Yiqi Nie

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Multimodal Models (4)Computer Vision (3)Speech & Audio (1)Red-Teaming & Adversarial Robustness (1)Eval Frameworks & Benchmarks (1)Natural Language Processing (1)

Frequent co-authors

Fei Wang (3)Junjie Chen (1)Fei Wang (1)Kun Li (1)Kun Li (1)Xun Yang (1)Yanbin Hao (1)Linfeng Zhang (1)

Papers (4)

Sep 28, 2026

2w ago·also Affiliation:, SJTU

EvolvingAvatar: Interactive 3D Head Generation That Adapts as Conversations Unfold

Conversational 3D heads no longer need static weights: turning live dyadic audiovisual streams into an online self-supervised training signal makes avatar motion up to 11.1% more coherent as dialogues unfold.

Junjie Chen, Fei Wang, Kun Li +6

Computer Vision Multimodal Models Speech & Audio

Apr 7, 2026

Apr 7, 2026·also HIT, NTU

3D Smoke Scene Reconstruction Guided by Vision Priors from Multimodal Large Language Models

Smoke-GS lets you see through the haze, reconstructing 3D scenes from smoky images with surprising clarity by explicitly modeling view-dependent smoke appearance.

Xinye Zheng, Fei Wang, Yiqi Nie +1

Computer Vision Multimodal Models

Mar 18, 2026

Evidence Packing for Cross-Domain Image Deepfake Detection with LVLMs

Forget fine-tuning: this method uses smart patch selection to adapt frozen LVLMs for deepfake detection, outperforming baselines without any training.

Fei Wang, Yiqi Nie, Zhangling Duan +1

Computer Vision Multimodal Models Red-Teaming & Adversarial Robustness

Mar 16, 2026

Tsinghua AIMar 16, 2026·also BJUT, HIT

MER-Bench: A Comprehensive Benchmark for Multimodal Meme Reappraisal

Can AI transform a grumpy cat meme into a beacon of positivity while keeping the cat recognizable?

Yiqi Nie, Fei Wang, Yudi Cai +1

Eval Frameworks & Benchmarks Multimodal Models Natural Language Processing