StrLoRA is a regularized two-stage expert routing method for streaming CVIT that selects experts via textual instructions and applies token-wise cross-modal weighting with historical routing alignment.
Drivelm: Driving with graph visual question answering,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A data-fusion pipeline generates pseudo-labels from video, telematics, and CV models to fine-tune QwenVL-2.5 with DoRA adapters, yielding reported gains in detecting and explaining safety-critical driving events.
CPO++ adapts reinforcement fine-tuning of MLLMs to endogenous multi-modal concept drift through counterfactual reasoning and preference optimization, yielding better coherence and cross-domain robustness in safety-critical settings.
citing papers explorer
-
StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMs
StrLoRA is a regularized two-stage expert routing method for streaming CVIT that selects experts via textual instructions and applies token-wise cross-modal weighting with historical routing alignment.
-
Enhancing Multimodal Large Language Models for Safety-Critical Driving Video Analysis
A data-fusion pipeline generates pseudo-labels from video, telematics, and CV models to fine-tune QwenVL-2.5 with DoRA adapters, yielding reported gains in detecting and explaining safety-critical driving events.
-
Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning
CPO++ adapts reinforcement fine-tuning of MLLMs to endogenous multi-modal concept drift through counterfactual reasoning and preference optimization, yielding better coherence and cross-domain robustness in safety-critical settings.