OP-CAD: On-Policy Clean-Audio Distillation for Robust Audio-Visual Reasoning

arXiv:2609.39150 · cs.CV, cs.SD · Submitted 2026-09-30 · Read on arXiv

cs.CV, cs.SD

Submitted: 2026-09-30

Updated: 2026-09-30

Terminology

• Distillation — 59× in this paper · explained in 2 episodes
• Accuracy — 27× in this paper · explained in 1 episode
• GRPO — 21× in this paper · explained in 6 episodes
• Robustness — 21× in this paper · explained in 5 episodes
• Benchmark — 15× in this paper · explained in 2 episodes
• Self-Distillation — 10× in this paper · explained in 7 episodes
• Alignment — 4× in this paper · explained in 1 episode
• On-Policy Distillation — 4× in this paper · explained in 3 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Acoustic Robustness — 3× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Knowledge Distillation — 2× in this paper · explained in 11 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
• VITA: Towards Open-Source Interactive Omni Multimodal LLM
• Distilling the Knowledge in a Neural Network
• CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation
• VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management
• Baichuan-Omni Technical Report
• VISD: Enhancing Video Reasoning via Structured Self-Distillation
• EchoDistill: Robust Large Audio Language Models via Noisy-to-Clean Self-Distillation
• VidForensics-M1: Meta-Detection Reinforcement Learning with Verifiable Temporal Grounding for AI-Generated Video Forensics
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• MUSAN: A Music, Speech, and Noise Corpus
• AdaThinkV: Adaptive Thinking for Token-Efficient Video Reasoning
• Qwen2.5-Omni Technical Report
• Qwen3-Omni Technical Report
• Focus Then Listen: An Empirical Study of Plug-and-Play Audio Enhancer for Noise-Robust Large Audio Language Models
• Generative Universal Verifier as Multimodal Meta-Reasoner
• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
• Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models