15 papers
ForkGRPO: Efficient Exploration and Fine-Grained Credit Assignment for Diffusion Language Models
Zhaoyan Jia, Chengwei Zhou, Gourav Datta +1
Diffusion large language models (dLLMs) have advanced rapidly, yet strengthening their reasoning through reinforcement learning (RL) remains an open challenge. Any-order generation…
Hardware-Aware Learned Representation Compression for Distributed In-Sensor Vision
Chengwei Zhou, Abu Masum, Xuming Chen +7
In-sensor computing reduces the cost of transmitting high-resolution image data by performing early-stage processing near the sensor. However, the logic chip integrated with a CMOS…
BRIDGE-EEG: Bridging Self-Supervised Pretraining and Efficient Deployment for Cross-Dataset EEG Classification
Meghna Roy Chowdhury, Chengwei Zhou, Haotian Yu +2
The growing use of electroencephalography (EEG) motivates automated analysis that is accurate, transferable, and deployable on constrained hardware. Recent EEG foundation models le…
PICasso: An AI-Enabled Design Framework for Autonomous Optimization of Silicon Photonic Devices
Deepak Vungarala, Deniz Najafi, Abdulrahman Aljoudi +6
We present PICasso, an AI-assisted framework for automated synthesis, verification, and optimization of photonic integrated circuits (PICs) from natural-language specifications. PI…
Sense Less, Infer More: Agentic Multimodal Transformers for Edge Medical Intelligence
Chengwei Zhou, Zhaoyan Jia, Haotian Yu +6
Edge-based multimodal medical monitoring requires models that balance diagnostic accuracy with severe energy constraints. Continuous acquisition of ECG, PPG, EMG, and IMU streams r…
Light-Bound Transformers: Hardware-Anchored Robustness for Silicon-Photonic Computer Vision Systems
Xuming Chen, Deniz Najafi, Chengwei Zhou +6
Deploying Vision Transformers (ViTs) on near-sensor analog accelerators demands training pipelines that are explicitly aligned with device-level noise and energy constraints. We in…
Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification
Vikash Singh, Debargha Ganguly, Haotian Yu +5
Vision-language models (VLMs) show promise in drafting radiology reports, yet they frequently suffer from logical inconsistencies, generating diagnostic impressions unsupported by…
RT-NeuS: Towards Real-Time Neuro-Symbolic Video Understanding via Adaptive Temporal Verification
Shawn Liang, Sahil Shah, Chengwei Zhou +5
Long-form video question answering (LVQA) requires answering natural-language queries about videos spanning minutes to hours, demanding temporal reasoning across thousands of frame…
Rethinking Vision Transformer Depth via Structural Reparameterization
Chengwei Zhou, Vipin Chaudhary, Gourav Datta
The computational overhead of Vision Transformers in practice stems fundamentally from their deep architectures, yet existing acceleration strategies have primarily targeted algori…
Learning Scalable Temporal Representations in Spiking Neural Networks Without Labels
Chengwei Zhou, Gourav Datta
Spiking neural networks (SNNs) exhibit temporal, sparse, and event-driven dynamics that make them appealing for efficient inference. However, extending these models to self-supervi…
BladderFormer: A Streaming Transformer for Real-Time Urological State Monitoring
Chengwei Zhou, Steve Majerus, Gourav Datta
Bladder pressure monitoring systems are increasingly vital in diagnosing and managing urinary tract dysfunction. Existing solutions rely heavily on hand-crafted features and shallo…
Opto-ViT: Architecting a Near-Sensor Region of Interest-Aware Vision Transformer Accelerator with Silicon Photonics
Mehrdad Morsali, Chengwei Zhou, Deniz Najafi +7
Vision Transformers (ViTs) have emerged as a powerful architecture for computer vision tasks due to their ability to model long-range dependencies and global contextual relationshi…
OASIS: Optimized Lightweight Autoencoder System for Distributed In-Sensor computing
Chengwei Zhou, Sreetama Sarkar, Yuming Li +5
In-sensor computing, which integrates computation directly within the sensor, has emerged as a promising paradigm for machine vision applications such as AR/VR and smart home syste…
EntroLLM: Entropy Encoded Weight Compression for Efficient Large Language Model Inference on Edge Devices
Arnab Sanyal, Gourav Datta, Prithwish Mukherjee +2
Large Language Models (LLMs) achieve strong performance across tasks, but face storage and compute challenges on edge devices. We propose EntroLLM, a compression framework combinin…
ReDistill: Residual Encoded Distillation for Peak Memory Reduction of CNNs
Fang Chen, Gourav Datta, Mujahid Al Rafi +2
The expansion of neural network sizes and the enhanced resolution of modern image sensors result in heightened memory and power demands to process modern computer vision models. In…