arXiv subjects

Sen Ye

Publications and source records attributed to Sen Ye.

5 recordsLinked to original sources

arXiv2026

Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models

Current research in multimodal models faces a key challenge where enhancing generative capabilities often comes at the expense of understanding, and vice versa. We analyzed this trade-off and identify the primary cause might be the potential conflict between generation and understanding, which creates a competitive dynamic within the model. To address this, we propose the Reason-Reflect-Refine (R3) framework. This innovative algorithm re-frames the single-step generation task into a multi-step process of "generate-understand-regenerate". By explicitly leveraging the model's understanding capability during generation, we successfully mitigate the optimization dilemma, achieved stronger generation results and improved understanding ability which are related to the generation process. This offers valuable insights for designing next-generation unified multimodal models. Code is available at https://github.com/sen-ye/R3.

cs.CV↗

arXiv2025

Geese achieve stationary takeoff via synergistic wing kinematics and enhanced aerodynamics

Stationary take-off, without a running start or elevated descent, requires substantial aerodynamic forces to overcome weight, particularly for large birds such as geese exceeding 2 kg. However, the complex wing motion and high-Reynolds-number (Re $\approx$$10^5$) flow dynamics challenge conventional expectations of avian flight aerodynamics, rendering this mechanism elusive. Analyzing 578 stationary take-offs from seven geese (\textit{Anser cygnoides}) and applying Principal Component Analysis (PCA), we reveal that the complex wing kinematics collapse onto a low-dimensional manifold dominated by two synergies: a Stroke Synergy responsible for fundamental rhythmic stroke, and a Morphing Synergy governing spanwise geometry. This modular control strategy orchestrates a stereotyped wing kinematics featuring an accelerated translational downstroke and a rapid tip-reversal upstroke. By integrating wing kinematic analysis with the mass distribution of the geese, we quantified the aerodynamic forces and found that entirely positive lift and thrust are generated throughout the motion cycle. The enhanced aerodynamic performance of geese takeoff results from three principal mechanisms. During the downstroke, significant lift generated from wing acceleration is predicted by the quasi-steady framework. Flow visualization reveals that wake capture further enhances the lift generation in downstroke by orienting the position of wake vortices. During the upstroke, the distal wing performs a rapid pitching motion and generates a substantial thrust, the vertical component of which contributes significantly to weight support.

physics.flu-dyn↗

arXiv2025

Distribution Matching Variational AutoEncoder

Most visual generative models compress images into a latent space before applying diffusion or autoregressive modelling. Yet, existing approaches such as VAEs and foundation model aligned encoders implicitly constrain the latent space without explicitly shaping its distribution, making it unclear which types of distributions are optimal for modeling. We introduce \textbf{Distribution-Matching VAE} (\textbf{DMVAE}), which explicitly aligns the encoder's latent distribution with an arbitrary reference distribution via a distribution matching constraint. This generalizes beyond the Gaussian prior of conventional VAEs, enabling alignment with distributions derived from self-supervised features, diffusion noise, or other prior distributions. With DMVAE, we can systematically investigate which latent distributions are more conducive to modeling, and we find that SSL-derived distributions provide an excellent balance between reconstruction fidelity and modeling efficiency, reaching gFID equals 3.2 on ImageNet with only 64 training epochs. Our results suggest that choosing a suitable latent distribution structure (achieved via distribution-level alignment), rather than relying on fixed priors, is key to bridging the gap between easy-to-model latents and high-fidelity image synthesis. Code is avaliable at https://github.com/sen-ye/dmvae.

cs.CV↗

arXiv2024

MMoE: Robust Spoiler Detection with Multi-modal Information and Domain-aware Mixture-of-Experts

Online movie review websites are valuable for information and discussion about movies. However, the massive spoiler reviews detract from the movie-watching experience, making spoiler detection an important task. Previous methods simply focus on reviews' text content, ignoring the heterogeneity of information in the platform. For instance, the metadata and the corresponding user's information of a review could be helpful. Besides, the spoiler language of movie reviews tends to be genre-specific, thus posing a domain generalization challenge for existing methods. To this end, we propose MMoE, a multi-modal network that utilizes information from multiple modalities to facilitate robust spoiler detection and adopts Mixture-of-Experts to enhance domain generalization. MMoE first extracts graph, text, and meta feature from the user-movie network, the review's textual content, and the review's metadata respectively. To handle genre-specific spoilers, we then adopt Mixture-of-Experts architecture to process information in three modalities to promote robustness. Finally, we use an expert fusion layer to integrate the features from different perspectives and make predictions based on the fused embedding. Experiments demonstrate that MMoE achieves state-of-the-art performance on two widely-used spoiler detection datasets, surpassing previous SOTA methods by 2.56% and 8.41% in terms of accuracy and F1-score. Further experiments also demonstrate MMoE's superiority in robustness and generalization. Our code is available at https://github.com/zzqbjt/Spoiler-Detection.

cs.AI↗

arXiv2023

HOFA: Twitter Bot Detection with Homophily-Oriented Augmentation and Frequency Adaptive Attention

Twitter bot detection has become an increasingly important and challenging task to combat online misinformation, facilitate social content moderation, and safeguard the integrity of social platforms. Though existing graph-based Twitter bot detection methods achieved state-of-the-art performance, they are all based on the homophily assumption, which assumes users with the same label are more likely to be connected, making it easy for Twitter bots to disguise themselves by following a large number of genuine users. To address this issue, we proposed HOFA, a novel graph-based Twitter bot detection framework that combats the heterophilous disguise challenge with a homophily-oriented graph augmentation module (Homo-Aug) and a frequency adaptive attention module (FaAt). Specifically, the Homo-Aug extracts user representations and computes a k-NN graph using an MLP and improves Twitter's homophily by injecting the k-NN graph. For the FaAt, we propose an attention mechanism that adaptively serves as a low-pass filter along a homophilic edge and a high-pass filter along a heterophilic edge, preventing user features from being over-smoothed by their neighborhood. We also introduce a weight guidance loss to guide the frequency adaptive attention module. Our experiments demonstrate that HOFA achieves state-of-the-art performance on three widely-acknowledged Twitter bot detection benchmarks, which significantly outperforms vanilla graph-based bot detection techniques and strong heterophilic baselines. Furthermore, extensive studies confirm the effectiveness of our Homo-Aug and FaAt module, and HOFA's ability to demystify the heterophilous disguise challenge.

cs.SI↗