiv2026

LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches

Mathematical reasoning is a hallmark of human intelligence, and whether large language models (LLMs) can meaningfully perform it remains a central question in artificial intelligence and cognitive science. As LLMs are increasingly integrated into scientific workflows, rigorous evaluation of their mathematical capabilities becomes a practical necessity. Existing benchmarks are limited by synthetic settings and data contamination. We present LiveMathematicianBench, a dynamic multiple-choice benchmark for research-level mathematical reasoning built from recent arXiv papers published after model training cutoffs. By grounding evaluation in newly published theorems, it provides a realistic testbed beyond memorized patterns. The benchmark introduces a thirteen-category logical taxonomy of theorem types (e.g., implication, equivalence, existence, uniqueness), enabling fine-grained evaluation across reasoning forms. It employs a proof-sketch-guided distractor pipeline that uses high-level proof strategies to construct plausible but invalid answer choices reflecting misleading proof directions, increasing sensitivity to genuine understanding over surface-level matching. We also introduce a substitution-resistant mechanism to distinguish answer recognition from substantive reasoning. Evaluation shows the benchmark is far from saturated: Gemini-3.1-pro-preview, the best model, achieves only 43.5%. Under substitution-resistant evaluation, accuracy drops sharply: GPT-5.4 scores highest at 30.6%, while Gemini-3.1-pro-preview falls to 17.6%, below the 20% random baseline. A dual-mode protocol reveals that proof-sketch access yields consistent accuracy gains, suggesting models can leverage high-level proof strategies for reasoning. Overall, LiveMathematicianBench offers a scalable, contamination-resistant testbed for studying research-level mathematical reasoning in LLMs.

cs.CL↗

arXiv2026

Scientific Image Quality Assessment via Multi-modal Retrieval-Augmented Generation

This paper proposes a Retrieval-Augmented Generation (RAG) framework for scientific image quality assessment, designed to simultaneously address both the understanding track (SIQA-U) and the scoring track (SIQA-S) of the SIQA challenge. We construct a multimodal index that integrates textual semantics with fine-grained visual features, and develop a multi-route retrieval and fusion mechanism to provide large language models with highly relevant reference cases, thereby enhancing their capability to evaluate complex scientific images. Experimental results demonstrate that the proposed framework effectively aligns with the judgment criteria of human experts. Ultimately, our method achieves 1st place in the SIQA-U track of the SIQA challenge at the ICME 2026 Grand Challenges.

cs.CV↗

arXiv2026

SenSASP: A Unified, Multi-Layer Database of Senescence and SASP Genes

Research on cellular senescence and the senescence-associated secretory phenotype (SASP) draws on independently curated gene resources that differ in scope, identifiers, and update cycles, making cross-resource integration error-prone. We unified four widely used resources, CellAge, GenAge, the SenMayo signature, and the Reactome Cellular Senescence pathway, onto a single canonical identifier (the Ensembl gene ID) and enriched every gene with three annotation layers absent from all four inputs: cross-species conservation, tissue and cell-type expression, and high-confidence protein-protein interactions. Unification collapsed 1,460 summed source entries into 1,250 unique genes (210 redundant entries removed, 14.4%) while preserving full source provenance: 173 genes are corroborated by two or more resources and two (IL6, JUN) by all four. The three annotation layers reach 95.8%, 97.9%, and 93.0% of genes, with 89.4% annotated across all three. A 500-gene random sample of identifier mappings was validated against HGNC and Ensembl (98.0% exact match). The result, SenSASP, is a single, machine-readable, provenance-tracked database of harmonized identifiers and net-new functional context, illustrated here with a gene-prioritization score and a tissue-expression atlas. SenSASP is freely available at https://xuan13hao.github.io/sensasp/

q-bio.OT↗

arXiv2026

scPyviewer: a Python-native interactive viewer from AnnData single-cell data

Motivation: Interactive web tools enabling non-programmers to explore single-cell datasets, embeddings, gene expression, metadata, and marker genes are standard laboratory infrastructure. However, actively maintained tools (e.g., ShinyCell, ScRDAVis, sCIRCLE) rely on R Shiny and require Seurat objects. Python/scanpy, the dominant framework for single-cell RNA-seq and spatial analysis, lacks a lightweight, native option pairing a shareable viewer with a scriptable Python API. Sharing scanpy results currently requires converting to Seurat or sharing code notebooks. Results: We present scPyviewer, a web viewer that ingests AnnData objects directly and reproduces incumbent interaction patterns within the Python stack. In a feature-parity audit against three R Shiny tools, scPyviewer matches or exceeds baseline capabilities (7/7), uniquely offering native AnnData ingestion without conversion and cross-dataset comparison over shared genes and matched cell types. Benchmark tests across three datasets (22,315 to ~313,000 cells) show scPyviewer renders every core view faster (up to 3.6x speedup) using lower memory (5.2x lower on the smallest dataset). On 313,000 cells, scPyviewer completes all views while Seurat exhausts an 8 GB memory limit and fails. Beyond the app, scPyviewer exposes a Python API returning Matplotlib figures and pandas tables for publication-ready output. Availability and implementation: Implemented in Python 3.11 (scanpy 1.11.5, anndata 0.12.19, streamlit 1.59.2, plotly 6.9.0) with a one-command interface to reproduce benchmarks, figures, and launch the app. Source code: https://github.com/xuan13hao/scPyviewer.git

q-bio.GN↗

arXiv2026

Exploring Autonomous Agentic Data Engineering for Model Specialization

Large Language Models (LLMs) have demonstrated strong performance on general tasks, while often struggling to adapt to specialized domains without high-quality domain-specific data. Existing LLM-based data curation methods primarily rely on human-designed workflows, leaving it unexamined whether LLMs can autonomously execute an end-to-end data engineering pipeline for model specialization. We formalize Autonomous Agentic Data Engineering, a novel task designed to evaluate LLMs as autonomous data engineers that drive model specialization through end-to-end data curation. We frame data as an optimizable component and study agents that plan, generate, and iteratively optimize training data across multiple domains, guided by post-training performance improvement. Experiments show that autonomous LLM data engineers yield substantial gains, as GPT-5.2 constructs a training curriculum that improves a student model by 57.29%, entirely through iterative, agent-driven data adaptation. By illuminating both potential and bottlenecks, our study establishes autonomous data engineering as a measurable capability and charts a path toward agent-driven model specialization (Code will be released at https://github.com/zjunlp/DataAgent).

cs.CL↗

arXiv2026

DesignAsCode: Bridging Structural Editability and Visual Fidelity in Graphic Design Generation

Graphic design generation demands a delicate balance between high visual fidelity and fine-grained structural editability. However, existing approaches typically bifurcate into either non-editable raster image synthesis or abstract layout generation devoid of visual content. Recent combinations of these two approaches attempt to bridge this gap but often suffer from rigid composition schemas and unresolvable visual dissonances (e.g., text-background conflicts) due to their inexpressive representation and open-loop nature. To address these challenges, we propose DesignAsCode, a novel framework that reimagines graphic design as a programmatic synthesis task using HTML/CSS. Specifically, we introduce a Plan-Implement-Reflect pipeline, incorporating a Semantic Planner to construct dynamic, variable-depth element hierarchies and a Visual-Aware Reflection mechanism that optimizes the code to rectify rendering artifacts. Extensive experiments demonstrate that DesignAsCode significantly outperforms baselines in both structural validity and aesthetic quality. Furthermore, our code-native representation unlocks advanced capabilities, including automatic layout retargeting, complex document generation (e.g., resumes), and CSS-based animation. Our project page is available at https://liuziyuan1109.github.io/design-as-code/.

cs.GR↗

arXiv2026

ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models

Action-conditioned video world models require low-latency causal generation and reliable responses to game-native controls. Although causal distillation enables one- or few-step video synthesis, extending it to interactive world models remains challenging, as discrete keyboard states and continuous mouse motion must remain aligned with temporally compressed latent chunks during causal training and autoregressive rollout. We introduce ForgeWM, a progressive framework that transforms a bidirectional action-conditioned video generator into efficient few-step world models through domain adaptation, teacher-forced causal training, causal consistency distillation, and on-policy distribution matching with a bidirectional teacher. The resulting budget-specialized students operate at steady-state denoising budgets of 1, 2, and 4 steps. ForgeWM further supports a dual-path deployment protocol combining latency-critical interaction with optional replay-time refinement, where the one-step student re-noises and refines its saved draft. On paired Minecraft trajectories, ForgeWM leads the evaluated systems in Imaging Quality, reference-aligned motion-profile agreement, action-sign accuracy, and mouse-control accuracy, while achieving the lowest reference LPIPS; the same four-stage recipe transfers to gamepad-controlled FPS gameplay. Replay-time refinement matches four-step reference quality while remaining roughly three times closer to the experienced trajectory than regeneration from noise. These results demonstrate ForgeWM's effectiveness for controllable few-step video generation.

cs.CV↗

arXiv2026

An Agentic Generative Large Language Model for Treatment Planning of Colorectal Cancer

Treatment planning in precision oncology requires synthesizing heterogeneous patient information with rapidly evolving clinical guidelines to ensure guideline-concordant care. While large language models (LLMs) show promise in many diagnostic tasks, their adoption for high-stakes treatment planning is hindered by complex reasoning, adherence to timely clinical guidelines, and safety concerns. In this study, we present GatorOnco, an agentic LLM for colorectal cancer (CRC) treatment planning. GatorOnco is developed using a total of 282 billion tokens of biomedical text, including healthcare system-scale clinical text comprising 166 billion tokens from UF Health. We implemented a domain-adaptation method that integrates pre-training, model merging, a two-stage post-training approach, and agent-based reinforcement learning. An agentic retrieval-augmented generation (RAG) approach dynamically integrates time-sensitive clinical guidelines into the reasoning process. In a blind, randomized clinical evaluation conducted by five UF Health oncologists, GatorOnco significantly outperformed open-source LLMs (P < 0.01) and achieved expert-level performance comparable to UF Health oncologists. Compared with expert oncologists, GatorOnco received significantly higher ratings for readability (4.46 vs. 4.19, P < 0.01) and completeness (3.91 vs. 3.52, P < 0.01), while showing statistically comparable performance in correctness (4.09 vs. 4.11, P = 0.921), currency (4.04 vs. 3.98, P = 0.478), and safety (4.22 vs. 4.22, P = 0.999). These findings demonstrate that integrating agentic reasoning with large-scale domain adaptation can help bridge the gap for generative AI in high-stakes cancer treatment planning.

cs.CL↗