Learning Dynamics of VLM Finetuning

Preference-based finetuning of vision--language models (VLMs) is brittle: trivially wrong negatives inject uninformative gradients that destabilize training. We recast alignment as learning-dynamics--aware optimization and introduce Cooling-Weighted DPO (CW-DPO), a two-stage recipe that explicitly models and exploits the training trajectory. Stage 1 performs supervised finetuning with gentle negatives: low-weight smoothed supervision that regularizes the base policy and curbs overconfidence without explicit penalties. Stage 2 applies a DPO objective in which the negative term is scaled by a cooling weight computed from the model's average token log-probability on each negative, suppressing uninformative gradients from easy or off-distribution samples while preserving signal from hard negatives. In practice, we emphasize on-policy negatives and allow mixed negatives by blending a controllable fraction of dataset negatives to maintain contrast freshness. Throughout, we instrument training with Delta!log p probes on positives and negatives as first-class signals for early stopping, curriculum design, and failure diagnosis. Across diverse VLM tasks, CW-DPO yields more stable optimization, better calibration, and higher pairwise win-rates than SFT-only and vanilla DPO, while converging in fewer steps. Ablations isolate the cooling-weight mechanism as the primary driver of these gains and show complementary benefits from mixing on-policy and dataset negatives. Taken together, our results show that smoothing learning dynamics before cooling preferences is a simple, general principle for robust VLM alignment.