Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Modelsby Sanghyun…
Addressing Vulnerabilities in AI-Image Detection: Challenges and Proposed Solutionsby Justin JiangFirst submitted to arxiv on:…
Planning vs Reasoning: Ablations to Test Capabilities of LoRA layersby Neel RedkarFirst submitted to arxiv…
Thai Financial Domain Adaptation of THaLLE – Technical Reportby KBTG Labs, Atthakorn Petchsod, Pornchanan Balee,…
Multi LoRA Meets Vision: Merging multiple adapters to create a multi task modelby Ege Kesim,…
Visual Cue Enhancement and Dual Low-Rank Adaptation for Efficient Visual Instruction Fine-Tuningby Pengkun Jiao, Bin…
Prompt-Efficient Fine-Tuning for GPT-like Deep Models to Reduce Hallucination and to Improve Reproducibility in Scientific…
StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaborationby Panwen Hu, Jin Jiang, Jianqi Chen, Mingfei…
V-LoRA: An Efficient and Flexible System Boosts Vision Applications with LoRA LMMby Liang Mi, Weijun…
DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusionby Weicai Ye, Chenhao…