UvA-DARE (Digital Academic Repository) Lost in Time: A New Temporal Benchmark for VideoLLMs
DanielCores, MichaelDorkenwald, M. Mucientes et al.
· 0 citations
We have 3 of 10 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Jul 2026
Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents
This work introduces MissionBench, a benchmark for mission-level evaluation of MLLMs in aerial 3D environments, and shows that mission-level competence requires coordinating multiple capabilities beyond spatial perception, including multi-step planning and adaptive reasoning.
Suman Navaratnarajah, Taehyoung Kim, Jona Ruthardt et al.
· arXiv.org · 0 citations
UvA-DARE (Digital Academic Repository) TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning
This paper proposes TWIST, a twin-expert stepwise tuning module that modifies the decoder of the language model using one frozen module pre-trained on image understanding tasks and another learnable one for visual grounding tasks, which allows the MLLM to retain previously learned knowledge and skills, while acquiring what is missing.
∗. AritraBhowmik, ∗. MohammadMahdiDerakhshani, Dennis C. Koelma et al.
· 0 citations