Peiwen Sun
8 papers · 2023–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Silver
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(10)
โ
The Questioner
Top co-authors
Research topics
Keywords
reinforcement learning
(1)
attention mechanism
(1)
speech synthesis
(1)
visual reasoning
(1)
time series
(1)
generative model
(1)
supervised fine-tuning
(1)
multimodal large language model
(1)
self-supervised pretraining
(1)
latent diffusion model
(1)
audio generation
(1)
text-to-audio generation
(1)
spatial audio
(1)
audio-language model
(1)
residual vector quantization
(1)
first-order ambisonics
(1)
multimodal generation
(1)
perspective video
(1)
text to speech
(1)
panoramic video
(1)
Papers
OneThinker: All-in-one Reasoning Model for Image and Video
CVPR 2026
Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation
ICLR 2025
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
AAAI 2025
OmniAudio: Generating Spatial Audio from 360-Degree Video
ICML 2025
Can Textual Semantics Mitigate Sounding Object Segmentation Preference?
ECCV 2024
Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes
ECCV 2024
Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation
ECCV 2024
A Method of Audio-Visual Person Verification by Mining Connections between Time Series
Interspeech 2023