Searcharxiv⌕ Search

arXiv subjects

Ziwen Wang

Publications and source records attributed to Ziwen Wang.

At least 19 recordsLinked to original sources
arXiv2026

IMPose: Closed-Loop Correction Propagation for Interactive Multi-Person Pose Annotation

High-quality dynamic human pose annotations provide important supervision for learning fine-grained human motion, yet dense multi-person video annotation remains labor-intensive. Sparse human corrections can reduce this effort, but their propagated locations may become unreliable and ambiguous across identities. Existing interactive refinement and temporal propagation methods do not explicitly address how imperfect propagated corrections should participate in subsequent multi-person pose inference. We propose IMPose, a correction-conditioned temporal inference framework for interactive multi-person pose annotation. IMPose separates temporal correspondence from pose estimation: propagated corrections are treated as geometric priors rather than final predictions and are refined by a correction-aware decoder using target-frame visual evidence. A keypoint-aware identity state further combines structured pose geometry with trajectory history to preserve person- and joint-level correspondence. The refined pose and identity state are fed back to subsequent frames, forming a closed temporal correction loop. Under a controlled sparse-correction protocol on PoseTrack21, one correction improves mean average precision (mAP) from 38.87 to 67.99 and Higher Order Tracking Accuracy (HOTA) from 52.21 to 64.89. At a 20-frame correction interval, IMPose achieves 89.03% keypoint-level Object Keypoint Similarity (K-OKS), compared with 81.41% for CoTracker and 70.12% for PoseWarper-based propagation. We further extend PoseTrack21 with 188K additional person instances through 3.55M annotation updates to keypoints, bounding boxes, and person IDs using 100 annotator-hours. The annotation tool, code, and extended dataset will be released.

cs.CV↗
arXiv2026

Text as an Index for Zero-Shot Cross-Domain Knowledge Tracing

Knowledge tracing (KT) predicts a student's next response from their history. New platforms often have question texts but no response logs for training, motivating zero-shot cross-domain KT. Existing transfer and cold-start methods use question semantics, but cross-platform semantic discrepancies limit transferability. We propose TIZSKT, which separates behavioral sequence modeling from domain-local historical evidence construction and uses text as an index rather than a directly transferable predictive representation. The Mastery-Dynamics Encoder learns correctness dynamics without question identifiers or text embeddings. Domain-Local Question Addressing builds fixed question addresses using a frozen text encoder and an unsupervised per-domain projection. The Text-Addressing Kernel uses these addresses to aggregate the current student's previous outcomes into a question-specific historical correctness summary. Cross-Segment Continuation retains access to earlier responses without extending the behavioral encoder's input sequence. Evidence-Volume Read-Out preserves the total kernel mass discarded by normalization and combines its log-compressed value with the behavioral state and historical correctness summary to predict the next response. All trainable parameters are learned from source domains; target inference uses public question texts and the current student's observed history without target-domain training. Leave-one-domain-out experiments on three public datasets show that TIZSKT achieves the highest mean AUC and accuracy among evaluated baselines on all target domains. Ablations confirm the contributions of text addressing and cross-segment continuation.

cs.CL↗
arXiv2026

Spark-Audio 1.0 Technical Report

This paper introduces Spark-Audio 1.0, a speech foundation model trained on domestically produced computing infrastructure. The model accepts text and speech inputs and generates text outputs. It supports multilingual (99 languages) and multi-dialect (202 dialects) speech recognition, speech translation, audio perception and understanding, and both text- and speech-based dialogue, marking a shift from merely ``hearing clearly'' to genuinely ``understanding'' speech. Architecturally, Spark-Audio 1.0 couples a 0.65B-parameter dense audio encoder with a 30B-A3B Mixture-of-Experts (MoE) large language model (LLM). The audio encoder is pretrained with representation-enhanced BEST-RQ and then refined through multi-task supervised training. The audio--LLM is trained through staged pretraining, followed by post-training that combines supervised fine-tuning with on-policy distillation. In total, the model is trained on 13 million hours of audio data together with large-scale text data. We evaluate Spark-Audio 1.0 on mainstream audio and text benchmarks, as well as on in-house test sets drawn from real-world application scenarios. Despite using substantially less audio training data than Qwen3.5-Omni-Flash, Spark-Audio 1.0 achieves comparable performance on most audio and text tasks, outperforms it in multilingual speech recognition, spoken dialogue, and real-world application scenarios, and approaches the performance of larger closed-source models. Nevertheless, there remains room for improvement in instruction following and complex audio reasoning. Finally, the successful training of Spark-Audio 1.0 on domestic hardware, including Huawei Ascend 910B and Hygon BW1000 chips, demonstrates the feasibility of a domestic technical pathway for building speech foundation models.

eess.AS↗
arXiv2026

Metaphotonics for High-Harmonic Generation

We summarise the recent advances on the generation of high-order harmonics in optical metaphotonic structures such as isolated resonators and metasurfaces. In such subwavelength-patterned structures, extreme nonlinear effects are expected from the interaction between ultrafast laser pulses and structured planar surfaces which support various resonances. High-harmonic generation (HHG) is considered as an effective tool for realising extreme ultraviolet light sources and attosecond pulses, and it was observed previously in gases, liquids, and solids. Resonant metaphotonics can offer a novel sub-wavelength platform for the HHG effects, and it can provide new strategies for the design of efficient integrated light sources. We start our discussion from a brief overview of HHG in gases, liquids, and unstructured solids, and then move to summarising the recent experimental observations of HHG in individual resonant nanoparticles and resonant dielectric metasurfaces. We focus on different types of resonances (plasmonic vs. Mie resonances vs. bound states in the continuum), and also present the observation of non-integer power dependencies of the generated harmonics driven by strong resonances. We also mention current unsolved problems and identify new promising research directions involving HHG in metasurfaces.

physics.optics↗
arXiv2026

Nonlinear Magneto-Optical Probing of Time-Reversal Symmetry Breaking

Solid-state harmonic generation provides a nonlinear probe of symmetries encoded in electronic wave functions. In the subgap and weak-injection regime, time reversal pairs the harmonic responses driven by fields of opposite ellipticity, strongly suppressing elliptical dichroism in time-reversal-symmetric crystals. We show that, in a magnetic crystal, spin-orbit coupling transfers time-reversal-symmetry breaking from the spin sector to the orbital wave functions and lifts this pairing through the geometric phases of the electric-dipole current. Semiconductor-Bloch-equation calculations for centrosymmetric bilayer Cr2Ge2Te6 predict pronounced third-harmonic elliptical dichroism that reverses with the magnetization. Under linearly polarized driving, SOC-induced geometric-phase accumulation generates a nonlinear transverse current and strongly enhances the harmonic rotation and ellipticity. These results identify the geometric phase as a key microscopic contribution to the nonlinear magneto-optical response. This work establishes helicity-resolved harmonic emission and nonlinear polarimetry as complementary probes of spin-orbit-coupled magnetic order.

physics.optics↗
arXiv2026

Laser-Driven Electron Emission Carrying Orbital Angular Momentum from Carbon Nanotubes

Extending the orbital angular momentum (OAM) degree of freedom to slow electrons would open a distinct regime of low-energy electron-matter interactions. Using time-dependent density-functional theory, we demonstrate that laser-driven armchair carbon nanotubes (CNTs) can emit OAM-carrying slow electrons. A circularly polarized OAM-writing pulse promotes circumferential electronic motion and generates OAM about the tube axis; a delayed linearly polarized extraction pulse releases slow electrons carrying the injected angular momentum. We find much higher ionization yields and net emitted axial OAM in representative CNTs than in oriented CO2 and benzene under identical laser conditions. Increasing the tube diameter enhances the ionization yield and OAM substantially, and moreover, reversing the helicity of the OAM-writing pulse flips the sign of the emitted OAM. Together, these findings establish CNTs as a platform for slow-electron emission with optically controllable OAM.

physics.optics↗
arXiv2026

ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning

Protein generative models have shown remarkable promise in protein design, yet their success rates remain constrained by reliance on curated sequence-structure datasets and by misalignment between supervised objectives and real design goals. We present ProteinZero, an online reinforcement learning framework for inverse folding models that enables scalable, automated, and continuous self-improvement with computationally efficient feedback. ProteinZero employs a reward pipeline that combines structural guidance from ESMFold with a novel self-derived ddG predictor, providing stable multi-objective signals while avoiding the prohibitive cost of physics-based methods. To ensure robustness in online RL, we further introduce a novel embedding-level diversity regularizer that mitigates mode collapse and promotes sequence-level diversity among generated designs. Within a general RL formulation balancing multi-reward optimization, KL-divergence from a reference model, and diversity regularization, ProteinZero achieves robust improvements across designability, predicted stability, recovery, and diversity. On the CATH-4.3 benchmark, it consistently outperforms state-of-the-art baselines including ProteinMPNN, ESM-IF, and InstructPLM, reducing design failure rates by 36-48% and achieving success rates above 90% across diverse folds. Importantly, a complete RL run can be executed on a single 8xGPU node within three days, including reward computation and data generation. These results indicate that efficient online RL fine-tuning can complement supervised pretraining by allowing protein generative models to evolve continuously from their own outputs and optimize multiple design objectives without labeled data, opening new possibilities for exploring the vast protein design space. Code and model checkpoints are available at https://github.com/ziwenwang28/ProteinZero.

cs.LG↗
arXiv2026

Where Does the Energy Go? Profiling LLM Agent Inference on Blackwell GPUs

LLM agents that iteratively reason, plan, and invoke tools create workload profiles fundamentally different from single-pass inference, yet how their energy consumption is distributed across hardware components and workload phases remains poorly understood. Characterizing these workloads therefore requires simultaneous visibility into both component-level power and phase-level execution. We conduct a full-stack energy profiling study combining NVML GPU counters, Intel RAPL CPU/DRAM counters, and Intelligent Platform Management Interface (IPMI) system-level sensors on 2x NVIDIA RTX PRO 6000 Blackwell GPUs, and profile three representative workloads with Qwen3.8-27B. For mathematical reasoning, we compare thinking-enabled and thinking-disabled modes. Our measurements reveal that GPU-only telemetry misses 41-45% of system energy across all three workloads, with non-GPU components accounting for the remainder. In our setup, the sequential agent workload consumes 63x more system energy per output token than saturated serving, reflecting the absence of batching, context growth across turns, and tool-induced idle periods. Extended thinking generates 21-75% more tokens per problem, while per-token energy differs by less than 1% between modes within each dataset, indicating that the resulting increase in energy is driven by output volume rather than a change in per-token efficiency. Continuous batching improves system-level energy efficiency by 3.2x from 1 to 16 requests per second, as GPU power plateaus while throughput continues to increase with batching depth. For the memory-bandwidth-bound reasoning workload, throughput remains unchanged under per-GPU power caps of 400-600 W but drops sharply at 300 W. These findings suggest that context-management techniques such as summarization and selective retrieval may help reduce energy consumption in agent deployments.

cs.DC↗
arXiv2026

Remarkable Enhancement of High Harmonic Generation from Superhard Material under High Pressure

High harmonic generation (HHG) in solids offers a pathway to develop compact extreme ultraviolet (EUV) sources crucial for attosecond science and advanced spectroscopy. Here, we demonstrate theoretically that high pressure dramatically enhances HHG in superhard hexagonal tungsten nitride (h-WN6). Compared with solid-state systems at ambient pressure, the reshaped electronic environment under high pressure leads to a unique band-gap widening in h-WN6, which raises the material's damage threshold, allowing the use of stronger laser fields and enabling access to higher-energy bands. This pressure-induced band-gap widening offers a promising strategy to overcome the cutoff limitation of solid-state EUV light sources.

physics.optics↗
arXiv2026

HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have demonstrated significant potential to advance a broad range of domains. However, current benchmarks for evaluating MLLMs primarily emphasize general knowledge and vertical step-by-step reasoning typical of STEM disciplines, while overlooking the distinct needs and potential of the Humanities and Social Sciences (HSS). Tasks in the HSS domain require more horizontal, interdisciplinary thinking and a deep integration of knowledge across related fields, which presents unique challenges for MLLMs, particularly in linking abstract concepts with corresponding visual representations. Addressing this gap, we present HSSBench, a dedicated benchmark designed to assess the capabilities of MLLMs on HSS tasks in multiple languages, including the six official languages of the United Nations. We also introduce a novel data generation pipeline tailored for HSS scenarios, in which multiple domain experts and automated agents collaborate to generate and iteratively refine each sample. HSSBench contains over 13,000 meticulously designed samples, covering six key categories. We benchmark more than 20 mainstream MLLMs on HSSBench and demonstrate that it poses significant challenges even for state-of-the-art models. We hope that this benchmark will inspire further research into enhancing the cross-disciplinary reasoning abilities of MLLMs, especially their capacity to internalize and connect knowledge across fields.

cs.CL↗
arXiv2026

Communication-efficient distributed hazard difference estimation for heterogeneous multi-site survival data

Multi-site collaboration can power survival models that no single hospital could fit alone, but privacy rules and protected computing environments block patient-level data sharing and the persistent server connections required by iterative federated methods. We present DiSAH (\underline{\textbf{Di}}stributed \underline{\textbf{S}}urvival via \underline{\textbf{A}}dditive \underline{\textbf{H}}azards), a federated algorithm for time-to-event analysis whose closed-form, non-iterative structure removes the need for a dedicated central server. Coordination requires only aggregation of summary statistics, which any site can perform, with no patient-level data leaving the site. DiSAH is the first federated method to estimate hazard differences, the absolute change in event rate attributable to each risk factor, providing an actionable scale for triage, resource allocation, and health-economic evaluation. Across simulations and 47,778 emergency-department patients from the United States and Singapore, DiSAH matches centralized analysis in accuracy and discrimination, recovers mortality risk factors no individual site was powered to detect, and outperforms meta-analysis and local models.

stat.ML↗
arXiv2026

Request-Level Energy Attribution for Batched LLM Serving

Batched LLM serving improves throughput but complicates energy accounting. GPU power telemetry is aggregate, whereas sustainability reporting, chargeback, and workload analysis often require request-level energy charges. Existing inference-energy benchmarks report model-, phase-, or token-level energy, and recent carbon-accounting work motivates Shapley fairness conceptually. Neither provides measured request-level ground truth, so how far the accounting rules used in practice deviate from a fair allocation has remained unknown. We present JouleShare, an attribution framework with two components. An offline harness establishes this ground truth by replaying request subsets under vLLM with a reproducible protocol, integrating GPU power telemetry, and computing exact Shapley energy for each request. A lightweight calibration model, JCalib, then learns to predict Shapley shares from cheap request features for use at serving time. Across 16 model/workload runs, token-proportional attribution differs from exact Shapley by 0.440 normalized L1 on average under static batching and by 0.458 under continuous batching, a gap that reproduces across three data-center GPUs. JCalib reduces this error to 0.116 under static batching and 0.177 under continuous batching, below even a standalone-measurement baseline that is unavailable online, while preserving exact batch-energy efficiency. Sampled Shapley extends the measured reference to larger group sizes, where the gap persists and a single offline calibration remains the most accurate deployable rule. The results show that token attribution is not a reliable proxy for marginal energy under batched execution, and that measured Shapley ground truth can calibrate low-cost request features toward fairer attribution.

cs.AI↗
arXiv2026

Learning Cross-View Semantic Priors for Single-Reference Unseen Object Pose Estimation

Single-reference unseen object 6D pose estimation reduces object onboarding by estimating poses of arbitrary novel objects from only one reference view. Recent correspondence-based pipelines have achieved robust performance with vision foundation model (VFM) features. However, they typically treat these features as intra-view descriptors, leaving dense visual-semantic cues, including appearance, structure, and context, insufficiently exchanged across views before geometric decoding. Consequently, the decoded point features may lack joint semantic and geometric discriminability, making correspondence estimation still difficult in challenging cases. Instead of processing features independently, we build the correspondence pipeline around an early cross-view semantic prior. Specifically, cross-view semantic interaction (CVSI) enables dense query and reference VFM tokens to exchange semantic context and form a cross-view prior. Nevertheless, direct CVSI may disturb the VFM token structure, while the resulting semantic prior still needs 3D representation consistency for rigid correspondence. To make this CVSI prior reliable for 3D correspondence learning, we introduce two complementary training-time constraints: the intra-view structure preservation (IVSP) loss preserves the original intra-view token affinity structure during interaction, while the reference-anchored geometric consistency (RAGC) loss enforces spatial representation consistency of decoded point features. The final pose is recovered from learned correspondences through weighted SVD. We further construct a challenging view-pair protocol from the BOP Challenge datasets YCB-V and TUD-L to evaluate robustness in difficult matching scenarios. Extensive experiments on six benchmarks under different view-pair settings show that our method achieves state-of-the-art performance while maintaining comparable inference speed.

cs.CV↗
arXiv2026

Protean Compiler: An Agile Framework to Drive Fine-grain Phase Ordering

The phase ordering problem has been a long-standing challenge since the late 1970s, yet it remains an open problem due to having a vast optimization space and an unbounded nature, making it an open-ended problem without a finite solution, one can limit the scope by reducing the number and the length of optimizations. Traditionally, such locally optimized decisions are made by hand-coded algorithms tuned for a small number of benchmarks, often requiring significant effort to be retuned when the benchmark suite changes. In the past 20 years, Machine Learning has been employed to construct performance models to improve the selection and ordering of compiler optimizations, however, the approaches are not baked into the compiler seamlessly and never materialized to be leveraged at a fine-grained scope of code segments. This paper presents Protean Compiler: An agile framework to enable LLVM with built-in phase-ordering capabilities at a fine-grained scope. The framework also comprises a complete library of more than 140 handcrafted static feature collection methods at varying scopes, and the experimental results showcase speedup gains of up to 4.1% on average and up to 15.7% on select Cbench applications wrt LLVM's O3 by just incurring a few extra seconds of build time on Cbench. Additionally, Protean compiler allows for an easy integration with third-party ML frameworks and other Large Language Models, and two applications of this two-step optimization show a gain of 10.1\% and 8.5\% speedup w.r.t. -O3 on CBench's Susan and Jpeg applications. Protean compiler is seamlessly integrated into LLVM and can be used as a new, enhanced, full-fledged compiler. We plan to release the project to the open-source community in the near future.

cs.PL↗
arXiv2026

DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks

Search Agents (SAs) typically leverage large language models (LLMs) to support complex information-seeking tasks by autonomously exploring web sources and synthesizing information into comprehensive responses. For SAs evaluation, prior benchmarks mainly focus on specialized tasks that are unlikely to arise in real-world user scenarios. Moreover, their reliance on coarse task-level rubrics often limits evaluation interpretability. To bridge this gap, we introduce DailyReport, an open-ended benchmark to evaluate SA capabilities on daily search tasks. It contains 150 open-ended tasks with 3,546 associated rubrics, capturing widely discussed and timely information demands of real-world users. Each task is decomposed into subtasks and evaluated with cascade rubrics across disentangled dimensions. Through cascade performance attribution and user-centric aggregation, we derive highly interpretable scores for each dimension, along with a user preference score. Our results on 17 agentic systems show that current systems still fall short of users' expectations. To facilitate future research, our dataset and code are made publicly available at https://github.com/AGI-Eval-Official/DailyReport.

cs.AI↗
arXiv2026

ATLAS: All-round Testing of Long-context Abilities across Scales

Long-context language models now advertise context windows up to millions of tokens, yet evaluations typically report a single length or a narrow task family, masking two failure modes: performance can collapse as length grows, and strong retrieval need not transfer to downstream use. We present ATLAS, a benchmarking framework that redefines long-context evaluation as length-dependent capability profiling. ATLAS contributes three methodological principles:(i) a layered taxonomy separating foundational operations from application workloads so failures can be attributed, (ii) length-aware AUC scoring that integrates score-length curves over a fixed 8K-1M grid, replacing single-point metrics with full degradation profiles, and (iii) ATLAScore, a harmonic-mean aggregate over taxonomy categories that penalizes imbalanced profiles, with end-to-end uncertainty propagation from subset scores through the nonlinear final aggregate. We instantiate the framework across eight capability dimensions with nine auditable components and 6,438 instances, and evaluate 26 models. Gemini-3.1-Pro-Preview leads at 128K, Claude-Opus-4.6 leads at 1M. Rankings reshuffle substantially between ATLASscore@8K-128K and ATLASscore@8K-1M: 7 models move by at least two ranks, and the two taxonomy layers share only 61% of cross-model variance, with individual rank gaps up to 12 positions. These results support reporting long-context quality by capability and length, not by a single headline score.

cs.CL↗
arXiv2026

WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation

Interactive world models are advancing rapidly, yet existing benchmarks cover only part of the required competencies, leaving no unified standard for systematic evaluation. To fill this gap, we introduce WBench, a comprehensive multi-turn benchmark for interactive world model evaluation along five dimensions, namely video quality, setting adherence, interaction adherence, consistency, and physics compliance. WBench contains 289 test cases and 1,058 interaction turns, where each case specifies a world setting and a multi-turn interaction sequence, covering diverse scenes, styles, subjects, and both first- and third-person perspectives, together with four interaction types, including navigation, subject action, event editing, and perspective switching. For navigation, WBench unifies text, 6-DoF pose, and discrete-action control, enabling evaluation of models with different native input interfaces. Evaluation uses 22 automatic sub-metrics that combine specialist vision models with large multimodal models, and all metrics are validated against human judgments. Across 20 state-of-the-art models, we find that no single model performs strongly across all dimensions. We provide detailed diagnostic insights into the characteristic strengths, weaknesses, and open challenges of each model. Code and data are available at https://github.com/meituan-longcat/WBench.

cs.CV↗
arXiv2026

SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering

Traditional Retrieval-Augmented Generation (RAG) effectively supports single-hop question answering with large language models but faces significant limitations in multi-hop question answering tasks, which require combining evidence from multiple documents. Existing chunk-based retrieval often provides irrelevant and logically incoherent context, leading to incomplete evidence chains and incorrect reasoning during answer generation. To address these challenges, we propose SentGraph, a sentence-level graph-based RAG framework that explicitly models fine-grained logical relationships between sentences for multi-hop question answering. Specifically, we construct a hierarchical sentence graph offline by first adapting Rhetorical Structure Theory to distinguish nucleus and satellite sentences, and then organizing them into topic-level subgraphs with cross-document entity bridges. During online retrieval, SentGraph performs graph-guided evidence selection and path expansion to retrieve fine-grained sentence-level evidence. Extensive experiments on four multi-hop question answering benchmarks demonstrate the effectiveness of SentGraph, validating the importance of explicitly modeling sentence-level logical dependencies for multi-hop reasoning.

cs.CL↗