dvlab-research / LSDBenchLinks
A benchmark that focuses on the sampling dilemma in long-video tasks. Through well-designed tasks, it evaluates the sampling efficiency of long-video VLMs. (ICCV2025)
☆20Updated last month
Alternatives and similar repositories for LSDBench
Users that are interested in LSDBench are comparing it to the libraries listed below
Sorting:
- Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning☆118Updated last month
- [ICLR'25] Reconstructive Visual Instruction Tuning☆116Updated 5 months ago
- Official repo for "Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge" ICLR2025☆75Updated 6 months ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?☆74Updated 2 months ago
- The official code of "Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning"☆40Updated last month
- [CVPR 2025] OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?☆85Updated 2 months ago
- [CVPR2025] BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding☆31Updated 5 months ago
- (ICLR 2025 Spotlight) Official code repository for Interleaved Scene Graph.☆28Updated last month
- Official repository of 'ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing’☆56Updated 3 months ago
- The code repository of UniRL☆41Updated 3 months ago
- Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing☆69Updated 2 months ago
- ICML2025☆57Updated 3 weeks ago
- [ICML 2025] Streamline Without Sacrifice - Squeeze out Computation Redundancy in LMM☆19Updated 4 months ago
- Official PyTorch Code of ReKV (ICLR'25)☆52Updated 6 months ago
- SpaceR: The first MLLM empowered by SG-RLVR for video spatial reasoning☆80Updated 2 months ago
- VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning☆32Updated 2 months ago
- ACL'24 (Oral) Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback☆73Updated last year
- ☆38Updated 2 months ago
- [CVPR 2025 Oral] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection☆117Updated last month
- CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms☆24Updated 3 months ago
- TStar is a unified temporal search framework for long-form video question answering☆67Updated 3 weeks ago
- Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency☆53Updated 3 months ago
- ☆21Updated 8 months ago
- Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision☆142Updated this week
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆87Updated 6 months ago
- [NIPS 2025 DB Oral] Official Repository of paper: Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing☆96Updated last week
- [NeurlPS 2024] One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos☆135Updated 9 months ago
- TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation☆217Updated last month
- ☆88Updated 3 months ago
- Code for "CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning"☆24Updated 6 months ago