| VideoJev: System One Model for Video Understanding and Interaction | ✓ Link | 65.5 | 81.0 | 72.5 | 54.4 | VideoJev-35B-A3B | 2026-10-13 |
| Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs | ✓ Link | 63.6 | 77.4 | 69.5 | 53.3 | Video-ORA-9B | 2026-08-20 |
| VideoJev: System One Model for Video Understanding and Interaction | ✓ Link | 62.8 | 78.8 | 70.5 | 51.4 | VideoJev-4B | 2026-10-13 |
| TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs | ✓ Link | 59.0 | 74.6 | 65.5 | 47.2 | TimeLens2-4B (extra data) | 2026-07-19 |
| Kwai Keye-VL-2.0 Technical Report | ✓ Link | 58.5 | | | | Kwai Keye-VL-2.0-30B-A3B | 2026-06-09 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 58.1 | 72.3 | 64.2 | 47.1 | Gemini-2.5-Pro | 2025-12-16 |
| Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding | ✓ Link | 54.1 | 69.8 | 59.4 | 42.3 | F2G (Qwen3-VL-8B, TimeLens-100K) (extra data) | 2026-05-21 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 53.2 | 68.9 | 58.4 | 40.6 | TimeLens-8B (extra data) | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 52.5 | 66.8 | 57.5 | 41.3 | Gemini-2.5-Flash | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 52.2 | 69.0 | 57.5 | 39.3 | Qwen3-VL-235B-A22B | 2025-12-16 |
| Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation | | 50.7 | 64.4 | 49.2 | 39.0 | Video-OPD 8B (Round 3) (extra data) | 2026-02-03 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 49.3 | 62.9 | 54.0 | 37.7 | Gemini-2.0-Flash | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 46.8 | 62.1 | 51.2 | 34.4 | Qwen3-VL-8B | 2025-12-16 |
| EventLens: Event-Structure Reinforcement Learning for Video Understanding | ✓ Link | 46.35 | | | | EventLens-8B | 2026-10-12 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 46.2 | 62.8 | 51.0 | 32.6 | TimeLens-7B (extra data) | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 42.9 | 57.4 | 44.9 | 30.4 | GPT-5 | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 40.4 | 55.2 | 41.4 | 25.8 | GPT-4o | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 35.5 | 49.3 | 38.7 | 22.4 | MiMo-VL-7B-RL | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 33.6 | 44.3 | 35.1 | 22.6 | TRACE-uni | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 33.1 | 44.8 | 31.0 | 19.0 | Time-R1-7B | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 32.7 | 43.4 | 33.9 | 22.0 | TRACE | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 31.4 | 44.1 | 31.0 | 16.1 | Qwen2.5-VL-7B | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 30.0 | 39.2 | 29.6 | 19.5 | Grounded-VideoLLM | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 25.0 | 35.0 | 23.9 | 11.3 | VideoChat-R1-7B | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 24.8 | 35.5 | 21.8 | 10.5 | VideoChat-Flash-7B | 2025-12-16 |
| TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs | ✓ Link | 19.8 | 27.1 | 17.5 | 8.6 | TimeSuite | 2025-12-16 |