Andrew Heuer, Ethan Hammer, and Nikhil Krishna, undergraduate researchers in the iCAS Lab, earned first place in the Engineering and Computing track at USC Discover for their project, “Node-wise Feature Encoding for Neural Performance Prediction.” Mentored by fellow iCAS Lab graduate member Matthew Grenier.

Their work addresses the challenge of accurately predicting latency and energy for neural networks deployed on resource-constrained edge devices. They introduced FeatureFormer, a neural performance predictor that integrates node-level information, such as FLOPs, parameter counts, and memory usage, into a graph attention framework, along with a large-scale dataset for evaluating energy consumption.

This work was supported by the Office of Naval Research (ONR) and the National Science Foundation (NSF), whose funding was instrumental in enabling the project’s development and success.

Dr Biplav Srivastava and Dr Forest Agostinelli are the general chairs of the 37th instance of a leading AI conference, International Conference on Automated Planning and Scheduling (ICAPS), and they are bringing it to Columbia, SC in the summer of 2027. This conference attracts 200-300 researchers from around the world and is coming to the south-east US for the first time.

For more details about ICAPS and ICAPS-2027, see https://icaps27.icaps-conference.org/

Computer Science Ph.D. student Misagh Soltani is passionate about artificial intelligence. As a graduate researcher at the Artificial Intelligence Institute of USC (AIISC), he channels his passion into furthering model-based deep reinforcement learning. It is work he hopes will make tasks easier and information more accessible for the betterment of society.

Reinforcement learning is a branch of machine learning where an agent interacts with an environment and learns, through trial and error, how to make decisions to efficiently achieve the desired goals. Reinforcement learning approaches can be used in a variety of domains from manufacturing, where it optimizes robot motion and automation, to the natural sciences. Read the full story here.

The iCAS Lab Ph.D. Students, Lily Lamb and MohammadReza Mohammadi, have received the Best Paper Award at the IEEE COINS 2025 Conference.

Their paper, which is part of a project funded by the NSF CAREER program, explores how to enable real-time perception in autonomous systems under real-world conditions. "MultiModal Vision at the Edge: Toward Low-Latency Perception for Autonomous Systems", by Lily Lamb, Mohammadreza Mohammadi, and Ramtin Zand.

Abstract: The paper introduces an extended YOLOv8 framework that fuses RGB, LiDAR-based depth, and grayscale inputs using early, mid, and late fusion strategies, optimized for edge AI platforms. To support real-time processing, the team developed a parallelized depth generation pipeline that transforms sparse LiDAR point clouds into dense maps. Evaluated on the KITTI dataset and benchmarked across Raspberry Pi 5, Jetson Nano, and Google Coral Edge TPU, the models reveal the trade-offs between accuracy and latency, where late fusion delivers the highest accuracy (mAP@50: 92.7%), and early fusion achieves the lowest latency.

The iCAS Lab Ph.D. students, Md Hasibul Amin and MohammadReza Mohammadi have received the Best Poster Award at the GLSCLSI 2025 Conference—a premier venue for disseminating research in VLSI, devices, and system-level design. Earlier this year, this work also earned second place at the CSE Research Symposium.

This is a collaborative work between Dr. Ramtin Zand's lab and Dr. Jason Bakos on a project funded by the National Science Foundation (NSF).

"CrossNAS: A Cross-Layer Neural Architecture Search Framework for PIM Systems", by  Md Hasibul Amin, MohammadReza Mohammadi, Jason Bakos, and Ramtin Zand. 

Abstract: This work introduces the CrossNAS framework, an automated approach for exploring a vast, multidimensional search space that spans various design abstraction layers—circuits, architecture, and systems—to optimize the deployment of machine learning workloads on analog processing-in-memory (PIM) systems. CrossNAS leverages the single-path one-shot weight-sharing strategy combined with the evolutionary search for the first time in the context of PIM system mapping and optimization. CrossNAS sets a new benchmark for PIM neural architecture search (NAS), outperforming previous methods in both accuracy and energy efficiency while maintaining comparable or shorter search times.

We are proud to announce that Dr. Christian O'Reilly has received an NSF CAREER Award for his project titiled "Multiscale Model-Driven Analysis of the Brain and its Disorders." He is looking forward to kicking off this project and raising the prominence of Computational Neuroscience at the College and at USC. Read the full article explaining his research. 

For the second year in a row, iCAS Lab has won the First Place Award in the University Demonstration competition at the DAC, The Chips to Systems Conference, recognized as the premier global event for chips to systems!

This year’s award-winning project was "PiCASo: Pi-Integrated Conversational AI for Social-Robot with. Optimized LLMS" led by Mahsa Ardakani and co-presented by herself and Jinendra Malekar, with contributions from Peyton Chandarana — all PhD students at the iCAS Lab directed by Dr. Ramtin Zand.

PiCASo is a fully integrated, voice-to-voice Conversational AI system that runs 𝘦𝘯𝘵𝘪𝘳𝘦𝘭𝘺 on a Raspberry Pi 5. It combines:

• Whisper for speech recognition
• Quantized LLMs for question-answering
• Piper for text-to-speech synthesis

Mahsa and Jinendra applied various post-training quantization (PTQ) strategies — including W2A8, W4A8, W6A8, W8A8 — for Gemma-2B, LLaMA-3B, Phi-3B, and LLaMA-8B, and utilized quantization-aware trained (QAT) BitNet models with Ternary weights and 8-bit activations to enable real-time, offline inference on resource-constrained hardware. This makes PiCASo ideal for education, accessibility, and other embedded AI applications.

Our work on LLM quantization was also presented at the 2025 IEEE/CVF Computer Vision and Pattern Recognition (CVPR) conference, and the paper is now available in the CVPR 2025 proceedings. "LLMPi: Optimizing LLMs for High-Throughput on Raspberry Pi". repo

Congratulations to the following CSE recipients of the ASPIRE-AI awards.

• Francisco Leon Oyala (PI, Pharamacology) and Agostinelli (Co-I), “ASPIRE-AI: Towards Affordable HIV Treatment: Discovering Cheaper Synthesis Paths for HIV Drugs with Artificial Intelligence”
• Agostinelli (PI) and Fu (Co-I), "Efficient Quantum Algorithm Compilation with Machine Learning and Heuristic Search"
• Hu (PI), "Generative AI for Data-driven Design of Sulfur Cathode Materials for Next-Generation Batteries"
• Srivastava (PI), "SafeGenChat: A Novel and General Approach for Building Risk-Aware Collaborative Assistants for Trust-sensitive Applications "
• Valafar (Co-I), "AI-Powered Modeling of Cytoplasmic Microviscosity as a Function of RNA Composition"
• Zand and Valafar (Co-I's), "Decoding Alzheimer’s Disease and Advancing AI in Biomedical Research"

In addition, one of our students, Vandana Srivastava, who is now affiliated with the University Libraries, has received funding as the PI.

We congratulate our faculty who received the following research awards:

• Christian O'Reilly, "Neonatal autonomic nervous system dysfunction as a predictor of autism spectrum disorder in preterm infants", (NIMH)/NIH, and "Cholinergic regulation of amygdalar circuits in emotional memory", (NIMH)/NIH.
• Biplav Srivastava,  "Demonstrating a Compact Foundation Model for Planning-Like(PL) Tasks for Next Generation Trusted Applications", NSF.

Ph.D. students, from Dr. Sanjib Sur's lab,  Zhuangzhuang Gu, Hem Regmi, and Reza Tavasoli, and Ryan Titus (USC Med Student, presenter) won the second place award at 2025 Discover USC Medical Scholar poster session.