2 citations · 2 across the 12 of their papers we have counts for
15 papers
Kronecker Product Attention: Memory-Efficient KV Compression via Structured Factorization
Bahareh Nikpour, Hossein Rajabzadeh, Maryam Dialameh +2
Efficient autoregressive generation is increasingly limited by the memory footprint of the key-value (KV) cache, which grows linearly with sequence length, batch size, and model de…
Conformal Prediction under Partial Verification
Zijun Yu, Yu Gu, Vahid Partovi Nia +1
Conformal prediction provides prediction sets with finite-sample guarantees, but the label verification required for calibration can be expensive. We develop a partial verification…
G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional Harm
Zijun Yu, Yu Gu, Vahid Partovi Nia +1
Small language model (SLM) agents need safety controls that track consequences across tool calls with little monitoring overhead. A private read, for example, becomes a leak when a…
From Fixed Keys to Readable Schemas: Small Language Models for Vehicle Agent Function Calls
Hamed Jafarzadeh Asl, Yuanhao Yu, Vahid Partovi Nia
In-vehicle assistants must translate natural-language requests into accurate vehicle function calls under strict memory and latency constraints, making small language models (SLMs)…
Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
Yu Gu, Zijun Yu, Vahid Partovi Nia +1
Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths. In this setting, correctness is no longer tied to a sin…
Enterprise Resource Planning Using Multi-type Transformers in Ferro-Titanium Industry
Samira Yazdanpourmoghadam, Mahan Balal Pour, Vahid Partovi Nia
Combinatorial optimization problems such as the Job-Shop Scheduling Problem (JSP) and Knapsack Problem (KP) are fundamental challenges in operations research, logistics, and eterpr…
HyWA: Architecture-Preserving Personalized Voice Activity Detection for Full-Duplex Voice Assistants
Hamed Jafarzadeh Asl, Amin Edraki, Mahsa Ghazvini Nejad +4
Voice activity detection (VAD) serves as an early gate in voice-assistant pipelines for smart devices. Because conventional VADs respond to speech from any speaker, nearby conversa…
MoKA: Mixture of Kronecker Adapters
Mohammadreza Sadeghi, Mahsa Ghazvini Nejad, MirHamed Jafarzadeh Asl +4
Parameter-efficient fine-tuning (PEFT) is essential for reducing the computational overhead of large language models (LLMs). Low-rank family adapters are commonly used to control t…
Tiny Noise-Robust Voice Activity Detector for Voice Assistants
Hamed Jafarzadeh Asl, Mahsa Ghazvini Nejad, Amin Edraki +2
Voice Activity Detection (VAD) in the presence of background noise remains a challenging problem in speech processing. Accurate VAD is essential in automatic speech recognition, vo…
PoTPTQ: A Two-step Power-of-Two Post-training for LLMs
Xinyu Wang, Vahid Partovi Nia, Peng Lu +4
Large Language Models (LLMs) have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, their deployment is challenging due to the su…
Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach
Alireza Ghaffari, Sharareh Younesian, Boxing Chen +2
As Large Language Models (LLMs) become increasingly computationally complex, developing efficient deployment strategies, such as quantization, becomes crucial. State-of-the-art Pos…
AdpQ: A Zero-shot Calibration Free Adaptive Post Training Quantization Method for LLMs
Alireza Ghaffari, Sharareh Younesian, Vahid Partovi Nia +2
The ever-growing computational complexity of Large Language Models (LLMs) necessitates efficient deployment strategies. The current state-of-the-art approaches for Post-training Qu…
OAC: Output-adaptive Calibration for Accurate Post-training Quantization
Ali Edalati, Alireza Ghaffari, Mahsa Ghazvini Nejad +4
Deployment of Large Language Models (LLMs) has major computational costs, due to their rapidly expanding size. Compression of LLMs reduces the memory footprint, latency, and energy…
Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers
Yiwei Lu, Yaoliang Yu, Xinlin Li +1
In neural network binarization, BinaryConnect (BC) and its variants are considered the standard. These methods apply the sign function in their forward pass and their respective gr…
Mitigating Outlier Activations in Low-Precision Fine-Tuning of Language Models
Alireza Ghaffari, Justin Yu, Mahsa Ghazvini Nejad +3
Low-precision fine-tuning of language models has gained prominence as a cost-effective and energy-efficient approach to deploying large-scale models in various applications. Howeve…