automated data generation 1benchmark 1long-context recall 1temporal grounding 1video-language understanding 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CV2026
NeMo: Needle in a Montage for Video-Language Understanding
Zi-Yuan Hu, Shuo Liang, Duo Zheng +10
The paper introduces the Needle in a Montage (NeMo) task and the NeMoBench benchmark to evaluate temporal understanding in video-language models, using an automated pipeline to gen…
cs.CV2025
Sharp Eyes and Memory for VideoLLMs: Information-Aware Visual Token Pruning for Efficient and Reliable VideoLLM Reasoning
Jialong Qin, Xin Zou, Di Lu +2
Current Video Large Language Models (VideoLLMs) suffer from quadratic computational complexity and key-value cache scaling, due to their reliance on processing excessive redundant…
cs.GR2025
Scalable Motion In-betweening via Diffusion and Physics-Based Character Adaptation
Jia Qin
We propose a two-stage framework for motion in-betweening that combines diffusion-based motion generation with physics-based character adaptation. In Stage 1, a character-agnostic…