2 citations · 7 across the 12 of their papers we have counts for
14 papers
Hidden Trajectories Don't Lie: Correcting Corruption Drift for Test-Time Adaptation
Amirhossein Sabour, Amir Khasahmadi, Mengliu Zhao
Test-time adaptation (TTA) adapts pretrained models to distribution shifts encountered during deployment. However, most existing methods rely on the weight representations of the f…
HypergraphFormer: Learning Hypergraphs from LLMs for Editable Floor Plan Generation
Nikita Klimenko, Hesam Salehipour, Parham Eftekhar +2
In this work, we propose HypergraphFormer, a novel and efficient approach to floor plan generation based on learning hypergraph representations with a large language model (LLM). T…
Majority of the Bests: Improving Best-of-N via Bootstrapping
Amin Rakhsha, Kanika Madan, Tianyu Zhang +2
Sampling multiple outputs from a Large Language Model (LLM) and selecting the most frequent (Self-consistency) or highest-scoring (Best-of-N) candidate is a popular approach to ach…
Aligning Constraint Generation with Design Intent in Parametric CAD
Evan Casey, Tianyu Zhang, Shu Ishida +6
We adapt alignment techniques from reasoning LLMs to the task of generating engineering sketch constraints found in computer-aided design (CAD) models. Engineering sketches consist…
e-SimFT: Alignment of Generative Models with Simulation Feedback for Pareto-Front Design Exploration
Hyunmin Cheong, Mohammadmehdi Ataei, Amir Hosein Khasahmadi +1
Deep generative models have recently shown success in solving complex engineering design problems where models predict solutions that address the design requirements specified as i…
Physics Context Builders: A Modular Framework for Physical Reasoning in Vision-Language Models
Vahid Balazadeh, Mohammadmehdi Ataei, Hyunmin Cheong +2
Physical reasoning remains a significant challenge for Vision-Language Models (VLMs). This limitation arises from an inability to translate learned knowledge into predictions about…
MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs
Saeid Asgari Taghanaki, Aliasgahr Khani, Amir Khasahmadi
Existing benchmarks for large language models (LLMs) increasingly struggle to differentiate between top-performing models, underscoring the need for more challenging evaluation fra…
CadVLM: Bridging Language and Vision in the Generation of Parametric CAD Sketches
Sifan Wu, Amir Khasahmadi, Mor Katz +4
Parametric Computer-Aided Design (CAD) is central to contemporary mechanical design. However, it encounters challenges in achieving precise parametric sketch modeling and lacks pra…
TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models
Saeid Asgari Taghanaki, Aliasghar Khani, Ali Saheb Pasand +4
Interpreting the learned features of vision models has posed a longstanding challenge in the field of machine learning. To address this issue, we propose a novel method that levera…
CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Language
Aditya Sanghi, Rao Fu, Vivian Liu +5
Recent works have demonstrated that natural language can be used to generate and edit 3D shapes. However, these methods generate shapes with limited fidelity and diversity. We intr…
SimCURL: Simple Contrastive User Representation Learning from Command Sequences
Hang Chu, Amir Hosein Khasahmadi, Karl D. D. Willis +5
User modeling is crucial to understanding user behavior and essential for improving user experience and personalized recommendations. When users interact with software, vast amount…
Group-disentangled Representation Learning with Weakly-Supervised Regularization
Linh Tran, Amir Hosein Khasahmadi, Aditya Sanghi +1
Learning interpretable and human-controllable representations that uncover factors of variation in data remains an ongoing key challenge in representation learning. We investigate…
Robust Representation Learning via Perceptual Similarity Metrics
Saeid Asgari Taghanaki, Kristy Choi, Amir Khasahmadi +1
A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream task, without overfitting to spurious inpu…
UVStyle-Net: Unsupervised Few-shot Learning of 3D Style Similarity Measure for B-Reps
Peter Meltzer, Hooman Shayani, Amir Khasahmadi +3
Boundary Representations (B-Reps) are the industry standard in 3D Computer Aided Design/Manufacturing (CAD/CAM) and industrial design due to their fidelity in representing stylisti…