arXiv subjects

Jiaxuan Zhao

Publications and source records attributed to Jiaxuan Zhao.

At least 19 recordsLinked to original sources

arXiv2026

CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume Understanding

Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices. However, this slice-wise formulation produces thousands of visual tokens that burden the LLM backbone, many of which capture overlapping visual evidence across adjacent slices. To understand how effectively a growing visual token budget improves performance, we perform scaling analyses on two 3D medical VQA benchmarks and find diminishing returns: cost keeps rising while accuracy saturates, and improving in-plane resolution is more effective than adding slices at comparable budgets. The budget should therefore be allocated more selectively rather than simply enlarged, yet most token compression methods are designed for 2D images or videos, where redundancy arises from spatial layout or temporal motion rather than from near-duplicate content along the depth axis. We present CARVE, a training-free framework that compresses visual tokens prior to LLM inference and casts token reduction as budget-constrained 2.5D allocation. CARVE partitions the depth axis into coherent windows and allocates tokens non-uniformly according to normalized cross-slice evidence. Under a shared budget, CARVE builds spatial anchors on representative slices and retrieves locally varying evidence from the full volume, then merges remaining eligible tokens into nearby anchors within each window. Removing roughly 80% of the visual tokens on Hulu-Med-7B, CARVE leads all compression baselines on every AMOS-MM report-generation metric, with 6.2 points higher retention of full-token quality than the strongest baseline, and preserves 98.1% of full-token performance across three VQA benchmarks.

cs.CV↗

arXiv2026

Brain-Adapter: A Dual-Stream Vision-Language MIL Framework for Comprehensive 3D CT Diagnosis of Acute Intracranial Pathologies

Automated diagnosis of 3D brain CT scans is essential for critical care, yet it remains challenging due to the heavy reliance on manual annotations and the limited semantic understanding of conventional models. While 2D foundation vision-language models (VLMs) have shown remarkable generalization, effectively transferring their representational power to 3D volumes remains an open problem. In this paper, we propose Brain-Adapter, a novel dual-stream multiple instance learning (MIL) framework that leverages pre-trained 2D biomedical VLMs and raw diagnostic reports for robust scan-level multi-label classification. Specifically, we introduce a Text-Conditioned Attention (TCA) mechanism, utilizing raw diagnostic sentences as semantic queries to dynamically align visual cues with specific disease concepts. Concurrently, a parallel visual MIL stream captures global scan characteristics, supervised by structured labels extracted via a Large Language Model (LLM). To ensure representation coherence, a consistency constraint enforces synergy between the two streams. During inference, an Uncertainty-Aware Refinement (UAR) module dynamically calibrates and fuses these dual-stream predictions to resolve ambiguous cases. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art 3D models and standard MIL approaches. By eliminating the reliance on dense annotations, Brain-Adapter provides a highly scalable and clinically viable solution for 3D acute intracranial pathology analysis.

cs.CV↗

arXiv2026

SafeRun: Enabling Determinism in LLM Planning for Running

Large Language Models enable flexible natural-language planning but remain unreliable in determinism-critical domains due to their probabilistic nature. This limitation is especially problematic in running planning, where violating safety rules can lead to safety risks. We propose SafeRun, a framework for deterministic LLM-based planning via a decoupled architecture. SafeRun separates soft interpretation by an LLM from hard constraint enforcement by a deterministic solver, ensuring strict safety constraints while preserving natural-language flexibility. To validate SafeRun, we build a comprehensive benchmark for running planning under realistic physiological and safety constraints. Experiments across five LLMs show that SafeRun achieves 100\% safety score (vs.\ 79.1\% PE average and 97.6\% CodeAct average) while maintaining competitive instruction-following scores. The SafeRun benchmark is publicly available at \href{https://huggingface.co/datasets/zzp-seeker/SafeRun-RunPlanning-Benchmark}{huggingface}.

cs.CL↗

arXiv2026

LDGuid: A Framework for Robust Change Detection via Latent Difference Guidance

Modern deep learning models for change detection (CD) often struggle to explicitly represent task-relevant semantic differences. This paper proposes the Latent Difference Guidance (LDGuid) framework that explicitly learns and injects semantic differences into CD models. LDGuid deploys adversarial autoencoding to implement a difference embedding (DE) module. The DE module is pretrained via the information bottleneck method, restricting it to learn only task-relevant differences between pre- and post-event samples. The learned latent difference is then used as an explicit guidance signal in the CD model. We validate LDGuid by integrating it into U-Net, BIT, and AERNet baselines for CD and evaluating it on LEVIR-CD, WHU-CD, SVCD, and CaBuAr datasets. Experimental results show that LDGuid enhances segmentation performance across all benchmarks, with particularly remarkable gains in challenging settings affected by spectral noise. The results further highlight the ability of LDGuid in incorporating domain knowledge, such as task-specific spectral indices. Our findings suggest that semantic difference learning can drastically enhance the robustness of CD in remote sensing.

cs.CV↗

arXiv2026

MIRL: Mutual Information-Guided Reinforcement Learning for Vision-Language Models

Vision-Language Models (VLMs) frequently suffer from visual perception errors and hallucinations that compromise answer accuracy in complex reasoning tasks. Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising solution by optimizing policies using answer correctness signals. Despite their effectiveness, prevailing RLVR methods face two critical limitations. First, much of the sampling budget is wasted on trajectories doomed to fail due to early visual description errors. Second, sparse rewards cannot distinguish whether failures stem from visual perception or reasoning stages. We introduce MIRL, a decoupled framework that addresses both limitations by leveraging mutual information (MI) between generated descriptions and visual inputs as a cheap pre-screening signal. This enables intelligent budget allocation toward high-potential trajectories via forking, while decoupled training provides independent MI-based rewards for visual perception optimization, resolving reward blindness. Experiments on six vision-language reasoning benchmarks demonstrate that MIRL achieves 70.22% average accuracy and successfully surpasses the performance of sampling 16 complete trajectories using only 10 pre-samples with top-6 selection (25% fewer complete trajectories). Our code is available at: https://anonymous.4open.science/r/mirl-main/.

cs.CV↗

arXiv2026

Learning Evolution via Optimization Knowledge Adaptation

The iterative search process of evolutionary algorithms (EAs) encapsulates optimization knowledge within historical populations and fitness evaluations. Effective utilization of this knowledge is crucial for facilitating knowledge transfer and online adaptation. However, current research typically addresses these goals in isolation and faces distinct limitations: evolutionary sequential transfer optimization often suffers from incomplete utilization of prior knowledge, while adaptive strategies, utilizing real-time knowledge, are limited to tailoring specific evolutionary operators. To simultaneously achieve these two capabilities, we introduce the Optimization Knowledge Adaptation Evolutionary Model (OKAEM), a unified learnable evolutionary framework capable of adaptively updating parameters based on available optimization knowledge. By parameterizing evolutionary operators via attention mechanisms, OKAEM enables learnable update rules that facilitate the utilization of optimization knowledge via two phases: pre-training to integrate extensive prior knowledge for efficient transfer, and adaptive optimization to dynamically update parameters based on real-time knowledge. Experimental results confirm that OKAEM significantly outperforms state-of-the-art sequential transfer methods across 12 transfer scenarios via pre-training, and surpasses advanced learnable EAs solely through its self-tuning mechanism in prior-free settings. Beyond demonstrating practical utility in prompt tuning for vision-language models, ablation studies validate the necessity of the learnable components, while visualization analyses reveal the model's capacity to autonomously discover interpretable evolutionary principles. The code can be accessed at https://gitee.com/Anonymity_Paper/code-of-okaem.

cs.NE↗

arXiv2026

Rewards as Labels: Revisiting RLVR from a Classification Perspective

Reinforcement Learning with Verifiable Rewards has recently advanced the capabilities of Large Language Models in complex reasoning tasks by providing explicit rule-based supervision. Among RLVR methods, GRPO and its variants have achieved strong empirical performance. Despite their success, we identify that they suffer from Gradient Misassignment in Positives and Gradient Domination in Negatives, which lead to inefficient and suboptimal policy updates. To address these issues, we propose Rewards as Labels (REAL), a novel framework that revisits verifiable rewards as categorical labels rather than scalar weights, thereby reformulating policy optimization as a classification problem. Building on this, we further introduce anchor logits to enhance policy learning. Our analysis reveals that REAL induces a monotonic and bounded gradient weighting, enabling balanced gradient allocation across rollouts and effectively mitigating the identified mismatches. Extensive experiments on mathematical reasoning benchmarks show that REAL improves training stability and consistently outperforms GRPO and strong variants such as DAPO. On the 1.5B model, REAL improves average Pass@1 over DAPO by 6.7%. These gains further scale to 7B model, REAL continues to outperform DAPO and GSPO by 6.2% and 1.7%, respectively. Notably, even with a vanilla binary cross-entropy, REAL remains stable and exceeds DAPO by 4.5% on average.

cs.LG↗

arXiv2026

Task-free Adaptive Meta Black-box Optimization

Handcrafted optimizers become prohibitively inefficient for complex black-box optimization (BBO) tasks. MetaBBO addresses this challenge by meta-learning to automatically configure optimizers for low-level BBO tasks, thereby eliminating heuristic dependencies. However, existing methods typically require extensive handcrafted training tasks to learn meta-strategies that generalize to target tasks, which poses a critical limitation for realistic applications with unknown task distributions. To overcome the issue, we propose the Adaptive meta Black-box Optimization Model (ABOM), which performs online parameter adaptation using solely optimization data from the target task, obviating the need for predefined task distributions. Unlike conventional metaBBO frameworks that decouple meta-training and optimization phases, ABOM introduces a closed-loop adaptive parameter learning mechanism, where parameterized evolutionary operators continuously self-update by leveraging generated populations during optimization. This paradigm shift enables zero-shot optimization: ABOM achieves competitive performance on synthetic BBO benchmarks and realistic unmanned aerial vehicle path planning problems without any handcrafted training tasks. Visualization studies reveal that parameterized evolutionary operators exhibit statistically significant search patterns, including natural selection and genetic recombination.

cs.NE↗

arXiv2025

CBP-Tuning: Efficient Local Customization for Black-box Large Language Models

The high costs of customizing large language models (LLMs) fundamentally limit their adaptability to user-specific needs. Consequently, LLMs are increasingly offered as cloud-based services, a paradigm that introduces critical limitations: providers struggle to support personalized customization at scale, while users face privacy risks when exposing sensitive data. To address this dual challenge, we propose Customized Black-box Prompt Tuning (CBP-Tuning), a novel framework that facilitates efficient local customization while preserving bidirectional privacy. Specifically, we design a two-stage framework: (1) a prompt generator trained on the server-side to capture domain-specific and task-agnostic capabilities, and (2) user-side gradient-free optimization that tailors soft prompts for individual tasks. This approach eliminates the need for users to access model weights or upload private data, requiring only a single customized vector per task while achieving effective adaptation. Furthermore, the evaluation of CBP-Tuning in the commonsense reasoning, medical and financial domain settings demonstrates superior performance compared to baselines, showcasing its advantages in task-agnostic processing and privacy preservation.

cs.CL↗

arXiv2025

DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts

Large language models (LLMs) with the Mixture-of-Experts (MoE) architecture achieve high cost-efficiency by selectively activating a subset of the parameters. Despite the inference efficiency of MoE LLMs, the training of extensive experts from scratch incurs substantial overhead, whereas reconstructing a dense LLM into an MoE LLM significantly reduces the training budget. However, existing reconstruction methods often overlook the diversity among experts, leading to potential redundancy. In this paper, we come up with the observation that a specific LLM exhibits notable diversity after being pruned on different calibration datasets, based on which we present a Diversity-Enhanced reconstruction method named DIVE. The recipe of DIVE includes domain affinity mining, pruning-based expert reconstruction, and efficient retraining. Specifically, the reconstruction includes pruning and reassembly of the feed-forward network (FFN) module. After reconstruction, we efficiently retrain the model on routers, experts and normalization modules. We implement DIVE on Llama-style LLMs with open-source training corpora. Experiments show that DIVE achieves training efficiency with minimal accuracy trade-offs, outperforming existing pruning and MoE reconstruction methods with the same number of activated parameters.

cs.CL↗

arXiv2025

PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild

This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025. It summarizes the challenge outcomes, participating methodologies, and future research directions. The challenge features two tracks: MOSE, which focuses on complex scene video object segmentation, and MeViS, which targets motion-guided, language-based video segmentation. Both tracks introduce new, more challenging datasets designed to better reflect real-world scenarios. Through detailed evaluation and analysis, the challenge offers valuable insights into the current state-of-the-art and emerging trends in complex video segmentation. More information can be found on the workshop website: https://pvuw.github.io/.

cs.CV↗

arXiv2025

MASSeg : 2nd Technical Report for 4th PVUW MOSE Track

Complex video object segmentation continues to face significant challenges in small object recognition, occlusion handling, and dynamic scene modeling. This report presents our solution, which ranked second in the MOSE track of CVPR 2025 PVUW Challenge. Based on an existing segmentation framework, we propose an improved model named MASSeg for complex video object segmentation, and construct an enhanced dataset, MOSE+, which includes typical scenarios with occlusions, cluttered backgrounds, and small target instances. During training, we incorporate a combination of inter-frame consistent and inconsistent data augmentation strategies to improve robustness and generalization. During inference, we design a mask output scaling strategy to better adapt to varying object sizes and occlusion levels. As a result, MASSeg achieves a J score of 0.8250, F score of 0.9007, and a J&F score of 0.8628 on the MOSE test set.

cs.CV↗

arXiv2025

When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges

Pre-trained large language models (LLMs) exhibit powerful capabilities for generating natural text. Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems. Motivated by the common collective and directionality of text generation and evolution, this paper first illustrates the conceptual parallels between LLMs and EAs at a micro level, which includes multiple one-to-one key characteristics: token representation and individual representation, position encoding and fitness shaping, position embedding and selection, Transformers block and reproduction, and model training and parameter adaptation. These parallels highlight potential opportunities for technical advancements in both LLMs and EAs. Subsequently, we analyze existing interdisciplinary research from a macro perspective to uncover critical challenges, with a particular focus on evolutionary fine-tuning and LLM-enhanced EAs. These analyses not only provide insights into the evolutionary mechanisms behind LLMs but also offer potential directions for enhancing the capabilities of artificial agents.

cs.NE↗

arXiv2024

Knowledge-aware Evolutionary Graph Neural Architecture Search

Graph neural architecture search (GNAS) can customize high-performance graph neural network architectures for specific graph tasks or datasets. However, existing GNAS methods begin searching for architectures from a zero-knowledge state, ignoring the prior knowledge that may improve the search efficiency. The available knowledge base (e.g. NAS-Bench-Graph) contains many rich architectures and their multiple performance metrics, such as the accuracy (#Acc) and number of parameters (#Params). This study proposes exploiting such prior knowledge to accelerate the multi-objective evolutionary search on a new graph dataset, named knowledge-aware evolutionary GNAS (KEGNAS). KEGNAS employs the knowledge base to train a knowledge model and a deep multi-output Gaussian process (DMOGP) in one go, which generates and evaluates transfer architectures in only a few GPU seconds. The knowledge model first establishes a dataset-to-architecture mapping, which can quickly generate candidate transfer architectures for a new dataset. Subsequently, the DMOGP with architecture and dataset encodings is designed to predict multiple performance metrics for candidate transfer architectures on the new dataset. According to the predicted metrics, non-dominated candidate transfer architectures are selected to warm-start the multi-objective evolutionary algorithm for optimizing the #Acc and #Params on a new dataset. Empirical studies on NAS-Bench-Graph and five real-world datasets show that KEGNAS swiftly generates top-performance architectures, achieving 4.27% higher accuracy than advanced evolutionary baselines and 11.54% higher accuracy than advanced differentiable baselines. In addition, ablation studies demonstrate that the use of prior knowledge significantly improves the search performance.

cs.NE↗

arXiv2024

Automatic Graph Topology-Aware Transformer

Existing efforts are dedicated to designing many topologies and graph-aware strategies for the graph Transformer, which greatly improve the model's representation capabilities. However, manually determining the suitable Transformer architecture for a specific graph dataset or task requires extensive expert knowledge and laborious trials. This paper proposes an evolutionary graph Transformer architecture search framework (EGTAS) to automate the construction of strong graph Transformers. We build a comprehensive graph Transformer search space with the micro-level and macro-level designs. EGTAS evolves graph Transformer topologies at the macro level and graph-aware strategies at the micro level. Furthermore, a surrogate model based on generic architectural coding is proposed to directly predict the performance of graph Transformers, substantially reducing the evaluation cost of evolutionary search. We demonstrate the efficacy of EGTAS across a range of graph-level and node-level tasks, encompassing both small-scale and large-scale graph datasets. Experimental results and ablation studies show that EGTAS can construct high-performance architectures that rival state-of-the-art manual and automated baselines.

cs.NE↗

arXiv2024

Research on Jing Dong's Self-built Logistics Based on Technology Acceptance Model

Today is a time of rapid e-commerce development, and Jing Dong, China's e-commerce giant, has taken its place in the highly competitive industry with its self-built logistics system. This paper analyzed the impact of Jing Dong's self-built logistics system characteristics on user satisfaction and continuous use intention by using the Technology Acceptance Model as the theoretical framework. This paper collected 295 valid samples using a questionnaire survey; all the respondents are users and potential users of Jing Dong from mainland China. The empirical results of data analysis showed that marketing information quality, logistics system quality, and logistics service have significant effects on the perceived usefulness of Jing Dong's self-built logistics, while only marketing information quality and logistics system quality have significant effects on the perceived usefulness of self-built logistics among the self-built logistics system characteristics dimensions. Additionally, the willingness to continue using a product and user satisfaction were both directly and significantly impacted by perceived usefulness; perceived ease of use had an indirect impact on users' willingness to continue use by affecting perceived usefulness and user satisfaction, and user satisfaction has the most significant impact on users' continuous use of Jing Dong shopping and using Jing Dong self-built logistics.

cs.CY↗

arXiv2023

The Robust Semantic Segmentation UNCV2023 Challenge Results

This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segmentation in urban environments, with a particular focus on natural adversarial scenarios. The report presents the results of 19 submitted entries, with numerous techniques drawing inspiration from cutting-edge uncertainty quantification methodologies presented at prominent conferences in the fields of computer vision and machine learning and journals over the past few years. Within this document, the challenge is introduced, shedding light on its purpose and objectives, which primarily revolved around enhancing the robustness of semantic segmentation in urban scenes under varying natural adversarial conditions. The report then delves into the top-performing solutions. Moreover, the document aims to provide a comprehensive overview of the diverse solutions deployed by all participants. By doing so, it seeks to offer readers a deeper insight into the array of strategies that can be leveraged to effectively handle the inherent uncertainties associated with autonomous driving and semantic segmentation, especially within urban environments.

cs.CV↗

arXiv2023

Balanced Coarsening for Multilevel Hypergraph Partitioning via Wasserstein Discrepancy

We propose a balanced coarsening scheme for multilevel hypergraph partitioning. In addition, an initial partitioning algorithm is designed to improve the quality of k-way hypergraph partitioning. By assigning vertex weights through the LPT algorithm, we generate a prior hypergraph under a relaxed balance constraint. With the prior hypergraph, we have defined the Wasserstein discrepancy to coordinate the optimal transport of coarsening process. And the optimal transport matrix is solved by Sinkhorn algorithm. Our coarsening scheme fully takes into account the minimization of connectivity metric (objective function). For the initial partitioning stage, we define a normalized cut function induced by Fiedler vector, which is theoretically proved to be a concave function. Thereby, a three-point algorithm is designed to find the best cut under the balance constraint.

cs.LG↗