Institution profile

Zhejiang Lab

Academic institutionasia · cn
Official website
Research library197linked papers
Opportunities0open roles
Selected work

Representative Papers

Pedestrian Trajectory Prediction Based on Social Interactions Learning With Random Weights

Jan 13, 2025IEEE transactions on multimedia

To address the limitations of rule-based pedestrian trajectory prediction in autonomous driving—particularly the difficulty in modeling implicit social interactions—this paper proposes DTGAN, the first generative adversarial framework specifically designed for graph-structured sequential data. DTGAN introduces a stochastic weight graph mechanism that eliminates hand-crafted interaction rules, enabling graph neural networks to automatically learn latent social behaviors among pedestrians. Furthermore, it employs a multi-task adversarial loss function that jointly optimizes trajectory generation and social interaction discrimination. Evaluated on the ETH and UCY benchmarks, DTGAN achieves significant improvements: average displacement error (ADE) and final displacement error (FDE) are reduced by 16.7% and 39.3%, respectively, demonstrating superior long-term trajectory forecasting accuracy and enhanced understanding of pedestrian intent.

5 citationsRead paper

Grouter: Decoupling Routing from Representation for Accelerated MoE Training

Feb 22, 2026

This work addresses the slow convergence and training instability commonly observed in traditional Mixture-of-Experts (MoE) models, which stem from the joint optimization of routing policies and expert weights. To overcome these limitations, the authors propose Grouter, a novel approach that introduces a preset routing mechanism: high-quality routing structures are distilled from a pre-trained MoE model and then fixed, effectively decoupling routing optimization from expert weight updates. Grouter further incorporates expert folding, expert fine-tuning, and structure-prior-guided training strategies to enable efficient adaptation across diverse model configurations and data distributions. Experimental results demonstrate that Grouter improves training data utilization by 4.28× and achieves up to 33.5% higher throughput, significantly enhancing both the efficiency and performance of MoE training.

2 citationsRead paper

PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models

Jan 16, 2026

This work addresses the lack of physical plausibility in existing Transformer-based video generation models, which often disregard rigid-body physics during pixel-level denoising, leading to unrealistic behaviors in collision scenarios. To overcome this limitation, we propose a physics-aware reinforcement learning paradigm that, for the first time, explicitly embeds Newtonian mechanics–driven collision rules as reinforcement signals directly into the high-dimensional generative space, rather than imposing them as post-hoc constraints. We introduce the Mimicry-Discovery Cycle (MDcycle), a unified framework that preserves physical feedback during large-scale fine-tuning, enabling co-optimization of physical fidelity and generative flexibility. Experiments on the newly established PhysRVGBench benchmark demonstrate that our approach significantly outperforms current methods in both physical realism and rigid-body motion consistency.

1 citationsRead paper

Advancing Remote Medical Palpation through Cognition and Emotion

Jul 08, 2024

Conventional remote palpation overemphasizes force feedback while neglecting the synergistic roles of cognition and emotion in tactile diagnosis. Method: This study pioneers a cognitive–affective coupling framework for clinical palpation, proposing a dual-pathway haptic perception model: an active, cognition-enhanced haptic integration pathway for clinicians, and a passive, emotion-modulated physiological response pathway for patients—treated as a novel diagnostic signal source. The system integrates multimodal sensing, active–passive haptic modeling, affective response recognition, and cognition-guided human–machine interfaces. Results: In simulated abdominal palpation tasks, the approach improved diagnostic consensus by 37%, significantly enhanced clinical discriminability and clinician decision confidence, and established an emotion-responsive paradigm for remote palpation.

1 citationsRead paper
Recent publications

Latest Papers