A Visual Dependence-Aware Framework for Multimodal Unsupervised Continual Post-Training
cs.CV, cs.AI
Submitted: 2026-08-26
Updated: 2026-08-26
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning
- Test-Time Learning for Large Language Models
- LLaVA-OneVision: Easy Visual Task Transfer
- Multimodal Continual Instruction Tuning with Dynamic Gradient Guidance
- Representational Continuity for Unsupervised Continual Learning
- PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
- Continual Lifelong Learning with Neural Networks: A Review
- Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models
- Self-Consistency Preference Optimization
- AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models
- PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems
- Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models
- Stabilizing Unsupervised Self-Evolution of MLLMs via Continuous Softened Retracing reSampling
- PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
- MLLM-CL: Continual Learning for Multimodal Large Language Models
- Self-Supervised Visual Preference Alignment
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