facebookresearch / EgoToMLinks
EgoToM is an egocentric theory-of-mind benchmark built on Ego4D videos, containing multi-choice questions that evaluate multimodal large language models' ability to infer a camera wearer's goals, in-the-moment belief states, and future actions.
☆13Updated 10 months ago
Alternatives and similar repositories for EgoToM
Users that are interested in EgoToM are comparing it to the libraries listed below
Sorting:
- [ICLR'25] Streaming Video Question-Answering with In-context Video KV-Cache Retrieval☆99Updated 3 months ago
- Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency☆60Updated 8 months ago
- The official code of "Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning"☆80Updated 3 months ago
- [CVPR 2025] OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?☆120Updated 6 months ago
- ☆46Updated 5 months ago
- This is a collection of recent papers on reasoning in video generation models.☆95Updated last month
- [CVPR 2025 Oral] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection☆134Updated 6 months ago
- Official codebase for the paper Latent Visual Reasoning☆109Updated 3 months ago
- [ACL 2025] PruneVid: Visual Token Pruning for Efficient Video Large Language Models☆66Updated 8 months ago
- [ICLR2025] Official code implementation of Video-UTR: Unhackable Temporal Rewarding for Scalable Video MLLMs☆61Updated 11 months ago
- [AAAI 2025] Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos☆31Updated 8 months ago
- ☆16Updated 4 months ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?☆86Updated 6 months ago
- Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)☆240Updated 6 months ago
- ☆28Updated last year
- Official code for MotionBench (CVPR 2025)☆64Updated 11 months ago
- TStar is a unified temporal search framework for long-form video question answering☆86Updated 5 months ago
- [CVPR 2025] Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Att…☆62Updated 4 months ago
- [ICLR'25] Reconstructive Visual Instruction Tuning☆135Updated 10 months ago
- Official repository of DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models☆88Updated last year
- [CVPR 2025] Official PyTorch code of "Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation".☆54Updated 8 months ago
- Official codebase for the paper "Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space"☆58Updated last month
- Official implementation of paper VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interact…☆43Updated last year
- Official repo for "Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge" ICLR2025☆100Updated 10 months ago
- Universal Video Temporal Grounding with Generative Multi-modal Large Language Models☆46Updated 2 months ago
- Code of LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents☆28Updated 2 months ago
- This repository is the official implementation of "Look-Back: Implicit Visual Re-focusing in MLLM Reasoning".☆84Updated 7 months ago
- ☆97Updated 7 months ago
- TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning☆114Updated last month
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆175Updated last month