PS
Peiwen Sun
cs.CVcs.AIcs.CLcs.SDeess.AScs.ROcs.LGcs.MM
On Valency
published · living versionsW_vtapev5x·v1 · currentpublished
Beyond Omni: A Unified MLLM for Embodied Sensory Understanding
with Shiyun Xiong, Dongming Wu, Bokang Yang, Jiaxu Wang +3
1 version
Preprints & journals
14 papers in the corpus · 2024–2026Beyond Omni: A Unified MLLM for Embodied Sensory Understanding2610.26751v1 · Shiyun Xiong, Dongming Wu, Peiwen Sun et al.2026 · 0 citationsarXivon Valency
Towards Agentic Robots: Model, Data, Environment, and Harness2610.20442v1 · Chonghan Qin, Dongming Wu, Kaituo Feng et al.2026 · 0 citationsarXiv
Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use2608.14047v3 · Ding Yi, Yanzhao Yu, Xili Dai et al.2026 · 0 citationsProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Findings (CVPRF), 2026, pp. 1346-1357
Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation2606.12199v1 · Zhen Ye, Xu Tan, Yiming Li et al.2026 · 0 citationsarXiv
LongSpace: Exploring Long-Horizon Spatial Memory from Perception to Recall in Video2606.05677v1 · Shiqiang Lang, Jing Liu, Haoyang He et al.2026 · 0 citationsarXiv
Benchmark Everything Everywhere All at Once2606.06462v1 · Shiyun Xiong, Dongming Wu, Peiwen Sun et al.2026 · 0 citationsarXiv
X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding2606.02482v3 · Peiwen Sun, Xudong Lu, Huadai Liu et al.2026 · 0 citationsarXiv
Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling2604.23586v2 · Zhen Ye, Xu Tan, Aoxiong Yin et al.2026 · 0 citationsarXiv
AURA: Always-On Understanding and Real-Time Assistance via Video Streams2604.04184v1 · Xudong Lu, Yang Bo, Jinpeng Chen et al.2026 · 0 citationsarXiv
PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios2601.22575v1 · Xudong Lu, Huankang Guan, Yang Bo et al.2026 · 0 citationsarXiv
Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation2407.11820v3 · Juncheng Ma, Peiwen Sun, Yaoting Wang et al.2024 · 11 citationsarXiv
Can Textual Semantics Mitigate Sounding Object Segmentation Preference?2407.10947v1 · Yaoting Wang, Peiwen Sun, Yuanchao Li et al.2024 · 8 citationsarXiv
Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes2407.10957v1 · Yaoting Wang, Peiwen Sun, Dongzhan Zhou et al.2024 · 12 citationsarXiv
FlashSpeech: Efficient Zero-Shot Speech Synthesis2404.14700v4 · Zhen Ye, Zeqian Ju, Haohe Liu et al.2024 · 12 citationsarXiv
Career total: 15 works. 14 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.