Ali Bahri

SHIFT-LLM: Distribution Shift Correction in Depth-Pruned LLMs

Ali Bahri, Hang Li, Hongliang Li +1

Depth pruning removes entire Transformer blocks to reduce the inference cost of large language models, but disrupts the hidden-state distributions expected by downstream layers, le…

Vision Meets WiFi: Physics-Grounded Estimation of Volumetric Mechanical Properties

Ali Bahri, Hongliang Li, Soufiane Lamghari +2

Estimating volumetric mechanical properties, including Young's modulus, Poisson's ratio, and density at each voxel, is intrinsically ambiguous from vision alone, as visually simila…

OCTOPUS: Enhancing the Spatial-Awareness of Vision SSMs with Multi-Dimensional Scans and Traversal Selection

Kunal Mahatha, Ali Bahri, Pierre Marza +5

State space models (SSMs) have recently emerged as an alternative to transformers due to their unique ability of modeling global relationships in text with linear complexity. Howev…

Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language Adaptation

Mehrdad Noori, Gustavo Adolfo Vargas Hakim, David Osowiechi +6

Medical Vision-language models (VLMs) have shown remarkable performances in various medical imaging domains such as histo\-pathology by leveraging pre-trained, contrastive models t…

Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token Purging

Moslem Yazdanpanah, Ali Bahri, Mehrdad Noori +5

Test-time adaptation (TTA) is crucial for mitigating performance degradation caused by distribution shifts in 3D point cloud classification. In this work, we introduce Token Purgin…

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses

Sahar Dastani, Ali Bahri, Gustavo Adolfo Vargas Hakim +7

State Space Models (SSMs) have emerged as efficient alternatives to Vision Transformers (ViTs), with VMamba standing out as a pioneering architecture designed for vision tasks. How…

CTA: Cross-Task Alignment for Better Test Time Training

Samuel Barbeau, Pedram Fekri, David Osowiechi +4

Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with…

SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds

Ali Bahri, Moslem Yazdanpanah, Sahar Dastani +6

Test-Time Training (TTT) has emerged as a promising solution to address distribution shifts in 3D point cloud classification. However, existing methods often rely on computationall…

Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation

Mehrdad Noori, David Osowiechi, Gustavo Adolfo Vargas Hakim +6

Recently, test-time adaptation has attracted wide interest in the context of vision-language models for image classification. However, to the best of our knowledge, the problem is…

Spectral Informed Mamba for Robust Point Cloud Processing

Ali Bahri, Moslem Yazdanpanah, Mehrdad Noori +7

State space models have shown significant promise in Natural Language Processing (NLP) and, more recently, computer vision. This paper introduces a new methodology leveraging Mamba…

Spectral State Space Model for Rotation-Invariant Visual Representation Learning

Sahar Dastani, Ali Bahri, Moslem Yazdanpanah +8

State Space Models (SSMs) have recently emerged as an alternative to Vision Transformers (ViTs) due to their unique ability of modeling global relationships with linear complexity.…

Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averaging

Ali Bahri, Moslem Yazdanpanah, Mehrdad Noori +7

Test-Time Adaptation (TTA) addresses distribution shifts during testing by adapting a pretrained model without access to source data. In this work, we propose a novel TTA approach…

FDS: Feedback-guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain Generalization

Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri +5

Domain Generalization techniques aim to enhance model robustness by simulating novel data distributions during training, typically through various augmentation or stylization strat…

WATT: Weight Average Test-Time Adaptation of CLIP

David Osowiechi, Mehrdad Noori, Gustavo Adolfo Vargas Hakim +7

Vision-Language Models (VLMs) such as CLIP have yielded unprecedented performance for zero-shot image classification, yet their generalization capability may still be seriously cha…

GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3D

Ali Bahri, Moslem Yazdanpanah, Mehrdad Noori +6

We introduce a pioneering approach to self-supervised learning for point clouds, employing a geometrically informed mask selection strategy called GeoMask3D (GM3D) to boost the eff…

CLIPArTT: Adaptation of CLIP to New Domains at Test Time

Gustavo Adolfo Vargas Hakim, David Osowiechi, Mehrdad Noori +5

Pre-trained vision-language models (VLMs), exemplified by CLIP, demonstrate remarkable adaptability across zero-shot classification tasks without additional training. However, thei…