arXiv subjects

Dong Li

Publications and source records attributed to Dong Li.

At least 127 records · Page 7Linked to original sources

arXiv2025

FreeInpaint: Tuning-free Prompt Alignment and Visual Rationality Enhancement in Image Inpainting

Text-guided image inpainting endeavors to generate new content within specified regions of images using textual prompts from users. The primary challenge is to accurately align the inpainted areas with the user-provided prompts while maintaining a high degree of visual fidelity. While existing inpainting methods have produced visually convincing results by leveraging the pre-trained text-to-image diffusion models, they still struggle to uphold both prompt alignment and visual rationality simultaneously. In this work, we introduce FreeInpaint, a plug-and-play tuning-free approach that directly optimizes the diffusion latents on the fly during inference to improve the faithfulness of the generated images. Technically, we introduce a prior-guided noise optimization method that steers model attention towards valid inpainting regions by optimizing the initial noise. Furthermore, we meticulously design a composite guidance objective tailored specifically for the inpainting task. This objective efficiently directs the denoising process, enhancing prompt alignment and visual rationality by optimizing intermediate latents at each step. Through extensive experiments involving various inpainting diffusion models and evaluation metrics, we demonstrate the effectiveness and robustness of our proposed FreeInpaint.

cs.CV↗

arXiv2025

Step-GUI Technical Report

Recent advances in multimodal large language models unlock unprecedented opportunities for GUI automation. However, a fundamental challenge remains: how to efficiently acquire high-quality training data while maintaining annotation reliability? We introduce a self-evolving training pipeline powered by the Calibrated Step Reward System, which converts model-generated trajectories into reliable training signals through trajectory-level calibration, achieving >90% annotation accuracy with 10-100x lower cost. Leveraging this pipeline, we introduce Step-GUI, a family of models (4B/8B) that achieves state-of-the-art GUI performance (8B: 80.2% AndroidWorld, 48.5% OSWorld, 62.6% ScreenShot-Pro) while maintaining robust general capabilities. As GUI agent capabilities improve, practical deployment demands standardized interfaces across heterogeneous devices while protecting user privacy. To this end, we propose GUI-MCP, the first Model Context Protocol for GUI automation with hierarchical architecture that combines low-level atomic operations and high-level task delegation to local specialist models, enabling high-privacy execution where sensitive data stays on-device. Finally, to assess whether agents can handle authentic everyday usage, we introduce AndroidDaily, a benchmark grounded in real-world mobile usage patterns with 3146 static actions and 235 end-to-end tasks across high-frequency daily scenarios (8B: static 89.91%, end-to-end 52.50%). Our work advances the development of practical GUI agents and demonstrates strong potential for real-world deployment in everyday digital interactions.

cs.CV↗

arXiv2025

Iterative Joint Detection of Kalman Filter and Channel Decoder for Sensor-to-Controller Link in Wireless Networked Control Systems

In this letter, we propose an iterative joint detection algorithm of Kalman filter (KF) and channel decoder for the sensor-to-controller link of wireless networked control systems, which utilizes the prior information of control system to improve control and communication performance. In this algorithm, we first use the KF to estimate the probability density of the control system outputs and calculate the prior probability of received signals to assist decoder. Then, the possible outputs of the control system are traversed to update the prior probability in order to implement iterative detection. The simulation results show that the prior information and the iterative structure can reduce the block error rate performance of communications while improving the root mean square error performance of controls.

cs.IT↗

arXiv2025

GuangMing-Explorer: A Four-Legged Robot Platform for Autonomous Exploration in General Environments

Autonomous exploration is a fundamental capability that tightly integrates perception, planning, control, and motion execution. It plays a critical role in a wide range of applications, including indoor target search, mapping of extreme environments, resource exploration, etc. Despite significant progress in individual components, a holistic and practical description of a completely autonomous exploration system, encompassing both hardware and software, remains scarce. In this paper, we present GuangMing-Explorer, a fully integrated autonomous exploration platform designed for robust operation across diverse environments. We provide a comprehensive overview of the system architecture, including hardware design, software stack, algorithm deployment, and experimental configuration. Extensive real-world experiments demonstrate the platform's effectiveness and efficiency in executing autonomous exploration tasks, highlighting its potential for practical deployment in complex and unstructured environments.

cs.RO↗

arXiv2025

PoreTrack3D: A Benchmark for Dynamic 3D Gaussian Splatting in Pore-Scale Facial Trajectory Tracking

We introduce PoreTrack3D, the first benchmark for dynamic 3D Gaussian splatting in pore-scale, non-rigid 3D facial trajectory tracking. It contains over 440,000 facial trajectories in total, among which more than 52,000 are longer than 10 frames, including 68 manually reviewed trajectories that span the entire 150 frames. To the best of our knowledge, PoreTrack3D is the first benchmark dataset to capture both traditional facial landmarks and pore-scale keypoints trajectory, advancing the study of fine-grained facial expressions through the analysis of subtle skin-surface motion. We systematically evaluate state-of-the-art dynamic 3D Gaussian splatting methods on PoreTrack3D, establishing the first performance baseline in this domain. Overall, the pipeline developed for this benchmark dataset's creation establishes a new framework for high-fidelity facial motion capture and dynamic 3D reconstruction. Our dataset are publicly available at: https://github.com/JHXion9/PoreTrack3D

cs.CV↗

arXiv2025

cMPI: Using CXL Memory Sharing for MPI One-Sided and Two-Sided Inter-Node Communications

Message Passing Interface (MPI) is a foundational programming model for high-performance computing. MPI libraries traditionally employ network interconnects (e.g., Ethernet and InfiniBand) and network protocols (e.g., TCP and RoCE) with complex software stacks for cross-node communication. We present cMPI, the first work to optimize MPI point-to-point communication (both one-sided and two-sided) using CXL memory sharing on a real CXL platform, transforming cross-node communication into memory transactions and data copies within CXL memory, bypassing traditional network protocols. We analyze performance across various interconnects and find that CXL memory sharing achieves 7.2x-8.1x lower latency than TCP-based interconnects deployed in small- and medium-scale clusters. We address challenges of CXL memory sharing for MPI communication, including data object management over the dax representation [50], cache coherence, and atomic operations. Overall, cMPI outperforms TCP over standard Ethernet NIC and high-end SmartNIC by up to 49x and 72x in latency and bandwidth, respectively, for small messages.

cs.DC↗

arXiv2025

ESS: An Offload-Centric Latent-Cache Management Architecture for DeepSeek-V3.2-Exp

DeepSeek-V3.2-Exp introduces a sparse attention mechanism that significantly reduces inference latency in long-context scenarios. Although the overall throughput has improved greatly, the Decode-stage of PD disaggregation remains to be a major bottleneck. This bottleneck primarily stems from the conflict between linear growth of Latent-Cache with sequence length and the limited GPU memory capacity, which constrains the feasible batch-size and thereby suppresses Decode-stage throughput. To address this challenge, we propose ESS (Extended Sparse Server), an offload-centric system design tailored for DeepSeek-V3.2-Exp. ESS selectively offloads Latent-Cache to CPU memory while preserving latency-critical components on GPU. By freeing up GPU memory, ESS effectively decoupling batch-size scaling from GPU memory constraints. This design significantly improves Decode-stage throughput, thereby reducing deployment costs in real-world settings. Our high-fidelity simulations show that ESS delivers 69.4\% throughput improvement at 32K context length and up to 123\% throughput improvement at 128K, demonstrating its effectiveness for large-context inference workloads. These results highlight ESS as a practical and scalable solution for long-context LLM serving.

cs.DC↗

arXiv2025

RefLSM: Linearized Structural-Prior Reflectance Model for Medical Image Segmentation and Bias-Field Correction

Medical image segmentation remains challenging due to intensity inhomogeneity, noise, blurred boundaries, and irregular structures. Traditional level set methods, while effective in certain cases, often depend on approximate bias field estimations and therefore struggle under severe non-uniform imaging conditions. To address these limitations, we propose a novel variational Reflectance-based Level Set Model (RefLSM), which explicitly integrates Retinex-inspired reflectance decomposition into the segmentation framework. By decomposing the observed image into reflectance and bias field components, RefLSM directly segments the reflectance, which is invariant to illumination and preserves fine structural details. Building on this foundation, we introduce two key innovations for enhanced precision and robustness. First, a linear structural prior steers the smoothed reflectance gradients toward a data-driven reference, providing reliable geometric guidance in noisy or low-contrast scenes. Second, a relaxed binary level-set is embedded in RefLSM and enforced via convex relaxation and sign projection, yielding stable evolution and avoiding reinitialization-induced diffusion. The resulting variational problem is solved efficiently using an ADMM-based optimization scheme. Extensive experiments on multiple medical imaging datasets demonstrate that RefLSM achieves superior segmentation accuracy, robustness, and computational efficiency compared to state-of-the-art level set methods.

cs.CV↗

arXiv2025

Evidence of a two-dimensional nitrogen crystalline structure on silver surfaces

Nitrogen, the most abundant element in Earth's atmosphere, exists as a diatomic gas under standard temperature and pressure. In the two-dimensional (2D) limit, atomically thin nitrogen, termed nitrogene, has been theoretically predicted to form crystalline materials with various polymorphic configurations, exhibiting diverse chemical and physical properties. However, the synthesis of nitrogene has remained elusive due to the strong nitrogen-nitrogen triple bonds. Here, we report experimental evidence of the formation of nitrogen-based crystalline structures compatible with nitrogene on silver surfaces via ion-beam-assisted epitaxy. Through a combination of scanning tunneling microscopy, angle-resolved photoemission spectroscopy, and first-principles calculations, we demonstrate that the nitrogene-like structure adopts a puckered honeycomb lattice. Notably, our calculations predict a nitrogene band gap of up to 7.5 eV, positioning it as a promising candidate for ultraviolet optoelectronic devices and high-k dielectric applications.

cond-mat.mtrl-sci↗

arXiv2025

AI Deception: Risks, Dynamics, and Controls

As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved from a speculative concern to an empirically demonstrated risk across language models, AI agents, and emerging frontier systems. This project provides a comprehensive and up-to-date overview of the AI deception field, covering its core concepts, methodologies, genesis, and potential mitigations. First, we identify a formal definition of AI deception, grounded in signaling theory from studies of animal deception. We then review existing empirical studies and associated risks, highlighting deception as a sociotechnical safety challenge. We organize the landscape of AI deception research as a deception cycle, consisting of two key components: deception emergence and deception treatment. Deception emergence reveals the mechanisms underlying AI deception: systems with sufficient capability and incentive potential inevitably engage in deceptive behaviors when triggered by external conditions. Deception treatment, in turn, focuses on detecting and addressing such behaviors. On deception emergence, we analyze incentive foundations across three hierarchical levels and identify three essential capability preconditions required for deception. We further examine contextual triggers, including supervision gaps, distributional shifts, and environmental pressures. On deception treatment, we conclude detection methods covering benchmarks and evaluation protocols in static and interactive settings. Building on the three core factors of deception emergence, we outline potential mitigation strategies and propose auditing approaches that integrate technical, community, and governance efforts to address sociotechnical challenges and future AI risks. To support ongoing work in this area, we release a living resource at www.deceptionsurvey.com.

cs.AI↗

arXiv2025

PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation

The autoregressive nature of large language models (LLMs) fundamentally limits inference speed, as each forward pass generates only a single token and is often bottlenecked by memory bandwidth. Speculative decoding has emerged as a promising solution, adopting a draft-then-verify strategy to accelerate token generation. While the EAGLE series achieves strong acceleration, its requirement of training a separate draft head for each target model introduces substantial adaptation costs. In this work, we propose \textbf{PARD (PARallel Draft)}, a novel speculative decoding method featuring \textit{target-independence} and \textit{parallel token prediction}. Specifically, PARD enables a single draft model to be applied across an entire family of target models without requiring separate training for each variant, thereby minimizing adaptation costs. Meanwhile, PARD substantially accelerates inference by predicting multiple future tokens within a single forward pass of the draft phase. To further reduce the training adaptation cost of PARD, we propose a COnditional Drop-token (COD) mechanism based on the integrity of prefix key-value states, enabling autoregressive draft models to be adapted into parallel draft models at low-cost. Our experiments show that the proposed COD method improves draft model training efficiency by \textbf{3$\times$} compared with traditional masked prediction training. On the \texttt{vLLM} inference framework, PARD achieves up to \textbf{3.67$\times$} speedup on LLaMA3.1-8B, reaching \textbf{264.88} tokens per second, which is \textbf{1.15$\times$} faster than EAGLE-3. Our code is available at https://github.com/AMD-AIG-AIMA/PARD.

cs.LG↗

arXiv2025

Pore-scale Image Patch Dataset and A Comparative Evaluation of Pore-scale Facial Features

The weak-texture nature of facial skin regions presents significant challenges for local descriptor matching in applications such as facial motion analysis and 3D face reconstruction. Although deep learning-based descriptors have demonstrated superior performance to traditional hand-crafted descriptors in many applications, the scarcity of pore-scale image patch datasets has hindered their further development in the facial domain. In this paper, we propose the PorePatch dataset, a high-quality pore-scale image patch dataset, and establish a rational evaluation benchmark. We introduce a Data-Model Co-Evolution (DMCE) framework to generate a progressively refined, high-quality dataset from high-resolution facial images. We then train existing SOTA models on our dataset and conduct extensive experiments. Our results show that the SOTA model achieves a FPR95 value of 1.91% on the matching task, outperforming PSIFT (22.41%) by a margin of 20.5%. However, its advantage is diminished in the 3D reconstruction task, where its overall performance is not significantly better than that of traditional descriptors. This indicates that deep learning descriptors still have limitations in addressing the challenges of facial weak-texture regions, and much work remains to be done in this field.

cs.CV↗

arXiv2025

Diagnostic Checking for Wasserstein Autoregression

Wasserstein autoregression provides a robust framework for modeling serial dependence among probability distributions, with wide-ranging applications in economics, finance, and climate science. In this paper, we develop portmanteau-type diagnostic tests for assessing the adequacy of Wasserstein autoregressive models. By defining autocorrelation functions for model errors and residuals in the Wasserstein space, we construct two related tests: one analogous to the classical McLeod type test, and the other based on the sample-splitting approach of Davis and Fernandes(2025). We establish that, under mild regularity conditions, the corresponding test statistics converge in distribution to chi-square limits. Simulation studies and empirical applications demonstrate that the proposed tests effectively detect model mis-specification, offering a principled and reliable diagnostic tool for distributional time series analysis.

stat.ME↗

arXiv2025

MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions

Out-of-tree kernel patches are essential for adapting the Linux kernel to new hardware or enabling specific functionalities. Maintaining and updating these patches across different kernel versions demands significant effort from experienced engineers. Large language models (LLMs) have shown remarkable progress across various domains, suggesting their potential for automating out-of-tree kernel patch migration. However, our findings reveal that LLMs, while promising, struggle with incomplete code context understanding and inaccurate migration point identification. In this work, we propose MigGPT, a framework that employs a novel code fingerprint structure to retain code snippet information and incorporates three meticulously designed modules to improve the migration accuracy and efficiency of out-of-tree kernel patches. Furthermore, we establish a robust benchmark using real-world out-of-tree kernel patch projects to evaluate LLM capabilities. Evaluations show that MigGPT significantly outperforms the direct application of vanilla LLMs, achieving an average completion rate of 74.07 for migration tasks.

cs.SE↗

arXiv2025

A note on parameter orthogonality for multi-parameter distributions

This note addresses issues raised by Cox and Reid in their seminal paper in 1987 regarding parameter orthogonality in statistical inference. We extend the orthogonality condition to cases with multiple parameters of interest and demonstrate its existence at a global level for some generally important distributions, despite previously expressed pessimism by them. Numerical results with the location-scale $t$-distribution reveal substantial gains in estimation accuracy and savings in computation time, thanks to the existence. We next show that the local parameter orthogonality can lead to efficient computational algorithms with the celebrated Whittle algorithm for multivariate autoregressive modeling as a showcase.

stat.ME↗

arXiv2025

Out-of-Distribution Detection with Positive and Negative Prompt Supervision Using Large Language Models

Out-of-distribution (OOD) detection is committed to delineating the classification boundaries between in-distribution (ID) and OOD images. Recent advances in vision-language models (VLMs) have demonstrated remarkable OOD detection performance by integrating both visual and textual modalities. In this context, negative prompts are introduced to emphasize the dissimilarity between image features and prompt content. However, these prompts often include a broad range of non-ID features, which may result in suboptimal outcomes due to the capture of overlapping or misleading information. To address this issue, we propose Positive and Negative Prompt Supervision, which encourages negative prompts to capture inter-class features and transfers this semantic knowledge to the visual modality to enhance OOD detection performance. Our method begins with class-specific positive and negative prompts initialized by large language models (LLMs). These prompts are subsequently optimized, with positive prompts focusing on features within each class, while negative prompts highlight features around category boundaries. Additionally, a graph-based architecture is employed to aggregate semantic-aware supervision from the optimized prompt representations and propagate it to the visual branch, thereby enhancing the performance of the energy-based OOD detector. Extensive experiments on two benchmarks, CIFAR-100 and ImageNet-1K, across eight OOD datasets and five different LLMs, demonstrate that our method outperforms state-of-the-art baselines.

cs.CV↗

arXiv2025

SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning

Long-context inference in large language models (LLMs) is increasingly constrained by the KV cache bottleneck: memory usage grows linearly with sequence length, while attention computation scales quadratically. Existing approaches address this issue by compressing the KV cache along the temporal axis through strategies such as token eviction or merging to reduce memory and computational overhead. However, these methods often neglect fine-grained importance variations across feature dimensions (i.e., the channel axis), thereby limiting their ability to effectively balance efficiency and model accuracy. In reality, we observe that channel saliency varies dramatically across both queries and positions: certain feature channels carry near-zero information for a given query, while others spike in relevance. To address this oversight, we propose SPARK, a training-free plug-and-play method that applies unstructured sparsity by pruning KV at the channel level, while dynamically restoring the pruned entries during attention score computation. Notably, our approach is orthogonal to existing KV compression and quantization techniques, making it compatible for integration with them to achieve further acceleration. By reducing channel-level redundancy, SPARK enables processing of longer sequences within the same memory budget. For sequences of equal length, SPARK not only preserves or improves model accuracy but also reduces KV cache storage by over 30% compared to eviction-based methods. Furthermore, even with an aggressive pruning ratio of 80%, SPARK maintains performance with less degradation than 5% compared to the baseline eviction method, demonstrating its robustness and effectiveness. Our code will be available at https://github.com/Xnhyacinth/SparK.

cs.CL↗

arXiv2025

AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache

Large Language Models (LLMs) are widely used in generative applications such as chatting, code generation, and reasoning. However, many realworld workloads such as classification, question answering, recommendation, and text embedding rely solely on the prefill stage of inference, where the model encodes input sequences without performing autoregressive decoding. In these prefill only scenarios, the self-attention computation becomes the primary performance bottleneck due to its quadratic complexity with respect to sequence length. In this paper, we observe that semantically different sentences often produce similar attention maps across layers and heads. Building on this insight, we propose AttnCache, a framework that accelerates the prefill stage of LLM inference by retrieving and reusing similar attention maps. Based on an attention map memorization database, AttnCache employs efficient caching and similarity search techniques to identify and reuse pre-cached attention maps during inference, thereby reducing the computational overhead of self-attention. Experimental results show that AttnCache achieves an average of 1.2x end-to-end and 2x attention speedup on CPU, and 1.6x end-to-end and 3x attention speedup on GPU, with negligible accuracy degradation.

cs.CL↗