Related papers: Efficient and Expressive Bytecode-Level Instrument…
With LLM watermarking already being deployed commercially, practical applications increasingly require multibit watermarks that encode more complex payloads, such as user IDs or timestamps, into the generated text. In this work, we propose…
Large language models (LLMs) are transforming the landscape of chemistry and materials science. Recent examples of LLM-accelerated experimental research include virtual assistants for parsing synthesis recipes from the literature, or using…
Multimodal Large Language Models (MLLMs) achieve versatility by reformulating diverse tasks into a unified instruction-following framework via instruction tuning. However, real-world deployment requires continuous adaptation to emerging…
Symbolic execution is a program analysis technique executing programs with symbolic instead of concrete inputs. This principle allows for exploring many program paths at once. Despite its wide adoption -- in particular for program testing…
Paisley is an extensible lightweight embedded domain-specific language for nondeterministic pattern matching in Java. Using simple APIs and programming idioms, it brings the power of functional-logic processing of arbitrary data objects to…
When programming resource-scarce embedded smart devices, the designer often requires both the low-level system programming features of a language such as C and higher level capability typical of a language like Java. The choice of a…
The substantial memory demands of pre-training and fine-tuning large language models (LLMs) require memory-efficient optimization algorithms. One promising approach is layer-wise optimization, which treats each transformer block as a single…
The deployment of large language models (LLMs) presents significant challenges due to their enormous memory footprints, low arithmetic intensity, and stringent latency requirements, particularly during the autoregressive decoding stage.…
Instrument recognition is a fundamental task in music information retrieval, yet little has been done to predict the presence of instruments in multi-instrument music for each time frame. This task is important for not only automatic…
Test Impact Analysis is an approach to obtain a subset of tests impacted by code changes. This approach is mainly applied to unit testing where the link between the code and its associated tests is easy to obtain. On the integration level,…
Scanning transmission electron microscopy (STEM) has become a cornerstone instrument for semiconductor materials metrology, enabling nanoscale analysis of complex multilayer structures that define device performance. Developing effective…
This study introduces a novel methodology for fault detection and cause identification within the Tennessee Eastman Process (TEP) by integrating a Bidirectional Long Short-Term Memory (BiLSTM) neural network with an Integrated Attention…
Robotic imitation learning typically requires models that capture multimodal action distributions while operating at real-time control rates and accommodating multiple sensing modalities. Although recent generative approaches such as…
The bispectrum stands out as a revolutionary tool in frequency domain analysis, leaping the usual power spectrum by capturing crucial phase information between frequency components. In our innovative study, we have utilized the bispectrum…
The deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications. However, computational resources for these networks are significantly constrained since they usually run on-call on edge…
A Brain-Computer Interface (BCI) acquires brain signals, analyzes and translates them into commands that are relayed to actuation devices for carrying out desired actions. With the widespread connectivity of everyday devices realized by the…
Recent work has shown that quantum simulation is a valuable tool for learning empirical models for quantum systems. We build upon these results by showing that a small quantum simulators can be used to characterize and learn control models…
As software systems grow in complexity, data and tools that provide valuable insights for easier program comprehension become increasingly important. OpenTelemetry has become a standard for the collection of monitoring data. In this work we…
Large Language Models (LLMs) are increasingly deployed in high-stakes contexts where their outputs influence real-world decisions. However, evaluating bias in LLM outputs remains methodologically challenging due to sensitivity to prompt…
The latest industrial inference engines, such as FasterTransformer and TurboTransformers, have verified that half-precision floating point (FP16) and 8-bit integer (INT8) quantization can greatly improve model inference speed. However, the…