arXiv subjects

Bojun Cheng

Publications and source records attributed to Bojun Cheng.

At least 19 recordsLinked to original sources

arXiv2026

Human-as-Humanoid: Enabling Zero-Shot Humanoid Learning from Ego-Exo Human Videos with Human-Aligned Embodiments

Vision-language-action (VLA) models across robot embodiments require high-quality observation--action supervision to learn deployable action distributions, yet scaling such robot data remains difficult, especially for high-DoF humanoids. Teleoperation provides controller-aligned supervision, while human egocentric videos capture diverse bimanual manipulation but do not directly provide executable robot actions. We introduce Human-as-Humanoid, a human-to-humanoid supervision framework that enables near-real-time human-centric action generation, making human demonstrations usable for high-DoF humanoid VLA training by jointly aligning the robot embodiment, the sensing setup, and the action-label interface. Built on PrimeU, a human-aligned 60-DoF upper-body humanoid, Human-as-Humanoid uses synchronized ego-exo videos to pair deployment-aligned egocentric observations with exocentric motion recovery, retargets the recovered human motion through staged Inverse Kinematics (IK) into controller-aligned 60-DoF action chunks, and trains the VLA model with Forward Kinematics (FK)-aware supervision to preserve wrist and fingertip task-space geometry. This converts large-scale human demonstrations from visual observations into executable observation--action supervision for the target humanoid. Experiments validate the conversion chain at the motion-recovery, robot-action-space, and real-robot deployment levels. Human-as-Humanoid yields a 4.8--7.2x raw demonstration-throughput gain over humanoid teleoperation in our data-collection analysis, and on several downstream tasks, policies post-trained only with the converted human labels generalize to real-robot deployment without target-task robot demonstrations. The official project website is available at https://zgc-embodyai.github.io/Human-as-Humanoid.

cs.RO↗

arXiv2026

DIMOS: Disentangling Instance-level Moving Object Segmentation

Moving instance segmentation (MIS) attracts increasing attention due to its broad applications in traffic surveillance, autonomous driving, and animal tracking. Event cameras record asynchronous brightness changes, providing high temporal resolution and dynamic range, which makes them highly sensitive to motion information. By fusing event and image features, motion cues from events can complement spatial details from images, enhancing the performance of MIS. However, current multimodal MIS methods still struggle to segment small moving instances, as event cameras often yield sparse features under limited resolution. Moreover, event features entangle appearance attributes with motion cues, which further restricts effective cross-modal fusion. To address these challenges, we first propose a dual-disentangling feature extraction framework that separates and extracts appearance and motion information within both image and event modalities, thereby improving feature density. Subsequently, a multi-granularity cross-modal alignment is introduced to align distributionally and semantically consistent features across modalities, enabling more effective fusion with rich spatial and temporal details. The experiment results demonstrate that our method achieves state-of-the-art performance in multimodal MIS, especially for small instances under challenging conditions such as fast motion and low-light settings.

cs.CV↗

arXiv2026

MDN: Parallelizing Stepwise Momentum for Delta Linear Attention

Linear Attention (LA) offers a promising paradigm for scaling large language models (LLMs) to long sequences by avoiding the quadratic complexity of self-attention. Recent LA models such as Mamba2 and GDN interpret linear recurrences as closed-form online stochastic gradient descent (SGD), but naive SGD updates suffer from rapid information decay and suboptimal convergence in optimization. While momentum-based optimizers provide a natural remedy, they pose challenges in simultaneously achieving training efficiency and effectiveness. To address this, we develop a chunkwise parallel algorithm for LA with a stepwise momentum rule by geometrically reordering the update coefficients. Further, from a dynamical systems perspective, we analyze the momentum-based recurrence as a second-order system that introduces complex conjugate eigenvalues. This analysis guides the design of stable gating constraints. The resulting model, Momentum DeltaNet (MDN), leverages Triton kernels to achieve comparable training throughput with competitive linear models such as Mamba2 and KDA. Extensive experiments on the 400M and 1.3B parameter models demonstrate consistent performance improvements over strong baselines, including Transformers, Mamba2 and GDN, across diverse downstream evaluation benchmarks. Code: https://github.com/HuuYuLong/MomentumDeltaNet .

cs.LG↗

arXiv2026

Exploring Data-Free LoRA Transferability for Video Diffusion Models

Video diffusion models leveraging step distillation or causal distillation have achieved remarkable performance. However, adapting existing LoRAs to these variants remains a critical challenge due to weight space mismatches. We observe that direct application leads to style degradation and structural collapse, yet the underlying mechanisms remain poorly understood. To fill this gap, we delve into the weight space and identify that the incompatibility stems from spectral interference within shared functional clusters defined over singular subspaces. Specifically, our analysis reveals that while both paradigms respect spectral rigidity, they establish conflicting routing pathways that clash through constructive overload or destructive cancellation. To address this issue, we propose Cluster-Aware Spectral Arbitration (CASA), a data-free framework that dynamically arbitrates between safeguarding the target's manifold and restoring LoRA alignment based on spectral density. Extensive experiments demonstrate that CASA effectively mitigates artifacts and revives LoRA functionality. Our code is available at https://github.com/Noahwangyuchen/CASA

cs.CV↗

arXiv2026

Sparsity-Aware Event-Driven Impulse Radio Transceivers for Reliable Neuromorphic Inference

The growing number of Internet-of-Things (IoT) based artificial intelligence (AI) applications deployed at resource-constrained network edge call for ultra-reliable and low-latency data processing pipelines from distributed front-end sensors to remote inference units. Meanwhile, brain-inspired neuromorphic computing featuring spiking neural networks (SNNs) have arisen as a new paradigm for energy-efficient AI inference. However, significant energy and time expenses incurred in high-complexity transceivers that combat fading and multi-user interference hinder implementations of multi-user neuromorphic inference for edge intelligence. To address this challenge, we consider in this paper a broadband multi-user remote inference system that integrates event-based sensing and time-hopping (TH) on-off keying (OOK) based ultra-wideband (UWB) communications for reliable neuromorphic inference. Specifically, we propose a novel two-timescale repetition coding that leverages intra-frame pulse sparsity for low-latency repetition. We also develop two neuromorphic inference schemes based on: (i) digital spike encoding that recovers each pixel of the event-frame by threshold-adaptive detection via an SNN based sparsity estimator; and (ii) analog spike encoding that converts noisy correlator outputs at the receiver into analog-valued inputs for end-to-end (E2E) classification. Finally, numerical results validate the effectiveness of the proposed coding schemes, and reveal a signal-to-noise ratio (SNR)-dependent performance crossover between the two inference schemes, indicating that analog spike encoding based schemes are preferable with mild or high SNR while digital spike encoding based schemes remain robust in low SNR regime.

eess.SP↗

arXiv2026

Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation

Classifier-free guidance (CFG) has helped diffusion models achieve great conditional generation in various fields. Recently, more diffusion guidance methods have emerged with improved generation quality and human preference. However, can these emerging diffusion guidance methods really achieve solid and significant improvements? In this paper, we rethink recent progress on diffusion guidance. Our work mainly consists of four contributions. First, we reveal a critical evaluation pitfall that common human preference models exhibit a strong bias towards large guidance scales. Simply increasing the CFG scale can easily improve quantitative evaluation scores due to strong semantic alignment, even if image quality is severely damaged (e.g., oversaturation and artifacts). Second, we introduce a novel guidance-aware evaluation (GA-Eval) framework that employs effective guidance scale calibration to enable fair comparison between current guidance methods and CFG by identifying the effects orthogonal and parallel to CFG effects. Third, motivated by the evaluation pitfall, we design Transcendent Diffusion Guidance (TDG) method that can significantly improve human preference scores in the conventional evaluation framework but actually does not work in practice. Fourth, in extensive experiments, we empirically evaluate recent eight diffusion guidance methods within the conventional evaluation framework and the proposed GA-Eval framework. Notably, simply increasing the CFG scales can compete with most studied diffusion guidance methods, while all methods suffer severely from winning rate degradation over standard CFG. Our work would strongly motivate the community to rethink the evaluation paradigm and future directions of this field.

cs.CV↗

arXiv2025

PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence

Robotic generalization relies on physical intelligence: the ability to reason about state changes, contact-rich interactions, and long-horizon planning under egocentric perception and action. Vision Language Models (VLMs) are essential to Vision-Language-Action (VLA) systems, but the reliance on third-person training data creates a viewpoint gap for humanoid robots. Collecting massive robot-centric data is an ideal but impractical solution due to cost and diversity constraints. Conversely, human egocentric videos offer a highly scalable data source with rich interaction context, yet the embodiment mismatch prevents the direct application. To bridge this gap, we propose an Egocentric2Embodiment Translation Pipeline that transforms raw human egocentric videos into multi-level, schema-driven embodiment supervision with enforced evidence grounding and temporal consistency, enabling the construction of the Egocentric2Embodiment dataset (E2E-3M) at scale. An egocentric-aware embodied brain, termed PhysBrain, is obtained by training on the E2E-3M dataset. PhysBrain exhibits substantially improved egocentric understanding, particularly for planning. It provides an egocentric-aware initialization that enables more sample-efficient VLA fine-tuning and higher success rates, demonstrating effective transfer from human egocentric supervision to downstream robot control.

cs.RO↗

arXiv2025

SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba

Large Language Models (LLMs) have achieved remarkable performance across tasks but remain energy-intensive due to dense matrix operations. Spiking neural networks (SNNs) improve energy efficiency by replacing dense matrix multiplications with sparse accumulations. Their sparse spike activity enables efficient LLMs deployment on edge devices. However, prior SNN-based LLMs often sacrifice performance for efficiency, and recovering accuracy typically requires full pretraining, which is costly and impractical. To address this, we propose SpikingMamba, an energy-efficient SNN-based LLMs distilled from Mamba that improves energy efficiency with minimal accuracy sacrifice. SpikingMamba integrates two key components: (a) SI-LIF, a signed-integer spiking neuron that preserves semantic polarity through signed multi-level spike representations. (b) A training-exclusive Smoothed Gradient Compensation (SGC) path mitigating quantization loss while preserving spike-driven efficiency. We employ a single-stage distillation strategy to transfer the zero-shot ability of pretrained Mamba and further enhance it via reinforcement learning (RL). Experiments show that SpikingMamba-1.3B achieves a 4.76$\times$ energy benefit, with only a 4.78\% zero-shot accuracy gap compared to the original Mamba. The model achieves a further 2.55\% accuracy improvement after RL, narrowing the performance gap from 4.78\% to 2.23\%. Code is available at: https://github.com/HuuYuLong/SpikingMamba .

cs.NE↗

arXiv2025

SIS-Challenge: Event-based Spatio-temporal Instance Segmentation Challenge at the CVPR 2025 Event-based Vision Workshop

We present an overview of the Spatio-temporal Instance Segmentation (SIS) challenge held in conjunction with the CVPR 2025 Event-based Vision Workshop. The task is to predict accurate pixel-level segmentation masks of defined object classes from spatio-temporally aligned event camera and grayscale camera data. We provide an overview of the task, dataset, challenge details and results. Furthermore, we describe the methods used by the top-5 ranking teams in the challenge. More resources and code of the participants' methods are available here: https://github.com/tub-rip/MouseSIS/blob/main/docs/challenge_results.md

cs.CV↗

arXiv2025

Event-Based Eye Tracking. 2025 Event-based Vision Workshop

This survey serves as a review for the 2025 Event-Based Eye Tracking Challenge organized as part of the 2025 CVPR event-based vision workshop. This challenge focuses on the task of predicting the pupil center by processing event camera recorded eye movement. We review and summarize the innovative methods from teams rank the top in the challenge to advance future event-based eye tracking research. In each method, accuracy, model size, and number of operations are reported. In this survey, we also discuss event-based eye tracking from the perspective of hardware design.

cs.CV↗

arXiv2025

Exploring Temporal Dynamics in Event-based Eye Tracker

Eye-tracking is a vital technology for human-computer interaction, especially in wearable devices such as AR, VR, and XR. The realization of high-speed and high-precision eye-tracking using frame-based image sensors is constrained by their limited temporal resolution, which impairs the accurate capture of rapid ocular dynamics, such as saccades and blinks. Event cameras, inspired by biological vision systems, are capable of perceiving eye movements with extremely low power consumption and ultra-high temporal resolution. This makes them a promising solution for achieving high-speed, high-precision tracking with rich temporal dynamics. In this paper, we propose TDTracker, an effective eye-tracking framework that captures rapid eye movements by thoroughly modeling temporal dynamics from both implicit and explicit perspectives. TDTracker utilizes 3D convolutional neural networks to capture implicit short-term temporal dynamics and employs a cascaded structure consisting of a Frequency-aware Module, GRU, and Mamba to extract explicit long-term temporal dynamics. Ultimately, a prediction heatmap is used for eye coordinate regression. Experimental results demonstrate that TDTracker achieves state-of-the-art (SOTA) performance on the synthetic SEET dataset and secured Third place in the CVPR event-based eye-tracking challenge 2025. Our code is available at https://github.com/rhwxmx/TDTracker.

cs.CV↗

arXiv2025

ClearSight: Human Vision-Inspired Solutions for Event-Based Motion Deblurring

Motion deblurring addresses the challenge of image blur caused by camera or scene movement. Event cameras provide motion information that is encoded in the asynchronous event streams. To efficiently leverage the temporal information of event streams, we employ Spiking Neural Networks (SNNs) for motion feature extraction and Artificial Neural Networks (ANNs) for color information processing. Due to the non-uniform distribution and inherent redundancy of event data, existing cross-modal feature fusion methods exhibit certain limitations. Inspired by the visual attention mechanism in the human visual system, this study introduces a bioinspired dual-drive hybrid network (BDHNet). Specifically, the Neuron Configurator Module (NCM) is designed to dynamically adjusts neuron configurations based on cross-modal features, thereby focusing the spikes in blurry regions and adapting to varying blurry scenarios dynamically. Additionally, the Region of Blurry Attention Module (RBAM) is introduced to generate a blurry mask in an unsupervised manner, effectively extracting motion clues from the event features and guiding more accurate cross-modal feature fusion. Extensive subjective and objective evaluations demonstrate that our method outperforms current state-of-the-art methods on both synthetic and real-world datasets.

cs.CV↗

arXiv2024

Scalable Event Cloud Network for Event-based Classification

Event cameras are biologically inspired sensors garnering significant attention from both industry and academia. Mainstream methods favor frame and voxel representations, which reach a satisfactory performance while introducing time-consuming transformations, bulky models, and sacrificing fine-grained temporal information. Alternatively, Point Cloud representation demonstrates promise in addressing the mentioned weaknesses, but it has limited scalability in abstracting features of higher spatial resolution and longer temporal sequence events. In this paper, we propose a Scalable Network named SECNet to leverage Event Cloud representation. SECNet integrates polarity at the structural level by innovating the Event-based Group and Sampling module rather than only at the input level. To accommodate the surge in the number of events, SECNet embraces feature extraction in the frequency domain via the Fourier transform.This approach not only substantially extinguishes the explosion of Multiply Accumulate Operations but also effectively abstracts spatio-temporal features. We conducted extensive experiments on \textbf{ten} event-based datasets, and substantiate the scalability, effectiveness, and efficiency of SECNet. Our code will be available at: https://github.com/rhwxmx/SECNet_ICML.

cs.CV↗

arXiv2024

Event-based Motion Deblurring via Multi-Temporal Granularity Fusion

Conventional frame-based cameras inevitably produce blurry effects due to motion occurring during the exposure time. Event camera, a bio-inspired sensor offering continuous visual information could enhance the deblurring performance. Effectively utilizing the high-temporal-resolution event data is crucial for extracting precise motion information and enhancing deblurring performance. However, existing event-based image deblurring methods usually utilize voxel-based event representations, losing the fine-grained temporal details that are mathematically essential for fast motion deblurring. In this paper, we first introduce point cloud-based event representation into the image deblurring task and propose a Multi-Temporal Granularity Network (MTGNet). It combines the spatially dense but temporally coarse-grained voxel-based event representation and the temporally fine-grained but spatially sparse point cloud-based event. To seamlessly integrate such complementary representations, we design a Fine-grained Point Branch. An Aggregation and Mapping Module (AMM) is proposed to align the low-level point-based features with frame-based features and an Adaptive Feature Diffusion Module (AFDM) is designed to manage the resolution discrepancies between event data and image data by enriching the sparse point feature. Extensive subjective and objective evaluations demonstrate that our method outperforms current state-of-the-art approaches on both synthetic and real-world datasets.

cs.CV↗

arXiv2024

PRF: Parallel Resonate and Fire Neuron for Long Sequence Learning in Spiking Neural Networks

Recently, there is growing demand for effective and efficient long sequence modeling, with State Space Models (SSMs) proving to be effective for long sequence tasks. To further reduce energy consumption, SSMs can be adapted to Spiking Neural Networks (SNNs) using spiking functions. However, current spiking-formalized SSMs approaches still rely on float-point matrix-vector multiplication during inference, undermining SNNs' energy advantage. In this work, we address the efficiency and performance challenges of long sequence learning in SNNs simultaneously. First, we propose a decoupled reset method for parallel spiking neuron training, reducing the typical Leaky Integrate-and-Fire (LIF) model's training time from $O(L^2)$ to $O(L\log L)$, effectively speeding up the training by $6.57 \times$ to $16.50 \times$ on sequence lengths $1,024$ to $32,768$. To our best knowledge, this is the first time that parallel computation with a reset mechanism is implemented achieving equivalence to its sequential counterpart. Secondly, to capture long-range dependencies, we propose a Parallel Resonate and Fire (PRF) neuron, which leverages an oscillating membrane potential driven by a resonate mechanism from a differentiable reset function in the complex domain. The PRF enables efficient long sequence learning while maintaining parallel training. Finally, we demonstrate that the proposed spike-driven architecture using PRF achieves performance comparable to Structured SSMs (S4), with two orders of magnitude reduction in energy consumption, outperforming Transformer on Long Range Arena tasks.

cs.NE↗

arXiv2024

Optical Spiking Neurons Enable High-Speed and Energy-Efficient Optical Neural Networks

Optical neural networks (ONNs) perform extensive computations using photons instead of electrons, resulting in passively energy-efficient and low-latency computing. Among various ONNs, the diffractive optical neural networks (DONNs) particularly excel in energy efficiency, bandwidth, and parallelism, therefore attract considerable attention. However, their performance is limited by the inherent constraints of traditional frame-based sensors, which process and produce dense and redundant information at low operating frequency. Inspired by the spiking neurons in human neural system, which utilize a thresholding mechanism to transmit information sparsely and efficiently, we propose integrating a threshold-locking method into neuromorphic vision sensors to generate sparse and binary information, achieving microsecond-level accurate perception similar to human spiking neurons. By introducing novel Binary Dual Adaptive Training (BAT) and Optically Parallel Mixture of Experts (OPMoE) inference methods, the high-speed, spike-based diffractive optical neural network (S2NN) demonstrates an ultra-fast operating speed of 3649 FPS, which is 30 fold faster than that of reported DONNs, delivering a remarkable computational speed of 417.96 TOPS and a system energy efficiency of 12.6 TOPS/W. Our work demonstrates the potential of incorporating neuromorphic architecture to facilitate optical neural network applications in real-world scenarios for both low-level and high-level machine vision tasks.

physics.optics↗

arXiv2024

FAPNet: An Effective Frequency Adaptive Point-based Eye Tracker

Eye tracking is crucial for human-computer interaction in different domains. Conventional cameras encounter challenges such as power consumption and image quality during different eye movements, prompting the need for advanced solutions with ultra-fast, low-power, and accurate eye trackers. Event cameras, fundamentally designed to capture information about moving objects, exhibit low power consumption and high temporal resolution. This positions them as an alternative to traditional cameras in the realm of eye tracking. Nevertheless, existing event-based eye tracking networks neglect the pivotal sparse and fine-grained temporal information in events, resulting in unsatisfactory performance. Moreover, the energy-efficient features are further compromised by the use of excessively complex models, hindering efficient deployment on edge devices. In this paper, we utilize Point Cloud as the event representation to harness the high temporal resolution and sparse characteristics of events in eye tracking tasks. We rethink the point-based architecture PEPNet with preprocessing the long-term relationships between samples, leading to the innovative design of FAPNet. A frequency adaptive mechanism is designed to realize adaptive tracking according to the speed of the pupil movement and the Inter Sample LSTM module is introduced to utilize the temporal correlation between samples. In the Event-based Eye Tracking Challenge, we utilize vanilla PEPNet, which is the former work to achieve the $p_{10}$ accuracy of 97.95\%. On the SEET synthetic dataset, FAPNet can achieve state-of-the-art while consuming merely 10\% of the PEPNet's computational resources. Notably, the computational demand of FAPNet is independent of the sensor's spatial resolution, enhancing its applicability on resource-limited edge devices.

cs.CV↗

arXiv2024

Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMamba

Event cameras draw inspiration from biological systems, boasting low latency and high dynamic range while consuming minimal power. The most current approach to processing Event Cloud often involves converting it into frame-based representations, which neglects the sparsity of events, loses fine-grained temporal information, and increases the computational burden. In contrast, Point Cloud is a popular representation for processing 3-dimensional data and serves as an alternative method to exploit local and global spatial features. Nevertheless, previous point-based methods show an unsatisfactory performance compared to the frame-based method in dealing with spatio-temporal event streams. In order to bridge the gap, we propose EventMamba, an efficient and effective framework based on Point Cloud representation by rethinking the distinction between Event Cloud and Point Cloud, emphasizing vital temporal information. The Event Cloud is subsequently fed into a hierarchical structure with staged modules to process both implicit and explicit temporal features. Specifically, we redesign the global extractor to enhance explicit temporal extraction among a long sequence of events with temporal aggregation and State Space Model (SSM) based Mamba. Our model consumes minimal computational resources in the experiments and still exhibits SOTA point-based performance on six different scales of action recognition datasets. It even outperformed all frame-based methods on both Camera Pose Relocalization (CPR) and eye-tracking regression tasks. Our code is available at: https://github.com/rhwxmx/EventMamba.

cs.CV↗