arXiv subjects

Weitao Jiang

Publications and source records attributed to Weitao Jiang.

3 recordsLinked to original sources

arXiv2026

simpleposter: A simple baseline for product poster generation

Product poster generation poses distinct challenges beyond general poster design, requiring both faithful preservation of product appearance and precise control over dense, multi-line text layouts. Prior methods typically adopt inpainting frameworks augmented with auxiliary modules such as ControlNet and OCR encoders. However, these approaches introduce architectural complexity and computational overhead while still suffering from text errors and subject extension artifacts. We present SimplePoster, a simple yet effective inpainting-based framework that achieves faithful subject preservation and accurate, position-controllable text rendering without external controllers. Our approach builds on two observations: (1) full-parameter fine-tuning of the base model effectively suppresses subject extension, outperforming ControlNet-based alternatives; and (2) a zero-cost character-level position encoding enables geometry-aware text generation without dedicated layout modules. Experiments show that SimplePoster achieves a $98.7\%$ subject preservation rate, compared to $55.2\%$ for SeedEdit 3.0 and $85.3\%$ for PosterMaker, while also improving text rendering accuracy. Code, models, benchmark and a part of training data will be available at https://github.com/Alibaba-YuFeng/SIMPLEPOSTER

cs.CV↗

arXiv2026

Towards Paradigm-General Suicide Risk Detection via Speech LLM

Suicide risk among adolescents remains a critical public health concern, and speech provides a non-invasive and scalable approach for its detection. Speech-based suicide risk assessment commonly relies on carefully designed speech elicitation paradigms (\textit{e.g.,} verbal fluency, reading, or question answering) to probe cognitive and affective states. Existing approaches, however, typically focus on one single paradigm at a time. This paper, for the first time, investigates cross-paradigm approaches that unify diverse speech elicitation paradigms within a single model. Specifically, we use a speech LLM as backbone with a mixture of DoRA experts (MoDE) to capture complementary cues across assessments dynamically, tested on 1,223 participants across ten speech elicitation paradigms. Results show that MoDE outperforms both paradigm-specific and conventional joint-learning models. Moreover, it can generalise to unseen paradigms and provide better confidence calibration.

eess.AS↗

arXiv2025

Propulsive transitions and scaling relations of a heaving flexible foil in a cylinder wake

We numerically investigate the propulsive dynamics of a heaving flexible foil immersed in the wake of a stationary circular cylinder, focusing on the coupled effects of unsteady wake forcing, passive structural flexibility, and prescribed heaving kinematics. The analysis employs a high-fidelity fluid-structure interaction solver based on a partitioned variational formulation with a nonlinear iterative force correction scheme. Systematic simulations are conducted over a broad parameter space of dimensionless heaving amplitude and frequency at a Reynolds number of 3000. Five distinct response modes are identified, namely full-wake, semi-wake, full-wake-flexible, semi-wake-flexible, and vortex-flexible, based on propulsive transitions and associated flow features. An empirical boundary plane is discovered, separating regimes where the wake hinders lift performance (wake-dominated) from those where it enhances performance (flapping-dominated). Scaling relations for the force and power coefficients are formulated by decomposing the contributions of quasi-steady motion, added-mass effects, structural curvature, wake momentum deficit, and transverse flow gradients. At sufficiently large amplitude and frequency, a two-way lock-in emerges: the foil not only synchronizes with the cylinder shedding but also modulates it, accelerating the wake and enhancing lift.Flexibility is found to be detrimental in fully immersed wakes but beneficial in partial wakes, where it creates extra suction without much extra drag in the semi-wake-flexible mode. These findings elucidate the energy-saving and maneuverability strategies employed by biological propulsors and provide predictive guidelines for the design of bio-inspired energy harvesters and unmanned vehicles in disturbed flows.

physics.flu-dyn↗