Usage
# pip install "transformers>=5.12" "peft>=0.19.1" qwen-vl-utilsimport torchfrom transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom peft import PeftModel base = "OpenGVLab/VideoChat-R1_7B"model = Qwen2_5_VLForConditionalGeneration.from_pretrained(base, torch_dtype=torch.bfloat16, device_map="auto")processor = AutoProcessor.from_pretrained(base)model = PeftModel.from_pretrained(model, "iclropen/evidence-audit-videochatr1-7b-twostage-a05-textfirst-s0")
The evaluation and audit scripts of the code repository take --model <base> --adapter <this repository or folder>.
Training
The placebo-controlled objective of Section 4 of the paper. It keeps the answer likelihood, weighted by α, and adds two margins for each edit operator: the annotated answer must be more likely on the clean video, and on a video with a matched placebo edit outside the event, than on the video with the event edited. A hinge keeps the drop under the placebo edit within a bound set by the reference model.
Table with columns: Setting, Value| Setting | Value |
|---|
| Operator weights | Group-DRO |
| α | 0.5 |
| β | 0.1 |
| Placebo bound | placebo drop ≤ 1.25 × reference drop + 0.10 |
| Training pairs | 2,400 from the Charades-STA training split |
| Optimizer steps | 300 |
| Gradient accumulation | 8 |
| Learning rate | 5e-6 |
| Seed | 0 |
| LoRA | r=16, alpha=32, dropout 0.05, on q/k/v/o and gate/up/down projections |
| Edit operators | swap, mask, blur, tshift, shuffle (two per example) |
| Video input | 2 fps, at most 768 frames |
| Prompt template | vchat |
| Message order | text first, then video |
| Initialised from | evidence-audit-videochatr1-7b-sft-textfirst-s0 |
| Trainer | code/27_papo_train_qcdro_v3seln_r5.py |
Citation
Anonymous. Accuracy Is Not Evidence: Measuring and Training Evidence Dependence in Video Temporal Grounding. ICLR 2027 submission, under review.