Showing 1–50 of 357 results for author: Liang, G

Agent-Based Test Assertion Generation via Diverse Perspective Aggregation

Authors: Dong Wang, Qiaoyu Han, Lin Yang, Jianyi Zhou, Guangtai Liang, Junjie Chen

Abstract: Test assertions are critical elements of unit tests, serving as checkpoints to validate expected behavior and ensure software correctness. Numerous techniques have been proposed to automate assertion generation, with recent progress notably driven by large language models (LLMs). Despite the promise, existing approaches such as ChatAssert suffer from modest accuracy, heavy reliance on oversampling… ▽ More Test assertions are critical elements of unit tests, serving as checkpoints to validate expected behavior and ensure software correctness. Numerous techniques have been proposed to automate assertion generation, with recent progress notably driven by large language models (LLMs). Despite the promise, existing approaches such as ChatAssert suffer from modest accuracy, heavy reliance on oversampling, and vulnerability to model randomness due to one-shot prompting. To address these limitations, we propose AssertMate, a novel agent-based assertion generation framework that enhances the quality and reliability of LLM-generated assertions through three key components: (1) actual value construction that identifies assertion targets via static analysis and type-aware heuristics; (2) multi-perspective expected value prediction using code generation, retrieval-augmented generation (RAG), and chain-of-thought (CoT) reasoning agents; and (3) an LLM-as-a-Judge collaboration mechanism to select the most appropriate assertion. Evaluation on the Defects4J benchmark demonstrates that AssertMate significantly outperforms state-of-the-art techniques in compilation success and pass rates, along with substantially higher bug detection capabilities. Integration with EvoSuite further validates AssertMate's practicality, yielding superior mutation coverage and kill counts. Ablation studies reveal that each of the three components makes a significant and complementary contribution to the overall performance. This work affirms the great potential of aggregating diverse perspectives to enhance the effectiveness of LLM-based assertion generation. △ Less

Submitted 6 August, 2026; originally announced August 2026.

Context Matters: Improving the Practical Reliability of LLM-Based Unit Test Generation

Authors: Junjie Chen, Ziqi Wang, Lin Yang, Chen Yang, Xiao Chu, Jianyi Zhou, Guangtai Liang, Qianxiang Wang, Dong Wang

Abstract: Automated unit test generation has recently benefited from advances in large language models (LLMs), yet our industrial deployments reveal a persistent gap between promising research results and practical usability. In real-world projects with complex frameworks and cross-file dependencies, LLM-generated tests frequently fail to compile, require costly manual repair, or provide unstable coverage i… ▽ More Automated unit test generation has recently benefited from advances in large language models (LLMs), yet our industrial deployments reveal a persistent gap between promising research results and practical usability. In real-world projects with complex frameworks and cross-file dependencies, LLM-generated tests frequently fail to compile, require costly manual repair, or provide unstable coverage improvements. This paper reports our experience in designing, deploying, and evaluating CATGen, a context-aware workflow for LLM-based unit test generation, informed by repeated industrial failures and refinements. Rather than relying on LLMs to infer incomplete project context, we found that compilation robustness critically depends on making project-level dependencies explicit, stabilizing test class scaffolding, and replacing iterative LLM-based repair with lightweight static analysis. These experience-driven insights shaped CATGen's multi-stage design, which combines structured context retrieval, deterministic test skeleton construction, and program analysis-based post-processing. We evaluate CATGen on real-world complex focal methods from proprietary industrial projects and additionally on the Defects4J benchmark to assess generalizability. Across both settings, CATGen substantially improves compilation success and structural coverage while significantly reducing generation time and token consumption compared to existing LLM-based approaches. Our results demonstrate that reliable LLM-based unit test generation in practice depends less on prompt engineering alone and more on systematic engineering support grounded in real-world development constraints. △ Less

Submitted 21 July, 2026; originally announced July 2026.

Comments: 23 pages, 5 figures, 7 tables

ACM Class: D.2.5; I.2.7

Connectivity-induced surface-loss penalty in superconducting qubit-coupler lattices

Authors: Xu-Yang Gu, Gui-Han Liang, Ming-Chuan Wang, Yongxi Xiao, Cheng-Lin Deng, Zheng-He Liu, Tian-Ming Li, Kai Xu, Zhongcheng Xiang, Heng Fan

Abstract: Recent advances in design and fabrication have increased the energy-relaxation times of isolated superconducting transmon qubits to the hundreds-of-microseconds regime, with reported values exceeding 500 $μ$s. However, the same progress has not automatically translated to multiqubit processors, where qubits are embedded in connected qubit-coupler lattices and often exhibit much shorter lifetimes t… ▽ More Recent advances in design and fabrication have increased the energy-relaxation times of isolated superconducting transmon qubits to the hundreds-of-microseconds regime, with reported values exceeding 500 $μ$s. However, the same progress has not automatically translated to multiqubit processors, where qubits are embedded in connected qubit-coupler lattices and often exhibit much shorter lifetimes than isolated qubits. To identify possible sources of this discrepancy, here we use finite-element simulation to investigate how surface participation ratios and the resulting surface dielectric loss change when a qubit is embedded in a flip-chip qubit-coupler lattice. Controlled comparisons show that higher connectivity can indeed lead to larger surface loss: in the simulated lattice, connecting a qubit to two and four couplers increases the surface loss by factors of 1.3 and 1.8, respectively. We attribute this change to the combined effects of added edge fields from coupling claws, field redistribution over the larger connected metal network, and hybridization with coupler modes. We further examine how this connectivity-induced surface-loss penalty depends on the geometric design parameters of both the qubit electrodes and the coupling claws, and derive guidelines for designing low-loss multiqubit processors. △ Less

Submitted 12 July, 2026; originally announced July 2026.

Learning to Annotate Delayed and False AEB Events: A Practical System for Extreme Class Imbalance and Asymmetric Label Noise

Authors: Mengxiang Hao, Xin Jiang, Xinghao Huang, Wenliang Su, Zhiteng Wang, Junjie Rao, Xiaotian Yang, Wei Liao, Chengyu Han, Gen Liang, Yulun Song, Zhitao Xu, Xianpeng Lang

Abstract: Autonomous Emergency Braking (AEB) optimization relies on accurately annotated real-world trigger events, particularly rare but critical delayed and false AEB triggers that expose system deficiencies. However, these minority samples comprise less than 5% of thousands of daily triggers, making manual annotation prohibitively expensive at scale. We present the first automated AEB annotation framewor… ▽ More Autonomous Emergency Braking (AEB) optimization relies on accurately annotated real-world trigger events, particularly rare but critical delayed and false AEB triggers that expose system deficiencies. However, these minority samples comprise less than 5% of thousands of daily triggers, making manual annotation prohibitively expensive at scale. We present the first automated AEB annotation framework to address this problem. During development, we identified two fundamental challenges that severely impair delayed/false trigger annotation accuracy: (1) Extreme class imbalance where delayed/false triggers are overwhelmed by true triggers; (2) Asymmetric label noise where mislabeled majority samples (true triggers) suppress minority samples (delayed/false triggers) learning. To overcome these challenges, we propose two key innovations: (1) Specific data augmentation that synthesizes realistic samples by manipulating focal target attributes, transplanting ego-vehicle dynamics, and masking non-focal agents; (2) noise suppression using stable hardness estimation and probe-guided adaptive threshold to clean mislabeled true trigger samples. Crucially, we deploy our model as a practical annotation system with full-stack architecture, efficiently identifying critical delayed/false triggers from thousands of daily AEB events. Production results demonstrate 80% improvement in recall of delayed/false triggers and 50% reduction in manual workload. Beyond immediate gains, the system enables continuous self-improvement through accumulated high-quality annotations, establishing a necessary data foundation for on-vehicle AEB system optimization △ Less

Submitted 17 June, 2026; v1 submitted 17 June, 2026; originally announced June 2026.

Comments: 8 pages, 5 figures, accepted by IEEE International Conference on Robotics and Automation (ICRA)

Journal ref: 2026 IEEE International Conference on Robotics and Automation (ICRA)

Programmable spectral symmetries in an anisotropic quantum Rabi simulator

Authors: Jia-Cheng Song, Yu Liu, Ming-Chuan Wang, Ke-Xiong Yan, Yang He, Yun-Hao Shi, Wei-Ping Yuan, Cheng-Lin Deng, Li Li, Zhen-Ting Bao, Yutao Chen, Xu-Yang Gu, Tian-Ming Li, Gui-Han Liang, Zheng-He Liu, Wei-Guo Ma, Zhen-Yu Peng, Shuai-Li Wang, Yong-Xi Xiao, Yi-Han Yu, Jia-Chi Zhang, Kui Zhao, Min-Xuan Zhou, Kaixuan Huang, Yu-Ran Zhang , et al. (6 additional authors not shown)

Abstract: The quantum Rabi model captures fundamental aspects of light--matter interaction, where symmetry dictates both spectra and dynamics. Over the past years, experiments have explored many of its nonperturbative properties, but have mostly focused on the isotropic limit, where rotating and counterrotating processes are locked together, leaving the broader symmetry landscape largely unexplored. Here we… ▽ More The quantum Rabi model captures fundamental aspects of light--matter interaction, where symmetry dictates both spectra and dynamics. Over the past years, experiments have explored many of its nonperturbative properties, but have mostly focused on the isotropic limit, where rotating and counterrotating processes are locked together, leaving the broader symmetry landscape largely unexplored. Here we realize a programmable anisotropic quantum Rabi model in a superconducting processor, with independent control of the rotating and counterrotating couplings $(g_1,g_2)$ and of a transverse bias $\varepsilon$. Continuous anisotropy tuning, combined with a duality mapping, gives access to the full parameter space from the Jaynes-Cummings to the anti-Jaynes-Cummings limits. In the deep-strong-coupling regime, we show that anisotropy reconstructs the spectrum and turns complete collapse-revival dynamics into incomplete revivals even near degeneracy. With adiabatic state preparation and joint tomography, we resolve an anisotropy-induced ground-state parity switch, a crossing that has no analogue in the isotropic model. We further observe selective tunnelling associated with hidden symmetry in biased Rabi models and track its anisotropic displacement within the same device. These results establish a controllable route to engineering nonperturbative light--matter Hamiltonians, where symmetry, spectrum, and dynamics can be programmed independently. △ Less

Submitted 3 June, 2026; originally announced June 2026.

Head-Aware Key-Value Compression for Efficient Autoregressive Image Generation

Authors: Guotao Liang, Baoquan Zhang, Zhiyuan Wen, Yunming Ye

Abstract: Autoregressive (AR) visual generation has achieved remarkable performance but suffers from high memory usage and low throughput, as it requires caching previously generated visual tokens. Recent research has shown that retaining only a few lines of cache tokens can maintain high-quality images while significantly reducing memory usage and improving throughput. However, these methods allocate a fix… ▽ More Autoregressive (AR) visual generation has achieved remarkable performance but suffers from high memory usage and low throughput, as it requires caching previously generated visual tokens. Recent research has shown that retaining only a few lines of cache tokens can maintain high-quality images while significantly reducing memory usage and improving throughput. However, these methods allocate a fixed budget to each attention head, overlooking the heterogeneity among attention heads, leading to suboptimal memory allocation. In this paper, we observe that attention heads across different layers exhibit diverse attention patterns, where some heads focus on local neighborhoods while others capture broader contextual dependencies. Based on this insight, we propose a novel head-aware key-value (KV) cache compression framework for autoregressive image generation, called HeadKV, which assigns smaller budgets to locality-biased heads and larger budgets to heads with broader attention. A key challenge lies in identifying the type of each attention head to guide cache compression. We further observe that, within the same layer, each head exhibits consistent attention patterns across token positions, \emph{i.e.}, a head's behavior for early tokens remains consistent with that for later tokens. This insight suggests that head types can be identified during the early stage and reused for KV compression throughout generation. Its advantage is that it requires no additional training or dataset-level statistics and generalizes seamlessly across different inputs. Moreover, we design a Stratified Token Eviction strategy to effectively preserve long-range information. Extensive experiments demonstrate its effectiveness across multiple autoregressive image generation models. △ Less

Submitted 19 May, 2026; originally announced May 2026.

Comments: Under review

Degradation-Aware Blur-Segmentation of Brain Tumor

Authors: Yuchun Wang, Xiaosong Li, Gefei Liang, Yang Liu

Abstract: Multimodal 3D MRI brain tumor segmentation is a pivotal step in radiotherapy target delineation, surgical planning and post-treatment assessment. Existing methods often assume artifact-free MRI images. However, inevitable patient motion during scanning introduces artifacts and blur that degrade boundary and texture features, leading to poor segmentation performance. To bridge this gap, we introduc… ▽ More Multimodal 3D MRI brain tumor segmentation is a pivotal step in radiotherapy target delineation, surgical planning and post-treatment assessment. Existing methods often assume artifact-free MRI images. However, inevitable patient motion during scanning introduces artifacts and blur that degrade boundary and texture features, leading to poor segmentation performance. To bridge this gap, we introduce Degradation-Aware Blur-Segmentation Net (DABSeg), a synchronous deblurring 3D multimodal MRI segmentation network that unifies blur removal and accurate segmentation. Specifically, we propose a feature-domain motion-deblurring stem to compensate for blur and rebalance intensity. Concurrently, the backbone network embeds a blur-aware cross-modal cross-attention module and multi-scale residual aggregation to yield effective modality complementarity. Notably, we optimize a joint loss that combines weighted Dice with a clear-reference reconstruction term, where imbalanced weights are applied to small targets to boost learning intensity and predictive stability for small lesions and border regions. Systematic comparisons and ablation experiments on the BraTS2020 dataset under both clear and degenerative conditions consistently demonstrate that DABSeg surpasses state-of-the-art methods in tumor Dice score and boundary precision. These results validate the effectiveness of degenerative-aware cross-task collaborative learning in improving the robustness and clinical utility of multi-modal 3D brain tumor segmentation under realistic degenerative conditions. The source code is available at https://github.com/YuchunWang24/DABSeg_ICPR △ Less

Submitted 15 May, 2026; originally announced May 2026.

Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance

Authors: Ziyun Zeng, Yiqi Lin, Guoqiang Liang, Mike Zheng Shou

Abstract: In recent years, open-source efforts like Senorita-2M have propelled video editing toward natural language instruction. However, current publicly available datasets predominantly focus on local editing or style transfer, which largely preserve the original scene structure and are easier to scale. In contrast, Background Replacement, a task central to creative applications such as film production a… ▽ More In recent years, open-source efforts like Senorita-2M have propelled video editing toward natural language instruction. However, current publicly available datasets predominantly focus on local editing or style transfer, which largely preserve the original scene structure and are easier to scale. In contrast, Background Replacement, a task central to creative applications such as film production and advertising, requires synthesizing entirely new, temporally consistent scenes while maintaining accurate foreground-background interactions, making large-scale data generation significantly more challenging. Consequently, this complex task remains largely underexplored due to a scarcity of high-quality training data. This gap is evident in poorly performing state-of-the-art models, e.g., Kiwi-Edit, because the primary open-source dataset that contains this task, i.e., OpenVE-3M, frequently produces static, unnatural backgrounds. In this paper, we trace this quality degradation to a lack of precise background guidance during data synthesis. Accordingly, we design a scalable pipeline that generates foreground and background guidance in a decoupled manner with strict quality filtering. Building on this pipeline, we introduce Sparkle, a dataset of ~140K video pairs spanning five common background-change themes, alongside Sparkle-Bench, the largest evaluation benchmark tailored for background replacement to date. Experiments demonstrate that our dataset and the model trained on it achieve substantially better performance than all existing baselines on both OpenVE-Bench and Sparkle-Bench. Our proposed dataset, benchmark, and model are fully open-sourced at https://showlab.github.io/Sparkle/. △ Less

Submitted 7 May, 2026; originally announced May 2026.

Comments: Tech Report. Project Page: https://showlab.github.io/Sparkle/

VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation

Authors: Guotao Liang, Zhangcheng Wang, Chuang Wang, Juncheng Hu, Haitao Zhou, Junhua Liu, Jing Zhang, Dong Xu, Qian Yu

Abstract: Scalable Vector Graphics (SVG) animation generation is pivotal for professional design due to their structural editability and resolution independence. However, this task remains challenging as it requires bridging discrete code representations with continuous visual dynamics. Existing optimization-based methods often destroy topological consistency, while general-purpose LLMs rely on rigid CSS/SM… ▽ More Scalable Vector Graphics (SVG) animation generation is pivotal for professional design due to their structural editability and resolution independence. However, this task remains challenging as it requires bridging discrete code representations with continuous visual dynamics. Existing optimization-based methods often destroy topological consistency, while general-purpose LLMs rely on rigid CSS/SMIL transformations, failing to model geometry-level non-rigid deformations. To address these limitations, we present VAnim, the first LLM-based framework for open-domain text-to-SVG animation. We reconceptualize animation not as sequence generation, but as Sparse State Updates (SSU) on a persistent SVG DOM tree. This paradigm compresses sequence length by over 9.8x while preserving the SVG DOM structure and non-participating elements by construction. To enable precise control, we propose an Identification-First Motion Planning mechanism that grounds textual instructions in explicit visual entities. Furthermore, to overcome the non-differentiable nature of SVG rendering, we employ Rendering-Aware Reinforcement Learning via Group Relative Policy Optimization (GRPO). By leveraging a hybrid reward from a state-of-the-art video perception encoder, we align discrete code updates with high-fidelity visual feedback. We also introduce SVGAnim-134k, the first benchmark for vector animation. Extensive experiments demonstrate that VAnim significantly outperforms state-of-the-art baselines in semantic alignment and structural validity, with additional appendix metrics further validating motion quality and identity preservation. △ Less

Submitted 2 May, 2026; originally announced May 2026.

Comments: Accepted to ICML 2026. Project page: https://yukinonooo.github.io/VAnimProject

Colinearity Decay: Training Quantization-Friendly ViTs with Outlier Decay

Authors: Jin Tong, Guang Liang, Peilin Sun, Jianxin Wu

Abstract: Low-bit quantization is a practical route for efficiently deploying vision Transformers, yet activation outliers complicate fully quantized deployment. Existing methods either handle quantization post-training or suppress large activations during training; however, aggressively restricting outliers in vision models can lead to a poorer trade-off between full-precision and quantized accuracy. We ar… ▽ More Low-bit quantization is a practical route for efficiently deploying vision Transformers, yet activation outliers complicate fully quantized deployment. Existing methods either handle quantization post-training or suppress large activations during training; however, aggressively restricting outliers in vision models can lead to a poorer trade-off between full-precision and quantized accuracy. We argue that rather than simply suppressing outliers, the training objective should control the structural amplification that makes them harmful. To this end, we introduce Colinearity-Decay (CD), a structural regularizer for ordered matrix pairs within Transformer blocks. CD penalizes detrimental cross-matrix alignment and mitigates extreme activations without altering the architecture or task loss. Applied as a decoupled update, CD is non-invasive and introduces minimal training overhead. Across ImageNet-1K pre-training, COCO detection, and downstream fine-tuning, CD consistently boosts quantized accuracy across multiple pipelines while preserving, or even improving, full-precision performance. Ultimately, our results demonstrate that structural regularization effectively prepares vision Transformers for low-bit deployment with zero inference-time overhead. △ Less

Submitted 2 May, 2026; originally announced May 2026.

Comments: 17 pages, 5 figures

Null-Space Flow Matching for MIMO Channel Estimation in Latency-Constrained Systems

Authors: Junjie Zhao, Guangming Liang, Xiaonan Liu, Dongzhu Liu

Abstract: Accurate yet low-latency channel state information (CSI) acquisition is essential for multiple-input multiple-output (MIMO) communication systems. While advanced deep generative models, such as score-based and diffusion models, enable high-fidelity CSI reconstruction from limited pilot observations, they often suffer from high inference latency. To achieve accurate CSI estimation under stringent l… ▽ More Accurate yet low-latency channel state information (CSI) acquisition is essential for multiple-input multiple-output (MIMO) communication systems. While advanced deep generative models, such as score-based and diffusion models, enable high-fidelity CSI reconstruction from limited pilot observations, they often suffer from high inference latency. To achieve accurate CSI estimation under stringent latency constraints, this paper proposes a null-space flow matching (FM) framework that leverages a range-null space decomposition to separate observation-informed and underdetermined channel components. Specifically, the pilot observations are used to regulate the observable range-space channel component, while an FM-based generative prior primarily resolves the ambiguous null-space degrees of freedom through iterative refinement. To further improve the robustness and efficiency of the proposed framework, we introduce a noise-aware adaptive correction strategy to suppress channel noise on the refinement trajectory, along with a power-law time schedule to better allocate the limited number of refinement steps. Experimental results demonstrate that our method achieves competitive normalized mean square error (NMSE) performance even under a strict latency budget of around 3 ms, while delivering a superior accuracy-latency tradeoff compared with both model-based and generative baselines. △ Less

Submitted 11 August, 2026; v1 submitted 23 April, 2026; originally announced April 2026.

Comments: 6 pages, 3 figures, 19 references

Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback

Authors: Guotao Liang, Zhangcheng Wang, Juncheng Hu, Haitao Zhou, Ziteng Xue, Jing Zhang, Dong Xu, Qian Yu

Abstract: Multimodal Large Language Models (MLLMs) have shown promising capabilities in generating Scalable Vector Graphics (SVG) via direct code synthesis. However, existing paradigms typically adopt an open-loop "blind drawing" approach, where models generate symbolic code sequences without perceiving intermediate visual outcomes. This methodology severely underutilizes the powerful visual priors embedded… ▽ More Multimodal Large Language Models (MLLMs) have shown promising capabilities in generating Scalable Vector Graphics (SVG) via direct code synthesis. However, existing paradigms typically adopt an open-loop "blind drawing" approach, where models generate symbolic code sequences without perceiving intermediate visual outcomes. This methodology severely underutilizes the powerful visual priors embedded in MLLMs vision encoders, treating SVG generation as a disjointed textual sequence modeling task rather than an integrated visuo-spatial one. Consequently, models struggle to reason about partial canvas states and implicit occlusion relationships, which are visually explicit but textually ambiguous. To bridge this gap, we propose Render-in-the-Loop, a novel generation paradigm that reformulates SVG synthesis as a step-wise, visual-context-aware process. By rendering intermediate code states into a cumulative canvas, the model explicitly observes the evolving visual context at each step, leveraging on-the-fly feedback to guide subsequent generation. However, we demonstrate that applying this visual loop naively to off-the-shelf models is suboptimal due to their inability to leverage incremental visual-code mappings. To address this, we first utilize fine-grained path decomposition to construct dense multi-step visual trajectories, and then introduce a Visual Self-Feedback (VSF) training strategy to condition the next primitive generation on intermediate visual states. Furthermore, a Render-and-Verify (RaV) inference mechanism is proposed to effectively filter degenerate and redundant primitives. Our framework, instantiated on a multimodal foundation model, outperforms strong open-weight baselines on the standard MMSVGBench. This result highlights the remarkable data efficiency and generalization capability of our Render-in-the-Loop paradigm for both Text-to-SVG and Image-to-SVG tasks. △ Less

Submitted 9 July, 2026; v1 submitted 22 April, 2026; originally announced April 2026.

Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning

Authors: Qin Zhou, Guoyan Liang, Qianyi Yang, Jingyuan Chen, Sai Wu, Chang Yao, Zhe Wang

Abstract: Recent reinforcement learning (RL) approaches have advanced radiology report generation (RRG), yet two core limitations persist: (1) report-level rewards offer limited evidence-grounded guidance for clinical faithfulness; and (2) current methods lack an explicit self-improving mechanism to align with clinical preference. We introduce clinically aligned Evidence-aware Self-Correcting Reinforcement… ▽ More Recent reinforcement learning (RL) approaches have advanced radiology report generation (RRG), yet two core limitations persist: (1) report-level rewards offer limited evidence-grounded guidance for clinical faithfulness; and (2) current methods lack an explicit self-improving mechanism to align with clinical preference. We introduce clinically aligned Evidence-aware Self-Correcting Reinforcement Learning (ESC-RL), comprising two key components. First, a Group-wise Evidence-aware Alignment Reward (GEAR) delivers group-wise, evidence-aware feedback. GEAR reinforces consistent grounding for true positives, recovers missed findings for false negatives, and suppresses unsupported content for false positives. Second, a Self-correcting Preference Learning (SPL) strategy automatically constructs a reliable, disease-aware preference dataset from multiple noisy observations and leverages an LLM to synthesize refined reports without human supervision. ESC-RL promotes clinically faithful, disease-aligned reward and supports continual self-improvement during training. Extensive experiments on two public chest X-ray datasets demonstrate consistent gains and state-of-the-art performance. △ Less

Submitted 15 April, 2026; originally announced April 2026.

Comments: 13 pages,4 figures, ACL2026-main

AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling

Authors: Juncheng Hu, Ziteng Xue, Guotao Liang, Anran Qi, Buyu Li, Sheng Wang, Dong Xu, Qian Yu

Abstract: We introduce AmodalSVG, a new framework for amodal image vectorization that produces semantically organized and geometrically complete SVG representations from natural images. Existing vectorization methods operate under a modal paradigm: tracing only visible pixels and disregarding occlusion. Consequently, the resulting SVGs are semantically entangled and geometrically incomplete, limiting SVG's… ▽ More We introduce AmodalSVG, a new framework for amodal image vectorization that produces semantically organized and geometrically complete SVG representations from natural images. Existing vectorization methods operate under a modal paradigm: tracing only visible pixels and disregarding occlusion. Consequently, the resulting SVGs are semantically entangled and geometrically incomplete, limiting SVG's structural editability. In contrast, AmodalSVG reconstructs full object geometries, including occluded regions, into independent, editable vector layers. To achieve this, AmodalSVG reformulates image vectorization as a two-stage framework, performing semantic decoupling and completion in the raster domain to produce amodally complete semantic layers, which are then independently vectorized. In the first stage, we introduce Semantic Layer Peeling (SLP), a VLM-guided strategy that progressively decomposes an image into semantically coherent layers. By hybrid inpainting, SLP recovers complete object appearances under occlusions, enabling explicit semantic decoupling. To vectorize these layers efficiently, we propose Adaptive Layered Vectorization (ALV), which dynamically modulates the primitive budget via an error-budget-driven adjustment mechanism. Extensive experiments demonstrate that AmodalSVG significantly outperforms prior methods in visual fidelity. Moreover, the resulting amodal layers enable object-level editing directly in the vector domain, capabilities not supported by existing vectorization approaches. Code will be released upon acceptance. △ Less

Submitted 12 April, 2026; originally announced April 2026.

Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems

Authors: Zhiqian Zhang, Xu Zhao, Xiaoqing Xu, Guangdong Liang, Weijia Wang, Xiaolei Lv, Bo Li, Jun Gao

Abstract: In recent years, multimodal large models have continued to improve on general benchmarks. However, in real-world content moderation and adversarial settings, mainstream models still suffer from degraded generalization and catastrophic forgetting because of limited fine-grained visual perception and insufficient modeling of long-tail noise. In this paper, we present Xuanwu VL-2B as a case study of… ▽ More In recent years, multimodal large models have continued to improve on general benchmarks. However, in real-world content moderation and adversarial settings, mainstream models still suffer from degraded generalization and catastrophic forgetting because of limited fine-grained visual perception and insufficient modeling of long-tail noise. In this paper, we present Xuanwu VL-2B as a case study of how general multimodal models can be developed into an industrial-grade foundation model for content ecosystems. The model adopts a compact InternViT-300M + MLP + Qwen3 1.7B architecture, balancing fine-grained visual perception, language-semantic alignment, and deployment cost within an approximately 2B-parameter budget. To balance business specialization with the retention of general capabilities, we developed a data iteration and curation mechanism and trained the model through a progressive three-stage pipeline: pre-training, mid-training, and post-training. Ablation studies and offline business evaluations show that Xuanwu VL-2B achieves an average score of 67.90 across seven OpenCompass multimodal metrics (vs. 64.27 for InternVL 3.5 2B), an average recall of 94.38% over seven independent business moderation tasks, and a weighted overall recall of 82.82% on policy-violating text in challenging adversarial OCR scenarios, outperforming Gemini-2.5-Pro (76.72%). These results show that, under a limited parameter budget, Xuanwu VL-2B achieves a practical balance among business alignment, visual perception, general capability retention, and deployment cost. △ Less

Submitted 30 March, 2026; originally announced March 2026.

Comments: 41 pages, 10 figures

Generalizable Self-Evolving Memory for Automatic Prompt Optimization

Authors: Guanbao Liang, Yuanchen Bei, Sheng Zhou, Yuheng Qin, Huan Zhou, Bingxin Jia, Bin Li, Jiajun Bu

Abstract: Automatic prompt optimization is a promising approach for adapting large language models (LLMs) to downstream tasks, yet existing methods typically search for a specific prompt specialized to a fixed task. This paradigm limits generalization across heterogeneous queries and prevents models from accumulating reusable prompting knowledge over time. In this paper, we propose MemAPO, a memory-driven f… ▽ More Automatic prompt optimization is a promising approach for adapting large language models (LLMs) to downstream tasks, yet existing methods typically search for a specific prompt specialized to a fixed task. This paradigm limits generalization across heterogeneous queries and prevents models from accumulating reusable prompting knowledge over time. In this paper, we propose MemAPO, a memory-driven framework that reconceptualizes prompt optimization as generalizable and self-evolving experience accumulation. MemAPO maintains a dual-memory mechanism that distills successful reasoning trajectories into reusable strategy templates while organizing incorrect generations into structured error patterns that capture recurrent failure modes. Given a new prompt, the framework retrieves both relevant strategies and failure patterns to compose prompts that promote effective reasoning while discouraging known mistakes. Through iterative self-reflection and memory editing, MemAPO continuously updates its memory, enabling prompt optimization to improve over time rather than restarting from scratch for each task. Experiments on diverse benchmarks show that MemAPO consistently outperforms representative prompt optimization baselines while substantially reducing optimization cost. △ Less

Submitted 22 March, 2026; originally announced March 2026.

Gauge-Invariant Non-Hermitian Quantum Theory: Foundation and Applications to Dynamical Phase Transitions

Authors: Fei Wang, Guoying Liang, Zecheng Zhao, Bao-Ming Xu

Abstract: The description of states and dynamics in non-Hermitian systems is fundamentally linked to the choice of an appropriate theoretical framework -- a point of ongoing debate in the field. This work addresses this issue by proposing a consistent formulation that reconciles existing controversies and establishes a unified theoretical understanding. Our approach rests on two foundational premises: (i) t… ▽ More The description of states and dynamics in non-Hermitian systems is fundamentally linked to the choice of an appropriate theoretical framework -- a point of ongoing debate in the field. This work addresses this issue by proposing a consistent formulation that reconciles existing controversies and establishes a unified theoretical understanding. Our approach rests on two foundational premises: (i) the dynamics of both left and right-vectors of a non-Hermitian system must satisfy the Schrödinger equation; (ii) the theoretical framework must preserve gauge invariance, ensuring that physical quantities are independent of unobservable phase choices. Building on these physically motivated assumptions, we refine the biorthogonal framework, leading to a gauge-invariant non-Hermitian quantum theory. Our framework naturally encompasses the open-system effective non-Hermitian evolution as a special case, and can naturally reduce to standard quantum mechanics in the Hermitian limit. As a concrete application, we analyze the dynamical phase transition in a one-dimensional Su-Schrieffer-Heeger (SSH) model within this gauge-invariant non-Hermitian quantum theory. Notably, our formulation naturally generalizes the known condition for such transitions in Hermitian two-band systems, namely, $\mathbf{d}_{k}^i\cdot\mathbf{d}_{k}^f=0$, to the non-Hermitian case, where it takes the form $\mathrm{Re}\Bigl[\frac{\mathbf{d}_{k}^i}{d_{k}^i}\cdot\frac{\mathbf{d}_{k}^f}{d_{k}^f}\Bigr]=0$. Furthermore, we identify entirely new dynamical phase transitions that cannot be characterized by the winding number. We hope that this gauge-invariant non-Hermitian quantum theory will find broad applications in the study of non-Hermitian systems. △ Less

Submitted 5 May, 2026; v1 submitted 22 March, 2026; originally announced March 2026.

Comments: 11 pages, 5 figures; Comments are welcome! Revised version

Demonstration of High-Fidelity Gates in a Strongly Anharmonic with Long-Coherence C-Shunt Flux Qubit

Authors: Silu Zhao, Li Li, Weiping Yuan, Xinhui Ruan, Jinzhe Wang, Bingjie Chen, Yunhao Shi, Guihan Liang, Shi Xiao, Jiacheng Song, Jinming Guo, Xiaohui Song, Kai Xu, Heng Fan, Zhongcheng Xiang, Dongning Zheng

Abstract: We demonstrate high-fidelity single-qubit gates on a C-shunt flux qubit that simultaneously combines a large anharmonicity ($\mathcal{A}/2π=848~\mathrm{MHz}$) with long relaxation time ($T_1 = 23~μ\text{s}$). The large anharmonicity significantly suppresses leakage to higher energy levels, enabling fast and precise microwave control. Using DRAG pulses and randomized benchmarking, the qubit achieve… ▽ More We demonstrate high-fidelity single-qubit gates on a C-shunt flux qubit that simultaneously combines a large anharmonicity ($\mathcal{A}/2π=848~\mathrm{MHz}$) with long relaxation time ($T_1 = 23~μ\text{s}$). The large anharmonicity significantly suppresses leakage to higher energy levels, enabling fast and precise microwave control. Using DRAG pulses and randomized benchmarking, the qubit achieves gate fidelities exceeding 99.9\%, highlighting the capability of C-shunt flux qubits for robust and high-performance quantum operations. These results establish them as a promising platform for scalable quantum information processing. △ Less

Submitted 12 March, 2026; originally announced March 2026.

Comments: 5 pages,3 figures

SJD-PV: Speculative Jacobi Decoding with Phrase Verification for Autoregressive Image Generation

Authors: Zhehao Yu, Baoquan Zhang, Bingqi Shan, Xinhao Liu, Dongliang Zhou, Guotao Liang, Guangming Ye, Yunming Ye

Abstract: Autoregressive (AR) image models have recently demonstrated remarkable generative capability, but their sequential nature results in significant inference latency. Existing training-free acceleration methods typically verify tokens independently, overlooking the strong co-occurrence patterns between adjacent visual tokens. This independence assumption often leads to contextual inconsistency and li… ▽ More Autoregressive (AR) image models have recently demonstrated remarkable generative capability, but their sequential nature results in significant inference latency. Existing training-free acceleration methods typically verify tokens independently, overlooking the strong co-occurrence patterns between adjacent visual tokens. This independence assumption often leads to contextual inconsistency and limits decoding efficiency. In this work, we introduce a novel training-free acceleration framework that performs phrase-level speculative verification, enabling the model to jointly validate multiple correlated tokens within each decoding window. To construct such phrase units, we analyze token co-occurrence statistics from the training corpus and group frequently co-occurring tokens into semantically coherent visual phrases. During inference, the proposed phrase-level verification evaluates aggregated likelihood ratios over each phrase, allowing simultaneous acceptance of multiple tokens while preserving generation quality. Extensive experiments on autoregressive text-to-image generation show that our method significantly reduces the number of function evaluations (NFE) and achieves up to 30% faster decoding without compromising visual fidelity. Our findings reveal that modeling short-range token co-occurrence provides an effective and general principle for accelerating autoregressive inference. △ Less

Submitted 2 March, 2026; originally announced March 2026.

WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces

Authors: Sicheng Fan, Rui Wan, Yifei Leng, Gaoning Liang, Li Ling, Yanyi Shang, Dehan Kong

Abstract: We introduce WebChain, the largest open-source dataset of human-annotated trajectories on real-world websites, designed to accelerate reproducible research in web agents. It contains 31,725 trajectories and 318k steps, featuring a core Triple Alignment of visual, structural, and action data to provide rich, multi-modal supervision. The data is collected via a scalable pipeline that ensures coverag… ▽ More We introduce WebChain, the largest open-source dataset of human-annotated trajectories on real-world websites, designed to accelerate reproducible research in web agents. It contains 31,725 trajectories and 318k steps, featuring a core Triple Alignment of visual, structural, and action data to provide rich, multi-modal supervision. The data is collected via a scalable pipeline that ensures coverage of complex, high-value tasks often missed by synthetic methods. Leveraging this dataset, we propose a Dual Mid-Training recipe that decouples spatial grounding from planning, achieving state-of-the-art performance on our proposed WebChainBench and other public GUI benchmarks. Our work provides the data and insights necessary to build and rigorously evaluate the next generation of scalable web agents. △ Less

Submitted 14 April, 2026; v1 submitted 5 March, 2026; originally announced March 2026.

Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance

Authors: Yiqi Lin, Guoqiang Liang, Ziyun Zeng, Zechen Bai, Yanzhe Chen, Mike Zheng Shou

Abstract: Instruction-based video editing has witnessed rapid progress, yet current methods often struggle with precise visual control, as natural language is inherently limited in describing complex visual nuances. Although reference-guided editing offers a robust solution, its potential is currently bottlenecked by the scarcity of high-quality paired training data. To bridge this gap, we introduce a scala… ▽ More Instruction-based video editing has witnessed rapid progress, yet current methods often struggle with precise visual control, as natural language is inherently limited in describing complex visual nuances. Although reference-guided editing offers a robust solution, its potential is currently bottlenecked by the scarcity of high-quality paired training data. To bridge this gap, we introduce a scalable data generation pipeline that transforms existing video editing pairs into high-fidelity training quadruplets, leveraging image generative models to create synthesized reference scaffolds. Using this pipeline, we construct RefVIE, a large-scale dataset tailored for instruction-reference-following tasks, and establish RefVIE-Bench for comprehensive evaluation. Furthermore, we propose a unified editing architecture, Kiwi-Edit, that synergizes learnable queries and latent visual features for reference semantic guidance. Our model achieves significant gains in instruction following and reference fidelity via a progressive multi-stage training curriculum. Extensive experiments demonstrate that our data and architecture establish a new state-of-the-art in controllable video editing. All datasets, models, and code is released at https://github.com/showlab/Kiwi-Edit. △ Less

Submitted 13 May, 2026; v1 submitted 2 March, 2026; originally announced March 2026.

Comments: Project page: https://showlab.github.io/Kiwi-Edit Huggingface Demo: https://huggingface.co/spaces/linyq/KiwiEdit

MedProbCLIP: Probabilistic Adaptation of Vision-Language Foundation Model for Reliable Radiograph-Report Retrieval

Authors: Ahmad Elallaf, Yu Zhang, Yuktha Priya Masupalli, Jeong Yang, Young Lee, Zechun Cao, Gongbo Liang

Abstract: Vision-language foundation models have emerged as powerful general-purpose representation learners with strong potential for multimodal understanding, but their deterministic embeddings often fail to provide the reliability required for high-stakes biomedical applications. This work introduces MedProbCLIP, a probabilistic vision-language learning framework for chest X-ray and radiology report repr… ▽ More Vision-language foundation models have emerged as powerful general-purpose representation learners with strong potential for multimodal understanding, but their deterministic embeddings often fail to provide the reliability required for high-stakes biomedical applications. This work introduces MedProbCLIP, a probabilistic vision-language learning framework for chest X-ray and radiology report representation learning and bidirectional retrieval. MedProbCLIP models image and text representations as Gaussian embeddings through a probabilistic contrastive objective that explicitly captures uncertainty and many-to-many correspondences between radiographs and clinical narratives. A variational information bottleneck mitigates overconfident predictions, while MedProbCLIP employs multi-view radiograph encoding and multi-section report encoding during training to provide fine-grained supervision for clinically aligned correspondence, yet requires only a single radiograph and a single report at inference. Evaluated on the MIMIC-CXR dataset, MedProbCLIP outperforms deterministic and probabilistic baselines, including CLIP, CXR-CLIP, and PCME++, in both retrieval and zero-shot classification. Beyond accuracy, MedProbCLIP demonstrates superior calibration, risk-coverage behavior, selective retrieval reliability, and robustness to clinically relevant corruptions, underscoring the value of probabilistic vision-language modeling for improving the trustworthiness and safety of radiology image-text retrieval systems. △ Less

Submitted 17 February, 2026; originally announced February 2026.

Comments: Accepted to the 2026 Winter Conference on Applications of Computer Vision (WACV) Workshops

TwiFF (Think With Future Frames): A Large-Scale Dataset for Dynamic Visual Reasoning

Authors: Junhua Liu, Zhangcheng Wang, Zhike Han, Ningli Wang, Guotao Liang, Kun Kuang

Abstract: Visual Chain-of-Thought (VCoT) has emerged as a promising paradigm for enhancing multimodal reasoning by integrating visual perception into intermediate reasoning steps. However, existing VCoT approaches are largely confined to static scenarios and struggle to capture the temporal dynamics essential for tasks such as instruction, prediction, and camera motion. To bridge this gap, we propose TwiFF-… ▽ More Visual Chain-of-Thought (VCoT) has emerged as a promising paradigm for enhancing multimodal reasoning by integrating visual perception into intermediate reasoning steps. However, existing VCoT approaches are largely confined to static scenarios and struggle to capture the temporal dynamics essential for tasks such as instruction, prediction, and camera motion. To bridge this gap, we propose TwiFF-2.7M, the first large-scale, temporally grounded VCoT dataset derived from $2.7$ million video clips, explicitly designed for dynamic visual question and answer. Accompanying this, we introduce TwiFF-Bench, a high-quality evaluation benchmark of $1,078$ samples that assesses both the plausibility of reasoning trajectories and the correctness of final answers in open-ended dynamic settings. Building on these foundations, we propose the TwiFF model, a unified modal that synergistically leverages pre-trained video generation and image comprehension capabilities to produce temporally coherent visual reasoning cues-iteratively generating future action frames and textual reasoning. Extensive experiments demonstrate that TwiFF significantly outperforms existing VCoT methods and Textual Chain-of-Thought baselines on dynamic reasoning tasks, which fully validates the effectiveness for visual question answering in dynamic scenarios. Our code and data is available at https://github.com/LiuJunhua02/TwiFF. △ Less

Submitted 11 February, 2026; originally announced February 2026.

Comments: preprint

T2VTree: User-Centered Visual Analytics for Agent-Assisted Thought-to-Video Authoring

Authors: Zhuoyun Zheng, Yu Dong, Gaorong Liang, Guan Li, Guihua Shan, Shiyu Cheng, Dong Tian, Jianlong Zhou, Jie Liang

Abstract: Generative models have substantially expanded video generation capabilities, yet practical thought-to-video creation remains a multi-stage, multi-modal, and decision-intensive process. However, existing tools either hide intermediate decisions behind repeated reruns or expose operator-level workflows that make exploration traces difficult to manage, compare, and reuse. We present T2VTree, a user-c… ▽ More Generative models have substantially expanded video generation capabilities, yet practical thought-to-video creation remains a multi-stage, multi-modal, and decision-intensive process. However, existing tools either hide intermediate decisions behind repeated reruns or expose operator-level workflows that make exploration traces difficult to manage, compare, and reuse. We present T2VTree, a user-centered visual analytics approach for agent-assisted thought-to-video authoring. T2VTree represents the authoring process as a tree visualization. Each node in the tree binds an editable specification (intent, referenced inputs, workflow choice, prompts, and parameters) with the resulting multimodal outputs, making refinement, branching, and provenance inspection directly operable. To reduce the burden of deciding what to do next, a set of collaborating agents translates step-level intent into an executable plan that remains visible and user-editable before execution. We further implement a visual analytics system that integrates branching authoring with in-place preview and stitching for convergent assembly, enabling end-to-end multi-scene creation without leaving the authoring context. We demonstrate T2VTreeVA through two multi-scene case studies and a comparative user study, showing how the T2VTree visualization and editable agent planning support reliable refinement, localized comparison, and practical reuse in real authoring workflows. T2VTree is available at: https://github.com/tezuka0210/T2VTree. △ Less

Submitted 9 February, 2026; originally announced February 2026.

Attention Retention for Continual Learning with Vision Transformers

Authors: Yue Lu, Xiangyu Zhou, Shizhou Zhang, Yinghui Xing, Guoqiang Liang, Wencong Zhang

Abstract: Continual learning (CL) empowers AI systems to progressively acquire knowledge from non-stationary data streams. However, catastrophic forgetting remains a critical challenge. In this work, we identify attention drift in Vision Transformers as a primary source of catastrophic forgetting, where the attention to previously learned visual concepts shifts significantly after learning new tasks. Inspir… ▽ More Continual learning (CL) empowers AI systems to progressively acquire knowledge from non-stationary data streams. However, catastrophic forgetting remains a critical challenge. In this work, we identify attention drift in Vision Transformers as a primary source of catastrophic forgetting, where the attention to previously learned visual concepts shifts significantly after learning new tasks. Inspired by neuroscientific insights into the selective attention in the human visual system, we propose a novel attention-retaining framework to mitigate forgetting in CL. Our method constrains attention drift by explicitly modifying gradients during backpropagation through a two-step process: 1) extracting attention maps of the previous task using a layer-wise rollout mechanism and generating instance-adaptive binary masks, and 2) when learning a new task, applying these masks to zero out gradients associated with previous attention regions, thereby preventing disruption of learned visual concepts. For compatibility with modern optimizers, the gradient masking process is further enhanced by scaling parameter updates proportionally to maintain their relative magnitudes. Experiments and visualizations demonstrate the effectiveness of our method in mitigating catastrophic forgetting and preserving visual concepts. It achieves state-of-the-art performance and exhibits robust generalizability across diverse CL scenarios. △ Less

Submitted 5 February, 2026; originally announced February 2026.

Comments: AAAI-2026 Camera Ready

Reliable Real-Time Value at Risk Estimation via Quantile Regression Forest with Conformal Calibration

Authors: Du-Yi Wang, Guo Liang, Kun Zhang, Qianwen Zhu

Abstract: Rapidly evolving market conditions call for real-time risk monitoring, but its online estimation remains challenging. In this paper, we study the online estimation of one of the most widely used risk measures, Value at Risk (VaR). Its accurate and reliable estimation is essential for timely risk control and informed decision-making. We propose to use the quantile regression forest in the offline-s… ▽ More Rapidly evolving market conditions call for real-time risk monitoring, but its online estimation remains challenging. In this paper, we study the online estimation of one of the most widely used risk measures, Value at Risk (VaR). Its accurate and reliable estimation is essential for timely risk control and informed decision-making. We propose to use the quantile regression forest in the offline-simulation-online-estimation (OSOA) framework. Specifically, the quantile regression forest is trained offline to learn the relationship between the online VaR and risk factors, and real-time VaR estimates are then produced online by incorporating observed risk factors. To further ensure reliability, we develop a conformalized estimator that calibrates the online VaR estimates. To the best of our knowledge, we are the first to leverage conformal calibration to estimate real-time VaR reliably based on the OSOA formulation. Theoretical analysis establishes the consistency and coverage validity of the proposed estimators. Numerical experiments confirm the proposed method and demonstrate its effectiveness in practice. △ Less

Submitted 2 February, 2026; originally announced February 2026.

Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning

Authors: Guoqiang Liang, Jianyi Wang, Zhonghua Wu, Shangchen Zhou, Chen Change Loy

Abstract: Image Quality Assessment (IQA) is a long-standing problem in computer vision. Previous methods typically focus on predicting numerical scores without explanation or providing low-level descriptions lacking precise scores. Recent reasoning-based vision language models (VLMs) have shown strong potential for IQA by jointly generating quality descriptions and scores. However, existing VLM-based IQA me… ▽ More Image Quality Assessment (IQA) is a long-standing problem in computer vision. Previous methods typically focus on predicting numerical scores without explanation or providing low-level descriptions lacking precise scores. Recent reasoning-based vision language models (VLMs) have shown strong potential for IQA by jointly generating quality descriptions and scores. However, existing VLM-based IQA methods often suffer from unreliable reasoning due to their limited capability of integrating visual and textual cues. In this work, we introduce Zoom-IQA, a VLM-based IQA model to explicitly emulate key cognitive behaviors: uncertainty awareness, region reasoning, and iterative refinement. Specifically, we present a two-stage training pipeline: 1) supervised fine-tuning (SFT) on our Grounded-Rationale-IQA (GR-IQA) dataset to teach the model to ground its assessments in key regions, and 2) reinforcement learning (RL) for dynamic policy exploration, stabilized by our KL-Coverage regularizer to prevent reasoning and scoring diversity collapse, with a Progressive Re-sampling Strategy for mitigating annotation bias. Extensive experiments show that Zoom-IQA achieves improved robustness, explainability, and generalization. The application to downstream tasks, such as image restoration, further demonstrates the effectiveness of Zoom-IQA. △ Less

Submitted 20 August, 2026; v1 submitted 6 January, 2026; originally announced January 2026.

Comments: ECCV 2026, Project Page: https://ethanliang99.github.io/ZOOMIQA-Projectpage

Forward Performance Processes under Multiple Default Risks

Authors: Wing Fung Chong, Roxana Dumitrescu, Gechun Liang, Kenneth Tsz Hin Ng

Abstract: This article constructs a forward exponential utility in a market with multiple defaultable risks. Using the Jacod-Pham decomposition for random fields, we first characterize forward performance processes in a defaultable market under the default-free filtration. We then construct a forward utility via a system of recursively defined, indexed infinite-horizon backward stochastic differential equat… ▽ More This article constructs a forward exponential utility in a market with multiple defaultable risks. Using the Jacod-Pham decomposition for random fields, we first characterize forward performance processes in a defaultable market under the default-free filtration. We then construct a forward utility via a system of recursively defined, indexed infinite-horizon backward stochastic differential equations (BSDEs) with discounting, and establish the existence, uniqueness, and boundedness of their solutions. To verify the required (super)martingale property of the performance process, we develop a rigorous characterization of this property with respect to the general filtration in terms of a set of (in)equalities relative to the default-free filtration. We further extend the analysis to a stochastic factor model with ergodic dynamics. In this setting, we derive uniform bounds for the Markovian solutions of the infinite-horizon BSDEs, overcoming technical challenges arising from the special structure of the system of BSDEs in the defaultable setting. Passing to the ergodic limit, we identify the limiting BSDE and relate its constant to the risk-sensitive long-run growth rate of the optimal wealth process. △ Less

Submitted 5 January, 2026; originally announced January 2026.

Environment-Aware Channel Inference via Cross-Modal Flow: From Multimodal Sensing to Wireless Channels

Authors: Guangming Liang, Mingjie Yang, Dongzhu Liu, Paul Henderson, Lajos Hanzo

Abstract: Accurate channel state information (CSI) underpins reliable and efficient wireless communication. However, acquiring CSI via pilot estimation incurs substantial overhead, especially in massive multiple-input multiple-output (MIMO) systems operating in high-Doppler environments. By leveraging the growing availability of environmental sensing data, this treatise investigates pilot-free channel infer… ▽ More Accurate channel state information (CSI) underpins reliable and efficient wireless communication. However, acquiring CSI via pilot estimation incurs substantial overhead, especially in massive multiple-input multiple-output (MIMO) systems operating in high-Doppler environments. By leveraging the growing availability of environmental sensing data, this treatise investigates pilot-free channel inference that estimates complete CSI directly from multimodal observations, including camera images, LiDAR point clouds, and GPS coordinates. In contrast to prior studies that rely on predefined channel models, we develop a data-driven framework that formulates the sensing-to-channel mapping as a cross-modal flow matching problem. The framework fuses multimodal features into a latent distribution within the channel domain, and learns a velocity field that continuously transforms the latent distribution toward the channel distribution. To make this formulation tractable and efficient, we reformulate the problem as an equivalent conditional flow matching objective and incorporate a modality alignment loss, while adopting low-latency inference mechanisms to enable real-time CSI estimation. In experiments, we build a procedural data generator based on Sionna and Blender to support realistic modeling of sensing scenes and wireless propagation. System-level evaluations demonstrate significant improvements over pilot- and sensing-based benchmarks in both channel estimation accuracy and spectral efficiency for the downstream beamforming task. The source code is available at https://github.com/gm-leung/environment-aware-channel-inference. △ Less

Submitted 22 July, 2026; v1 submitted 4 December, 2025; originally announced December 2025.

Comments: 17 pages, 15 figures, 44 references, to appear in IEEE Transactions on Mobile Computing (TMC)

TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummies

Authors: Guang Liang, Jie Shao, Ningyuan Tang, Xinyao Liu, Jianxin Wu

Abstract: Native FP8 support in modern hardware is essential for training large Transformers, but is severely hindered by extreme activation outliers. Existing solutions either rely on complex mixed-precision engineering or invasive architectural modifications. This paper fundamentally challenges the conventional wisdom that outliers are data-driven. We demonstrate that extreme outliers are a data-independe… ▽ More Native FP8 support in modern hardware is essential for training large Transformers, but is severely hindered by extreme activation outliers. Existing solutions either rely on complex mixed-precision engineering or invasive architectural modifications. This paper fundamentally challenges the conventional wisdom that outliers are data-driven. We demonstrate that extreme outliers are a data-independent, mechanically-produced artifact of training, originating from specific structural properties of the weight matrices (i.e., colinearity). Based on this insight, we propose TWEO (Transformers Without Extreme Outliers), a novel, non-invasive loss function. TWEO effectively prevents extreme outliers via a very simple loss term, which reduces outliers from 10000+ to less than 20. TWEO then enables full-model FP8 pre-training with neither engineering tricks nor architectural changes for both LLM and ViT. When standard FP8 training catastrophically collapses, TWEO achieves performance comparable to the BF16 baseline while delivering a 36% increase in training throughput. Also, TWEO enables a new quantization paradigm. Hardware-friendly W8A8 per-tensor static quantization of LLMs, previously considered completely unusable due to outliers, achieves SOTA performance for the first time on TWEO-trained models. △ Less

Submitted 28 November, 2025; originally announced November 2025.

Cold Dark Matter and Dark Energy Based on an Analogy with Superconductivity

Authors: Guanming Liang

Abstract: We present a novel candidate for cold dark matter consisting of condensed Cooper pairs in a theory of interacting fermions with broken chiral symmetry. Establishing the thermal history from the early radiation era to the present, the fermions are shown to behave like standard radiation at high temperatures, but then experience a critical era decaying faster than radiation, akin to freeze-out that… ▽ More We present a novel candidate for cold dark matter consisting of condensed Cooper pairs in a theory of interacting fermions with broken chiral symmetry. Establishing the thermal history from the early radiation era to the present, the fermions are shown to behave like standard radiation at high temperatures, but then experience a critical era decaying faster than radiation, akin to freeze-out that sets the relic abundance. Through a second-order phase transition, fermion - antifermion pairs condense and the system asymptotes towards zero temperature and pressure. By the present era, the non-relativistic, massive condensate decays slightly faster than in the standard scenario -- a unique prediction that may be tested by combined measurements of the cosmic microwave background and large scale structure. We also show that in the case of massive fermions, the phase transition is frustrated, and freeze-out instead leaves a residual, long-lived △ Less

Submitted 24 November, 2025; originally announced November 2025.

Comments: This senior thesis provides more details and explanations to PhysRevLett.134.191004. Comments welcome!

Journal ref: PhysRevLett.134.191004, 2025

The Empowerment of Science of Science by Large Language Models: New Tools and Methods

Authors: Guoqiang Liang, Jingqian Gong, Mengxuan Li, Gege Lin, Shuo Zhang

Abstract: Large language models (LLMs) have exhibited exceptional capabilities in natural language understanding and generation, image recognition, and multimodal tasks, charting a course towards AGI and emerging as a central issue in the global technological race. This manuscript conducts a comprehensive review of the core technologies that support LLMs from a user standpoint, including prompt engineering,… ▽ More Large language models (LLMs) have exhibited exceptional capabilities in natural language understanding and generation, image recognition, and multimodal tasks, charting a course towards AGI and emerging as a central issue in the global technological race. This manuscript conducts a comprehensive review of the core technologies that support LLMs from a user standpoint, including prompt engineering, knowledge-enhanced retrieval augmented generation, fine tuning, pretraining, and tool learning. Additionally, it traces the historical development of Science of Science (SciSci) and presents a forward looking perspective on the potential applications of LLMs within the scientometric domain. Furthermore, it discusses the prospect of an AI agent based model for scientific evaluation, and presents new research fronts detection and knowledge graph building methods with LLMs. △ Less

Submitted 19 November, 2025; originally announced November 2025.

Comments: The manuscript is currently ongoing the underreview process of the journal of information science

MSC Class: F.2.2

Survival of Hermitian Criticality in the Non-Hermitian Framework

Authors: Fei Wang, Guoying Liang, Zecheng Zhao, Lin-Yue Luo, Da-Jian Zhang, Bao-Ming Xu

Abstract: In this work, we investigate many-body phase transitions in a one-dimensional anisotropic XY model subject to a complex-valued transverse field. Within the biorthogonal framework, we calculate the ground-state correlation functions and entanglement entropy, confirming that their scaling behavior remains identical to that in the Hermitian XY model. The preservation of Hermitian phase transition fea… ▽ More In this work, we investigate many-body phase transitions in a one-dimensional anisotropic XY model subject to a complex-valued transverse field. Within the biorthogonal framework, we calculate the ground-state correlation functions and entanglement entropy, confirming that their scaling behavior remains identical to that in the Hermitian XY model. The preservation of Hermitian phase transition features in the non-Hermitian setting is rooted in the persistence and emergence of symmetries and their breaking. Specifically, the ferromagnetic (FM) phase arises from the breaking of a $Z_2$ symmetry, while the Luttinger liquid (LL) phase is enabled by the emergence of a $U(1)$ symmetry together with the degeneracy of the real part of the energy spectrum. The nontrivial topology of the LL phase are characterized by the winding number around the exceptional point (EP). Given that non-Hermitian systems are inherently open, this research opens a new avenue for exploring conventional quantum phase transitions that are typically vulnerable to decoherence and environmental disruption in open quantum systems. △ Less

Submitted 27 April, 2026; v1 submitted 15 November, 2025; originally announced November 2025.

Comments: 9 pages, 5 figures, 1 table

Journal ref: Phys. Rev. B 113, 165149 (2026)

Improved Masked Image Generation with Knowledge-Augmented Token Representations

Authors: Guotao Liang, Baoquan Zhang, Zhiyuan Wen, Zihao Han, Yunming Ye

Abstract: Masked image generation (MIG) has demonstrated remarkable efficiency and high-fidelity images by enabling parallel token prediction. Existing methods typically rely solely on the model itself to learn semantic dependencies among visual token sequences. However, directly learning such semantic dependencies from data is challenging because the individual tokens lack clear semantic meanings, and thes… ▽ More Masked image generation (MIG) has demonstrated remarkable efficiency and high-fidelity images by enabling parallel token prediction. Existing methods typically rely solely on the model itself to learn semantic dependencies among visual token sequences. However, directly learning such semantic dependencies from data is challenging because the individual tokens lack clear semantic meanings, and these sequences are usually long. To address this limitation, we propose a novel Knowledge-Augmented Masked Image Generation framework, named KA-MIG, which introduces explicit knowledge of token-level semantic dependencies (\emph{i.e.}, extracted from the training data) as priors to learn richer representations for improving performance. In particular, we explore and identify three types of advantageous token knowledge graphs, including two positive and one negative graphs (\emph{i.e.}, the co-occurrence graph, the semantic similarity graph, and the position-token incompatibility graph). Based on three prior knowledge graphs, we design a graph-aware encoder to learn token and position-aware representations. After that, a lightweight fusion mechanism is introduced to integrate these enriched representations into the existing MIG methods. Resorting to such prior knowledge, our method effectively enhances the model's ability to capture semantic dependencies, leading to improved generation quality. Experimental results demonstrate that our method improves upon existing MIG for class-conditional image generation on ImageNet. △ Less

Submitted 14 November, 2025; originally announced November 2025.

Comments: AAAI-26

Beta Distribution Learning for Reliable Roadway Crash Risk Assessment

Authors: Ahmad Elallaf, Nathan Jacobs, Xinyue Ye, Mei Chen, Gongbo Liang

Abstract: Roadway traffic accidents represent a global health crisis, responsible for over a million deaths annually and costing many countries up to 3% of their GDP. Traditional traffic safety studies often examine risk factors in isolation, overlooking the spatial complexity and contextual interactions inherent in the built environment. Furthermore, conventional Neural Network-based risk estimators typica… ▽ More Roadway traffic accidents represent a global health crisis, responsible for over a million deaths annually and costing many countries up to 3% of their GDP. Traditional traffic safety studies often examine risk factors in isolation, overlooking the spatial complexity and contextual interactions inherent in the built environment. Furthermore, conventional Neural Network-based risk estimators typically generate point estimates without conveying model uncertainty, limiting their utility in critical decision-making. To address these shortcomings, we introduce a novel geospatial deep learning framework that leverages satellite imagery as a comprehensive spatial input. This approach enables the model to capture the nuanced spatial patterns and embedded environmental risk factors that contribute to fatal crash risks. Rather than producing a single deterministic output, our model estimates a full Beta probability distribution over fatal crash risk, yielding accurate and uncertainty-aware predictions--a critical feature for trustworthy AI in safety-critical applications. Our model outperforms baselines by achieving a 17-23% improvement in recall, a key metric for flagging potential dangers, while delivering superior calibration. By providing reliable and interpretable risk assessments from satellite imagery alone, our method enables safer autonomous navigation and offers a highly scalable tool for urban planners and policymakers to enhance roadway safety equitably and cost-effectively. △ Less

Submitted 6 November, 2025; originally announced November 2025.

Comments: Accepted to AAAI 2026

Scalar superradiance in the charged black-bounce spacetimes

Authors: Zhiming Shuai, Xiangdong Zhang, Gui-Rong Liang

Abstract: We numerically investigate the superradiant amplification effect of a charged scalar filed in the scattering experiment and the black hole bomb model in a charged black-bounce spacetime. Due to the shallowing effect on the effective potential by the introduced quantum parameter $ł$, superradiance in both the above cases are verified to be weakened. In a scattering experiment, the quantum parameter… ▽ More We numerically investigate the superradiant amplification effect of a charged scalar filed in the scattering experiment and the black hole bomb model in a charged black-bounce spacetime. Due to the shallowing effect on the effective potential by the introduced quantum parameter $ł$, superradiance in both the above cases are verified to be weakened. In a scattering experiment, the quantum parameter and the field mass suppress the amplification in all frequency ranges, while the black hole and field charge influence it differently in high and low frequencies. In a Type I black hole bomb model, where the reflective mirror is placed outside the ergo-region, we find a new distinct eigen-mode for the scalar field evolution in a high $ł$ value, which is however absent in the case of Type II black bomb where the mirror is set inside the ergo-region. Moreover, we investigate the heavy field mass scenario in a Type II black hole bomb and find no amplification effect in this confined configuration. △ Less

Submitted 5 November, 2025; originally announced November 2025.

Comments: 25 pages, 9 figures

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Authors: Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Yuanhong Zheng, Dongsheng Ma, Zirui Tang, Boyu Niu, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang , et al. (36 additional authors not shown)

Abstract: We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency. Our approach employs a coarse-to-fine, two-stage parsing strategy that decouples global layout analysis from local content recognition. In the first stage, the model performs efficient layout analysis on downsamp… ▽ More We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency. Our approach employs a coarse-to-fine, two-stage parsing strategy that decouples global layout analysis from local content recognition. In the first stage, the model performs efficient layout analysis on downsampled images to identify structural elements, circumventing the computational overhead of processing high-resolution inputs. In the second stage, guided by the global layout, it performs targeted content recognition on native-resolution crops extracted from the original image, preserving fine-grained details in dense text, complex formulas, and tables. To support this strategy, we developed a comprehensive data engine that generates diverse, large-scale training corpora for both pretraining and fine-tuning. Ultimately, MinerU2.5 demonstrates strong document parsing ability, achieving state-of-the-art performance on multiple benchmarks, surpassing both general-purpose and domain-specific models across various recognition tasks, while maintaining significantly lower computational overhead. △ Less

Submitted 29 September, 2025; v1 submitted 26 September, 2025; originally announced September 2025.

Comments: Technical Report; GitHub Repo: https://github.com/opendatalab/MinerU Hugging Face Model: https://huggingface.co/opendatalab/MinerU2.5-2509-1.2B Hugging Face Demo: https://huggingface.co/spaces/opendatalab/MinerU

Accelerated Discovery of Topological Conductors for Nanoscale Interconnects

Authors: Alexander C. Tyner, William Rogers, Po-Hsin Shih, Yi-Hsin Tu, Gengchiau Liang, Hsin Lin, Ching-Tzu Chen, James M. Rondinelli

Abstract: The sharp increase in resistivity of copper interconnects at ultra-scaled dimensions threatens the continued miniaturization of integrated circuits. Topological semimetals (TSMs) with gapless surface states (Fermi arcs) provide conduction channels resistant to localization. Here we develop an efficient computational framework to quantify 0K surface-state transmission in nanowires derived from Wann… ▽ More The sharp increase in resistivity of copper interconnects at ultra-scaled dimensions threatens the continued miniaturization of integrated circuits. Topological semimetals (TSMs) with gapless surface states (Fermi arcs) provide conduction channels resistant to localization. Here we develop an efficient computational framework to quantify 0K surface-state transmission in nanowires derived from Wannier tight-binding models of topological conductors that faithfully reproduce relativistic density functional theory results. Sparse matrix techniques enable scalable simulations incorporating disorder and surface roughness, allowing systematic materials screening across sizes, chemical potentials, and transport directions. A dataset of 3000 surface transmission values reveals TiS, ZrB$_{2}$, and nitrides AN where A=(Mo, Ta, W) as candidates with conductance matching or exceeding copper and benchmark TSMs NbAs and NbP. This dataset further supports machine learning models for rapid interconnect compound identification. Our results highlight the promise of topological conductors in overcoming copper's scaling limits and provide a roadmap for data-driven discovery of next-generation interconnects. △ Less

Submitted 18 September, 2025; originally announced September 2025.

Comments: 12 + 111 pages, 6 + 6 figures

Journal ref: Advanced Science 13, e20535 (2026)

Unravelling the unique kinetic interactions between N2O and unsaturated hydrocarbons

Authors: Hongqing Wu, Guojie Liang, Tianzhou Jiang, Fan Li, Yang Li, Rongpei Jiang, Ruoyue Tang, Song Cheng

Abstract: The interaction between unsaturated hydrocarbons and N2O has attracted considerable attention in recent years due to their important roles as potential propellants for advanced propulsion systems e.g. NOFBX, key combustion intermediates in EGR systems, and as major pollutants and precursors in atmospheric chemistry. Although experimental studies and kinetic models have been developed to investigat… ▽ More The interaction between unsaturated hydrocarbons and N2O has attracted considerable attention in recent years due to their important roles as potential propellants for advanced propulsion systems e.g. NOFBX, key combustion intermediates in EGR systems, and as major pollutants and precursors in atmospheric chemistry. Although experimental studies and kinetic models have been developed to investigate its fuel chemistry, discrepancies remain between modeled and measured ignition delay times at low temperatures. In this work, we characterize previously unreported direct interaction pathways between N2O and unsaturated hydrocarbons C2H4, C3H6, C2H2, and C3H4 through quantum chemistry calculations, comprehensive kinetic modeling, and experimental validation. These reactions proceed via O-atom addition from N2O to unsaturated hydrocarbons, forming five membered ring intermediates that decompose into N2 and hydrocarbon specific products. Distinct mechanistic differences are identified between alkenes and alkynes, arising from the disparity in N C bond lengths within the intermediates 1.480 A vs. 1.381 A, which governs their decomposition pathways. The corresponding rate coefficients are determined and implemented into multiple kinetic models, with autoignition simulations showing a pronounced promoting effect on model reactivity and improved agreement with experiments, especially at low temperatures. Flux analysis further reveals that the new pathways suppress conventional inhibiting channels while enabling aldehyde and ketone forming pathways that enhance overall reactivity. This work provides a more complete description of N2O hydrocarbon interactions, advancing predictive capability for combustion and atmospheric chemistry. △ Less

Submitted 2 September, 2025; originally announced September 2025.

Comments: 14 pages

Quantum States in Twisted Tubes with Linear Cross-Section Variation

Authors: Guo-Hua Liang, Ai-Guo Mei, Men-Yun Lai, Shu-Sheng Xu

Abstract: We study the quantum dynamics of a particle confined in a twisted tube with a linearly varying cross section. By relating a general linear transformation matrix to the system's Hamiltonian, we use an extended thin-layer method to derive an effective Hamiltonian for tangential motion under mild and general linear transformations. Explicit forms are provided for three fundamental transformations: ro… ▽ More We study the quantum dynamics of a particle confined in a twisted tube with a linearly varying cross section. By relating a general linear transformation matrix to the system's Hamiltonian, we use an extended thin-layer method to derive an effective Hamiltonian for tangential motion under mild and general linear transformations. Explicit forms are provided for three fundamental transformations: rotation, scaling, and shearing. Rotation introduces a gauge field coupled to angular momentum, while scaling and shearing produce geometric potentials that lift degeneracies in non-circular cross sections. In square cross sections, these transformations cause energy splittings among formerly degenerate states, whereas circular cross sections retain degeneracy. Through an example combining rotation and squeezing, we analyze state evolution and compute the quantum geometric tensor to quantify geometric response. Our results demonstrate how geometric transformations can tailor quantum states and suggest that circular waveguides are more robust against mode mixing. △ Less

Submitted 30 August, 2025; originally announced September 2025.

Multi-Object Sketch Animation with Grouping and Motion Trajectory Priors

Authors: Guotao Liang, Juncheng Hu, Ximing Xing, Jing Zhang, Qian Yu

Abstract: We introduce GroupSketch, a novel method for vector sketch animation that effectively handles multi-object interactions and complex motions. Existing approaches struggle with these scenarios, either being limited to single-object cases or suffering from temporal inconsistency and poor generalization. To address these limitations, our method adopts a two-stage pipeline comprising Motion Initializat… ▽ More We introduce GroupSketch, a novel method for vector sketch animation that effectively handles multi-object interactions and complex motions. Existing approaches struggle with these scenarios, either being limited to single-object cases or suffering from temporal inconsistency and poor generalization. To address these limitations, our method adopts a two-stage pipeline comprising Motion Initialization and Motion Refinement. In the first stage, the input sketch is interactively divided into semantic groups and key frames are defined, enabling the generation of a coarse animation via interpolation. In the second stage, we propose a Group-based Displacement Network (GDN), which refines the coarse animation by predicting group-specific displacement fields, leveraging priors from a text-to-video model. GDN further incorporates specialized modules, such as Context-conditioned Feature Enhancement (CCFE), to improve temporal consistency. Extensive experiments demonstrate that our approach significantly outperforms existing methods in generating high-quality, temporally consistent animations for complex, multi-object sketches, thus expanding the practical applications of sketch animation. △ Less

Submitted 21 August, 2025; originally announced August 2025.

Comments: Accepted by ACM MM 2025

Non-Equilibrium Criticality-Enhanced Quantum Sensing with Superconducting Qubits

Authors: Hao Li, Yaoling Yang, Yun-Hao Shi, Zheng-An Wang, Ziting Wang, Jintao Li, Yipeng Zhang, Kui Zhao, Yue-Shan Xu, Cheng-Lin Deng, Yu Liu, Wei-Guo Ma, Tian-Ming Li, Jia-Chi Zhang, Cai-Ping Fang, Jia-Cheng Song, Hao-Tian Liu, Si-Yun Zhou, Zheng-He Liu, Bing-Jie Chen, Gui-Han Liang, Xiaohui Song, Zhongcheng Xiang, Kai Xu, Kaixuan Huang , et al. (2 additional authors not shown)

Abstract: Exploiting quantum features allows for estimating external parameters with precisions well beyond the capacity of classical sensors, a phenomenon known as quantum-enhanced precision. Quantum criticality has been identified as a resource for achieving such enhancements with respect to the probe size. However, they demand complex probe preparation and measurement and the achievable enhancement is ul… ▽ More Exploiting quantum features allows for estimating external parameters with precisions well beyond the capacity of classical sensors, a phenomenon known as quantum-enhanced precision. Quantum criticality has been identified as a resource for achieving such enhancements with respect to the probe size. However, they demand complex probe preparation and measurement and the achievable enhancement is ultimately restricted to narrow parameter regimes. On the other hand, non-equilibrium probes harness dynamics, enabling quantum-enhanced precision with respect to time over a wide range of parameters through simple probe initialization. Here, we unify these approaches through a Stark-Wannier localization platform, where competition between a linear gradient field and particle tunneling enables quantum-enhanced sensitivity across an extended parameter regime. The probe is implemented on a 9-qubit superconducting quantum device, in both single- and double-excitation subspaces, where we explore its performance in the extended phase, the critical point and the localized phase. Despite employing only computational-basis measurements we have been able to achieve near-Heisenberg-limited precision by combining outcomes at distinct evolution times. In addition, we demonstrate that the performance of the probe in the entire extended phase is significantly outperforming the performance in the localized regime. Our results highlight Stark-Wannier systems as versatile platforms for quantum sensing, where the combination of criticality and non-equilibrium dynamics enhances precision over a wide range of parameters without stringent measurement requirements. △ Less

Submitted 20 August, 2025; originally announced August 2025.

Comments: 22 pages, 15 figures, 1 table

Journal ref: Science Bulletin 71, 2996-3003 (2026)

Quantum Parrondo Paradox via a Single Phase Defect Symmetry Breaking and Directed Transport

Authors: Jen-Yu Chang, Yun-Hsuan Chen, Gooi Zi Liang, Chih-Yu Chen, Tsung-Wei Huang

Abstract: Parrondo paradox describes the counterintuitive phenomenon in which alternating two individually losing games yields a winning outcome. Extending this effect to the quantum regime has typically required high dimensional coin spaces, entangled initial states, or engineered decoherence. Here we show that a genuine and persistent quantum Parrondo effect can be realized with minimal resources a single… ▽ More Parrondo paradox describes the counterintuitive phenomenon in which alternating two individually losing games yields a winning outcome. Extending this effect to the quantum regime has typically required high dimensional coin spaces, entangled initial states, or engineered decoherence. Here we show that a genuine and persistent quantum Parrondo effect can be realized with minimal resources a single-qubit coin, a fixed periodic sequence of two SU (2) operators, and a single localized phase defect at the origin of a discrete-time quantum walk. By breaking translational symmetry, the phase defect acts as a scattering center that enables momentum mixing and interference-induced rectification, converting two losing games into a directed quantum ratchet. We critically reassess the winning criterion and demonstrate that the position expectation value, rather than the commonly used probability asymmetry, is the appropriate metric for validating the paradox. Harmonic analysis of the drift velocity reveals a complex, resonance type dependence with high-order Fourier components, reflecting nontrivial multi-path interference at the defect site. We further show that winning strategies are associated with cyclic restoration of coin-position entanglement, and that the ratchet effect is robust across a wide range of initial states. Our results establish that spatial inhomogeneity, rather than additional quantum resources, is the essential ingredient for a sustainable quantum Parrondo effect, offering a resource efficient blueprint for directed transport on near-term quantum platforms. △ Less

Submitted 13 April, 2026; v1 submitted 12 August, 2025; originally announced August 2025.

Multi-level Collaborative Distillation Meets Global Workspace Model: A Unified Framework for OCIL

Authors: Shibin Su, Guoqiang Liang, De Cheng, Shizhou Zhang, Lingyan Ran

Abstract: Online Class-Incremental Learning (OCIL) enables models to learn continuously from non-i.i.d. data streams. Since samples of the data streams can be seen only once, it is more suitable for real-world scenarios compared to offline learning. However, this constraint intensifies the challenge for OCIL in maintaining an appropriate balance between stability and plasticity. Moreover, under stricter mem… ▽ More Online Class-Incremental Learning (OCIL) enables models to learn continuously from non-i.i.d. data streams. Since samples of the data streams can be seen only once, it is more suitable for real-world scenarios compared to offline learning. However, this constraint intensifies the challenge for OCIL in maintaining an appropriate balance between stability and plasticity. Moreover, under stricter memory buffer constraints in real world, current replay-based methods are less effective. While ensemble methods improve plasticity, they often struggle with stability. Inspired by the Global Workspace Theory (GWT), we propose a novel approach that enhances ensemble learning through a Global Workspace Model (GWM)-a shared, implicit memory that guides the learning of multiple student models. The GWM is formed by fusing the parameters of all students within each training batch, capturing the historical learning trajectory and serving as a dynamic anchor for knowledge consolidation. Like the broadcasting mechanism of GWT, the GWM is redistributed periodically to students, stabilizing learning and promoting cross-task consistency. In addition, we introduce a multi-level collaborative distillation mechanism. It enforces peer-to-peer consistency among students and preserves historical knowledge by aligning each student with the GWM. As a result, student models remain adaptable to new tasks while maintaining previously learned knowledge, striking a better balance between stability and plasticity. Extensive experiments on three standard OCIL benchmarks show that our method delivers significant performance improvement for several OCIL models across various memory budgets. The code is available at https://github.com/susususushi/GWM. △ Less

Submitted 27 May, 2026; v1 submitted 12 August, 2025; originally announced August 2025.

Comments: 15 pages, 8 figures

Observation and Modulation of the Quantum Mpemba Effect on a Superconducting Quantum Processor

Authors: Yueshan Xu, Cai-Ping Fang, Bing-Jie Chen, Ming-Chuan Wang, Zi-Yong Ge, Yun-Hao Shi, Yu Liu, Cheng-Lin Deng, Kui Zhao, Zheng-He Liu, Tian-Ming Li, Hao Li, Ziting Wang, Gui-Han Liang, Da'er Feng, Xueyi Guo, Xu-Yang Gu, Yang He, Hao-Tian Liu, Zheng-Yang Mei, Yongxi Xiao, Yu Yan, Yi-Han Yu, Wei-Ping Yuan, Jia-Chi Zhang , et al. (11 additional authors not shown)

Abstract: In non-equilibrium quantum systems, the quantum Mpemba effect (QME) emerges as a counterintuitive phenomenon: systems exhibiting greater initial symmetry breaking restore symmetry faster. It has been attracting broad interest in studying QME dynamics and potential applications in quantum information science. While theoretical exploration of QME has surged, experimental studies, specifically on its… ▽ More In non-equilibrium quantum systems, the quantum Mpemba effect (QME) emerges as a counterintuitive phenomenon: systems exhibiting greater initial symmetry breaking restore symmetry faster. It has been attracting broad interest in studying QME dynamics and potential applications in quantum information science. While theoretical exploration of QME has surged, experimental studies, specifically on its flexible modulation, remain limited. Here, we report the observation and modulation of QME using a superconducting processor featuring an all-to-all connected, tunable-coupling architecture that enables precise control from short- to long-range interactions. This platform allows independent manipulation of coupling regimes, on-site potentials, and initial states, enabling us to elucidate their roles in QME. To quantify symmetry restoration, we employ entanglement asymmetry (EA), derived from the reconstructed density matrix via quantum state tomography, as a sensitive probe. In strong short-range coupling regimes, EA crossovers during quenches from tilted Néel states confirm the presence of QME. In contrast, in intermediate coupling regimes, synchronized EA and entanglement entropy dynamics reveal the suppression of QME. Remarkably, QME reemerges with the introduction of on-site linear potentials or quenches from tilted ferromagnetic states, the latter proving robust against on-site disorder. Our study demonstrates flexible QME modulation on a superconducting platform with multiple controllable parameters, shedding light on quantum many-body non-equilibrium dynamics and opening avenues for quantum information applications. △ Less

Submitted 29 May, 2026; v1 submitted 11 August, 2025; originally announced August 2025.

Comments: Figures modified and new discussions added. Final version published in PRL

Journal ref: Phys. Rev. Lett. 137, 010402 (2026)

Tensorized Clustered LoRA Merging for Multi-Task Interference

Authors: Zhan Su, Fengran Mo, Guojun Liang, Jinghan Zhang, Bingbing Wen, Prayag Tiwari, Jian-Yun Nie

Abstract: Despite the success of the monolithic dense paradigm of large language models (LLMs), the LoRA adapters offer an efficient solution by fine-tuning small task-specific modules and merging them with the base model. However, in multi-task settings, merging LoRA adapters trained on heterogeneous sources frequently causes \textit{task interference}, degrading downstream performance. To address this, we… ▽ More Despite the success of the monolithic dense paradigm of large language models (LLMs), the LoRA adapters offer an efficient solution by fine-tuning small task-specific modules and merging them with the base model. However, in multi-task settings, merging LoRA adapters trained on heterogeneous sources frequently causes \textit{task interference}, degrading downstream performance. To address this, we propose a tensorized clustered LoRA (TC-LoRA) library targeting to address the task interference at the \textit{text-level} and \textit{parameter-level}. At the \textit{text-level}, we cluster the training samples in the embedding space to capture input-format similarities, then train a specialized LoRA adapter for each cluster. At the \textit{parameter-level}, we introduce a joint Canonical Polyadic (CP) decomposition that disentangles task-specific and shared factors across LoRA adapters. This joint factorization preserves essential knowledge while reducing cross-task interference. Extensive experiments on out-of-domain zero-shot and skill-composition tasks-including reasoning, question answering, and coding. Compared to strong SVD-based baselines, TC-LoRA achieves +1.4\% accuracy on Phi-3 and +2.3\% on Mistral-7B (+2.3\%), demonstrating the effectiveness of TC-LoRA in LLM adaptation. △ Less

Submitted 5 August, 2025; originally announced August 2025.

Many-body delocalization with a two-dimensional 70-qubit superconducting quantum simulator

Authors: Tian-Ming Li, Zheng-Hang Sun, Yun-Hao Shi, Zhen-Ting Bao, Yong-Yi Wang, Jia-Chi Zhang, Yu Liu, Cheng-Lin Deng, Yi-Han Yu, Zheng-He Liu, Chi-Tong Chen, Li Li, Hao Li, Hao-Tian Liu, Si-Yun Zhou, Zhen-Yu Peng, Yan-Jun Liu, Ziting Wang, Yue-Shan Xu, Kui Zhao, Yang He, Da'er Feng, Jia-Cheng Song, Cai-Ping Fang, Junrui Deng , et al. (13 additional authors not shown)

Abstract: Quantum many-body systems with sufficiently strong disorder can exhibit a non-equilibrium phenomenon, known as the many-body localization (MBL), which is distinct from conventional thermalization. While the MBL regime has been extensively studied in one dimension, its existence in higher dimensions remains elusive, challenged by the avalanche instability. Here, using a 70-qubit two-dimensional (2D… ▽ More Quantum many-body systems with sufficiently strong disorder can exhibit a non-equilibrium phenomenon, known as the many-body localization (MBL), which is distinct from conventional thermalization. While the MBL regime has been extensively studied in one dimension, its existence in higher dimensions remains elusive, challenged by the avalanche instability. Here, using a 70-qubit two-dimensional (2D) superconducting quantum simulator, we experimentally explore the robustness of the MBL regime in controlled finite-size 2D systems. We observe that the decay of imbalance becomes more pronounced with increasing system sizes, scaling up from 21, 42 to 70 qubits, with a relatively large disorder strength, and for the first time, provide an evidence for the many-body delocalization in 2D disordered systems. Our experimental results are consistent with the avalanche theory that predicts the instability of MBL regime beyond one spatial dimension. This work establishes a scalable platform for probing high-dimensional non-equilibrium phases of matter and their finite-size effects using superconducting quantum circuits. △ Less

Submitted 22 July, 2025; originally announced July 2025.

Comments: main text: 7 pages, 3 figures; supplementary information: 19 pages, 17 figures

MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results

Authors: Yuki Kondo, Norimichi Ukita, Riku Kanayama, Yuki Yoshida, Takayuki Yamaguchi, Xiang Yu, Guang Liang, Xinyao Liu, Guan-Zhang Wang, Wei-Ta Chu, Bing-Cheng Chuang, Jia-Hua Lee, Pin-Tseng Kuo, I-Hsuan Chu, Yi-Shein Hsiao, Cheng-Han Wu, Po-Yi Wu, Jui-Chien Tsou, Hsuan-Chi Liu, Chun-Yi Lee, Yuan-Fu Yang, Kosuke Shigematsu, Asuka Shin, Ba Tran

Abstract: Small Multi-Object Tracking (SMOT) is particularly challenging when targets occupy only a few dozen pixels, rendering detection and appearance-based association unreliable. Building on the success of the MVA2023 SOD4SB challenge, this paper introduces the SMOT4SB challenge, which leverages temporal information to address limitations of single-frame detection. Our three main contributions are: (1)… ▽ More Small Multi-Object Tracking (SMOT) is particularly challenging when targets occupy only a few dozen pixels, rendering detection and appearance-based association unreliable. Building on the success of the MVA2023 SOD4SB challenge, this paper introduces the SMOT4SB challenge, which leverages temporal information to address limitations of single-frame detection. Our three main contributions are: (1) the SMOT4SB dataset, consisting of 211 UAV video sequences with 108,192 annotated frames under diverse real-world conditions, designed to capture motion entanglement where both camera and targets move freely in 3D; (2) SO-HOTA, a novel metric combining Dot Distance with HOTA to mitigate the sensitivity of IoU-based metrics to small displacements; and (3) a competitive MVA2025 challenge with 78 participants and 308 submissions, where the winning method achieved a 5.1x improvement over the baseline. This work lays a foundation for advancing SMOT in UAV scenarios with applications in bird strike avoidance, agriculture, fisheries, and ecological monitoring. △ Less

Submitted 17 July, 2025; originally announced July 2025.

Comments: This paper is the official challenge report for SMOT4SB and is published in the proceedings of MVA 2025 (19th International Conference on Machine Vision and Applications). Official challenge page: https://www.mva-org.jp/mva2025/challenge

YOLOv8-SMOT: An Efficient and Robust Framework for Real-Time Small Object Tracking via Slice-Assisted Training and Adaptive Association

Authors: Xiang Yu, Xinyao Liu, Guang Liang

Abstract: Tracking small, agile multi-objects (SMOT), such as birds, from an Unmanned Aerial Vehicle (UAV) perspective is a highly challenging computer vision task. The difficulty stems from three main sources: the extreme scarcity of target appearance features, the complex motion entanglement caused by the combined dynamics of the camera and the targets themselves, and the frequent occlusions and identity… ▽ More Tracking small, agile multi-objects (SMOT), such as birds, from an Unmanned Aerial Vehicle (UAV) perspective is a highly challenging computer vision task. The difficulty stems from three main sources: the extreme scarcity of target appearance features, the complex motion entanglement caused by the combined dynamics of the camera and the targets themselves, and the frequent occlusions and identity ambiguity arising from dense flocking behavior. This paper details our championship-winning solution in the MVA 2025 "Finding Birds" Small Multi-Object Tracking Challenge (SMOT4SB), which adopts the tracking-by-detection paradigm with targeted innovations at both the detection and association levels. On the detection side, we propose a systematic training enhancement framework named \textbf{SliceTrain}. This framework, through the synergy of 'deterministic full-coverage slicing' and 'slice-level stochastic augmentation, effectively addresses the problem of insufficient learning for small objects in high-resolution image training. On the tracking side, we designed a robust tracker that is completely independent of appearance information. By integrating a \textbf{motion direction maintenance (EMA)} mechanism and an \textbf{adaptive similarity metric} combining \textbf{bounding box expansion and distance penalty} into the OC-SORT framework, our tracker can stably handle irregular motion and maintain target identities. Our method achieves state-of-the-art performance on the SMOT4SB public test set, reaching an SO-HOTA score of \textbf{55.205}, which fully validates the effectiveness and advancement of our framework in solving complex real-world SMOT problems. The source code will be made available at https://github.com/Salvatore-Love/YOLOv8-SMOT. △ Less

Submitted 20 July, 2025; v1 submitted 16 July, 2025; originally announced July 2025.

Contrastive Conditional-Unconditional Alignment for Long-tailed Diffusion Model

Authors: Fang Chen, Alex Villa, Gongbo Liang, Fuxing Li, Xiaoyi Lu, Meng Tang

Abstract: Training data for class-conditional image synthesis often exhibit a long-tailed distribution with limited amount of images for tail classes. Such an imbalance causes mode collapse and reduces the diversity of synthesized images for tail classes. For class-conditional diffusion models trained with imbalanced data, we aim to improve the diversity and fidelity of tail class images without compromisin… ▽ More Training data for class-conditional image synthesis often exhibit a long-tailed distribution with limited amount of images for tail classes. Such an imbalance causes mode collapse and reduces the diversity of synthesized images for tail classes. For class-conditional diffusion models trained with imbalanced data, we aim to improve the diversity and fidelity of tail class images without compromising the quality of head class images. We propose contrastive conditional-unconditional alignment (CCUA), which comprises two synergistic loss functions. Our first loss is an Alignment Loss (AL) that aligns class-conditional generation with unconditional generation at large timesteps. Alignment loss makes the denoising process insensitive to class conditions for the initial steps, which enriches tail classes through knowledge sharing from head classes. Secondly, we diversify unconditional generation via an Unsupervised Contrastive Loss (UCL) to increase the distance/dissimilarity among synthetic images. We combine the two losses to implicitly diversify conditional generation. Our framework is easy to implement as demonstrated on both U-Net based architecture and Diffusion Transformer. Our method outperforms vanilla denoising diffusion probabilistic models, score-based diffusion model, and alternative contrastive methods for class-imbalanced image generation across various datasets, in particular ImageNet-LT with 256$\times$256 resolution. △ Less

Submitted 23 June, 2026; v1 submitted 11 July, 2025; originally announced July 2025.

Comments: 20 pages, 11 figures