RefereeBench shows that even the strongest video MLLMs reach only around 60% accuracy on multi-sport refereeing tasks and struggle with rule application and temporal grounding.
Videoreasonbench: Can mllms perform vision-centric complex video reasoning?
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
dataset 3
citation-polarity summary
roles
dataset 3polarities
use dataset 3representative citing papers
Introduces VURB benchmark and VUP-35K dataset to train discriminative and generative video reward models that achieve SOTA performance on VURB and VideoRewardBench.
Video-MME-v2 is a new benchmark that applies progressive visual-to-reasoning levels and non-linear group scoring to expose gaps in video MLLM capabilities.
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
Seed1.8 is a new foundation model that adds unified agentic capabilities for search, code execution, and GUI interaction to existing LLM and vision strengths.
EasyVideoR1 delivers an optimized RL pipeline for video understanding in large vision-language models, achieving 1.47x throughput gains and aligned results on 22 benchmarks.
citing papers explorer
-
RefereeBench: Are Video MLLMs Ready to be Multi-Sport Referees
RefereeBench shows that even the strongest video MLLMs reach only around 60% accuracy on multi-sport refereeing tasks and struggle with rule application and temporal grounding.
-
Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models
Introduces VURB benchmark and VUP-35K dataset to train discriminative and generative video reward models that achieve SOTA performance on VURB and VideoRewardBench.
-
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
Video-MME-v2 is a new benchmark that applies progressive visual-to-reasoning levels and non-linear group scoring to expose gaps in video MLLM capabilities.
-
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
-
Seed1.8 Model Card: Towards Generalized Real-World Agency
Seed1.8 is a new foundation model that adds unified agentic capabilities for search, code execution, and GUI interaction to existing LLM and vision strengths.
-
EasyVideoR1: Easier RL for Video Understanding
EasyVideoR1 delivers an optimized RL pipeline for video understanding in large vision-language models, achieving 1.47x throughput gains and aligned results on 22 benchmarks.