6 papers
PolyAlign: Conditional Human-Distribution Alignment
L. D. M. S. Sai Teja, Ufaq Khan, Sathira Silva +2
Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective fo…
Objects Before Words: Object-First Inductive Biases for Grounding Language in Child-View Video
Sathira Silva, Abrham Kahsay Gebreselasie, Muhammad Umer Sheikh +3
Learning grounded word meaning from natural experience requires resolving two ambiguities in infant-view recordings: when the named referent appears and where it is in a cluttered…
microCLIP: Unsupervised CLIP Adaptation via Coarse-Fine Token Fusion for Fine-Grained Image Classification
Sathira Silva, Eman Ali, Chetan Arora +1
Unsupervised adaptation of CLIP-based vision-language models (VLMs) for fine-grained image classification requires sensitivity to microscopic local cues. While CLIP exhibits strong…
Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score
Eman Ali, Sathira Silva, Chetan Arora +1
Vision-language models (VLMs) like CLIP excel in zero-shot learning by aligning image and text representations through contrastive pretraining. Existing approaches to unsupervised…
A Spatiotemporal Approach to Tri-Perspective Representation for 3D Semantic Occupancy Prediction
Sathira Silva, Savindu Bhashitha Wannigama, Gihan Jayatilaka +2
Holistic understanding and reasoning in 3D scenes are crucial for the success of autonomous driving systems. The evolution of 3D semantic occupancy prediction as a pretraining task…
DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Models
Eman Ali, Sathira Silva, Muhammad Haris Khan
Vision-language models (VLMs), e.g., CLIP, have shown remarkable potential in zero-shot image classification. However, adapting these models to new domains remains challenging, esp…