Anna Khoreva

@anna_khoreva

Head of Applied Science @Zalando, previously Senior Research Manager @Bosch_AI, PhD @cvml_mpiinf. GenAI and Computer Vision enthusiast. Opinions are my own.

Berlin, Deutschland

scholar.google.de/citations?user…

Replies Reposts Media

Pinned
Anna Khoreva
@anna_khoreva
Jan 25, 2025
Happy to share - “VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis” has been accepted to @iclr_conf #ICLR2025 Code: lnkd.in/eu6SMeKT Paper: lnkd.in/e3mbE9PP Kudos to the amazing team: @YumengLi_007 Bill Beluch @margret_keuper @isDanZhang ❤️
Anna Khoreva
@anna_khoreva
Oct 14, 2024
Code for VSTAR is released 🚀 It enables longer video synthesis w/o re-training and allows to control the dynamics of the synthesised video. Check it out 👇
1
Anna Khoreva
@anna_khoreva
Jun 26, 2025
I'm #hiring for the Sr. Applied Scientist role at @Zalando. We're looking for AI enthusiasts skilled in scaling deep learning pipelines. #career #jobs #AI Apply here 👇 Sr. Applied Scientist - Scaling Deep Learning Experimentation jobs.zalando.com/en/jobs/272085…
Anna Khoreva
@anna_khoreva
Jun 16, 2025
I'm #hiring for 2 Sr. Applied Scientists roles at @Zalando. We're looking for exceptional talent skilled in GenAI and Vision Language Models. #career #jobs Apply here 👇 - Sr. Applied Scientist (GenAI) jobs.zalando.com/de/jobs/272030… - Sr. Applied Scientist (VLMs) jobs.zalando.com/en/jobs/272030…
Anna Khoreva
@anna_khoreva
Oct 14, 2024
Code for VSTAR is released 🚀 It enables longer video synthesis w/o re-training and allows to control the dynamics of the synthesised video. Check it out 👇
Yumeng Li
@YumengLi_007
Oct 14, 2024
🤗Code is out: github.com/boschresearch/… 🚀TL;DR: VSTAR generates longer videos with dynamic visual evolution in a single pass. No fine-tuning is needed! 🙌Check out our project page: yumengli007.github.io/VSTAR/ Bill Beluch @margret_keuper @isDanZhang @anna_khoreva @Bosch_AI ❤️
Anna Khoreva
@anna_khoreva
Sep 4, 2024
Are pose estimators ready for the open world? To answer this, we propose STAGE - a synthetic data generation toolkit for auditing 3D human pose estimators. Check out our paper for more details: arxiv.org/abs/2408.16536 Joint work with @NikitaKister @Istvan_Sarandi @GerardPonsMoll1
Nikita Kister
@NikitaKister
Sep 4, 2024
Are 3D human pose estimators robust to clothing, location, weather etc.? Nobody knows, as current benchmarks can't answer this. We therefore introduce STAGE, a GenAI toolkit to create custom benchmarks, and use it to reveal weaknesses of SOTA models in the open world.
00:00