← Search

Yan Wen

6 accepted papers

2026

STFMamba: A Neurocognitive-Inspired Dual-Path State Space Model for Surgical Phase Recognition

RA-L 2026

Surgical phase recognition is critical in computer-assisted surgery. Clinically, surgeons discriminate surgical phases through visuospatial analysis of instrument-tissue interactions. However, existing methods fail to adequately account for the critical role of the visual-neural mechanisms of the su

Cited by 0SourceScholar
2025

Asymmetric Conflict and Synergy in Post-training for LLM-based Multilingual Machine Translation

ACL 2025finding

The emergence of Large Language Models (LLMs) has advanced the multilingual machine translation (MMT), yet the Curse of Multilinguality (CoM) remains a major challenge. Existing work in LLM-based MMT typically mitigates this issue via scaling up training and computation budget, which raises a critic…

Cited by 0SourcePDFScholar
2025

Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning

CVPR 2025poster

Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed in diffusion models. However, achieving 4-bit quantization remains challenging. Existing methods, primarily based on integer quantization and post-training quantization fine-tuning, s…

Cited by 0SourcePDFScholar
2025

Wheel-Legged SLAM: Indoor LiDAR-Inertial SLAM Integrating Kinematic Model of Wheel-Legged Robots

RA-L 2025

SLAM is the key technique for localization and surrounding perception in indoor environments. However, the dynamic posture adjustments of wheel-legged robots cast new challenges that affect the accuracy of localization. Therefore, this letter presents the Wheel-Legged SLAM, a novel indoor SLAM metho

Cited by 3SourceScholar