Yiwen Zhao's Portfolio

OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery

[CVPR 2026] | project page | paper | code

CRISP: Contact-guided Real2Sim from Monocular Video with Planar Scene Primitives

[ICLR 2026] | project page | paper | code

SoundscapeAgent: Agentic Soundscape Construction for Controllable Synthesis and Scalable Audio-Language Supervision

[SLT 2026] | project page | paper

(Work done during internship at Tencent America)

FreeDance: Towards Harmonic Free-Number Group Dance Generation via a Unified Framework

[ICCV 2025]Travel Grant | project page | paper | code

ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation

[NeurIPS 2025]Spotlight | paper | code

Adapting Speech Language Model to Singing Voice Synthesis

[NeurIPSW 2025 AI4Music]Student Grant | project page | paper | code

ESPnet-SpeechLM: An Open Speech Language Model Toolkit

[NAACL 2025] (Demo) | paper | code

Robust Training of Singing Voice Synthesis Using Prior and Posterior Uncertainty

[ASRU 2025] | project page | paper | code

VERSA-v2: A Modular and Scalable Toolkit for Speech and Audio Evaluation with Expanded Metrics, Visualization, and LLM Integration

[ASRU 2025] (Demo) Best Demo Candidate | paper | code

VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music

[NAACL 2025] (Demo) | paper | code

Fashion Chatroom: An Automated Pipeline for Fashion Dataset Construction

[AAAIW 2024 AI4CSE] | paper

Exploring Locomotion Methods with Upright Redirected Views for VR Users in Reclining & Lying Positions

[UIST 2023]Oral | paper

Publications