| VideoJev: System One Model for Video Understanding and Interaction | ✓ Link | 63.7 | 74.8 | 44.5 | 86.1 | VideoJev-35B-A3B | 2026-10-13 |
| Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs | ✓ Link | 61.8 | 71.6 | 42.4 | 84.5 | Video-ORA-9B | 2026-08-20 |
| VideoJev: System One Model for Video Understanding and Interaction | ✓ Link | 60.1 | 69.4 | 40.3 | 82.8 | VideoJev-4B | 2026-10-13 |
| TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs | ✓ Link | 58.6 | 68.0 | 38.9 | 80.9 | TimeLens2-8B (extra data) | 2026-07-19 |
| Kwai Keye-VL-2.0 Technical Report | ✓ Link | 58.4 | | | | Kwai Keye-VL-2.0-30B-A3B | 2026-06-09 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 55.2 | 63.0 | 35.2 | 76.6 | TimeLens-8B (extra data) | 2025-12-16 |
| Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding | ✓ Link | 54.9 | 63.1 | 36.3 | 74.2 | F2G (Qwen3-VL-8B, TimeLens-100K) (extra data) | 2026-05-21 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 52.8 | 61.1 | 34.0 | 74.1 | Gemini-2.5-Pro | 2025-12-16 |
| Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence | ✓ Link | 51.1 | | | | Open-o3-Video-v2-8B | 2026-10-13 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 48.8 | 55.6 | 28.4 | 70.5 | TimeLens-7B (extra data) | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 48.6 | 56.1 | 30.6 | 68.7 | Gemini-2.5-Flash | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 48.3 | 53.4 | 27.5 | 69.2 | Qwen3-VL-8B | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 47.8 | 50.8 | 24.5 | 71.7 | Qwen3-VL-235B-A22B | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 46.7 | 53.5 | 27.1 | 66.4 | Gemini-2.0-Flash | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 41.8 | 44.5 | 23.5 | 60.6 | GPT-4o | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 40.5 | 42.0 | 22.0 | 59.3 | GPT-5 | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 39.7 | 37.9 | 17.8 | 60.2 | VideoChat-Flash-7B | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 39.6 | 42.6 | 20.5 | 57.9 | MiMo-VL-7B-RL | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 39.3 | 37.8 | 16.6 | 59.7 | Qwen2.5-VL-7B | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 38.1 | 35.5 | 18.0 | 56.3 | TimeSuite | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 36.6 | 32.0 | 16.9 | 57.9 | Time-R1-7B | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 33.7 | 30.8 | 11.7 | 51.9 | VideoChat-R1-7B | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 30.0 | 28.7 | 13.5 | 43.3 | Grounded-VideoLLM | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 28.1 | 22.9 | 10.4 | 38.2 | TRACE-uni | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 27.1 | 21.8 | 9.6 | 37.2 | TRACE | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | | 63.0 | | | TimeLens | 2025-12-16 |
| Structured Causal Video Reasoning via Multi-Objective Alignment | | | 40.4 | 21.6 | | Factum-4B | 2026-04-06 |