arXiv subjects

Jiaqi Tang

Publications and source records attributed to Jiaqi Tang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?

Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in visual understanding, yet their performance degrades significantly under real-world visual corruptions. While existing robustness enhancement approaches exist, they are limited: black-box feature alignment lacks interpretability, and white-box text-based reasoning cannot restore lost pixel-level details. This work investigates a fundamental research question: Can MLLMs recover corrupted visual content by themselves? To address this, we propose Robust-U1, a novel framework that equips MLLMs with explicit visual self-recovery capability for robust understanding. The approach comprises three core stages: supervised fine-tuning for initial reconstruction, reinforcement learning with dual rewards (pixel-level SSIM and semantic-level CLIP similarity) for aligning high visual quality, and multimodal reasoning that jointly considers both the corrupted input and the recovered image. Extensive experiments demonstrate that Robust-U1 achieves state-of-the-art robustness on the real-world corruption benchmark and maintains superior performance under adversarial corruptions on general VQA benchmarks. Analysis confirms that high-quality visual recovery directly enhances reasoning performance, establishing self-recovery as a critical mechanism for robust visual understanding. The source code is available at https://github.com/jqtangust/Robust-U1.

cs.CV↗

arXiv2026

Topology-Driven Transferability Estimation of Medical Foundation Models for Segmentation

The advent of large-scale self-supervised learning (SSL) has produced a vast zoo of medical foundation models. However, selecting optimal medical foundation models for specific segmentation tasks remains a computational bottleneck. Existing Transferability Estimation (TE) metrics, primarily designed for classification, rely on global statistical assumptions and fail to capture the topological complexity essential for dense prediction. We propose a novel Topology-Driven Transferability Estimation framework that evaluates manifold tractability rather than statistical overlap. Our approach introduces three components: (1) Global Representation Topology Divergence (GRTD), utilizing Minimum Spanning Trees to quantify feature-label structural isomorphism; (2) Local Boundary-Aware Topological Consistency (LBTC), which assesses manifold separability specifically at critical anatomical boundaries; and (3) Task-Adaptive Fusion, which dynamically integrates global and local metrics based on the semantic cardinality of the target task. Validated on the large-scale OpenMind benchmark across diverse anatomical targets and SSL foundation models, our approach significantly outperforms state-of-the-art baselines by around 31% relative improvement in the weighted Kendall metric, providing a robust, training-free proxy for efficient model selection without the cost of fine-tuning. The code will be made publicly available upon acceptance.

cs.CV↗

arXiv2026

Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding

Proactive streaming video understanding requires Video-LLMs to decide when to respond as a video unfolds, a task where existing methods often fall short due to their implicit, query-agnostic modeling of visual evidence. We introduce Response-G1, a novel framework that establishes explicit, structured alignment between the accumulated video evidence and the query's expected response conditions via scene graphs. The framework operates in three fine-tuning-free stages: (1) online query-guided scene graph generation from streaming clips; (2) memory-based retrieval of the most semantically relevant historical scene graphs; and (3) retrieval-augmented trigger prompting for per-frame "silence/response" decisions. By grounding both evidence and conditions in a shared graph representation, Response-G1 achieves more interpretable and accurate response timing decisions. Experimental results on established benchmarks demonstrate the superiority of our method in both proactive and reactive tasks, validating the advantage of explicit scene graph modeling and retrieval in streaming video understanding.

cs.CV↗

arXiv2026

LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization

The advent of autonomous agents is transforming interactions with Graphical User Interfaces (GUIs) by employing natural language as a powerful intermediary. Despite the predominance of Supervised Fine-Tuning (SFT) methods in current GUI agents for achieving spatial localization, these methods face substantial challenges due to their limited capacity to accurately perceive positional data. Existing strategies, such as reinforcement learning, often fail to assess positional accuracy effectively, thereby restricting their utility. In response, we introduce Location Preference Optimization (LPO), a novel approach that leverages locational data to optimize interaction preferences. LPO uses information entropy to predict interaction positions by focusing on zones rich in information. Besides, it further introduces a dynamic location reward function based on physical distance, reflecting the varying importance of interaction positions. Supported by Group Relative Preference Optimization (GRPO), LPO facilitates an extensive exploration of GUI environments and significantly enhances interaction precision. Comprehensive experiments demonstrate LPO's superior performance, achieving SOTA results across both offline benchmarks and real-world online evaluations. Our code will be made publicly available soon, at https://github.com/jqtangust/LPO.

cs.LG↗

arXiv2026

Quasiperiodic Elliptic Operators: Projection Method and Convergence Analysis

Quasiperiodic elliptic operators (QEOs) serve as fundamental models in both mathematics and physics, as exemplified by their role in the numerical modeling of one-dimensional photonic quasicrystals. However, distinct from periodic elliptic operators, approximating eigenpairs for QEOs poses significant challenges, particularly in capturing the full spectral structure (notably the continuous spectrum) and deriving convergence guarantees in the absence of compactness. In this paper, we develop a high-accuracy numerical method to compute eigenpairs of QEOs based on the projection method, which embeds quasiperiodic operators into a higher-dimensional periodic torus. To address the non-compactness issue, we construct a directional-derivative Hilbert space along irrational manifolds of a high-dimensional torus and characterize operators equivalent to QEOs within this space. By integrating spectral theory for non-compact operators into the Babuška-Osborn eigenproblem framework, we establish rigorous convergence analysis and prove that our method achieves spectral accuracy. Numerical experiments validate the accuracy and efficiency of the proposed method, including a one-dimensional photonic quasicrystal and two- and three-dimensional QEOs.

math.NA↗

arXiv2026

ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall

Large Language Models (LLMs) require efficient knowledge editing (KE) to update factual information, yet existing methods exhibit significant performance decay in multi-hop factual recall. This failure is particularly acute when edits involve intermediate implicit subjects within reasoning chains. Through causal analysis, we reveal that this limitation stems from an oversight of how chained knowledge is dynamically represented and utilized at the neuron level. We discover that during multi hop reasoning, implicit subjects function as query neurons, which sequentially activate corresponding value neurons across transformer layers to accumulate information toward the final answer, a dynamic prior KE work has overlooked. Guided by this insight, we propose ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall, a framework that leverages neuron-level attribution to identify and edit these critical query-value (Q-V) pathways. ACE provides a mechanistically grounded solution for multi-hop KE, empirically outperforming state-of-the-art methods by 9.44% on GPT-J and 37.46% on Qwen3-8B. Our analysis further reveals more fine-grained activation patterns in Qwen3 and demonstrates that the semantic interpretability of value neurons is orchestrated by query-driven accumulation. These findings establish a new pathway for advancing KE capabilities based on the principled understanding of internal reasoning mechanisms.

cs.CL↗

arXiv2026

Fake It Right: Injecting Anatomical Logic into Synthetic Supervised Pre-training for Medical Segmentation

Vision Transformers (ViTs) excel in 3D medical segmentation but require massive annotated datasets. While Self-Supervised Learning (SSL) mitigates this using unlabeled data, it still faces strict privacy and logistical barriers. Formula-Driven Supervised Learning (FDSL) offers a privacy-preserving alternative by pre-training on synthetic mathematical primitives. However, a critical semantic gap limits its efficacy: generic shapes lack the morphological fidelity, fixed spatial layouts, and inter-organ relationships of real anatomy, preventing models from learning essential global structural priors. To bridge this gap, we propose an Anatomy-Informed Synthetic Supervised Pre-training framework unifying FDSL's infinite scalability with anatomical realism. We replace basic primitives with a lightweight shape bank with de-identified, label-only segmentation masks from 5 subjects. Furthermore, we introduce a structure-aware sequential placement strategy to govern the patch synthesis process. Instead of random placement, we enforce physiological plausibility using spatial anchors for correct localization and a topological graph to manage inter-organ interactions (e.g., preventing impossible overlaps). Extensive experiments on BTCV and MSD datasets demonstrate that our method significantly outperforms state-of-the-art FDSL baselines and SSL methods by 1.74\% and up to 1.66\%, while exhibiting a robust scaling effect where performance improves with increased synthetic data volume. This provides a data-efficient, privacy-compliant solution for medical segmentation. The code will be made publicly available upon acceptance.

cs.CV↗

arXiv2026

The Texture-Shape Dilemma: Boundary-Safe Synthetic Generation for 3D Medical Transformers

Vision Transformers (ViTs) have revolutionized medical image analysis, yet their data-hungry nature clashes with the scarcity and privacy constraints of clinical archives. Formula-Driven Supervised Learning (FDSL) has emerged as a promising solution to this bottleneck, synthesizing infinite annotated samples from mathematical formulas without utilizing real patient data. However, existing FDSL paradigms rely on simple geometric shapes with homogeneous intensities, creating a substantial gap by neglecting tissue textures and noise patterns inherent in modalities like CT and MRI. In this paper, we identify a critical optimization conflict termed boundary aliasing: when high-frequency synthetic textures are naively added, they corrupt the image gradient signals necessary for learning structural boundaries, causing the model to fail in delineating real anatomical margins. To bridge this gap, we propose a novel Physics-inspired Spatially-Decoupled Synthesis framework. Our approach orthogonalizes the synthesis process: it first constructs a gradient-shielded buffer zone based on boundary distance to ensure stable shape learning, and subsequently injects physics-driven spectral textures into the object core. This design effectively reconciles robust shape representation learning with invariance to acquisition noise. Extensive experiments on the BTCV and MSD datasets demonstrate that our method significantly outperforms previous FDSL, as well as SSL methods trained on real-world medical datasets, by 1.43% on BTCV and up to 1.51% on MSD task, offering a scalable, annotation-free foundation for medical ViTs. The code will be made publicly available upon acceptance.

cs.CV↗

arXiv2026

Adaptive Debiasing Tsallis Entropy for Test-Time Adaptation

Mainstream Test-Time Adaptation (TTA) methods for adapting vision-language models, e.g., CLIP, typically rely on Shannon Entropy (SE) at test time to measure prediction uncertainty and inconsistency. However, since CLIP has a built-in bias from pretraining on highly imbalanced web-crawled data, SE inevitably results in producing biased estimates of uncertainty entropy. To address this issue, we notably find and demonstrate that Tsallis Entropy (TE), a generalized form of SE, is naturally suited for characterizing biased distributions by introducing a non-extensive parameter q, with the performance of SE serving as a lower bound for TE. Building upon this, we generalize TE into Adaptive Debiasing Tsallis Entropy (ADTE) for TTA, customizing a class-specific parameter q^l derived by normalizing the estimated label bias from continuously incoming test instances, for each category. This adaptive approach allows ADTE to accurately select high-confidence views and seamlessly integrate with a label adjustment strategy to enhance adaptation, without introducing distribution-specific hyperparameter tuning. Besides, our investigation reveals that both TE and ADTE can serve as direct, advanced alternatives to SE in TTA, without any other modifications. Experimental results show that ADTE outperforms state-of-the-art methods on ImageNet and its five variants, and achieves the highest average performance on 10 cross-domain benchmarks, regardless of the model architecture or text prompts used. Our code is available at https://github.com/Jinx630/ADTE.

cs.CV↗

arXiv2025

LongVideoAgent: Multi-Agent Reasoning with Long Videos

Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets, weakening temporal grounding and missing fine-grained cues. We propose a multi-agent framework in which a master LLM coordinates a grounding agent to localize question-relevant segments and a vision agent to extract targeted textual observations. The master agent plans with a step limit, and is trained with reinforcement learning to encourage concise, correct, and efficient multi-agent cooperation. This design helps the master agent focus on relevant clips via grounding, complements subtitles with visual detail, and yields interpretable trajectories. On our proposed LongTVQA and LongTVQA+ which are episode-level datasets aggregated from TVQA/TVQA+, our multi-agent system significantly outperforms strong non-agent baselines. Experiments also show reinforcement learning further strengthens reasoning and planning for the trained agent. Code and data will be shared at https://longvideoagent.github.io/.

cs.AI↗

arXiv2025

Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding

Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that focuses solely on visual encoder generalization, suffering from limited interpretability and isolated optimization. To overcome these limitations, we propose Robust-R1, a novel framework that explicitly models visual degradations through structured reasoning chains. Our approach integrates: (i) supervised fine-tuning for degradation-aware reasoning foundations, (ii) reward-driven alignment for accurately perceiving degradation parameters, and (iii) dynamic reasoning depth scaling adapted to degradation intensity. To facilitate this approach, we introduce a specialized 11K dataset featuring realistic degradations synthesized across four critical real-world visual processing stages, each annotated with structured chains connecting degradation parameters, perceptual influence, pristine semantic reasoning chain, and conclusion. Comprehensive evaluations demonstrate state-of-the-art robustness: Robust-R1 outperforms all general and robust baselines on the real-world degradation benchmark R-Bench, while maintaining superior anti-degradation performance under multi-intensity adversarial degradations on MMMB, MMStar, and RealWorldQA.

cs.CV↗

arXiv2025

Shaping Initial State Prevents Modality Competition in Multi-modal Fusion: A Two-stage Scheduling Framework via Fast Partial Information Decomposition

Multi-modal fusion often suffers from modality competition during joint training, where one modality dominates the learning process, leaving others under-optimized. Overlooking the critical impact of the model's initial state, most existing methods address this issue during the joint learning stage. In this study, we introduce a two-stage training framework to shape the initial states through unimodal training before the joint training. First, we propose the concept of Effective Competitive Strength (ECS) to quantify a modality's competitive strength. Our theoretical analysis further reveals that properly shaping the initial ECS by unimodal training achieves a provably tighter error bound. However, ECS is computationally intractable in deep neural networks. To bridge this gap, we develop a framework comprising two core components: a fine-grained computable diagnostic metric and an asynchronous training controller. For the metric, we first prove that mutual information(MI) is a principled proxy for ECS. Considering MI is induced by per-modality marginals and thus treats each modality in isolation, we further propose FastPID, a computationally efficient and differentiable solver for partial information decomposition, which decomposes the joint distribution's information into fine-grained measurements: modality-specific uniqueness, redundancy, and synergy. Guided by these measurements, our asynchronous controller dynamically balances modalities by monitoring uniqueness and locates the ideal initial state to start joint training by tracking peak synergy. Experiments on diverse benchmarks demonstrate that our method achieves state-of-the-art performance. Our work establishes that shaping the pre-fusion models' initial state is a powerful strategy that eases competition before it starts, reliably unlocking synergistic multi-modal fusion.

cs.LG↗

arXiv2025

Sage Deer: A Super-Aligned Driving Generalist Is Your Copilot

The intelligent driving cockpit, an important part of intelligent driving, needs to match different users' comfort, interaction, and safety needs. This paper aims to build a Super-Aligned and GEneralist DRiving agent, SAGE DeeR. Sage Deer achieves three highlights: (1) Super alignment: It achieves different reactions according to different people's preferences and biases. (2) Generalist: It can understand the multi-view and multi-mode inputs to reason the user's physiological indicators, facial emotions, hand movements, body movements, driving scenarios, and behavioral decisions. (3) Self-Eliciting: It can elicit implicit thought chains in the language space to further increase generalist and super-aligned abilities. Besides, we collected multiple data sets and built a large-scale benchmark. This benchmark measures the deer's perceptual decision-making ability and the super alignment's accuracy.

cs.CV↗

arXiv2025

Advancing Radar Hand Gesture Recognition: A Hybrid Spectrum Synthetic Framework Merging Simulation with Neural Networks

Millimeter wave (mmWave) radar sensors play a vital role in hand gesture recognition (HGR) by detecting subtle motions while preserving user privacy. However, the limited scale of radar datasets hinders the performance. Existing synthetic data generation methods fall short in two key areas. On the one hand, modeling-based approaches fail to accurately simulate the wave propagation and reflection at the hand-gesture level, facing unique complexities such as diffraction and occlusion. On the other hand, generative model-based methods are hard to converge while radar data is limited, lacking interpretability, and sometimes fail to produce kinematically plausible results. To overcome these limitations, we propose a novel hybrid spectrum synthetic framework leveraging visual hand gesture data. It combines a cylinder mesh-based hand reflection model with a small-scale neural network called RadarWeightNet, which focuses on assigning weights to simulated signals. Our framework addresses two key challenges: achieving accurate simulation of complex hand geometry and bridging the simulation-to-real gap in a data-driven manner while preserving interpretability, which balances physical accuracy with machine learning adaptability. We tested our framework under extreme scenarios where radar data is scarce. The results demonstrate the effectiveness of our hybrid framework, achieving up to 63% SSIM in synthetic performance and up to 30% improvement in classification performance in few-shot learning.

cs.HC↗

arXiv2025

Locating and Mitigating Gradient Conflicts in Point Cloud Domain Adaptation via Saliency Map Skewness

Object classification models utilizing point cloud data are fundamental for 3D media understanding, yet they often struggle with unseen or out-of-distribution (OOD) scenarios. Existing point cloud unsupervised domain adaptation (UDA) methods typically employ a multi-task learning (MTL) framework that combines primary classification tasks with auxiliary self-supervision tasks to bridge the gap between cross-domain feature distributions. However, our further experiments demonstrate that not all gradients from self-supervision tasks are beneficial and some may negatively impact the classification performance. In this paper, we propose a novel solution, termed Saliency Map-based Data Sampling Block (SM-DSB), to mitigate these gradient conflicts. Specifically, our method designs a new scoring mechanism based on the skewness of 3D saliency maps to estimate gradient conflicts without requiring target labels. Leveraging this, we develop a sample selection strategy that dynamically filters out samples whose self-supervision gradients are not beneficial for the classification. Our approach is scalable, introducing modest computational overhead, and can be integrated into all the point cloud UDA MTL frameworks. Extensive evaluations demonstrate that our method outperforms state-of-the-art approaches. In addition, we provide a new perspective on understanding the UDA problem through back-propagation analysis.

cs.CV↗

arXiv2025

SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity

Despite the growing integration of deep models into mobile terminals, the accuracy of these models declines significantly due to various deployment interferences. Test-time adaptation (TTA) has emerged to improve the performance of deep models by adapting them to unlabeled target data online. Yet, the significant memory cost, particularly in resource-constrained terminals, impedes the effective deployment of most backward-propagation-based TTA methods. To tackle memory constraints, we introduce SURGEON, a method that substantially reduces memory cost while preserving comparable accuracy improvements during fully test-time adaptation (FTTA) without relying on specific network architectures or modifications to the original training procedure. Specifically, we propose a novel dynamic activation sparsity strategy that directly prunes activations at layer-specific dynamic ratios during adaptation, allowing for flexible control of learning ability and memory cost in a data-sensitive manner. Among this, two metrics, Gradient Importance and Layer Activation Memory, are considered to determine the layer-wise pruning ratios, reflecting accuracy contribution and memory efficiency, respectively. Experimentally, our method surpasses the baselines by not only reducing memory usage but also achieving superior accuracy, delivering SOTA performance across diverse datasets, architectures, and tasks.

cs.CV↗

arXiv2025

CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model

Chinese calligraphy, a UNESCO Heritage, remains computationally challenging due to visual ambiguity and cultural complexity. Existing AI systems fail to contextualize their intricate scripts, because of limited annotated data and poor visual-semantic alignment. We propose CalliReader, a vision-language model (VLM) that solves the Chinese Calligraphy Contextualization (CC$^2$) problem through three innovations: (1) character-wise slicing for precise character extraction and sorting, (2) CalliAlign for visual-text token compression and alignment, (3) embedding instruction tuning (e-IT) for improving alignment and addressing data scarcity. We also build CalliBench, the first benchmark for full-page calligraphic contextualization, addressing three critical issues in previous OCR and VQA approaches: fragmented context, shallow reasoning, and hallucination. Extensive experiments including user studies have been conducted to verify our CalliReader's \textbf{superiority to other state-of-the-art methods and even human professionals in page-level calligraphy recognition and interpretation}, achieving higher accuracy while reducing hallucination. Comparisons with reasoning models highlight the importance of accurate recognition as a prerequisite for reliable comprehension. Quantitative analyses validate CalliReader's efficiency; evaluations on document and real-world benchmarks confirm its robust generalization ability.

cs.CV↗

arXiv2025

Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference

Recent advances in large language models (LLMs) have showcased exceptional performance in long-context tasks, while facing significant inference efficiency challenges with limited GPU memory. Existing solutions first proposed the sliding-window approach to accumulate a set of historical \textbf{key-value} (KV) pairs for reuse, then further improvements selectively retain its subsets at each step. However, due to the sparse attention distribution across a long context, it is hard to identify and recall relevant KV pairs, as the attention is distracted by massive candidate pairs. Additionally, we found it promising to select representative tokens as probe-Query in each sliding window to effectively represent the entire context, which is an approach overlooked by existing methods. Thus, we propose \textbf{ActQKV}, a training-free, \textbf{Act}ivation-aware approach that dynamically determines probe-\textbf{Q}uery and leverages it to retrieve the relevant \textbf{KV} pairs for inference. Specifically, ActQKV monitors a token-level indicator, Activation Bias, within each context window, enabling the proper construction of probe-Query for retrieval at pre-filling stage. To accurately recall the relevant KV pairs and minimize the irrelevant ones, we design a dynamic KV cut-off mechanism guided by information density across layers at the decoding stage. Experiments on the Long-Bench and $\infty$ Benchmarks demonstrate its state-of-the-art performance with competitive inference quality and resource efficiency.

cs.CL↗