Yukuan Zhang

Dayuan Chen, Kai Tang, Yukuan Zhang et al.

This paper presents a phase-conditioned, force-aware framework for robust deformable object manipulation. Standard imitation learning policies such as Action Chunking with Transformers (ACT) rely on a Markovian assumption at inference, causing state aliasing when visually similar observations require contradictory actions and preventing autonomous recovery from execution failures. We address this with a closed-loop hierarchical architecture. A FiLM-conditioned ACT encoder modulates feature extraction based on the current task phase, enabling a single unified policy to produce phase-specific behaviors while sharing action dynamics across phases. A multi-modal phase predictor fusing visual, force, and pose feedback estimates the phase in real time, detecting contact failures that are invisible to vision alone and autonomously triggering recovery trajectories. The system is completed by a hybrid impedance controller for compliant execution and a haptic teleoperation interface for force-aware data collection. Ablation studies show that FiLM-based modulation significantly outperforms both unconditioned and token-level conditioned baselines, and t-SNE analysis confirms that FiLM induces well-separated, phase-specific feature representations. Validated on hanging and removing a T-shirt with dual arms, the closed-loop system improves the hanging success rate from 56\% to 87\% through autonomous error recovery. Code and videos: https://leledeyuan00.github.io/phaser/

Yukuan Zhang, Jiarui Zhao, Shangqing Nie et al.

Cross-modal hashing retrieval encodes heterogeneous data into compact binary codes for efficient Hamming-space search. Existing methods usually learn cross-modal semantics in continuous feature spaces and generate binary codes through a final sign operation, which weakly couples training optimization with discrete hash retrieval. We propose SpikeHash, a unified spiking framework that formulates cross-modal hashing as spike-state evolution, directional spike interaction, and competitive spike readout. Specifically, SpikeHash converts image and text features into multi-timestep spike sequences. In a shared Hamming space, the two spike sequences jointly drive the temporal evolution of a shared hash state. Cross-modal interaction is further performed through directional spike modulation, enabling each modality to influence the firing dynamics of the other. Crucially, SpikeHash replaces the conventional continuous hash head with a positive-negative spiking hash readout, where each hash bit is produced by temporal competition between paired spike channels. Experimental results show that SpikeHash achieves competitive retrieval accuracy on three benchmark datasets while reducing the parameter size, operation count, and estimated energy of the hash learning stage, suggesting a compact spiking alternative to conventional continuous hash mapping. The project page is available at https://shuqiao-111.github.io/.

Yukuan Zhang, Yunhua Jia, Housheng Xie et al.

Object tracking is divided into single-object tracking (SOT) and multi-object tracking (MOT). MOT aims to maintain the identities of multiple objects across a series of continuous video sequences. In recent years, MOT has made rapid progress. However, modeling the motion and appearance models of objects in complex scenes still faces various challenging issues. In this paper, we design a novel direction consistency method for smooth trajectory prediction (STP-DC) to increase the modeling of motion information and overcome the lack of robustness in previous methods in complex scenes. Existing methods use pedestrian re-identification (Re-ID) to model appearance, however, they extract more background information which lacks discriminability in occlusion and crowded scenes. We propose a hyper-grain feature embedding network (HG-FEN) to enhance the modeling of appearance models, thus generating robust appearance descriptors. We also proposed other robustness techniques, including CF-ECM for storing robust appearance information and SK-AS for improving association accuracy. To achieve state-of-the-art performance in MOT, we propose a robust tracker named Rt-track, incorporating various tricks and techniques. It achieves 79.5 MOTA, 76.0 IDF1 and 62.1 HOTA on the test set of MOT17.Rt-track also achieves 77.9 MOTA, 78.4 IDF1 and 63.3 HOTA on MOT20, surpassing all published methods.

Yukuan Zhang, Mengxin Zheng, Qian Lou

Cryptographically secure neural network inference typically relies on secure computing techniques such as Secure Multi-Party Computation (MPC), enabling cloud servers to process client inputs without decrypting them. Although prior privacy-preserving inference systems co-design network optimizations with MPC, they remain slow and costly, limiting real-world deployment. A major bottleneck is their use of a single, fixed transformer model for all encrypted inputs, ignoring that different inputs require different model sizes to balance efficiency and accuracy. We present SecureRouter, an end-to-end encrypted routing and inference framework that accelerates secure transformer inference through input-adaptive model selection under encryption. SecureRouter establishes a unified encrypted pipeline that integrates a secure router with an MPC-optimized model pool, enabling coordinated routing, inference, and protocol execution while preserving full data and model confidentiality. The framework includes training-phase and inference-phase components: an MPC-cost-aware secure router that predicts per-model utility and cost from encrypted features, and an MPC-optimized model pool whose architectures and quantization schemes are co-trained to minimize MPC communication and computation overhead. Compared to prior work, SecureRouter achieves a latency reduction by 1.95x with negligible accuracy loss, offering a practical path toward scalable and efficient secure AI inference. Our open-source implementation is available at: https://github.com/UCF-ML-Research/SecureRouter

Xidong Wu, Yukuan Zhang, Yuqiong Ji et al.

Large language model (LLM) routing has emerged as a critical strategy to balance model performance and cost-efficiency by dynamically selecting services from various model providers. However, LLM routing adds an intermediate layer between users and LLMs, creating new privacy risks to user data. These privacy risks have not been systematically studied. Although cryptographic techniques such as Secure Multi-Party Computation (MPC) enable privacy-preserving computation, their protocol design and implementation remain under-explored, and naïve implementations typically incur prohibitive computational overhead. To address this, we propose a privacy-preserving LLM routing framework (PPRoute). PPRoute includes multiple strategies to speed up encoder inference and nearest neighbor search under the MPC and maintain the quality of LLM routing. First, PPRoute uses MPC-friendly operations to boost the encoder inference. Second, PPRoute uses a multiple-step model training algorithm to maintain routing quality despite the constraints of the encrypted domain. Third, PPRoute proposes an unsorted Top-k algorithm with $O(1)$ communication complexity for secure sorting in model search, significantly reducing communication latency. Across different datasets, PPRoute achieves the performance of plaintext counterparts, while achieving approximately a 20$\times$ speedup over naïve MPC implementations.

Housheng Xie, Junhui Qiu, Yuan Dai et al.

As an essential processing step before the fusing of infrared and visible images, the performance of image registration determines whether the two images can be fused at correct spatial position. In the actual scenario, the varied imaging devices may lead to a change in perspective or time gap between shots, making significant non-rigid spatial relationship in infrared and visible images. Even if a large number of feature points are matched, the registration accuracy may still be inadequate, affecting the result of image fusion and other vision tasks. To alleviate this problem, we propose a Semantic-Aware on-Demand registration network (SA-DNet), which mainly purpose is to confine the feature matching process to the semantic region of interest (sROI) by designing semantic-aware module (SAM) and HOL-Deep hybrid matching module (HDM). After utilizing TPS to transform infrared and visible images based on the corresponding feature points in sROI, the registered images are fused using image fusion module (IFM) to achieve a fully functional registration and fusion network. Moreover, we point out that for different demands, this type of approach allows us to select semantic objects for feature matching as needed and accomplishes task-specific registration based on specific requirements. To demonstrate the robustness of SA-DNet for non-rigid distortions, we conduct extensive experiments by comparing SA-DNet with five state-of-the-art infrared and visible image feature matching methods, and the experimental results show that our method adapts better to the presence of non-rigid distortions in the images and provides semantically well-registered images.

Yukuan Zhang, Jiarui Zhao, Shangqing Nie et al.

Multimodal semantic cues, such as textual descriptions, have shown strong potential in enhancing target perception for tracking. However, existing methods rely on static textual descriptions from large language models, which lack adaptability to real-time target state changes and prone to hallucinations. To address these challenges, we propose a unified multimodal vision-language tracking framework, named EPIPTrack, which leverages explicit and implicit prompts for dynamic target modeling and semantic alignment. Specifically, explicit prompts transform spatial motion information into natural language descriptions to provide spatiotemporal guidance. Implicit prompts combine pseudo-words with learnable descriptors to construct individualized knowledge representations capturing appearance attributes. Both prompts undergo dynamic adjustment via the CLIP text encoder to respond to changes in target state. Furthermore, we design a Discriminative Feature Augmentor to enhance visual and cross-modal representations. Extensive experiments on MOT17, MOT20, and DanceTrack demonstrate that EPIPTrack outperforms existing trackers in diverse scenarios, exhibiting robust adaptability and superior performance.