CT-OPD: Counterfactual Trace On-Policy Distillation for Diffusion Vision-Language Models
cs.CV, cs.LG
Submitted: 2026-09-26
Updated: 2026-09-26
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Beyond Mode-Seeking RL: Trajectory-Balance Post-Training for Diffusion Language Models
- Qwen3-VL Technical Report
- dOPSD: On-Policy Self-Distillation for Diffusion Language Models
- MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models
- Sequence-Level Knowledge Distillation
- LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models
- Self-Rewarding Vision-Language Model via Reasoning Decomposition
- OPTD: On-Policy Transition Distillation with Consistency-Guided Adaptive Compression for Few-Step Diffusion Language Models
- Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models
- Large Language Diffusion Models
- Diffusion-State Policy Optimization for Masked Diffusion Language Models
- d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation
- Trace-Based On-Policy Distillation for Masked Diffusion Language Models
- Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation
- Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization
- Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
- Qwen-Image Technical Report
- Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM
- LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
- A Dual-Space Framework for General Knowledge Distillation of Large Language Models
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