Searcharxiv⌕ Search

arXiv subjects

Bowen Wang

Publications and source records attributed to Bowen Wang.

At least 19 recordsLinked to original sources
arXiv2026

BRF-GS: Hyperspectral Bidirectional Reflectance Factor Modeling and Image Generation Based on 3D Gaussian Splatting

The bidirectional reflectance factor (BRF) characterizes the directional radiative properties of terrestrial surfaces. However, existing three-dimensional (3D) radiative transfer models require complex scene construction and computationally intensive radiative transfer solvers, limiting efficient generation of multi-angle hyperspectral reflectance imagery. 3D Gaussian Splatting (3DGS) offers an efficient framework for neural scene representation and novel view synthesis, but its low-order spherical harmonics representation is insufficient for complex directional reflectance, while the high dimensionality and inter-band quality differences of hyperspectral data introduce additional challenges. To address these challenges, we propose BRF-GS, a 3DGS-based framework for BRF modeling and hyperspectral reflectance image generation. BRF-GS introduces a hybrid BRDF-driven kernel to represent complex directional reflectance, selects geometry-reliable spectral bands for robust 3D scene initialization, and adopts a two-stage training strategy that decouples geometry optimization from spectral modeling. We further construct the AIR-BRF dataset, a multi-angle hyperspectral directional reflectance dataset comprising three scenes with diverse natural and artificial targets. Experiments demonstrate that BRF-GS achieves superior spatial and spectral fidelity and accurately reproduces characteristic view-dependent BRF responses. The proposed framework provides an efficient data-driven approach for BRF modeling and multi-angle hyperspectral reflectance image generation in remote sensing scenes.

cs.CV↗
arXiv2026

The Blending Ratio Is Not Where the Performance Is: Diagnosing Prototype Blending for Few-Shot Adaptation of Vision-Language Models

Many few-shot adaptation methods for vision-language models classify with a convex combination of the zero-shot text prototype and the mean of the K labelled image features, with a single blending ratio routinely tuned on held-out labels, often on the test set itself. We ask what the family's own bias-variance justification invites: what is the right ratio, can it be estimated without validation data, and is finding it where the performance is? First, the ratio minimising prototype mean-squared error has a closed form whose support-set plug-in is exactly a positive-part James-Stein coefficient shrinking towards the text prototype. Across 4,800 cells (ten datasets, five backbones including SigLIP, five shot counts, five seeds, four prompt tiers) this theoretically optimal ratio is a reliable estimate of the wrong quantity: on the 950 primary-tier cells where it is defined it trails a test-set-oracle ratio by 8.5 points. It saturates near 1, discarding the text prior for a nearest-class-mean classifier, because 78% of the text-image prototype distance it treats as bias is a class-independent offset that the arg max largely cancels. We prove the mechanism and bound its share of the damage at 26% by a counterfactual. Second, leave-one-out on the support set alone sets a ratio landing within 0.9 points of the oracle blend, so it is estimable without validation data. Third, validation-free linear probes beat even the oracle-tuned blend: CLAP by +1.9 points and LP++ by +1.5 on average, and at K >= 4 all four validation-free baselines sit above the oracle, the linear probes by margins excluding zero. These results locate the ceiling in the model class, not the hyperparameter: the ratio can be set near-optimally for free, and it is still not where the performance is. Code, cached features, per-cell records: https://huggingface.co/datasets/Liangzhi-Li/clipbench-blending

cs.CV↗
arXiv2026

Qwen-CUA: Native Computer Use for (almost) Everything

Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive experience, and learning from sparse yet verifiable outcomes. We introduce Qwen-CUA, a native computer-use agent with a 397B-A17B Qwen mixture-of-experts backbone. It observes only screenshots and acts through keyboard and mouse events, without DOM trees, accessibility metadata, or task-specific APIs. Its scaffold maintains up to 20 active screenshots and folds older visual history in fixed-size blocks to retain recent evidence while preserving reusable prompt prefixes. For training, we build a cloud rollout fleet with access to nearly 100,000 vCPUs and tens of thousands of concurrent environments, construct approximately 40,000 verifiable tasks, and collect personalized long-horizon workflows across everyday and professional software. We optimize complete trajectories with verifiable rewards and trajectory slicing, while iterative training runs refresh supervised data and recalibrate reinforcement-learning tasks. Across eight benchmarks, Qwen-CUA outperforms Qwen3.7 and remains competitive with leading proprietary systems, reaching 86.2 on OSWorld-Verified and 18.5/48.4 binary/partial completion on OSWorld 2.0. Scaling the same recipe to a model with over one trillion parameters yields Qwen-CUA-Max, improving these scores to 87.6 and 21.2/53.3. Qwen-CUA also reduces RedTeamCUA attack success from 36.6 to 16.4 relative to Qwen3.7. Efficiency analyses, a browser deployment, and Bash-augmented experiments further characterize practical behavior. These results establish native computer use as a broadly capable agent foundation and highlight scalable verifiable interaction and hybrid tool use as key directions.

cs.LG↗
arXiv2026

DS@GT ARC at ImageCLEFmedical 2026: Architectural Diversity for Concept Detection and Foundation-Model Scaling for Caption Prediction in Medical Image Analysis

We describe the DS@GT submissions to the ImageCLEFmedical Caption 2026 challenge, which continues a long-running benchmark on the ROCOv2 dataset with two tracks: Concept Detection (Task 1), assigning UMLS Concept Unique Identifiers (CUIs) to radiology images, and Caption Prediction (Task 2), generating natural-language captions. For Task 1, our primary submission was a three-way late-fusion ensemble of ConvNeXt-V2, BiomedCLIP ViT-B/16, and DenseNet-169 with a regularized ''Honest Threshold Tuning'' procedure designed to avoid validation overfitting on rare concepts; this submission ranked first on the official submission with a primary $F_1$ of $0.5790$ and a secondary $F_1$ of $0.9657$. In parallel, we submitted a training-free KNN retrieval pipeline over frozen BiomedCLIP embeddings, which reached a primary $F_1$ of $0.5780$ and a secondary $F_1$ of $0.9599$-essentially matching the fine-tuned ensemble on the primary track at a fraction of the cost. For Task 2, our submissions included a fine-tuned Gemma-3 27B model (overall $0.3571$, ranking third in the official submission), a fully fine-tuned BLIP pipeline with custom Vizwins merging ($0.3564$), and a zero-shot MedGemma-4B run with a PubMed-style prompt ($0.3186$), spanning a wide range of model scales and training costs. Code: https://github.com/dsgt-arc/imageclef-caption-2026.

cs.CV↗
arXiv2026

At-the-Roofline Sparse Tensor Contractions on Vector Processors for Transformer Inference

Fine-grained weight pruning and activation sparsification have emerged as effective approaches for reducing the compute and memory cost of inference for Transformer models. In the moderate-sparsity regime, Gustavson's dataflow provides a natural execution model for exploiting both activation and weight sparsity on vector processors through metadata-driven indexed accumulation. However, existing RVV architectures lack native support for this pattern, forcing kernels to rely on software index decoding and L1-backed indexed memory operations that keep sparse tensor contractions far below their roofline performance bound. We present Ventaglio, a runtime-configurable sparse execution unit coupled with RVV ISA extensions that drives sparse tensor contractions toward their roofline through indexed gather-accumulate-scatter support. Integrated into an open-source vector processing cluster and implemented in 12nm FinFET, Ventaglio accelerates sparse tensor contraction kernels by $6.9\text{--}7.4\times$ over optimized RVV baselines, with only $3.1\%$ area overhead for a cluster of tightly-L1 coupled vector processing elements. We build a performance-accurate instruction-level model of the Ventaglio extension, calibrate it against RTL implementation, and leverage it for scale-out performance analysis on a large $4\times4$ multi-cluster system. Using a DuoGPT-pruned LLaMA-3-8B model with practical $40\text{--}60\%$ dual sparsity, Ventaglio achieves $2.40\text{--}5.25\times$ and $2.06\text{--}3.16\times$ speedup over dense baselines during prefill and autoregressive decoding, respectively.

cs.AR↗
arXiv2026

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents. We introduce OSWorld 2.0, a benchmark of 108 long-horizon computer-use workflows across everyday and professional tasks, designed to capture complex and challenging real-world phenomena. Each task represents a realistic end-to-end workflow that takes human users a median of about 1.6 hours to complete and requires an average of 318 tool calls with Claude Opus 4.7 using maximum thinking, compared with about 30 in OSWorld 1.0. OSWorld 2.0 targets challenge phenomena that are common in real workflows yet underrepresented in prior benchmarks, spanning interaction-design challenges such as streaming interaction and dynamic environments, as well as agent-pattern challenges such as cross-source reasoning, implicit-state inference, and visual-spatial precision. Tasks are grounded in authentic input artifacts and cross-referenced against realistic stateful user profile data, and include separate safety reports auditing safety-sensitive execution. Under our primary binary-completion metric at 500 steps, Claude Opus 4.8 with maximum thinking and batched tool calls scores best but still completes only 20.6% of tasks at a 54.8% partial score; GPT-5.5 is far more token-efficient yet plateaus near 13%. These results show that current agents are still far from professional-level computer use: rather than stumbling on basic GUI control or coding, they lose track of constraints, miss information that arrives mid-task, guess rather than ask the user, and skip verification, struggling most when a task hinges on hidden state they must recover.

cs.AI↗
arXiv2026

Carbon Layer Orientation and Closed-Pore Construction Achieving Ultra-Low Specific Surface Area Hard Carbon for High-Performance Na-ion Storage

Addressing the critical trade-off between initial Coulombic efficiency (ICE) and reversible capacity in hard carbon anodes for Na-ion batteries (NIBs), we introduce a novel coupling strategy that combines carbon layer orientation reconstruction with closed-pore construction to produce hard carbon with an ultra-low specific surface area. We demonstrate that the nanographite domains within the hard carbon precursor undergo entropy-driven orientation reconstruction through the synergistic regulation of heteroatom doping and medium-temperature carbonization. This process not only increases interlayer spacing and promotes structural disorder but also enables the formation of dense, closed pores and ultramicropores at domain boundaries via confined atomic migration, while simultaneously encapsulating surface open pores within internal closed ones. Due to this unique pore architecture, our hard carbon exhibits an ultra-low specific surface area of 1.89 m2 g-1 with a markedly higher proportion of closed pores. As a result, our hard carbon achieves a remarkable reversible capacity of 342.3 mAh g-1 at 20 mA g-1, with an exceptional ICE of 90.4% and a dominant plateau capacity of 262.3 mAh g-1 (76.6%) for NIBs. We believe this coupling strategy provides a new paradigm for the structural engineering of high-ICE anode materials in advanced NIBs.

cond-mat.mtrl-sci↗
arXiv2026

Towards Healthy Evolution: Exploring the Role and Mechanisms of Human-Agent Interaction in Self-Evolving Systems

Self-evolving agents improve through continual self-play and self-generated learning signals, but autonomous evolution can also cause capability degradation and safety drift. Although human feedback has proven effective for static and post-trained agents, its role in self-evolving systems remains underexplored. We introduce Agent Norm Correction through Human-like Oversight and Review (ANCHOR), an LLM-based framework that simulates human supervision and delivers feedback at various phases of self-evolution. With ANCHOR, we evaluate two representative open-source self-evolving agent systems across coding, mathematical reasoning, and safety. Our results show that even limited supervision substantially mitigates safety degradation while preserving stable performance on core evolutionary objectives. Further analysis shows that supervision over the output verification phase is the most effective for intervention, whereas increasing supervision frequency yields diminishing returns. These findings provide empirical evidence and practical guidance for designing more stable, controllable, and human-aligned self-evolving agent systems.

cs.AI↗
arXiv2026

Spatiotemporal Tracking in Cooperative ISAC Networks: A Stochastic Geometry Framework

We adopt a stochastic-geometry framework to study continuous target tracking in integrated sensing and communication (ISAC) networks, with base-station locations modelled as a Poisson point process. The single-BS analysis shows that the antenna energy-conservation identity forces the mean inter-BS coupling gain to unity, making densification an antenna-irreducible liability for monostatic sensing, while a first-passage-time analysis reveals a target-distance-dependent beamwidth trap. These findings rule out single-BS tracking under densification, motivating a multi-BS cooperative treatment. The static-cluster cooperative mean tracking lifetime is then shown to exhibit a sharp percolation phase transition, with the resulting sensing-capacity ceiling saturating above a critical macro density. Yet the static-cluster idealisation itself misrepresents modern network deployments, where the cooperating cluster is dynamically re-selected as the target drifts; we therefore lift this assumption with a dynamic clustering model that maps the $K$-nearest-neighbour handover onto a 2D Brownian motion with stochastic resetting, and obtain a Bessel-function closed form for the dynamic mean tracking lifetime that dissolves the phase transition under any positive handover rate. With a per-link reliability floor, the dynamic clustering framework preserves classical linear density scaling throughout the realistic 6G regime and delivers an order-of-magnitude capacity lift at small-cell densities. Monte-Carlo simulations corroborate all theoretical predictions.

eess.SP↗
arXiv2026

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents

Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agents (CUAs) has been bottlenecked by the scarcity of scalable training data with deterministic rewards. Constructing such data for CUAs requires consistent task instruction, executable environment, and verifiable reward. However, hand-curated benchmarks achieve high reward fidelity but cover few applications and LLM-as-judge-based datasets scale broadly but lack reliable verification. We present CUA-Gym, a scalable pipeline that co-generates task instructions, environment states, and reward functions. Concretely, a Generator agent constructs the initial and golden environment states, and a separate Discriminator agent writes the reward function from the task specification. An orchestrator agent drives the two through iterative rounds upon execution. Generated tuples then pass a final filter combining LLM majority voting and agent rollouts, ensuring quality beyond the per-task adversarial loop. To address the scarcity of training environments, we further synthesize CUA-Gym-Hub, a broad suite of high-fidelity mock web applications grounded in real-world software-use distributions, expanding the scale of CUA RLVR data by magnitude. Using this pipeline, we construct CUA-Gym, a dataset of 32,112 verified RLVR training tuples grounded in 110 environments. Trained with GSPO on CUA-Gym, our CUA-Gym-A3B and CUA-Gym-A17B achieve 62.1% and 72.6% on OSWorld-Verified, outperforming prior open-source CUAs at comparable scales, with performance scaling smoothly in both data volume and environment diversity. The same checkpoints also improve on the held-out WebArena benchmark, indicating transfer beyond the training environments. We will open-source the full synthesis pipeline, dataset, CUA-Gym-Hub environments, and models.

cs.AI↗
arXiv2026

Online Conformal Prediction with Corrupted Feedback

Modern artificial intelligence systems require calibrated uncertainty estimates that remain reliable in sequential and non-stationary environments. Online conformal prediction (OCP) addresses this challenge through adaptively updated prediction sets that provide deterministic long-run miscoverage guarantees. These guarantees, however, hinge on the assumption of perfect feedback about the coverage of past prediction sets. In practice, the observed miscoverage indicator may be corrupted by noise, communication failures, or adversarial manipulation, which can severely degrade OCP's calibration guarantees. In this paper, we study OCP under corrupted feedback. We first model feedback corruption as an arbitrary binary flip sequence, and analyze how feedback corruption affects and degrades the miscoverage performance of standard OCP. We then propose two robust schemes: robust OCP via filtering, which leverages the structural properties of the predicted threshold to filter corrupted feedback, and robust OCP via active compensation, which incorporates an active compensation mechanism to mitigate the effect of corrupted feedback. For both methods, we establish explicit miscoverage guarantees, which are further specialized for an independent stochastic flip model and for an arbitrary error model with memory bounds. Experiments on real-world datasets validate the proposed approach, showing markedly improved calibration and significantly smaller prediction sets compared with baseline OCP methods under corrupted feedback.

cs.LG↗
arXiv2026

Accelerating Precise End-to-End Simulation: Latency-Sensitive Many-core System Modeling

Modern large language model workloads put increasing demands on parallel compute capability and on-chip memory capacity, while also stressing fine-grained data movement and synchronization. These trends motivate exploring and designing many-core accelerators with tightly coupled scratchpad memory (SPM) for scalable compute and predictable, explicitly managed data access. However, this architectural shift raises two challenges: cycle-accurate register-transfer level (RTL) simulation becomes prohibitively slow as system complexity grows, and performance estimation requires precise modeling of latency-sensitive interconnect behavior. This paper presents a fast yet accurate end-to-end modeling approach for latency-sensitive many-core architectures, targeting large-scale instances such as TeraNoC with 1024 cores and a 4MiB globally shared L1 SPM. The approach captures timing behavior of latency-sensitive SPM accesses across multiple interconnect scales, while abstracting non-essential hardware details. Across diverse benchmarks, the model tracks a cycle-accurate RTL golden model with errors below 7%, while delivering up to 115x faster simulation. The framework also provides detailed profiling across processing elements and interconnect, enabling efficient end-to-end software development and hardware design exploration. Two case studies demonstrate its practicality: profiling-guided optimization of FlashAttention-2 to reduce interconnect stalls and synchronization overhead, and design space exploration of network-on-chip (NoC) router remapping to alleviate traffic imbalance and improve throughput.

cs.AR↗
arXiv2026

Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization

Current LLM agent benchmarks, which predominantly focus on binary pass/fail tasks such as code generation or search-based question answering, often neglect the value of real-world engineering that is often captured through the iterative optimization of feasible designs. To this end, we introduce Frontier-Eng, a human-verified benchmark for generative optimization -- an iterative propose-execute-evaluate loop in which an agent generates candidate artifacts, receives executable verifier feedback, and revises them under a fixed interaction budget -- spanning $47$ tasks across five broad engineering categories. Unlike previous suites, Frontier-Eng tasks are grounded in industrial-grade simulators and verifiers that provide continuous reward signals and enforce hard feasibility constraints under constrained budgets. We evaluate eight frontier language models using representative search frameworks, finding that while GPT 5.4 achieves the most robust performance, the benchmark remains challenging for all models. Our analysis suggests a dual power-law decay in improvement frequency ($\sim$ 1/iteration) and magnitude ($\sim$ 1/improvement count). We further show that although width improves parallelism and diversity, depth remains crucial for hard-won improvements under a fixed budget. Frontier-Eng establishes a new standard for assessing the capacity of AI agents to integrate domain knowledge with executable feedback to solve complex, open-ended engineering problems.

cs.AI↗
arXiv2026

TeraPool: A Physical Design Aware, 1024 RISC-V Cores Shared-L1-Memory Scaled-up Cluster Design with High Bandwidth Main Memory Link

Shared L1-memory clusters of streamlined instruction processors (processing elements - PEs) are commonly used as building blocks in modern, massively parallel computing architectures (e.g. GP-GPUs). Scaling out these architectures by increasing the number of clusters incurs computational and power overhead, caused by the requirement to split and merge large data structures in chunks and move chunks across memory hierarchies via the high-latency global interconnect. Scaling up the cluster reduces buffering, copy, and synchronization overheads. However, the complexity of a fully connected cores-to-L1-memory crossbar grows quadratically with PE-count, posing a major physical implementation challenge. We present TeraPool, a physically implementable, >1000 floating-point-capable RISC-V PEs scaled-up cluster design, sharing a Multi-MegaByte >4000-banked L1 memory via a low latency hierarchical interconnect (1-7/9/11 cycles, depending on target frequency). Implemented in 12nm FinFET technology, TeraPool achieves near-gigahertz frequencies (910MHz) typical, 0.80 V/25C. The energy-efficient hierarchical PE-to-L1-memory interconnect consumes only 9-13.5pJ for memory bank accesses, just 0.74-1.1x the cost of a FP32 FMA. A high-bandwidth main memory link is designed to manage data transfers in/out of the shared L1, sustaining transfers at the full bandwidth of an HBM2E main memory. At 910MHz, the cluster delivers up to 1.89 single precision TFLOP/s peak performance and up to 200GFLOP/s/W energy efficiency (at a high IPC/PE of 0.8 on average) in benchmark kernels, demonstrating the feasibility of scaling a shared-L1 cluster to a thousand PEs, four times the PE count of the largest clusters reported in literature.

cs.DC↗
arXiv2026

Edge AI Inference in ISCC Networks: Sensing Accuracy Analysis and Precoding Design

This work explores the relationship between sensing accuracy and precoding coefficients for edge artificial intelligence (AI) inference in integrated sensing, communication and computation (ISCC) networks. We start by constructing a system model of an over-the-air-empowered ISCC network for edge AI inference, involving distributed edge sensors for feature extraction and an edge server for classification. Based on this model, we introduce a discriminant gain (DG) to characterize sensing accuracy and novelly derive an explicit function of the DG about precoding coefficients, giving valuable insights into precoding design. Guided by this, we propose an effective precoding algorithm to solve a non-convex DG-maximization problem. Simulation results demonstrate that the proposed design achieves up to 15% and 10% sensing accuracy improvements on synthetic and real-world datasets, respectively, over the conventional scheme at low SNR, thereby validating its effectiveness and superiority for edge AI inference in ISCC networks.

eess.SP↗
arXiv2025

Let the Barbarians In: How AI Can Accelerate Systems Performance Research

Artificial Intelligence (AI) is beginning to transform the research process by automating the discovery of new solutions. This shift depends on the availability of reliable verifiers, which AI-driven approaches require to validate candidate solutions. Research focused on improving systems performance is especially well-suited to this paradigm because system performance problems naturally admit such verifiers: candidates can be implemented in real systems or simulators and evaluated against predefined workloads. We term this iterative cycle of generation, evaluation, and refinement AI-Driven Research for Systems (ADRS). Using several open-source ADRS instances (i.e., OpenEvolve, GEPA, and ShinkaEvolve), we demonstrate across ten case studies (e.g., multi-region cloud scheduling, mixture-of-experts load balancing, LLM-based SQL, transaction scheduling) that ADRS-generated solutions can match or even outperform human state-of-the-art designs. Based on these findings, we outline best practices (e.g., level of prompt specification, amount of feedback, robust evaluation) for effectively using ADRS, and we discuss future research directions and their implications. Although we do not yet have a universal recipe for applying ADRS across all of systems research, we hope our preliminary findings, together with the challenges we identify, offer meaningful guidance for future work as researcher effort shifts increasingly toward problem formulation and strategic oversight. Note: This paper is an extension of our prior work [14]. It adds extensive evaluation across multiple ADRS frameworks and provides deeper analysis and insights into best practices.

cs.SE↗
arXiv2025

Design in Tiles: Automating GEMM Deployment on Tile-Based Many-PE Accelerators

Tile-based many-Processing Element (PE) accelerators can achieve competitive performance on General Matrix Multiplication (GEMM), but they are extremely hard to program, as their optimal software mapping is deeply coupled with hardware design which is unwieldy to manual deployment. We propose "Design in Tiles (DiT)", an automated framework connecting a deployment toolchain with a configurable executable model for these accelerators. For evaluation, we apply our framework to GEMM targeting a large acceleration configuration (e.g., 32x32 tiles, 1979 TFLOPS@FP8, 4 TB/s Bandwidth) comparable to an NVIDIA GH200. We achieve higher PE utilization than GH200 with its expert-tuned GEMM libraries, achieving 1.2-2.0x speedup across diverse matrix shapes.

cs.DC↗
arXiv2025

dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model

Document Layout Parsing serves as a critical gateway for Artificial Intelligence (AI) to access and interpret the world's vast stores of structured knowledge. This process,which encompasses layout detection, text recognition, and relational understanding, is particularly crucial for empowering next-generation Vision-Language Models. Current methods, however, rely on fragmented, multi-stage pipelines that suffer from error propagation and fail to leverage the synergies of joint training. In this paper, we introduce dots_ocr, a single Vision-Language Model that, for the first time, demonstrates the advantages of jointly learning three core tasks within a unified, end-to-end framework. This is made possible by a highly scalable data engine that synthesizes a vast multilingual corpus, empowering the model to deliver robust performance across a wide array of tasks, encompassing diverse languages, layouts, and domains. The efficacy of our unified paradigm is validated by state-of-the-art performance on the comprehensive OmniDocBench. Furthermore, to catalyze research in global document intelligence, we introduce XDocParse, a challenging new benchmark spanning 126 languages. On this benchmark, dots_ocr achieves state-of-the-art performance, delivering an approximately 10% relative improvement and demonstrating strong multilingual capability.

cs.CV↗