EVIDENT

Checkpoints of EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding (NeurIPS 2026).

[Paper] [Code]

Each folder holds an EVIDENT model fine-tuned from Qwen2.5-VL-7B-Instruct on one source dataset: LoRA weights (adapter_model.safetensors), EB Adapter weights (eb_adapter.safetensors) and the adapter/prompt configuration (evident_config.json).

Folder	Source	Frames	Timestamps	λ (EBD)
charades/	Charades-STA	20	relative integers in [0, 100]	0.1
qvhighlights/	QVHighlights	60	integer seconds	1.0

Results

R1@{0.3, 0.5, 0.7} / mIoU, Table 1 of the paper (Charades-STA and DiDeMo evaluated with 20 frames, QVHighlights with 60).

Source → Target	R1@0.3	R1@0.5	R1@0.7	mIoU
Charades-STA → Charades-STA	80.3	69.1	49.2	59.9
Charades-STA → QVHighlights	77.5	59.8	36.9	55.2
Charades-STA → DiDeMo	69.2	55.4	32.3	48.5
QVHighlights → Charades-STA	73.3	50.2	28.0	49.0
QVHighlights → QVHighlights	89.5	82.2	69.1	75.3
QVHighlights → DiDeMo	62.4	36.0	17.4	40.6

Usage

Install the code, then:

from evident.model import load_evident

model = load_evident("mreraser/EVIDENT", subfolder="charades")  # or "qvhighlights"

To evaluate:

torchrun --nproc_per_node=8 evaluate.py --checkpoint mreraser/EVIDENT --subfolder charades \
    --annotation data/annotations/qvhighlights_test.json --video_dir $QVH_VIDEOS \
    --num_frames 60 --output results/cha2qvh.json

The checkpoints are released under Apache 2.0. Please also follow the licenses of the datasets they were trained on (Charades-STA is for non-commercial use).

Citation

@inproceedings{ahn2026evident,
  title     = {EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding},
  author    = {Ahn, Geo and Han, Jiwook and Kim, Youngrae and Lee, Joonseok and Choi, Jinwoo},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2026}
}