Large language models (LLMs) have shown remarkable capabilities across diverse coding tasks.However, their adoption requires a true understanding of program execution rather than relying on surface-level patterns.Existing benchmarks primarily focus on predicting program properties tied to specific inputs (e.g., code coverage, program outputs).As a result, they provide a narrow view of dynamic code reasoning and are prone to data contamination.We argue that understanding program execution requires evaluating its inherent duality through two complementary reasoning tasks: (i) predicting a program's observed behavior for a given input, and (ii) inferring how the input must be mutated toward a specific behavioral objective.Both tasks jointly probe a model's causal understanding of execution flow.We instantiate this duality in DEXBENCH, a benchmark comprising 445 paired instances, and evaluate 13 LLMs.Our results demonstrate that dual-path reasoning provides a robust and discriminative proxy for dynamic code understanding.

Eftekhar Hossain, Sanjeev Kumar Sinha, Naman Bansal, R. Alexander Knipper, Souvika Sarkar, John Salvador, Yash Mahajan, Sri Ram Pavan Kumar Guttikonda, Mousumi Akter, Md. Mahadi Hassan, Matthew Freestone, Matthew C. Williams Jr., Dongji Feng, Santu Karmaker. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Voice-controlled systems are becoming ubiquitous in many IoT-specific applications such as home/industrial automation, automotive infotainment, and healthcare. While cloud-based voice services (\eg Alexa, Siri) can leverage high-performance computing servers, some use cases (\eg robotics, automotive infotainment) may require to execute the natural language processing (NLP) tasks offline, often on resource-constrained embedded devices. Transformer-based language models such as BERT and its variants are primarily developed with compute-heavy servers in mind. Despite the great performance of BERT models across various NLP tasks, their large size and numerous parameters pose substantial obstacles to offline computation on embedded systems. Lighter replacement of such language models (\eg DistilBERT and TinyBERT) often sacrifice accuracy, particularly for complex NLP tasks. Until now, it is still unclear \ca whether the state-of-the-art language models, \viz BERT and its variants are deployable on embedded systems with a limited processor, memory, and battery power and \cb if they do, what are the "right'' set of configurations and parameters to choose for a given NLP task. This paper presents aperformance study of transformer language models under different hardware configurations and accuracy requirements and derives empirical observations about these resource/accuracy trade-offs. In particular, we study how the most commonly used BERT-based language models (\viz BERT, RoBERTa, DistilBERT, and TinyBERT) perform on embedded systems. We tested them on \textitfour off-the-shelf embedded platforms (\hardware) with 2 GB and 4 GB memory (\ie a total of \textiteight hardware configurations) and \textitfour datasets (\ie HuRIC, GoEmotion, CoNLL, WNUT17) running various NLP tasks. Our study finds that executing complex NLP tasks (such as "sentiment'' classification) on embedded systems isfeasible even without any GPUs (\eg \rpi with 2 GB of RAM). We release our implementations for community use. Our findings can help designers understand the deployability and performance of transformer language models, especially those based on BERT architectures.

Software Defined Networking (SDN) decouples the control plane from the data plane, thereby enhancing flexibility in network management. Earlier works on SDN modeling only focused on packet-level arrivals without considering flow-level arrivals. However, a model without considering flow-level arrivals cannot correctly reflect the probability of sending packets to the controller. In this paper, we propose an analytical model of SDN considering flow-level (TCP connection) arrivals and packet-level arrivals simultaneously. We use an analytical method termed as 4D state model, which uses four-dimensional states. We have derived the state transition rates of the model and also the packet delay and packet loss probability. We have conducted numerical analysis and extensive simulations. Our results show good matches, which verify the suitability and correctness of our analysis. Error ratios of the analytical results for 4D state model and M/M/1 model against simulation results are also given. Results show that for data packet delays, 4D state can achieve error ratios of 1.16-3.30%, which is much better than 8.57-35.7% attained by M/M/1 model, which only considers packet-level arrivals.