Scholar

Pinxin Liu

Google Scholar ID: ZJQldrQAAAAJ

Univeristy of Rochester

Computer VisionNatural Language ProcessingData Mining

Homepage↗Google Scholar↗

Citations & Impact

All-time

Citations

335

H-index

9

i10-index

9

Publications

20

Co-authors

10

list available

Contact

Emailpliu23@u.rochester.edu GitHubOpen ↗

Publications

16 items

GestureFAR: Streaming Co-Speech Gesture Generation with Flow Autoregression

2026

Cited

0

BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender

2026

Cited

0

From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Models

2026

Cited

0

TDMM-LM: Bridging Facial Understanding and Animation via Language Models

2026

Cited

0

Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models

2025

Cited

0

Can Sound Replace Vision in LLaVA With Token Substitution?

2025

Cited

0

MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness

2025

Cited

0

$I^2G$: Generating Instructional Illustrations via Text-Conditioned Diffusion

2025

Cited

0

Resume

Academic Achievements

Jun 2025: Two first-author papers accepted to ICCV 2025
Jun 2025: One first-author paper accepted to ACM Multimedia 2025
Nov 2024: One first-author paper accepted to 3DV 2025
Jul 2024: One first-author paper accepted to ECCV 2024
Sep 2024: One co-author paper accepted to Siggraph Asia 2024
Sep 2025: Co-authored papers accepted to NeurIPS 2025 and Cell Reports Methods
Served as reviewer for CVPR (2024–2026), ICLR (2025–2026), NeurIPS 2025, and others

Co-authors

9 total

University of Rochester

University of Rochester

Univeristy of Rochester

University of Rochester

University of Rochester

PhD Candidate @ University of Rochester; BEng @ HUST

The University of Tokyo

University of Rochester