PY
Peiran Yin
cs.CLcs.CVcs.AIcs.LGcs.RO
On Valency
published · living versionsW_8n8ynzbg·v1 · currentpublished
ReInsVLN: Revisiting Historical Evidence for Training-Free Vision-and-Language Navigation
with Siwei Cheng, Hao Wu, Zitong Qi, Xinming Zhang +5
1 version
Preprints & journals
7 papers in the corpus · 2026ReInsVLN: Revisiting Historical Evidence for Training-Free Vision-and-Language Navigation2610.26545v1 · Siwei Cheng, Hao Wu, Zitong Qi et al.2026 · 0 citationsarXivon Valency
Bifocal: Training-Free Mixed Granularity Visual Token Pruning for Multimodal LLMs2610.18399v2 · Peiran Yin, Hao Wu, Zihao Yang et al.2026 · 0 citationsarXiv
GeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMs2610.13035v1 · Yongxin Zheng, Hao Wu, Fang Li et al.2026 · 0 citationsarXiv
MWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMs2610.01434v1 · Xudong Wang, Hao Wu, Haozhe Hu et al.2026 · 0 citationsarXiv
WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning2607.28418v2 · Haozhe Hu, Hao Wu, Peiran Yin et al.2026 · 0 citationsarXiv
Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomy2606.09080v2 · Haozhe Hu, Hao Wu, Anhao Zhao et al.2026 · 0 citationsarXiv
From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models2603.04592v3 · Junlong Tong, Zilong Wang, YuJie Ren et al.2026 · 0 citationsarXiv
Career total: 7 works. 7 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.