SYNCR: Diagnosing and Learning Cross-Video Reasoning from Simulation

arXiv:2609.37918 · cs.CV, cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Accuracy — 57× in this paper · explained in 1 episode
• Benchmark — 41× in this paper · explained in 2 episodes
• Temporal Reasoning — 24× in this paper · explained in 2 episodes
• GRPO — 17× in this paper · explained in 6 episodes
• Alignment — 15× in this paper · explained in 1 episode
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Generalization — 6× in this paper · explained in 13 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Sim-to-Real Transfer — 3× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• New York University Abu Dhabi — 1× in this paper
• Robustness — 1× in this paper · explained in 5 episodes
• Segmentation Masks — 1× in this paper · explained in 2 episodes

Sources

• MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding
• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding
• Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning
• ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models
• LLaVA-OneVision: Easy Visual Task Transfer
• MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs
• Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI
• SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents
• CLEVRER: CoLlision Events for Video REpresentation and Reasoning
• MLVU: Benchmarking Multi-task Long Video Understanding
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
• CVBench: Benchmarking Cross-Video Synergies for Complex Multimodal Reasoning

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models