arXiv subjects

Bin Li

Publications and source records attributed to Bin Li.

At least 145 records · Page 8Linked to original sources

arXiv2026

PRISM-XR: Empowering Privacy-Aware XR Collaboration with Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) enhance collaboration in Extended Reality (XR) environments by enabling flexible object and animation creation through the combination of natural language and visual inputs. However, visual data captured by XR headsets includes real-world backgrounds that may contain irrelevant or sensitive user information, such as credit cards left on the table or facial identities of other users. Uploading those frames to cloud-based MLLMs poses serious privacy risks, particularly when such data is processed without explicit user consent. Additionally, existing colocation and synchronization mechanisms in commercial XR APIs rely on time-consuming, privacy-invasive environment scanning and struggle to adapt to the highly dynamic nature of MLLM-integrated XR environments. In this paper, we propose PRISM-XR, a novel framework that facilitates multi-user collaboration in XR by providing privacy-aware MLLM integration. PRISM-XR employs intelligent frame preprocessing on the edge server to filter sensitive data and remove irrelevant context before communicating with cloud generative AI models. Additionally, we introduce a lightweight registration process and a fully customizable content-sharing mechanism to enable efficient, accurate, and privacy-preserving content synchronization among users. Our numerical evaluation results indicate that the proposed platform achieves nearly 90% accuracy in fulfilling user requests and less than 0.27 seconds registration time while maintaining spatial inconsistencies of less than 3.5 cm. Furthermore, we conducted an IRB-approved user study with 28 participants, demonstrating that our system could automatically filter highly sensitive objects in over 90% of scenarios while maintaining strong overall usability.

cs.CR↗

arXiv2026

ERNIE 5.0 Technical Report

In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio. All modalities are trained from scratch under a unified next-group-of-tokens prediction objective, based on an ultra-sparse mixture-of-experts (MoE) architecture with modality-agnostic expert routing. To address practical challenges in large-scale deployment under diverse resource constraints, ERNIE 5.0 adopts a novel elastic training paradigm. Within a single pre-training run, the model learns a family of sub-models with varying depths, expert capacities, and routing sparsity, enabling flexible trade-offs among performance, model size, and inference latency in memory- or time-constrained scenarios. Moreover, we systematically address the challenges of scaling reinforcement learning to unified foundation models, thereby guaranteeing efficient and stable post-training under ultra-sparse MoE architectures and diverse multimodal settings. Extensive experiments demonstrate that ERNIE 5.0 achieves strong and balanced performance across multiple modalities. To the best of our knowledge, among publicly disclosed models, ERNIE 5.0 represents the first production-scale realization of a trillion-parameter unified autoregressive model that supports both multimodal understanding and generation. To facilitate further research, we present detailed visualizations of modality-agnostic expert routing in the unified model, alongside comprehensive empirical analysis of elastic training, aiming to offer profound insights to the community.

cs.CL↗

arXiv2026

MPF-Net: Exposing High-Fidelity AI-Generated Video Forgeries via Hierarchical Manifold Deviation and Micro-Temporal Fluctuations

With the rapid advancement of video generation models such as Veo and Wan, the visual quality of synthetic content has reached a level where macro-level semantic errors and temporal inconsistencies are no longer prominent. However, this does not imply that the distinction between real and cutting-edge high-fidelity fake is untraceable. We argue that AI-generated videos are essentially products of a manifold-fitting process rather than a physical recording. Consequently, the pixel composition logic of consecutive adjacent frames residual in AI videos exhibits a structured and homogenous characteristic. We term this phenomenon `Manifold Projection Fluctuations' (MPF). Driven by this insight, we propose a hierarchical dual-path framework that operates as a sequential filtering process. The first, the Static Manifold Deviation Branch, leverages the refined perceptual boundaries of Large-Scale Vision Foundation Models (VFMs) to capture residual spatial anomalies or physical violations that deviate from the natural real-world manifold (off-manifold). For the remaining high-fidelity videos that successfully reside on-manifold and evade spatial detection, we introduce the Micro-Temporal Fluctuation Branch as a secondary, fine-grained filter. By analyzing the structured MPF that persists even in visually perfect sequences, our framework ensures that forgeries are exposed regardless of whether they manifest as global real-world manifold deviations or subtle computational fingerprints.

cs.CV↗

arXiv2026

MarkCleaner: High-Fidelity Watermark Removal via Imperceptible Micro-Geometric Perturbation

Semantic watermarks exhibit strong robustness against conventional image-space attacks. In this work, we show that such robustness does not survive under micro-geometric perturbations: spatial displacements can remove watermarks by breaking the phase alignment. Motivated by this observation, we introduce MarkCleaner, a watermark removal framework that avoids semantic drift caused by regeneration-based watermark removal. Specifically, MarkCleaner is trained with micro-geometry-perturbed supervision, which encourages the model to separate semantic content from strict spatial alignment and enables robust reconstruction under subtle geometric displacements. The framework adopts a mask-guided encoder that learns explicit spatial representations and a 2D Gaussian Splatting-based decoder that explicitly parameterizes geometric perturbations while preserving semantic content. Extensive experiments demonstrate that MarkCleaner achieves superior performance in both watermark removal effectiveness and visual fidelity, while enabling efficient real-time inference. Our code will be made available upon acceptance.

eess.IV↗

arXiv2026

Boosting Large Language Models for Mental Manipulation Detection via Data Augmentation and Distillation

Mental manipulation on social media poses a covert yet serious threat to individuals' psychological well-being and the integrity of online interactions. Detecting such behavior is challenging due to the difficult-to-annotate training data, its highly covert and multi-turn nature, and the lack of real-world datasets. To address these challenges, we propose MentalMAD, a framework that enhances large language models for mental manipulation detection. Our approach consists of three key components: EvoSA, an annotation-free data augmentation method that combines evolutionary operations with speech-act-aware prompting; teacher-model-generated complementary-task supervision; and Complementary-Convergent Distillation, a phase-wise strategy for transferring manipulation-specific knowledge to student models. We then constructed the ReaMent dataset, comprising 5,000 real-world-sourced dialogues. Extensive experiments show that MentalMAD improves accuracy by 14.0%, macro-F1 by 27.3%, and weighted F1 by 15.1% over the strongest baseline. The code and the dataset are publicly available at https://github.com/Yuansheng-Gao/MentalMAD.

cs.CL↗

arXiv2026

Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis

Attention patterns play a crucial role in both training and inference of large language models (LLMs). Prior works have identified individual patterns such as retrieval heads, sink heads, and diagonal traces, yet these observations remain fragmented and lack a unifying explanation. To bridge this gap, we introduce \textbf{Temporal Attention Pattern Predictability Analysis (TAPPA), a unifying framework that explains diverse attention patterns by analyzing their underlying mathematical formulations} from a temporally continuous perspective. TAPPA both deepens the understanding of attention behavior and guides inference acceleration approaches. Specifically, TAPPA characterizes attention patterns as predictable patterns with clear regularities and unpredictable patterns that appear effectively random. Our analysis further reveals that this distinction can be explained by the degree of query self-similarity along the temporal dimension. Focusing on the predictable patterns, we further provide a detailed mathematical analysis of three representative cases through the joint effect of queries, keys, and Rotary Positional Embeddings (RoPE). We validate TAPPA by applying its insights to KV cache compression and LLM pruning tasks. Across these tasks, a simple metric motivated by TAPPA consistently improves performance over baseline methods. The code is available at https://github.com/MIRALab-USTC/LLM-TAPPA.

cs.CL↗

arXiv2026

Efficient Autoregressive Video Diffusion with Dummy Head

The autoregressive video diffusion model has recently gained considerable research interest due to its causal modeling and iterative denoising. In this work, we identify that the multi-head self-attention in these models under-utilizes historical frames: approximately 25% heads attend almost exclusively to the current frame, and discarding their KV caches incurs only minor performance degradation. Building upon this, we propose Dummy Forcing, a simple yet effective method to control context accessibility across different heads. Specifically, the proposed heterogeneous memory allocation reduces head-wise context redundancy, accompanied by dynamic head programming to adaptively classify head types. Moreover, we develop a context packing technique to achieve more aggressive cache compression. Without additional training, our Dummy Forcing delivers up to 2.0x speedup over the baseline, supporting video generation at 24.3 FPS with less than 0.5% quality drop. Project page is available at https://csguoh.github.io/project/DummyForcing/.

cs.CV↗

arXiv2026

DV-VLN: Dual Verification for Reliable LLM-Based Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) requires an embodied agent to navigate in a complex 3D environment according to natural language instructions. Recent progress in large language models (LLMs) has enabled language-driven navigation with improved interpretability. However, most LLM-based agents still rely on single-shot action decisions, where the model must choose one option from noisy, textualized multi-perspective observations. Due to local mismatches and imperfect intermediate reasoning, such decisions can easily deviate from the correct path, leading to error accumulation and reduced reliability in unseen environments. In this paper, we propose DV-VLN, a new VLN framework that follows a generate-then-verify paradigm. DV-VLN first performs parameter-efficient in-domain adaptation of an open-source LLaMA-2 backbone to produce a structured navigational chain-of-thought, and then verifies candidate actions with two complementary channels: True-False Verification (TFV) and Masked-Entity Verification (MEV). DV-VLN selects actions by aggregating verification successes across multiple samples, yielding interpretable scores for reranking. Experiments on R2R, RxR (English subset), and REVERIE show that DV-VLN consistently improves over direct prediction and sampling-only baselines, achieving competitive performance among language-only VLN agents and promising results compared with several cross-modal systems.Code is available at https://github.com/PlumJun/DV-VLN.

cs.RO↗

arXiv2026

DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models

Vision-Language Action (VLA) models have shown remarkable progress in robotic manipulation by leveraging the powerful perception abilities of Vision-Language Models (VLMs) to understand environments and directly output actions. However, by default, VLA models may overly attend to image tokens in the task-irrelevant region, which we describe as 'distracting tokens'. This behavior can disturb the model from the generation of the desired action tokens in each step, affecting the success rate of tasks. In this paper, we introduce a simple yet effective plug-and-play Distracting Token Pruning (DTP) framework, which dynamically detects and prunes these distracting image tokens. By correcting the model's visual attention patterns, we aim to improve the task success rate, as well as exploring the performance upper boundaries of the model without altering its original architecture or adding additional inputs. Experiments on the SIMPLER Benchmark (Li et al., 2024) show that our method consistently achieving relative improvements in task success rates across different types of novel VLA models, demonstrating generalizability to transformer-based VLAs. Further analysis reveals a negative correlation between the task success rate and the amount of attentions in the task-irrelevant region for all models tested, highlighting a common phenomenon of VLA models that could guide future research. We also publish our code at: https://anonymous.4open.science/r/CBD3.

cs.CV↗

arXiv2026

Universal activated aging and weak ergodicity breaking in spin and structural glasses

Glasses possess complex energy landscapes and exhibit non-equilibrium aging dynamics. Here, we propose a generalized trap model for activated aging based on a key static property of the energy landscape: the distribution of energy barriers. Our theory predicts that, upon cooling, weak ergodicity breaking (WEB) in quenching dynamics occurs prior to strong ergodicity breaking in equilibrium dynamics. Furthermore, the theory indicates that the characteristic size of activation clusters can be deduced from the logarithmic decay of the time-correlation function. We rigorously test the model's assumptions and predictions using the simplest spin glass model - the random energy model. The predicted aging behavior is also universally observed in paradigmatic structural glasses, including the Weeks-Chandler-Andersen (WCA) model and amorphous silica. Remarkably, applying our framework to the WCA model allows us to extract a static length from the non equilibrium dynamics, extending its observable growth range from a mere factor of 2-3 to a full order of magnitude and providing supportive evidence for the random first-order transition scenario. Finally, we propose a unified ergodic-WEB phase diagram for aging dynamics in general glassy systems.

cond-mat.dis-nn↗

arXiv2026

TimeGMM: Single-Pass Probabilistic Forecasting via Adaptive Gaussian Mixture Models with Reversible Normalization

Probabilistic time series forecasting is crucial for quantifying future uncertainty, with significant applications in fields such as energy and finance. However, existing methods often rely on computationally expensive sampling or restrictive parametric assumptions to characterize future distributions, which limits predictive performance and introduces distributional mismatch. To address these challenges, this paper presents TimeGMM, a novel probabilistic forecasting framework based on Gaussian Mixture Models (GMM) that captures complex future distributions in a single forward pass. A key component is GMM-adapted Reversible Instance Normalization (GRIN), a novel module designed to dynamically adapt to temporal-probabilistic distribution shifts. The framework integrates a dedicated Temporal Encoder (TE-Module) with a Conditional Temporal-Probabilistic Decoder (CTPD-Module) to jointly capture temporal dependencies and mixture distribution parameters. Extensive experiments demonstrate that TimeGMM consistently outperforms state-of-the-art methods, achieving maximum improvements of 22.48\% in CRPS and 21.23\% in NMAE.

cs.LG↗

arXiv2026

Unleashing the Potential of Tracklets for Unsupervised Video Person Re-Identification

With rich temporal-spatial information, video-based person re-identification methods have shown broad prospects. Although tracklets can be easily obtained with ready-made tracking models, annotating identities is still expensive and impractical. Therefore, some video-based methods propose using only a few identity annotations or camera labels to facilitate feature learning. They also simply average the frame features of each tracklet, overlooking unexpected variations and inherent identity consistency within tracklets. In this paper, we propose the Self-Supervised Refined Clustering (SSR-C) framework without relying on any annotation or auxiliary information to promote unsupervised video person re-identification. Specifically, we first propose the Noise-Filtered Tracklet Partition (NFTP) module to reduce the feature bias of tracklets caused by noisy tracking results, and sequentially partition the noise-filtered tracklets into "sub-tracklets". Then, we cluster and further merge sub-tracklets using the self-supervised signal from the tracklet partition, which is enhanced through a progressive strategy to generate reliable pseudo labels, facilitating intra-class cross-tracklet aggregation. Moreover, we propose the Class Smoothing Classification (CSC) loss to efficiently promote model learning. Extensive experiments on the MARS and DukeMTMC-VideoReID datasets demonstrate that our proposed SSR-C for unsupervised video person re-identification achieves state-of-the-art results and is comparable to advanced supervised methods. The code is available at https://github.com/Darylmeng/SSRC-Reid.

cs.CV↗

arXiv2026

Service Provisioning and Path Planning with Obstacle Avoidance for Low-Altitude Wireless Networks

This paper investigates the three-dimensional (3D) deployment of uncrewed aerial vehicles (UAVs) as aerial base stations in heterogeneous communication networks under constraints imposed by diverse ground obstacles. Given the diverse data demands of user equipments (UEs), a user satisfaction model is developed to provide personalized services. In particular, when a UE is located within a ground obstacle, the UAV must approach the obstacle boundary to ensure reliable service quality. Considering constraints such as UAV failures due to battery depletion, heterogeneous UEs, and obstacles, we aim to maximize overall user satisfaction by jointly optimizing the 3D trajectories of UAVs, transmit beamforming vectors, and binary association indicators between UAVs and UEs. To address the complexity and dynamics of the problem, a block coordinate descent method is adopted to decompose it into two subproblems. The beamforming subproblem is efficiently addressed via a bisection-based water-filling algorithm. For the trajectory and association subproblem, we design a deep reinforcement learning algorithm based on proximal policy optimization to learn an adaptive control policy. Simulation results demonstrate that the proposed scheme outperforms baseline schemes in terms of convergence speed and overall system performance. Moreover, it achieves efficient association and accurate obstacle avoidance.

eess.SP↗

arXiv2026

When Generative AI Meets Extended Reality: Enabling Scalable and Natural Interactions

Extended Reality (XR), including virtual, augmented, and mixed reality, provides immersive and interactive experiences across diverse applications, from VR-based education to AR-based assistance and MR-based training. However, widespread XR adoption remains limited due to two key challenges: 1) the high cost and complexity of authoring 3D content, especially for large-scale environments or complex interactions; and 2) the steep learning curve associated with non-intuitive interaction methods like handheld controllers or scripted gestures. Generative AI (GenAI) presents a promising solution by enabling intuitive, language-driven interaction and automating content generation. Leveraging vision-language models and diffusion-based generation, GenAI can interpret ambiguous instructions, understand physical scenes, and generate or manipulate 3D content, significantly lowering barriers to XR adoption. This paper explores the integration of XR and GenAI through three concrete use cases, showing how they address key obstacles in scalability and natural interaction, and identifying technical challenges that must be resolved to enable broader adoption.

cs.HC↗

arXiv2026

On the Robustness of Age for Learning-Based Wireless Scheduling in Unknown Environments

The constrained combinatorial multi-armed bandit model has been widely employed to solve problems in wireless networking and related areas, including the problem of wireless scheduling for throughput optimization under unknown channel conditions. Most work in this area uses an algorithm design strategy that combines a bandit learning algorithm with the virtual queue technique to track the throughput constraint violation. These algorithms seek to minimize the virtual queue length in their algorithm design. However, in networks where channel conditions change abruptly, the resulting constraints may become infeasible, leading to unbounded growth in virtual queue lengths. In this paper, we make the key observation that the dynamics of the head-of-line age, i.e. the age of the oldest packet in the virtual queue, make it more robust when used in algorithm design compared to the virtual queue length. We therefore design a learning-based scheduling policy that uses the head-of-line age in place of the virtual queue length. We show that our policy matches state-of-the-art performance under i.i.d. network conditions. Crucially, we also show that the system remains stable even under abrupt changes in channel conditions and can rapidly recover from periods of constraint infeasibility.

cs.LG↗

arXiv2026

Electric field switching of altermagnetic spin-splitting in multiferroic skyrmions

Magnetic skyrmions are localized magnetic structures that retain their shape and stability over time, thanks to their topological nature. Recent theoretical and experimental progress has laid the groundwork for understanding magnetic skyrmions characterized by negligible net magnetization and ultrafast dynamics. Notably, skyrmions emerging in materials with altermagnetism, a novel magnetic phase featuring lifted Kramers degeneracy-have remained unreported until now. In this study, we demonstrate that BiFeO3, a multiferroic renowned for its strong coupling between ferroelectricity and magnetism, can transit from a spin cycloid to a Neel-type skyrmion under antidamping spin-orbit torque at room temperature. Strikingly, the altermagnetic spin splitting within BiFeO3 skyrmion can be reversed through the application of an electric field, revealed via the Circular photogalvanic effect. This quasiparticle, which possesses a neutral topological charge, holds substantial promise for diverse applications-most notably, enabling the development of unconventional computing systems with low power consumption and magnetoelectric controllability.

cond-mat.mtrl-sci↗

arXiv2026

Consistency-Aware Parameter-Preserving Knowledge Editing Framework for Multi-Hop Question Answering

Parameter-Preserving Knowledge Editing (PPKE) enables updating models with new information without retraining or parameter adjustment. Recent PPKE approaches used knowledge graphs (KG) to extend knowledge editing (KE) capabilities to multi-hop question answering (MHQA). However, these methods often lack consistency, leading to knowledge contamination, unstable updates, and retrieval behaviors that are misaligned with the intended edits. Such inconsistencies undermine the reliability of PPKE in multi-hop reasoning. We present CAPE-KG, Consistency-Aware Parameter-Preserving Editing with Knowledge Graphs, a novel consistency-aware framework for PPKE on MHQA. CAPE-KG ensures KG construction, update, and retrieval are always aligned with the requirements of the MHQA task, maintaining coherent reasoning over both unedited and edited knowledge. Extensive experiments on the MQuAKE benchmark show accuracy improvements in PPKE performance for MHQA, demonstrating the effectiveness of addressing consistency in PPKE.

cs.CL↗

arXiv2026

Distributionally Robust Game for Proof-of-Work Blockchain Mining Under Resource Uncertainties

Blockchain plays a crucial role in ensuring the security and integrity of decentralized systems, with the proof-of-work (PoW) mechanism being fundamental for achieving distributed consensus. As PoW blockchains see broader adoption, an increasingly diverse set of miners with varying computing capabilities participate in the network. In this paper, we consider the PoW blockchain mining, where the miners are associated with resource uncertainties. To characterize the uncertainty computing resources at different mining participants, we establish an ambiguous set representing uncertainty of resource distributions. Then, the networked mining is formulated as a non-cooperative game, where distributionally robust performance is calculated for each individual miner to tackle the resource uncertainties. We prove the existence of the equilibrium of the distributionally robust mining game. To derive the equilibrium, we propose the conditional value-at-risk (CVaR)-based reinterpretation of the best response of each miner. We then solve the individual strategy with alternating optimization, which facilitates the iteration among miners towards the game equilibrium. Furthermore, we consider the case that the ambiguity of resource distribution reduces to Gaussian distribution and the case that another uncertainties vanish, and then characterize the properties of the equilibrium therein along with a distributed algorithm to achieve the equilibrium. Simulation results show that the proposed approaches effectively converge to the equilibrium, and effectively tackle the uncertainties in blockchain mining to achieve a robust performance guarantee.

eess.SY↗