Search arXiv⌕ Search

arXiv subjects

Nan Wang

Publications and source records attributed to Nan Wang.

At least 19 recordsLinked to original sources
arXiv2026

RxnMiner: A Multimodal Agent for Structured Reaction Data Extraction from Chemistry Figures

Reaction data underpin machine learning for reaction prediction, condition recommendation, and retrosynthetic planning, yet extracting these data from literature figures still requires substantial manual effort. Many figures encode multiple experiments through shared templates, substituent tables, and product grids. Recovering concrete reaction records therefore requires molecular recognition, association of evidence with individual experimental entries, and reconstruction of indirectly specified participants. We present RxnMiner, a multimodal agent system that combines an expert-informed extraction procedure with a chemistry toolbox to coordinate these operations. The agent reads molecular structures, resolves shared and entry-specific evidence, and instantiates participants from templates to assemble source-linked reaction records. We also introduce ChemRxn-Bench, a benchmark of 603 reaction figures with 8,547 manually annotated and reviewed reaction records, evaluated under a common protocol for exact molecular identity and reactant-product pairing. On this benchmark, with Qwen3.8-Flash-Next as the backbone, RxnMiner raises stereochemistry-aware reaction macro-F1 from 21.0% under direct prediction to 71.0%, compared with 25.0% for the strongest existing extraction system. Across five backbones, it also outperforms the same base agent without the extraction procedure and chemistry toolbox by 9.4 to 25.5 points. Applied without human intervention to 10,107 literature figures, RxnMiner produces a silver corpus of 88,202 source-linked reaction records.

cs.AI↗
arXiv2026

Leveraging high-performance head-only gradients to enable ~2-fold higher multiband acceleration in SMS-EPI and SMS-EPTI

High-performance head-only gradient systems can substantially reduce echo spacing (ESP) in echo-planar imaging (EPI), but the resulting encoding speed is typically used to shorten readouts and reduce distortion. Here, we instead leverage the increased echo budget to enable denser k-space sampling and higher simultaneous-multislice (SMS) acceleration in SMS-EPI and SMS-EPTI. Fast k-space traversal with denser ky-kz sampling is achieved using peripheral nerve stimulation (PNS)-optimized gradient waveforms, while high-quality reconstruction is obtained using field-correcting GRAPPA (FCG). The resulting ESPs on MAGNUS 3T and Impulse 7T are approximately half those of high-performance whole-body systems, enabling approximately 2-fold higher multiband (MB) acceleration. This facilitates high-quality 2.5-mm isotropic whole-brain resting-state fMRI at 7T with MB28 and a repetition time (TR) of 123 ms.

eess.SP↗
arXiv2026

RTP-LLM: Building an Evolvable and Reliable LLM Inference Engine at Alibaba Scale

Large language models and inference techniques evolve rapidly, making model enablement a recurring production task rather than a one-time integration effort. At Alibaba, a shared inference infrastructure must keep pace with new models and serving capabilities while remaining reliable across heterogeneous production environments. To reconcile rapid evolution with production reliability, we present RTP-LLM, an open-source production inference engine developed and deployed at Alibaba. Its architecture separates model-specific execution from shared request processing, state management, and resource coordination. Explicit interfaces localize compatible model changes while allowing models and deployment configurations to reuse common serving mechanisms. RTP-LLM has evolved from an exploratory system into a shared production engine that supports $\sim$100 models and processes hundreds of trillions of tokens per day. We describe how its architecture and production practices accommodate model evolution and contain the impact of failures, and share lessons for building evolvable and reliable inference engines at enterprise scale.

cs.OS↗
arXiv2026

FESTiVE: Self-calibrated Spatial-temporal Gradient Characterization for Non-cartesian Imaging on High Performance Systems

Gradient imperfections disrupt the encoding benefits of long-readout imaging applications on high-performance systems. Currently, external field monitoring hardware provides the only reliable solution for general spatial-temporal gradient characterization. We present FESTiVE, a data-driven alternative to higher-order field monitoring. FESTiVE leverages parallel imaging to both implicitly model and explicitly recover field imperfections. Using a fast k-t mapping calibration scan, FESTiVE formulates a time-varying GRAPPA problem which maps k-space data corrupted by a time-varying gradient imperfection against a clean reference. This mapping is represented compactly with an implicit neural representation, from which the spatial-temporal fields are recovered in image space using coil sensitivities. In phantom, FESTiVE produces comparable field measurements to a Skope field camera across multiple non-cartesian 2D acquisition strategies and gradient specifications. In vivo, FESTiVE achieves state-of-the-art image quality for a high-performance diffusion spiral protocol on the head-only MAGNUS 3T, where higher-order phase imperfections are significant. At 7T, on the head-only Siemens TerraX system, FESTiVE enables 300μm spiral imaging where conventional field camera-based approaches fall below probe dephasing limits. In conclusion, FESTiVE enables robust high-resolution non-cartesian imaging on high-performance gradients, characterizing gradient imperfections using parallel imaging rather than field monitoring hardware.

eess.SP↗
arXiv2026

CLOSURE: Cross-Channel Closure for Multivariate Time Series Anomaly Detection

Multivariate time series produced by industrial installations and server clusters are under continuous monitoring, and anomaly detection is the first line of defense before a local fault escalates into a system-wide failure. In the absence of labels, the dominant paradigm trains a reconstruction model on normal data and scores the residual to reach a verdict. Recent work has steadily enriched the expressiveness of the recovery map through Transformers, diffusion models, and cross-scale associations. A residual, however, only certifies that an observation can be recovered; it does not certify that the variables still explain one another as they do under normal operation. A coordinated yet unfamiliar operating transition inflates the residual without breaking any relationship, whereas a sensor drifting away from its peers may leave the residual silent. Methods that fold inter-variable dependencies into the reconstruction objective inherit this ambiguity, because their relational evidence is ultimately supervised by the same recovery loss. We therefore propose CLOSURE, which evaluates recoverability and cross-channel consistency as two normal-data prediction tasks learned in separation. The recoverability task is solved by a diffusion reconstructor conditioned on a discrete memory of normal temporal bases. The consistency task is solved by a relation-closure operator that predicts every channel exclusively from the others, where the target's own trajectory is withheld and sparse signed gates decide which peers are actually used. The two scores are reconciled only through calibration on normal data. Extensive experiments show that CLOSURE consistently outperforms recent reconstruction-, frequency-, and topology-based detectors on public benchmark streams, confirming the value of examining consistency alongside recoverability.

cs.AI↗
arXiv2026

Rollback: Experience Backtracking in World Models for Policy Improvement

Action-conditioned world models offer a scalable alternative to costly real-world interaction for improving robot policies. However, existing world-model-based methods largely treat world models as forward-only surrogates of the physical environment, leaving untapped a capability no physical environment affords: rewinding to past decision points to explore counterfactual futures. We introduce Rollback, a policy improvement paradigm that turns world models from passive simulators into counterfactual engines: it rolls back to critical decision points, branches into alternative actions, and contrasts their outcomes to attribute success to individual decisions. This concentrates imagination where it matters most and distills counterfactual outcomes into fine-grained, action-level supervision without a separately learned value model. We build a scalable training system that unifies distributed world-model search with asynchronous real-robot execution, forming a self-reinforcing cycle: real-world experience continually sharpens the world model, and a sharper world model in turn drives further policy improvement. We term the world-model side of this cycle test-time physics grounding, a capability that hand-built physics simulators lack: while the world model serves as the training environment, real transitions from the policy it trains correct its dynamics through a lightweight LoRA pipeline. Experiments on three challenging real-world tasks show that Rollback improves success rates over the strongest baseline by an absolute 10.67%, 11.11%, and 11.85% on block extraction, ball tossing, and tabletop curling, respectively, while achieving more stable improvement throughout training. Although initialized from teleoperated demonstrations far below human level, Rollback surpasses the average success rate of human players on both ball tossing and tabletop curling within 8 hours of training.

cs.RO↗
arXiv2026

GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation

World-action models (WAM) predict future states to guide robot actions, enabling learning from both action-free video and action-labeled interaction. Most inherit pretrained video generators, leaving WAM pretraining and scaling underexplored. We introduce Genie Envisioner Act 2.0 (GE-Act 2.0), a world-action model whose trainable generative and action components are all initialized from scratch on manipulation data. It combines a control-oriented autoencoder (CoAE), a single-step visual planner (SVP), and an inverse dynamics model (IDM). CoAE retains action- and instruction-relevant information under aggressive compression, while SVP produces a complete future state in one differentiable pass, so visual planning and inverse dynamics can be pretrained separately on complementary data. The components are then jointly trained with knowledge-aligned selective optimization (KASO), which reduces mismatched supervision by selecting only predicted futures judged behaviorally compatible with the recorded action. We evaluate pretrained checkpoints directly, without per-task fine-tuning, on 100 tasks across 20 manipulation skill groups with held-out scenes, backgrounds, lighting, and object instances. Scaling co-training data from 300 to 30,000 hours raises success from 17.1% to 44.1% on G1-OP and from 13.4% to 31.1% on G2-90D; despite comprising less than 2% of the co-training data, G2-90D improves by 17.7 points, suggesting cross-embodiment transfer. Gains span 19/20 and 18/20 skill groups, and skill-specific coverage strongly correlates with zero-shot out-of-distribution (OOD) success (Pearson r=0.80; Spearman rho=0.85). Under the same protocol, the model grounds object, color, shape, and position references in at least 90% of trials and follows explicit instructions even when they conflict with an already-committed behavior or a conventional scene association.

cs.RO↗
arXiv2026

WorldOracle: Benchmarking Action-Conditioned World Models against Real-World Executions

We introduce WorldOracle, a benchmark specifically designed to evaluate action-conditioned world models (ACWMs) against paired real-world executions. Given the same initial observation and low-level action sequence, WorldOracle asks whether a predicted rollout reproduces what happens in the real world, including physical consequences and task-state transitions. We evaluate models along four complementary dimensions: physical state correctness, interaction spatial alignment, key interaction area fidelity, and multi-view action coherence. To support this evaluation, we curate real-world training and evaluation suites that cover different interaction dynamics and embodiments. The evaluation suite contains long, multi-segment episodes with both successful and failed executions, enabling evaluation across varied action outcomes and behavior distributions. Experiments on seven representative ACWMs reveal distinct model strengths and failure modes. WorldOracle provides a systematic foundation for measuring and advancing action-conditioned world modeling for manipulation. We release the datasets, evaluation code, and leaderboard: https://worldoracle-benchmark.github.io/.

cs.RO↗
arXiv2026

Tradeoff-Aware Territory Design: A Multi-Objective Decision System for Enterprise Customer-to-Seller Allocation

Enterprise customer journeys are shaped not only by product experiences and marketing, but also by recurring resource-allocation decisions. In B2B go-to-market (GTM) organizations, territory carving determines which accounts receive seller coverage, which seller-account relationships are preserved, and how limited field capacity is distributed. Yet the process often remains manual, making it difficult to compare opportunities, value continuity, and evaluate tradeoffs among growth, balance, capacity, and feasibility. We present a production decision system for tradeoff-aware customer-to-seller allocation in enterprise GTM planning. It integrates three components: a multidimensional account-value layer that combines predictive signals to score opportunity; an observational continuity-valuation layer that estimates the cost of breaking seller-account relationships using a synthetic-control-style counterfactual framework; and a multi-objective optimization layer that allocates coverage to high-value accounts while considering continuity, opportunity balance, and operational constraints. Deployed as a scenario-based decision-support system, the framework enables planners to inspect and compare allocation tradeoffs. Historical backtesting shows that optimizer-generated scenarios substantially improve assignment compliance while maintaining comparable seller-level opportunity distribution. In production planning, adopted scenarios improved both assignment compliance and opportunity balance relative to the previous baseline. Directing scarce seller capacity toward higher-value accounts also offers incremental revenue potential at enterprise scale. The key contribution is an integrated, inspectable framework that turns territory carving into a governable decision process.

cs.AI↗
arXiv2026

RoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models

Robotic value models assess task execution from visual observations and instructions, providing feedback for policy learning and execution monitoring. However, existing evaluations cover only selected aspects of execution understanding, leaving the reliability of value feedback insufficiently tested. We introduce RoboValue, a fine-grained sim-and-real benchmark for unified evaluation of robotic value models. Its framework evaluates four complementary capability dimensions through shared interfaces: task-state understanding, temporal progress monitoring, failure and recovery reasoning, and value consistency. Diagnostic trajectories and instruction variations test whether value judgments accurately reflect task requirements and changes throughout execution. RoboValue-Dataset covers 15 simulation and 20 real-world manipulation tasks, providing expert demonstrations for training and annotated trajectories for fine-grained evaluation. We evaluate representative robotic value models in zero-shot and one-shot settings under standard conditions and separate shifts in robot embodiment and environment. Our results reveal errors in fine-grained instruction grounding, history-dependent progress tracking, and recovery assessment, even in models with strong outcome and forward-progress scores. The same semantic subtask can also receive substantially different value gains across valid execution orders. These findings identify concrete targets for value supervision, while the dataset and public leaderboard support continued assessment of feedback reliability. The website is available at https://robovalue-benchmark.github.io/.

cs.RO↗
arXiv2026

Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents

LLM agents operate in stateful environments, where a single erroneous step can waste limited interaction budget or cause irreversible effects before task failure becomes apparent. Reliable deployment therefore requires step-level confidence estimation: estimating, before execution, the probability that a proposed action will advance the task. Existing LLM confidence estimators are typically designed for static question answering under a fixed task context and evaluation criterion. For an agent, however, its action productivity depends on an environment transition that is observed only after execution. To address this challenge, we introduce Critic Experience Bank (CEB), a training-free framework that turns feedback from completed trajectories into reusable evidence for future confidence judgments. After each trajectory, an LLM assigns hindsight productivity pseudo-labels to individual actions and stores them with the critic's original pre-execution confidence, task context, action, and observed feedback. For a new action, by retrieving related productive and unproductive experiences, CEB grounds pre-execution confidence in feedback from completed trajectories to condition a fixed LLM critic. CEB thereby adapts over a task stream without parameter updates or ground-truth step labels at deployment. Across four agent benchmarks spanning offline and live web navigation, mobile GUI and shell tasks, and three critic backbones, CEB achieves the best or tied-best ECE, Brier score, and AUC in all twelve benchmark-backbone settings under rule-based step labels, reducing ECE by up to 53.8% relative to the strongest training-free baseline. Its confidence scores also improve downstream utility in selective execution and simulated task success.

cs.AI↗
arXiv2026

Hybrid Latent Attention for Looped Language Models

Looped language models apply the same stack of layers T times to each token, which deepens the model without adding parameters but multiplies its key-value (KV) cache by T. The larger cache limits how many sequences a GPU can decode at once and slows each decoding step, which reads the whole cache. We propose Hybrid Latent Attention (HLA), which keeps exact keys and values within a sliding window of W recent tokens and stores each older token as a compact latent that the query of each loop reads directly, without reconstructing keys and values. We uptrain HLA on Ouro looped models (T=4) with 1.4B and 2.6B parameters, keeping the pretrained weights frozen and training only the added parameters to reproduce the original attention. The cache shrinks by 10.7x per token, fitting 4.0-8.8x as many concurrent sequences per GPU, and decoding throughput improves by 2.5x at 1K-token contexts and by up to 7.4x at 16K. HLA retains over 97% of the original accuracy on math, knowledge and reasoning benchmarks, and 96-100% on long-context retrieval up to 16K tokens. After supervised fine-tuning, it performs on par with the fine-tuned original model on competition-level math.

cs.CL↗
arXiv2026

ShellfishNet: A Domain-Specific Benchmark for Visual Recognition of Marine Molluscs

Reliable visual recognition of shellfish is important for ecological monitoring and aquaculture, but real-world imagery exhibits substantial variation in acquisition conditions, appearance, and posture. Existing marine vision resources cover diverse taxa and imaging settings, but fine-grained mollusc recognition remains underexplored in a group-disjoint benchmark that jointly evaluates class prediction, representation-space retrieval, and condition sensitivity. To address this gap, we introduce ShellfishNet, a provenance-aware, group-disjoint benchmark of 40,130 images from 100 marine mollusc classes, organized into 30,879 acquisition or observation groups. Rather than treating recognition as a single clean-accuracy leaderboard, ShellfishNet evaluates model configurations across classification, image-to-image retrieval, taxonomic error structure, and controlled condition sensitivity. We benchmark representative convolutional, transformer-based, hybrid and efficient, self-supervised, and vision-language models on classification and retrieval. Separately, we evaluate open image-captioning and vision-language models on the captioning subset and assess selected fixed checkpoints under controlled generic and marine-inspired synthetic transformations. Across the benchmark, image-level and class-aware classification largely agree, whereas retrieval provides complementary model rankings and taxonomy projection reveals that a non-negligible subset of exact-class errors remains correct at higher taxonomic ranks. Selected fixed checkpoints with similar clean accuracy can also exhibit distinct sensitivity profiles under controlled transformations. These results show that model comparison on shellfish imagery should account for both task and image condition, rather than rely on a single clean classification score. The dataset and evaluation protocols will be publicly released.

cs.CV↗
arXiv2026

PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention

We propose PostCam, a streamlined framework for novel-view video generation that achieves superior detail preservation and precise camera trajectory editing in dynamic scenes. Current methods often struggle with a trade-off between pose-based control, which lacks visual detail, and rendering-based guidance, which is overly sensitive to geometric accuracy. Despite recent hybrid attempts, achieving precise motion and visual consistency remains challenging due to the lack of effective cross-modal alignment. We argue that robust control stems from the deep alignment of multimodal signals rather than increased input complexity. Our core contribution is the Query-Shared Cross-Attention mechanism, which projects 6-DoF poses and rendered features into a unified latent space. This allows the model to spontaneously achieve intrinsic consistency between motion cues and pixel-level guidance during denoising. Experiments demonstrate that PostCam maintains high-fidelity visual details while outperforming state-of-the-art methods by 20% in trajectory precision, exhibiting superior robustness in complex dynamic scenes. Our project webpage is publicly available at: https://cccqaq.github.io/PostCam.github.io/

cs.CV↗
arXiv2026

VPEvolve: A Self-Evolving Virtual Process Engineer for Computational Lithography

Optical proximity correction (OPC) recipes grow as engineers add local rules to repair newly discovered lithography hotspots. Each correction can interact with existing rules, while lessons from commercial-tool trials remain scattered across code and logs. \system combines a Virtual Process Engineer (VPE) harness with a Skill Bank of measured engineering experience. The harness equips a frozen language model with process manuals, layout analysis, recipe editing, and commercial-tool evaluation. The actor proposes changes to the global parameters, local targeted rules, or diagnostic trials. After each evaluation, an LLM reflector and curator turn the measured response into evidence-linked judgments. The actor retrieves them before its next trial. Feasible improvements update the retained recipe; every measured trial informs the Skill Bank that guides the next edit. The model weights remain fixed. On a FreePDK45-derived benchmark with ten commercial-tool evaluations per case, \system reduces the mean per-case maximum edge placement error from 18.294 to 5.361 nm on Poly and from 22.052 to 15.692 nm on Metal1. Every final recipe satisfies the predefined quality constraints and improves the maximum error by at least 0.1 nm.

cs.AI↗
arXiv2026

Aero Hand Open: A Simulation-Ready Tendon-Driven Hand for Dexterous Manipulation Learning

Tendon-driven hands are anthropomorphic, and moving the actuators off the joints is what makes a hand of this capability affordable to build. Two effects produce that saving. Routing force through a cable removes the requirement that a motor fit inside the joint it drives, so smaller and cheaper motors suffice, and one motor can drive several joints through a single cable, so fewer motors are needed. They are also harder to learn on than a direct-drive hand. The underactuated transmission that produces the saving is itself difficult to represent in a simulator, and the joints one cable drives are not independently commandable. We present Aero Hand Open, a tendon-driven anthropomorphic hand that is released simulation-ready. Three things ship with it. A simulation model reproduces the cable transmission itself. An identified actuation map connects that model to the motor commands in both directions, including the three-way coupling of the thumb. A reinforcement learning package trains policies for the hand. Together they let a policy be trained entirely in simulation and run on the hand with no fine-tuning and no state estimation. We release the mechanical design, the simulation model, the identified mapping, the training environment and the deployment stack.

cs.RO↗
arXiv2026

High-Temporal-Resolution Motion Correction in Magnetic Resonance Fingerprinting Using a Quantitative Scout and Compact Spiral Navigators

Motion correction in magnetic resonance fingerprinting (MRF) helps preserve the accuracy of quantitative maps; however, existing approaches provide motion updates only every 7-8 seconds. We propose a navigation framework that integrates compact k-space navigators throughout the MRF acquisition, enabling sub-second motion estimation at minimal sequence overhead. A 3D spiral-projection MRF sequence was augmented with three orthogonal spiral navigators inserted every 0.5 seconds, enabling motion estimation by comparing navigator signals with quantitative scout (Q-Scout) data, i.e., motion-free low-resolution k-space with matching contrast evolution. The Q-Scout is obtained via a rapid calibration during the dummy preparation period, incurring no additional scan time. Motion estimation is formulated as dictionary matching in a discriminant subspace with optimization refinement. The method was evaluated in simulation and in vivo for 1 mm isotropic brain 3D MRF at 3 T. Across 35 motion-corrupted acquisitions with motion-free references available, the proposed motion correction reduced MRF reconstruction normalized root-mean-square error (NRMSE) by 7.1% and increased the structural similarity index measure (SSIM) by 0.085. Motion estimates aligned with 8 second temporal-rate image-based navigation (mean absolute difference of 0.15 mm and 0.23 degrees), while the proposed method provided higher temporal resolution and improved motion correction. The proposed framework enables robust motion navigation in MRF at 0.5 second temporal resolution with minimal sequence overhead. By using contrast-consistent modeling and efficient inference, it improves the reliability of quantitative MRI under rapid, unpredictable motion.

eess.SP↗
arXiv2026

Fundamental Limits of Joint Target Detection and Parameter Estimation - Characterizing Mixed-State Sensing Limits via Posterior Entropy Volume

The development of integrated sensing and communication calls for a unified theoretical foundation for sensing. This paper models target-presence patterns and continuous physical parameters as a mixed discrete-continuous state $Ξ$ on a branched reference measure, and treats posterior entropy volume and joint mutual information as two complementary representations of the same limit. Entropy volume carries physical units, can be compared with engineering scales such as resolution cells, and remains meaningful when the number of active targets varies; mutual information is dimensionless, invariant to coordinates and units, and additive through the chain rule. We define entropy number, entropy volume, and mixed entropy volume for discrete, continuous, and mixed states, respectively. The maximum-entropy principle for the uniform distribution on a support of fixed measure explains the measure-theoretic meaning of the exponential entropy scale, while the main limit follows from a mixed asymptotic equipartition property and a posterior probability-volume inequality through conditional typical sets. For asymptotically reliable high-probability sensing regions, the minimum achievable first-order posterior mixed entropy volume equals the prior mixed entropy volume multiplied by $2^{-I(Ξ;Y)}$, where $I(Ξ;Y)=I(V;Y)+I(X_V;Y\mid V)$. Thus, detection and estimation contributions multiply in the volume domain and add in the bit domain, and one sensing bit halves the posterior effective measure. We further prove that posterior-preserving cascades attain the direct-inference limit, while arbitrary intermediate compression incurs the exact information loss $I(Ξ;Y\mid Z)$. Numerical results for a single-target presence-range model illustrate the information composition, posterior entropy-volume contraction, and cascade-interface loss.

cs.IT↗