Scholar
Yifan Yu
Google Scholar ID: S2OksN4AAAAJ
ByteDance
Computer Vision
3D Vision
Human-Computer Interaction
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
305
H-index
3
i10-index
3
Publications
7
Co-authors
10
list available
Publications
19 items
QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs
2026
Cited
0
From Position Risks to Block Survival: Faster Generation for Diffusion Language Models
2026
Cited
0
Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding
2026
Cited
0
Harsher on Male? Evaluating LLMs on Gender-Asymmetric Moral Framing Across Diverse Conflict Scenarios
2026
Cited
0
Interdependent Hitting Times
2026
Cited
0
EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy
2026
Cited
0
Introspective Diffusion Language Models
2026
Cited
0
From Dyads to Groups: Rethinking Emotional Support with Conversational AI
2026
Cited
0
Load more
Co-authors
9 total
Marc Pollefeys
Professor of Computer Science, ETH Zurich, and Director Spatial AI Lab, Microsoft
Viktor Larsson
Assistant Professor at Lund University
Rémi Pautrat
Microsoft, ETH Zürich, Ecole polytechnique, INRIA
Shaohui Liu
ETH Zurich
Zhongang Cai (蔡中昂)
SenseTime Research
Iago Suárez
Machine Learning Engineer, Qualcomm XR Labs Europe
Panwang Pan
ByteDance
Chenguo Lin
Peking University
