17 citations · 46 across the 18 of their papers we have counts for
20 papers
Evaluating the Diagnostic Robustness of Vision-Language Models Under Visual and Textual Perturbations
Ali Khoramfar, Mohammad Javad Dousti, Alireza Mohamadian +1
Standard accuracy metrics for VLMs often mask significant reliability failures in sensitive domains. In this work, we utilize a histopathology-validated brain MRI dataset to system…
MDP-GRPO: Stabilized Group Relative Policy Optimization for Multi-Constraint Instruction Following
Mohammad Mahdi Salmani-Zarchi, Zahra Rahimi, Heshaam Faili +1
Reinforcement learning with verifiable rewards is ideal for multi-constraint instruction following, yet standard group-relative policy optimization (GRPO) becomes unstable under di…
Dynamic Jointly Batch Selection for Data Efficient Machine Translation Fine-Tuning
Mohammad Amin Ghanizadeh, Mohammad Javad Dousti
Data quality and its effective selection are fundamental to improving the performance of machine translation models, serving as cornerstones for achieving robust and reliable trans…
DeepQuestion: Systematic Generation of Real-World Challenges for Evaluating LLMs Performance
Ali Khoramfar, Ali Ramezani, Mohammad Mahdi Mohajeri +3
While Large Language Models (LLMs) achieve near-human performance on standard benchmarks, their capabilities often fail to generalize to complex, real-world problems. To bridge thi…
: Data-Driven LoRA Initialization for Low Resource Tasks
Javad SeraJ, Mohammad Mahdi Mohajeri, Mohammad Javad Dousti
Tuning large language models is essential for optimizing their performance across diverse applications, particularly in scenarios with limited data availability. Tuning large langu…
Towards Data-Efficient Language Models: A Child-Inspired Approach to Language Learning
Mohammad Amin Ghanizadeh, Mohammad Javad Dousti
In this work, we explain our approach employed in the BabyLM Challenge, which uses various methods of training language models (LMs) with significantly less data compared to tradit…
Optimizing Alignment with Less: Leveraging Data Augmentation for Personalized Evaluation
Javad Seraj, Mohammad Mahdi Mohajeri, Mohammad Javad Dousti +1
Automatic evaluation by large language models (LLMs) is a prominent topic today; however, judgment and evaluation tasks are often subjective and influenced by various factors, maki…
CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt
Mohammad Mahdi Mohajeri, Mohammad Javad Dousti, Majid Nili Ahmadabadi
Text classification is a fundamental task in natural language processing (NLP), and large language models (LLMs) have demonstrated their capability to perform this task across vari…
CULL-MT: Compression Using Language and Layer pruning for Machine Translation
Pedram Rostami, Mohammad Javad Dousti
Multilingual machine translation models often outperform traditional bilingual models by leveraging translation knowledge transfer. Recent advancements have led to these models sup…
PersianMind: A Cross-Lingual Persian-English Large Language Model
Pedram Rostami, Ali Salemi, Mohammad Javad Dousti
Large language models demonstrate remarkable proficiency in various linguistic tasks and have extensive knowledge across various domains. Although they perform best in English, the…
Mismatching-Aware Unsupervised Translation Quality Estimation For Low-Resource Languages
Fatemeh Azadi, Heshaam Faili, Mohammad Javad Dousti
Translation Quality Estimation (QE) is the task of predicting the quality of machine translation (MT) output without any reference. This task has gained increasing attention as an…
TEASEL: A Transformer-Based Speech-Prefixed Language Model
Mehdi Arjmand, Mohammad Javad Dousti, Hadi Moradi
Multimodal language analysis is a burgeoning field of NLP that aims to simultaneously model a speaker's words, acoustical annotations, and facial expressions. In this area, lexicon…
Streaming Simultaneous Speech Translation with Augmented Memory Transformer
Xutai Ma, Yongqiang Wang, Mohammad Javad Dousti +2
Transformer-based models have achieved state-of-the-art performance on speech translation tasks. However, the model architecture is not efficient enough for streaming scenarios sin…
SimulEval: An Evaluation Toolkit for Simultaneous Translation
Xutai Ma, Mohammad Javad Dousti, Changhan Wang +2
Simultaneous translation on both text and speech focuses on a real-time and low-latency scenario where the model starts translating before reading the complete source input. Evalua…
Self-Training for End-to-End Speech Translation
Juan Pino, Qiantong Xu, Xutai Ma +2
One of the main challenges for end-to-end speech translation is data scarcity. We leverage pseudo-labels generated from unlabeled audio by a cascade and an end-to-end speech transl…
Squash 2: A Hierarchical Scalable Quantum Mapper Considering Ancilla Sharing
Mohammad Javad Dousti, Alireza Shafaei, Massoud Pedram
We present a multi-core reconfigurable quantum processor architecture, called Requp, which supports a hierarchical approach to mapping a quantum algorithm while sharing physical an…
Design of a Universal Logic Block for Fault-Tolerant Realization of any Logic Operation in Trapped-Ion Quantum Circuits
Hadi Goudarzi, Mohammad Javad Dousti, Alireza Shafaei +1
This paper presents a physical mapping tool for quantum circuits, which generates the optimal Universal Logic Block (ULB) that can perform any logical fault-tolerant (FT) quantum o…
LEQA: Latency Estimation for a Quantum Algorithm Mapped to a Quantum Circuit Fabric
Mohammad Javad Dousti, Massoud Pedram
This paper presents LEQA, a fast latency estimation tool for evaluating the performance of a quantum algorithm mapped to a quantum fabric. The actual quantum algorithm latency can…
Squash: A Scalable Quantum Mapper Considering Ancilla Sharing
Mohammad Javad Dousti, Alireza Shafaei, Massoud Pedram
Quantum algorithms for solving problems of interesting size often result in circuits with a very large number of qubits and quantum gates. Fortunately, these algorithms also tend t…
Minimizing the Latency of Quantum Circuits during Mapping to the Ion-Trap Circuit Fabric
Mohammad Javad Dousti, Massoud Pedram
Quantum computers are exponentially faster than their classical counterparts in terms of solving some specific, but important problems. The biggest challenge in realizing a quantum…