1 citations · 1 across the 12 of their papers we have counts for
14 papers
Mind the Temporal Gap: Evaluating Video Models for Temporal Understanding in Driving
Shiva Sreeram, Erfan Aasi, Tsun-Hsuan Wang +2
Modern video-language models are increasingly treated as general-purpose video reasoners, yet it remains unclear whether they robustly capture temporal dynamics in safety-critical…
Kernel Reboot: Breaking the Boundaries of Neural Tangent Kernels for Neural Fields
Amir Mallak, Alaa Maalouf, Lior Wolf +2
Neural fields (NFs) map continuous coordinates to signals such as color or density, but fast high-quality reconstruction from sparse observations remains difficult. Classical Neura…
Supportive Token Revealing for Fast Diffusion Language Model Decoding
Giries Abu Ayoub, Mario Barbara, Lluís Pastor-Pérez +4
Discrete diffusion language models can generate text efficiently by updating multiple masked positions in parallel, but this parallelism introduces a quality-latency trade-off. Agg…
Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching
Alaa Khamis, Alaa Maalouf
Test-time finetuning (TTFT) is a rapidly evolving paradigm that adapts a language model to each prompt by retrieving related sequences, updating the model on them, and then evaluat…
Autonomous Sea Turtle Robot for Marine Fieldwork
Zach J. Patterson, Emily Sologuren, Levi Cai +4
Autonomous robots can transform how we observe marine ecosystems, but close-range operation in reefs and other cluttered habitats remains difficult. Vehicles must maneuver safely n…
Robustness Is a Function, Not a Number: A Factorized Comprehensive Study of OOD Robustness in Vision-Based Driving
Amir Mallak, Alaa Maalouf
Out of distribution (OOD) robustness in autonomous driving is often reduced to a single number, hiding what breaks a policy. We decompose environments along five axes: scene (rural…
See Less, Drive Better: Generalizable End-to-End Autonomous Driving via Foundation Models Stochastic Patch Selection
Amir Mallak, Erfan Aasi, Shiva Sreeram +3
Recent advances in end-to-end autonomous driving show that policies trained on patch-aligned features extracted from foundation models generalize better to Out-of-Distribution (OOD…
Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples
Shiva Sreeram, Alaa Maalouf, Pratyusha Sharma +1
Recently, Sharma et al. suggested a method called Layer-SElective-Rank reduction (LASER) which demonstrated that pruning high-order components of carefully chosen LLM's weight matr…
Decentralized Vision-Based Autonomous Aerial Wildlife Monitoring
Makram Chahine, William Yang, Alaa Maalouf +6
Wildlife field operations demand efficient parallel deployment methods to identify and interact with specific individuals, enabling simultaneous collective behavioral analysis, and…
Prompts to Summaries: Zero-Shot Language-Guided Video Summarization with Large Language and Video Models
Mario Barbara, Alaa Maalouf
The explosive growth of video data intensified the need for flexible user-controllable summarization tools that operate without training data. Existing methods either rely on domai…
DataS^3: Dataset Subset Selection for Specialization
Neha Hulkund, Alaa Maalouf, Levi Cai +15
In many real-world machine learning (ML) applications (e.g. detecting broken bones in x-ray images, detecting species in camera traps), in practice models need to perform well on s…
Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features
Makram Chahine, Alex Quach, Alaa Maalouf +2
End-to-end learning directly maps sensory inputs to actions, creating highly integrated and efficient policies for complex robotics tasks. However, such models often struggle to ge…
Probing Multimodal LLMs as World Models for Driving
Shiva Sreeram, Tsun-Hsuan Wang, Alaa Maalouf +3
We provide a sober look at the application of Multimodal Large Language Models (MLLMs) in autonomous driving, challenging common assumptions about their ability to interpret dynami…
Drive Anywhere: Generalizable End-to-end Autonomous Driving with Multi-modal Foundation Models
Tsun-Hsuan Wang, Alaa Maalouf, Wei Xiao +5
As autonomous driving technology matures, end-to-end methodologies have emerged as a leading strategy, promising seamless integration from perception to control via deep learning.…