>mfw Research news

07/04/2025

>Activation Reward Models for Few-Shot Model Alignment
https://arxiv.org/abs/2507.01368

>Long-Tailed Distribution-Aware Router For Mixture-of-Experts in LVLM
https://arxiv.org/abs/2507.01351

>Towards Decentralized and Sustainable Foundation Model Training with the Edge
https://arxiv.org/abs/2507.01803

>DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation
https://arxiv.org/abs/2507.01603

>Subjective Camera: Bridging Human Cognition and Visual Reconstruction through Sequence-Aware Sketch-Guided Diffusion
https://arxiv.org/abs/2506.23711

>TurboVSR: Fantastic Video Upscalers and Where to Find Them
https://arxiv.org/abs/2506.23618

>On the Domain Robustness of Contrastive VLM
https://arxiv.org/abs/2506.23663

>Oneta: Multi-Style Image Enhancement Using Eigentransformation Functions
https://arxiv.org/abs/2506.23547

>AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation
https://arxiv.org/abs/2506.23150

>LLM-enhanced Action-aware Multi-modal Prompt Tuning for Image-Text Matching
https://arxiv.org/abs/2506.23502

>TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity
https://arxiv.org/abs/2506.23484

>Efficient Multi-Crop Saliency Partitioning for Automatic Image Cropping
https://arxiv.org/abs/2506.22814

>Attention to Burstiness: Low-Rank Bilinear Prompt Tuning
https://arxiv.org/abs/2506.22908

>Listener-Rewarded Thinking in VLMs for Image Preferences
https://huggingface.co/alexgambashidze/qwen2.5vl_image_preference_reasoner

>STR-Match: Matching SpatioTemporal Relevance Score for Training-Free Video Editing
https://arxiv.org/abs/2506.22868

>Efficient Diffusion Training through Parallelization with Truncated Karhunen-Loève Expansion
https://arxiv.org/abs/2503.17657

>HalCECE: A Framework for Explainable Hallucination Detection through Conceptual Counterfactuals in Image Captioning
https://arxiv.org/abs/2503.00436