16 citations · 19 across the 12 of their papers we have counts for
14 papers
Safety of Latent Communication in Multi-Agent Systems
Muhammad Huzaifa, Sina Mavali, Thorsten Eisenhofer
Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and latency overhead of text-ba…
WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation
Muhammad Huzaifa, Lea Schönherr, Thorsten Eisenhofer
Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively querying supervision. However, most…
VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes
Paul Gavrikov, Wei Lin, M. Jehanzeb Mirza +6
Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answering (VQA) benchmark comprising 2,720 que…
EFSA: Episodic Few-Shot Adaptation for Text-to-Image Retrieval
Muhammad Huzaifa, Yova Kementchedjhieva
Text-to-image retrieval is a critical task for managing diverse visual content, but common benchmarks for the task rely on small, single-domain datasets that fail to capture real-w…
An Integrated Approach to Robotic Object Grasping and Manipulation
Owais Ahmed, M Huzaifa, M Areeb +1
In response to the growing challenges of manual labor and efficiency in warehouse operations, Amazon has embarked on a significant transformation by incorporating robotics to assis…
Towards Energy-Efficiency by Navigating the Trilemma of Energy, Latency, and Accuracy
Boyuan Tian, Yihan Pang, Muhammad Huzaifa +2
Extended Reality (XR) enables immersive experiences through untethered headsets but suffers from stringent battery and resource constraints. Energy-efficient design is crucial to e…
Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models
Raza Imam, Hanan Gani, Muhammad Huzaifa +1
The conventional modus operandi for adapting pre-trained vision-language models (VLMs) during test-time involves tuning learnable prompts, ie, test-time prompt tuning. This paper i…
ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes
Hashmat Shadab Malik, Muhammad Huzaifa, Muzammal Naseer +2
Given the large-scale multi-modal training of recent vision-based models and their generalization capabilities, understanding the extent of their robustness is critical for their r…
Domain Adaptable Fine-Tune Distillation Framework For Advancing Farm Surveillance
Raza Imam, Muhammad Huzaifa, Nabil Mansour +2
In this study, we propose an automated framework for camel farm monitoring, introducing two key contributions: the Unified Auto-Annotation framework and the Fine-Tune Distillation…
On enhancing the robustness of Vision Transformers: Defensive Diffusion
Raza Imam, Muhammad Huzaifa, Mohammed El-Amine Azz
Privacy and confidentiality of medical data are of utmost importance in healthcare settings. ViTs, the SOTA vision model, rely on large amounts of patient data for training, which…
On-Device CPU Scheduling for Sense-React Systems
Aditi Partap, Samuel Grayson, Muhammad Huzaifa +5
Sense-react systems (e.g. robotics and AR/VR) have to take highly responsive real-time actions, driven by complex decisions involving a pipeline of sensing, perception, planning, a…
Trireme: Exploring Hierarchical Multi-Level Parallelism for Domain Specific Hardware Acceleration
Georgios Zacharopoulos, Adel Ejjeh, Ying Jing +9
The design of heterogeneous systems that include domain specific accelerators is a challenging and time-consuming process. While taking into account area constraints, designers mus…
Exploring Extended Reality with ILLIXR: A New Playground for Architecture Research
Muhammad Huzaifa, Rishi Desai, Samuel Grayson +11
As we enter the era of domain-specific architectures, systems researchers must understand the requirements of emerging application domains. Augmented and virtual reality (AR/VR) or…
Specializing Coherence, Consistency, and Push/Pull for GPU Graph Analytics
Giordano Salvador, Wesley H. Darvin, Muhammad Huzaifa +3
This work provides the first study to explore the interaction of update propagation with and without fine-grained synchronization (push vs. pull), emerging coherence protocols (GPU…