Searcharxiv⌕ Search

arXiv subjects

Juntao Xu

Publications and source records attributed to Juntao Xu.

10 recordsLinked to original sources

Keep Images in Sight: Visual Position Re-Anchoring for Long-Context MLLMs

Long-context multimodal intelligence requires revisiting earlier images as conversations and documents accumulate, yet retaining an image does not guarantee reliable access to its details. By varying context length, redistributing a fixed text passage around the image, and changing positions without adding text, we identify the positional relation between images and questions as a direct influence on visual access. To address this gap, we propose Visual Position Re-Anchoring (VPR), a training-free method that shifts cached visual-key rotary phases toward a short-context reference before question processing. It operates directly on the existing KV cache, preserving standard attention computation without extracting attention maps or adding model forward passes. We develop static and continuous compensation schedules, using the static schedule by default. Across ten checkpoints and ten benchmarks, static VPR improves 97 of 100 model--task scores. Further analysis shows greater attention to regions containing answer evidence across six checkpoints, with minimal runtime overhead under fixed rotary frequencies. These findings demonstrate an efficient way to sustain visual access through positional adjustment within the cache.

cs.CV↗

ToPO: Token-Oriented Preference Optimization for Text-to-Image Diffusion Models

Diffusion models have achieved remarkable success in text-to-image generation, yet aligning their outputs with human preferences remains challenging. Diffusion-DPO learns from image preference pairs, but their global labels do not specify how supervision should be allocated across spatial locations and denoising timesteps. The semantic roles of prompt tokens are also not explicitly considered when assigning these local weights. To address these limitations, we propose Token-Oriented Preference Optimization (ToPO), which builds a token-conditioned spatial-temporal weighting map for each pair. A frozen reference denoiser obtains spatial and temporal weights from local noise-prediction error differences under shared noise, while preferred-branch cross-attention links spatial evidence to content tokens. The map reweights Diffusion-DPO and supports an auxiliary pixel-midpoint ordering loss. It requires neither local preference annotations nor a separately trained reward model. Extensive experiments across multiple preference and compositional evaluations show that ToPO achieves state-of-the-art performance among the compared methods with only 500 training updates, demonstrating the potential of token-conditioned preference allocation for high-quality diffusion alignment within a limited update budget.

cs.CV↗

VidEdit3D: Flexible 3D Gaussian Editing with Video Diffusion

Recent advancements in text-guided 3D editing, particularly with 3D Gaussian Splatting (3DGS), have shown promise but still lag behind the flexibility of 2D editing tools. Existing methods face a critical trade-off between preserving multi-view consistency and allowing structural modifications. Image-based editors can also struggle to apply the intended edit to objects viewed from unusual angles. To address these limitations, we introduce VidEdit3D, a framework that reformulates 3D scene editing as a trajectory-based video editing task. By drawing a parallel between camera movement in static 3D scenes and temporal dynamics in video, we leverage the robust spatiotemporal priors of pre-trained Video Diffusion Models (VDMs) to encourage semantic and structural coherence across views. Specifically, we propose Trajectory-Guided Rendering (TGR) to select informative keyframes and construct smooth video clips aligned with VDM input requirements. To propagate edits from an anchor view to these clips, we develop Flow-Aligned Video Editing (FAVE), a training-free framework incorporating an Editing Consistency Guidance (ECG) mechanism. ECG contrasts source and edited image conditions at a shared latent state, using scheduled source-image amplification to strengthen adherence to the edited reference while maintaining original scene context. Finally, we introduce Region-Selective 3DGS Refinement (RS-GS) to strictly confine geometric and appearance updates to target primitives, reducing background attribute leakage. Experiments demonstrate stronger instruction alignment and better multi-view consistency than the baselines.

cs.CV↗

DART: Distillation-Aware Reparameterization for Training-Free LoRA Reuse in Few-Step Video Diffusion Models

Few-step distillation reduces the inference cost of image-to-video generation, but directly reusing LoRA adapters trained for long denoising trajectories can weaken their intended effects and degrade video quality. We observe that adapters with similar measured static parameter geometry can behave differently under the shortened target schedule, motivating response-aware transfer. We propose DART, a training-free reparameterization method that transports source LoRAs into aligned coordinates through a low-rank distillation bridge. Paired forward evaluations measure channel-level incremental responses under the target schedule to fit coefficients that calibrate response direction, source-relative magnitude, and timestep allocation. Coordinate transport establishes update directions, while calibration adapts their contributions, requiring neither source training videos nor backpropagation. Experiments across multiple distilled I2V models demonstrate improved generation quality and aggregate functional retention over direct reuse. Further analyses show that coordinate transport complements response calibration, with adapter-level benefits encompassing both functional preservation and reduced negative transfer.

cs.AI↗

Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory Unfolds

Text-to-image diffusion models can generate individual concepts well, but they often omit or merge concepts incorrectly with multiple concepts. We trace these failures to an early coordination bottleneck: before denoising begins, prompt-conditioned attention may allocate different concepts to strongly overlapping spatial support, which can keep their attention coupled as denoising proceeds. This observation motivates treating compositional generation as a boundary-condition problem rather than repeatedly controlling the evolving trajectory. To this end, we propose Rectify-then-Diffuse (RTD), a training-free framework that rectifies the initial allocation once before standard denoising. Firstly, we propose Soft-Overlap Disentanglement (SOD), which converts normalized overlap between pilot concept maps into a differentiable and layout-agnostic separation objective. Secondly, we introduce Isotropic Gradient Rectification (IGR), which normalizes the SOD gradient and applies a bounded latent displacement with a consistent scale across prompts and initializations. Extensive experiments show that RTD achieves state-of-the-art compositional fidelity and robust gains. On the AE-Bench object pair subset, RTD improves BLIP-VQA by 45.8% and ImageReward by 19.6% over CO3 while running 2.3$\times$ faster. Code will be released at https://github.com/Z-yiwei/rectify-then-diffuse

cs.CV↗

One Knob to Rule Them All: A Unified Optimal Transport View of Cold-Start Active Learning

Cold-Start Active Learning (CSAL) aims to select a valuable subset from an unlabeled pool without any prior knowledge or human assistance. Existing methods take diverse routes based on typicality, coverage, or diversity. Each rests on its own inductive bias and therefore performs well on some tasks yet poorly on others. We argue that the real challenge is not to design yet another selection heuristic, but to make CSAL adapt automatically to the data and task at hand. To this end, we revisit CSAL through the lens of optimal transport. First, we propose a generalized transport selection framework that reveals the shared allocation structure of existing methods and exactly subsumes representative formulations. Second, we introduce a theoretical analysis that characterizes the trade-off controlled by entropic regularization and establishes a task-agnostic minimax bound for cold-start selection. These results provide a principled foundation for adapting the regularization strength to the unlabeled data. Third, we derive a data-adaptive regularization rule and present a novel Sinkhorn-based CSAL algorithm, termed $ε$-Adaptive Selection ($ε$-AS). Extensive experiments on six public datasets and multiple annotation budgets show that $ε$-AS consistently achieves state-of-the-art performance. On ImageNet-1k, it improves the average accuracy over ActiveFT by 1.29% while reducing selection time by 56.2%. Code will be released at https://github.com/Z-yiwei/OT-CSAL

cs.AI↗

Edge-Side Residual Timing and Frequency Control for Software-Defined Ground Stations in 5G NTN Uplinks

This paper studies a ground-segment implementation problem in 5G non-terrestrial networks (NTN): once UE-side geometric pre-compensation has produced a coarse timing/frequency prior, can an edge-side residual loop keep the uplink inside an NR-feasible operating region under rapid LEO dynamics? We examine this question with a software-defined ground station (SDGS) design that keeps the coarse prior at the UE and closes the residual timing-advance (TA) / carrier-frequency-offset (CFO) loop at the ground-station edge. This paper takes a systems-and-control view rather than proposing a full-stack intelligent architecture. Its evidence base consists of a March 2026 hardware-in-the-loop (HIL) campaign and a companion uncertainty analysis. The HIL campaign includes same-window reference runs collected on the same platform with edge residual control disabled, but it does not include a cloud-loop benchmark. The placement claim is therefore architectural and control-oriented rather than a head-to-head cloud-versus-edge proof. In the Shenzhen steady-state tracking interval, the edge-controlled mode lowers mean RTT from 70.51 +/- 2.34 ms to 32.84 +/- 2.56 ms and, within the retained Layer-3 transport mapping, improves artifact-level goodput from 80.14 +/- 0.14 Mbps to 196.04 +/- 1.87 Mbps relative to that reference configuration. Across four ground-station locations, the closed-loop controller keeps residual TA P95 at 0.49 us and residual CFO P95 within 76-77 Hz. Together with the uncertainty analysis, these observations support a bounded claim: an edge-side residual timing/frequency loop can keep the SDGS uplink in a more stable NR-feasible operating regime under the assumptions retained in the current HIL artifact.

cs.NI↗

Reliability Assessment of Information Sources Based on Random Permutation Set

In pattern recognition, handling uncertainty is a critical challenge that significantly affects decision-making and classification accuracy. Dempster-Shafer Theory (DST) is an effective reasoning framework for addressing uncertainty, and the Random Permutation Set (RPS) extends DST by additionally considering the internal order of elements, forming a more ordered extension of DST. However, there is a lack of a transformation method based on permutation order between RPS and DST, as well as a sequence-based probability transformation method for RPS. Moreover, the reliability of RPS sources remains an issue that requires attention. To address these challenges, this paper proposes an RPS transformation approach and a probability transformation method tailored for RPS. On this basis, a reliability computation method for RPS sources, based on the RPS probability transformation, is introduced and applied to pattern recognition. Experimental results demonstrate that the proposed approach effectively bridges the gap between DST and RPS and achieves superior recognition accuracy in classification problems.

cs.AI↗

Evaluating Evidential Reliability In Pattern Recognition Based On Intuitionistic Fuzzy Sets

Determining the reliability of evidence sources is a crucial topic in Dempster-Shafer theory (DST). Previous approaches have addressed high conflicts between evidence sources using discounting methods, but these methods may not ensure the high efficiency of classification models. In this paper, we consider the combination of DS theory and Intuitionistic Fuzzy Sets (IFS) and propose an algorithm for quantifying the reliability of evidence sources, called Fuzzy Reliability Index (FRI). The FRI algorithm is based on decision quantification rules derived from IFS, defining the contribution of different BPAs to correct decisions and deriving the evidential reliability from these contributions. The proposed method effectively enhances the rationality of reliability estimation for evidence sources, making it particularly suitable for classification decision problems in complex scenarios. Subsequent comparisons with DST-based algorithms and classical machine learning algorithms demonstrate the superiority and generalizability of the FRI algorithm. The FRI algorithm provides a new perspective for future decision probability conversion and reliability analysis of evidence sources.

cs.AI↗

Learning Consistency Pursued Correlation Filters for Real-Time UAV Tracking

Correlation filter (CF)-based methods have demonstrated exceptional performance in visual object tracking for unmanned aerial vehicle (UAV) applications, but suffer from the undesirable boundary effect. To solve this issue, spatially regularized correlation filters (SRDCF) proposes the spatial regularization to penalize filter coefficients, thereby significantly improving the tracking performance. However, the temporal information hidden in the response maps is not considered in SRDCF, which limits the discriminative power and the robustness for accurate tracking. This work proposes a novel approach with dynamic consistency pursued correlation filters, i.e., the CPCF tracker. Specifically, through a correlation operation between adjacent response maps, a practical consistency map is generated to represent the consistency level across frames. By minimizing the difference between the practical and the scheduled ideal consistency map, the consistency level is constrained to maintain temporal smoothness, and rich temporal information contained in response maps is introduced. Besides, a dynamic constraint strategy is proposed to further improve the adaptability of the proposed tracker in complex situations. Comprehensive experiments are conducted on three challenging UAV benchmarks, i.e., UAV123@10FPS, UAVDT, and DTB70. Based on the experimental results, the proposed tracker favorably surpasses the other 25 state-of-the-art trackers with real-time running speed ($\sim$43FPS) on a single CPU.

cs.CV↗