9 papers
Attention Guided Alignment in Efficient Vision-Language Models
Shweta Mahajan, Hoang Le, Hyojin Park +3
Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs) to integrate visual and textual info…
Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generation
Shubhankar Borse, Phuc Pham, Farzad Farhadzadeh +6
Despite recent advances in personalized image generation, existing models consistently fail to produce reliable multi-human scenes, often merging or losing facial identity. We pres…
Resolving the Identity Crisis in Text-to-Image Generation
Shubhankar Borse, Farzad Farhadzadeh, Munawar Hayat +1
State-of-the-art text-to-image models suffer from a persistent identity crisis when generating scenes with multiple humans: producing duplicate faces, merging identities, and misco…
Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models
Farzad Farhadzadeh, Debasmit Das, Shubhankar Borse +1
We introduce ProLoRA, enabling zero-shot adaptation of parameter-efficient fine-tuning in text-to-image diffusion models. ProLoRA transfers pre-trained low-rank adjustments (e.g.,…
LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation
Farzad Farhadzadeh, Debasmit Das, Shubhankar Borse +1
The rising popularity of large foundation models has led to a heightened demand for parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), which offer perform…
Sort-free Gaussian Splatting via Weighted Sum Rendering
Qiqi Hou, Randall Rauwendaal, Zifeng Li +5
Recently, 3D Gaussian Splatting (3DGS) has emerged as a significant advancement in 3D scene reconstruction, attracting considerable attention due to its ability to recover high-fid…
Neural Graphics Texture Compression Supporting Random Access
Farzad Farhadzadeh, Qiqi Hou, Hoang Le +4
Advances in rendering have led to tremendous growth in texture assets, including resolution, complexity, and novel textures components, but this growth in data volume has not been…
Low-Latency Neural Stereo Streaming
Qiqi Hou, Farzad Farhadzadeh, Amir Said +2
The rise of new video modalities like virtual reality or autonomous driving has increased the demand for efficient multi-view video compression methods, both in terms of rate-disto…
Bitstream Organization for Parallel Entropy Coding on Neural Network-based Video Codecs
Amir Said, Hoang Le, Farzad Farhadzadeh
Video compression systems must support increasing bandwidth and data throughput at low cost and power, and can be limited by entropy coding bottlenecks. Efficiency can be greatly i…