Model weights for the paper "Data-Augmented Phrase-Level Alignment for Mitigating Object Hallucination"
Pritam Sarkar
pritamqu
AI & ML interests
multimodal learning with vision, language, and audio; generative modeling; large multimodal models (LMMs); multimodal LLMs (MLLMs); AI agents; alignments; representation learning; self-supervised and unsupervised learning; vision-language models; audio-visual models; foundation models; computer vision
Organizations
None yet
models 10
pritamqu/LongVU_Qwen2_7B-RRPO-16f
8B • Updated • 4 • 1
pritamqu/LLaVA-Video-7B-Qwen2-RRPO-32f
8B • Updated • 6
pritamqu/LLaVA-Video-7B-Qwen2-RRPO-16f
8B • Updated • 5
pritamqu/VideoChat2_stage3_Mistral_7B-RRPO-16f-LORA
Updated • 4
pritamqu/LLaVA-Video-7B-Qwen2-RRPO-32f-LORA
Updated • 3
pritamqu/LLaVA-Video-7B-Qwen2-RRPO-16f-LORA
Updated • 7
pritamqu/LongVU_Qwen2_7B-RRPO-16f-LORA
Updated
pritamqu/halva13b-lora
Updated • 4
pritamqu/halva7b-lora
Updated • 4
pritamqu/halva13b384-lora
Updated • 4