Compact3D: Compressing Gaussian Splat Radiance Field Models with Vector Quantization

1 code implementation • 30 Nov 2023 • KL Navaneet, Kossar Pourahmadi Meibodi, Soroush Abbasi Koohpayegani, Hamed Pirsiavash

3D Gaussian Splatting is a new method for modeling and rendering 3D radiance fields that achieves much faster learning and rendering time compared to SOTA NeRF methods.

Quantization

NOLA: Compressing LoRA using Linear Combination of Random Basis

1 code implementation • 4 Oct 2023 • Soroush Abbasi Koohpayegani, KL Navaneet, Parsa Nooralinejad, Soheil Kolouri, Hamed Pirsiavash

These methods can reduce the number of parameters needed to fine-tune an LLM by several orders of magnitude.

SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers

1 code implementation • 4 Oct 2023 • KL Navaneet, Soroush Abbasi Koohpayegani, Essam Sleiman, Hamed Pirsiavash

We show that such models can be vulnerable to a universal adversarial patch attack, where the attacker optimizes for a patch that when pasted on any image, can increase the compute and power consumption of the model.

Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning

1 code implementation • 8 Dec 2021 • KL Navaneet, Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Kossar Pourahmadi, Akshayvarun Subramanya, Hamed Pirsiavash

On the other hand, far away NNs may not be semantically related to the query.

Pseudo Label Representation Learning +1