Searcharxiv⌕ Search

arXiv subjects

Jiang Bian

Publications and source records attributed to Jiang Bian.

At least 19 recordsLinked to original sources
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↗
arXiv2026

Studying Competing Events with Federated Cumulative Incidence Curves

Combining electronic health record (EHR) data from multiple institutions is a valuable strategy for conducting post-market safety surveillance of medical products, but privacy concerns limit sharing individual-level data. We develop a novel federated learning (FL) method for multi-site post-market safety surveillance of medical products using competing risks data. We apply this method to study immune-related adverse events (irAEs) following treatment with immune checkpoint inhibitors (ICIs) in patients with auto-immune disease (AID). We provide an algorithm for constructing non-parametric cumulative incidence curves for competing event types, which can be used to compare exposure groups (e.g. treated and untreated) with no sharing of patient-level data across institutions. We incorporate covariate adjustment via inverse propensity weighting, and informative causal comparison using the area under cumulative incidence curves, known as restricted mean time lost. We apply our method to $N=10,281$ cancer patients with no pre-existing endocrine-related AID receiving ICIs across $K=10$ sites from the OneFlorida+ network, comparing patients with a pre-existing non-endocrine AID to those with no pre-existing AID. After covariate adjustment, we found that patients with a pre-existing non-endocrine AID lost 4.8 [95% CI: 4.3,5.2] months of event-free survival time to endocrine irAEs in the first 18 months following treatment, compared to 3.2 [95% CI: 3.1,3.3] months in the group without prior AID. As patients with prior AID were initially excluded from clinical trials of ICIs, our findings provide important new information to clinicians and patients receiving or considering ICI treatment. Our proposed non-parametric federated algorithm is the first to allow investigators to use some of the most crucial non-parametric tools for conducting postmarket safety surveillance across multiple institutions.

stat.ME↗
arXiv2026

Fracture Risk Prediction in Adults Over 50 Years Old Using DXA and EHR: Comparison of Traditional and Machine Learning Models in Two Large Cohorts

Accurate fracture risk prediction is important for osteoporosis management, but commonly used clinical tools may not fully use information available in electronic health records (EHRs) and dual-energy X-ray absorptiometry (DXA) reports. We developed and externally validated time-to-event fracture prediction models among adults aged 50 years or older with clinically obtained DXA reports in 2 US health care systems. The development cohort was derived from NewYork-Presbyterian/Weill Cornell Medical Center and the external validation cohort from the Indiana Network for Patient Care. Predictors included demographics, lifestyle factors, prior fracture, comorbidities, medication exposures, osteoporosis treatment history, and DXA-derived T-scores extracted from radiology reports. The outcome was time from index DXA to first incident fragility fracture identified from structured diagnosis codes. We evaluated penalized Cox regression, random survival forest, gradient-boosting survival, and XGBoost survival models using 2 prespecified predictor settings and compared discrimination with clinically reported FRAX major osteoporotic fracture probabilities. The development cohort included 11,510 adults, of whom 858 sustained incident fragility fractures; the external validation cohort included 1,932 adults, of whom 180 sustained fractures. In internal validation, the expanded Cox model achieved a mean Harrell C-index of 0.779, compared with 0.653 for FRAX. In external validation, the corresponding Cox model achieved a Harrell C-index of 0.714, compared with 0.590 for FRAX; gradient-boosting survival had the highest external discrimination (0.725). EHR- and DXA-enhanced models showed better discrimination than clinically reported FRAX scores in this DXA-tested population, but calibration assessment, prospective evaluation, and implementation workflow assessment are needed before clinical use.

stat.AP↗
arXiv2026

Privacy-preserving causal mediation analysis using distributed electronic health record networks

Electronic health record (EHR) networks provide unprecedented opportunities to study treatment mechanisms at scale, but mediation analyses across institutions are often hindered by privacy and governance constraints that restrict sharing of patient-level data. We developed a privacy-preserving federated mediation framework that enables estimation of natural direct and indirect effects without exchanging individual-level records across participating sites. The proposed approach integrates renewable learning with counterfactual causal mediation analysis, allowing institutions to collaboratively investigate treatment mechanisms using only low-dimensional summary statistics. Both simulation studies and the real-world application demonstrated that the federated estimator closely reproduced pooled-data results while preserving patient privacy. We applied the method to 32,146 patients in the Indiana Network for Patient Care to evaluate the extent to which body mass index (BMI) mediates the effect of GLP-1 receptor agonist on glycated hemoglobin (HbA1c) reduction. The BMI-mediated pathway accounted for only a small proportion of the overall treatment effect, suggesting that most glycemic improvement occurred through mechanisms other than weight loss.

stat.AP↗
arXiv2026

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

Translating complex biomedical data into patient-friendly narratives is central to modern biomedical informatics. This study presents a comparative analysis of training small language models (SLMs) in specialized biomedical datato-text generation tasks. We explore widely adopted post-training methods including supervised fine-tuning (SFT), direct preference optimization (DPO), odds ratio preference optimization (ORPO), and group relative policy optimization (GRPO) with Qwen-based SLMs on a medicine package leaflets dataset. To assess cross-dataset generalizability, we also curated drug label data from openFDA. We evaluate models using both standard lexical overlap metrics like ROUGE as well as semantic similarity measures. Across our experiments, the results show that (1) the aligned SLMs outperform proprietary models like GPT-5; (2) ORPO outperforms the SFTbaselines; (3) GRPO yields the most robust cross-dataset performance among the alignment methods tested as well as GPT-5.

cs.CL↗
arXiv2026

MonteRET: AI Agent Enhancing Multimodal LLMs with Multi-granularity Knowledge Retrieval for Chest CT Report Generation

Automated chest CT report generation remains challenging because clinically faithful reporting requires both whole-volume understanding and accurate description of localized anatomical findings. Here we developed and retrospectively evaluated MonteRET, a region-aware retrieval-enhanced framework for generating chest CT findings sections. MonteRET integrates global CT features with region-level anatomical representations, retrieves clinically relevant knowledge using predicted medical conditions and region-level vision-language alignment, and refines initial reports through a knowledge-guided report rewriting agent. We trained our model on a public cohort with 24,128 CT scans from RadGenome-ChestCT. We evaluated MonteRET on the public RadGenome-ChestCT test set of 1,564 CT scans and an external cohort of 82 CT scans from NewYork-Presbyterian/Weill Cornell Medical Center. MonteRET improved report quality, semantic similarity, and clinical efficacy compared with a matched baseline and several state-of-the-art methods. Gains were most pronounced for recall, suggesting fewer omitted findings. Human expert evaluation by radiology residents also favored MonteRET.

cs.CV↗
arXiv2026

The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning

Knowledge distillation from powerful reasoning models is widely used to improve Small Language Models (SLMs) on mathematical reasoning, often assuming that traces with higher reward model scores provide more useful supervision. We identify a counterintuitive \textbf{Quality-Utility Paradox} in mathematical reasoning distillation. Data refined or synthesized by a stronger Oracle obtains higher perceived quality according to reward models, yet consistently underperforms traces generated by the SLM itself and selected through rejection sampling across Qwen2.5, LLaMA-3, and DeepSeek families. Our analysis shows that Oracle refinement couples logical repair with distributional drift away from the SLM's native reasoning distribution. This drift increases the learner's adaptation cost and can outweigh the benefit of improved reasoning logic. To test this mechanism, we introduce \textbf{Style-Aligned Refinement}, which preserves the native trajectory of the SLM while retaining logical repair from the Oracle. This intervention lowers adaptation cost and restores downstream utility. These findings suggest that effective mathematical reasoning distillation should jointly optimize perceived solution quality and learner-data compatibility, rather than relying solely on reward-model scores. The datasets and code are available at https://github.com/Dracoqhl/Quality-Utility-Paradox.

cs.AI↗
arXiv2026

SkillWiki: A Living Knowledge Infrastructure for Agent Skills

While knowledge is managed through Wikipedia and software through GitHub, agent skills still lack an infrastructure for large-scale production, governance, and evolution. SkillWiki is a living knowledge infrastructure that supports the organization, grounding, and continuous evolution of agent skills by transforming heterogeneous knowledge into reusable skill assets linked to their originating evidence. Our demonstration presents the complete skill lifecycle, from knowledge ingestion and skill production to provenance-aware exploration, governance, and execution-driven evolution. SkillWiki highlights a future in which knowledge, skills, and execution experience co-evolve within a shared infrastructure. The live demonstration and source code are publicly available at https://github.com/Huangdingcheng/SkillWiki.

cs.CL↗
arXiv2026

OmniBioTwin: A System-of-Twinned-Systems Framework for Health Digital Twins

Health digital twins (HDTs) promise patient-specific modeling and decision support but current approaches remain structurally fragmented: monolithic models that address a single organ or task lack cross-scale fidelity, while system-level twins lack generalizable architectural frameworks. We propose OmniBioTwin, a System-of-Twinned-Systems (SoTS) framework that organizes HDTs as modular computational entities coupled through explicit interaction operators within a multi-layer network architecture. The framework comprises seven coordinated layers - spanning data integration, autonomous twin modeling, cross-scale coupling, temporal synchronization, and human-in-the-loop decision support. We demonstrate OmniBioTwin by instantiating a multiscale twin for glucagon-like peptide-1 (GLP-1) signaling pathways in Alzheimer's disease, illustrating how molecular, cellular, and organ-level twins can be composed and coupled within a unified system.

q-bio.QM↗
arXiv2026

PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment

Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final correctness but provide limited guidance on which intermediate reasoning steps or tool interactions contribute to the outcome. The difficulty is especially pronounced in multi-turn search agents, where successful trajectories may contain misleading actions and failed trajectories may contain valuable evidence-gathering steps. We propose PBSD (Privileged Bayesian Self-Distillation), a Bayes-calibrated self-distillation method for fine-grained credit assignment under sparse final rewards. PBSD measures trajectory quality through the posterior-to-prior probability ratio of the verified answer and applies Bayes' rule to convert this hard-to-estimate answer-side ratio into a tractable likelihood ratio between a standard student model and a privileged answer-conditioned teacher model. Autoregressive decomposition of this Bayesian evidence score yields turn-level signals that identify whether each intermediate turn supports or undermines the verified outcome. Consequently, PBSD provides a principled and elegant reweighting scheme that transforms sparse outcome supervision into Bayes-calibrated turn-level credit signals, while remaining fully compatible with standard policy optimization. Experiments demonstrate that PBSD consistently enhances performance across both in-domain and out-of-domain settings, and effectively transfers knowledge from short-context training to long-context inference, suggesting that its fine-grained credit assignment mechanism facilitates more effective policy learning and yields improved generalization.

cs.LG↗
arXiv2026

Multi-Granularity 3D Kidney Lesion Characterization from CT Volumes

Radiology reports describe kidney lesions by type, size, enhancement, and attenuation, yet existing 3D methods predict only at the patient or organ level. We reformulate kidney CT characterization as a per-lesion set-prediction task: one model emits a variable number of lesions per kidney, each with four clinical attributes. We curated 2,619 CT volumes from 788 patients at one academic medical center, with multi-granularity side- and per-lesion labels, and used KiTS23 (489 cases) for zero-shot external validation. We propose \textbf{LesionDETR}, a DETR-style architecture with size-distance Hungarian matching and a hierarchical loss that aggregates per-slot outputs to side-level objectives. Across four input representations and six encoder initializations, two design choices dominate: a segmentation mask as an input channel, and same-domain abdominal pretraining (SuPreM); generic large-corpus pretraining is no better than random initialization. LesionDETR reaches bilateral side-level abnormality AUC $0.799 \pm 0.009$ on UF-Health and $0.817 \pm 0.072$ on KiTS23. A count-conditioned variant reaches per-lesion mAP $0.190 \pm 0.083$ on cystic lesions; rare solid-lesion AP stays at the noise floor, pointing to targeted data collection, not architecture, as the next bottleneck. The framework yields verified per-lesion predictions for downstream structured report generation.

cs.CV↗
arXiv2026

Foundation VAEs for 3D CT Reconstruction, Augmentation, and Generation

Variational autoencoders (VAEs) compress high resolution CT volumes into compact latents while preserving clinically relevant structure. However, training CT-specific VAEs from scratch or heavily fine-tuning them incurs substantial computational and engineering cost, and often degrades under heterogeneous scanners, protocols, and diseases. This paper makes a progressive stride toward training-free medical VAEs by leveraging a critical observation: a single Foundation VAE, pretrained at scale on natural images and videos, can serve as a unified interface for CT Reconstruction, Augmentation, and Generation. With both encoder and decoder frozen, the Foundation VAE reconstructs CT volumes with preserved anatomy while suppressing acquisition noise; training segmentation models on these reconstructions improves surface accuracy by 3.9% NSD on average for pancreatic tumor and lung tumor. Within the same Foundation VAE latent space, a conditional latent diffusion model achieves 3.9% lower average FVD with 36.2% higher CT CLIP score, and improves multi-disease generation faithfulness across 18 types by 2.76% AUC. These results demonstrate Foundation VAEs as a practical interface for scalable CT representation reuse and faithful CT generation. Our code and demo are available at https://github.com/qic999/Foundation-VAE.

cs.CV↗
arXiv2026

Battery-Sim-Agent: Leveraging LLM-Agent for Inverse Battery Parameter Estimation

Parameterizing high-fidelity "digital twins" of batteries is a critical yet challenging inverse problem that hinders the pace of battery innovation. Prevailing methods formulate this as a black-box optimization (BBO) task, employing algorithms that are sample-inefficient and blind to the underlying physics. In this work, we introduce a new paradigm that reframes the inverse problem as a reasoning task, and present Battery-Sim-Agent, the first framework to deploy a Large Language Model (LLM) agent in a closed loop with a high-fidelity battery simulator. The agent mimics a human scientist's workflow: it interprets rich, multi-modal feedback from the simulator, forms physically-grounded hypotheses to explain discrepancies, and proposes structured parameter updates. On a systematically constructed benchmark suite spanning diverse battery chemistries, operating conditions, and difficulty levels, our agent significantly outperforms strong BBO baselines like Bayesian optimization in identifying accurate parameters. We further demonstrate the framework's capability in complex long-horizon degradation fitting tasks and validate its practical applicability on real-world battery datasets. Our results highlight the promise of LLM-agents as reasoning-based optimizers for scientific discovery and battery parameter estimation.

cs.AI↗
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

Skillful high-resolution weather forecasting independent of physical models

Accurate and timely weather forecasts are critical for high-impact decisions in modern society. Machine-learning-based weather prediction is emerging as an alternative for producing initial conditions, forecasts, and even both in end-to-end systems. These methods deliver predictions faster and often with higher skill than traditional numerical weather prediction (NWP). However, even end-to-end models typically rely on NWP-generated reanalyses for supervision, thereby inheriting the biases and resolution limitations of those NWPs, and limiting adaptation to settings where suitable reanalysis products are unavailable, infrequently updated, or expensive to produce. Here we introduce ObsCast, a regional system that generates both analysis and predictions, without using any NWP-derived data in either training or inference, while still achieving state-of-the-art performance in short-term high-resolution regional modeling. Over the contiguous United States and Europe, ObsCast outperforms operational NWP for near-surface variables through 18 h and produces skillful precipitation forecasts. It provides a simpler and more adaptable route to build and refine regional forecasting services directly from local observations, without the need to develop complex and costly traditional forecasting pipelines.

physics.ao-ph↗
arXiv2026

What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models

Reinforcement learning (RL) fine-tuning has shown promise for Vision-Language-Action (VLA) models in robotic manipulation, but deployment-time visual shifts pose practical challenges. A key difficulty is that standard task rewards supervise task success, but offer limited guidance on whether a visual change is task-irrelevant or changes the behavior required for manipulation. We propose PAIR-VLA (Paired Action Invariance & Sensitivity for Visually Robust VLA), an RL fine-tuning framework to address this difficulty by adding two auxiliary objectives over paired visual variants during PPO optimization: an invariance term that reduces the discrepancy between action distributions for a task-preserving pair (e.g., different distractors), and a sensitivity objective that encourages separable action distributions for a task-altering pair (e.g., target object in a different pose). Together, these objectives turn visual variants from mere observation diversity into behavior-level guidance on policy responses during RL fine-tuning. We evaluate on ManiSkill3 across two representative VLA architectures, OpenVLA and $\pi_{0.5}$, under diverse out-of-distribution visual shifts including unseen distractors, texture changes, target object pose variation, viewpoint shifts, and lighting changes. Our method consistently improves over standard PPO, achieving average improvements of 16.62% on $\pi_{0.5}$ and 9.10% on OpenVLA. Notably, ablations further show generalization across visual shifts: invariance guidance learned from distractor and texture variants transfers to target-pose and lighting shifts, while adding sensitivity guidance on target-pose variants further improves robustness to nuisance shifts, highlighting the broader transferability of behavior-level RL guidance.

cs.RO↗
arXiv2026

GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation

Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that provide only coarse supervision. While finer-grained credit assignment is promising for effective policy updates, obtaining reliable local credit and assigning it to the right parts of the long-horizon trajectory remains an open challenge. In this paper, we propose Granularity-adaptivE Advantage Reweighting (GEAR), an adaptive-granularity credit assignment framework that reshapes the trajectory-level GRPO advantage using token- and segment-level signals derived from self-distillation. GEAR compares an on-policy student with a ground-truth-conditioned teacher to obtain a reference-guided divergence signal for identifying adaptive segment boundaries and modulating local advantage weights. This divergence often spikes at the onset of a semantic deviation, while later tokens in the same autoregressive continuation may return to low divergence. GEAR therefore treats such spikes as anchors for adaptive credit regions: where the student remains aligned with the teacher, token-level resolution is preserved; where it departs, GEAR groups the corresponding continuation into an adaptive segment and uses the divergence at the departure point to modulate the segment' s advantage. Experiments across eight mathematical reasoning and agentic tool-use benchmarks with Qwen3 4B and 8B models show that GEAR consistently outperforms standard GRPO, self-distillation-only baselines, and token- or turn-level credit-assignment methods. The gains are especially strong on benchmarks with lower GRPO baseline accuracy, reaching up to around 20\% over GRPO, suggesting that the proposed adaptive reweighting scheme is especially useful in more challenging long-horizon settings.

cs.LG↗