Related papers: LLM-Driven Adaptive Source-Sink Identification and…
Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in…
Recent advances in LLM-based Text-to-SQL have achieved remarkable gains on public benchmarks such as BIRD and Spider. Yet, these systems struggle to scale in realistic enterprise settings with large, complex schemas, diverse SQL dialects,…
Static program analysis plays an essential role in program optimization, bug detection, and debugging. However, reliance on compilation and limited customization hinder its adoption in the real world. This paper presents a compositional…
Health-related misinformation is very prevalent and potentially harmful. It is difficult to identify, especially when claims distort or misinterpret scientific findings. We investigate the impact of synthetic data generation and lightweight…
Reactivity is central to Angular applications, yet subtle misuse of Observables, Signals, and change-detection often leads to performance regressions that are difficult to diagnose. Although Angular 17 introduced a unified, signal-first…
Masked Diffusion Language Models (MDLMs) enable parallel token decoding, providing a promising alternative to the sequential nature of autoregressive generation. However, their iterative denoising process remains computationally expensive…
Software aging is a phenomenon that affects long-running systems, leading to progressive performance degradation and increasing the risk of failures. To mitigate this problem, this work proposes an adaptive approach based on machine…
Large language models can consult information that fixed static analyzers cannot, such as documentation, current security advisories, version-specific metadata, and informal API contracts. This makes LLMs a compelling option for program…
Transfer learning in reinforcement learning (RL) seeks to accelerate learning in new tasks by leveraging knowledge from related sources. Existing neurosymbolic transfer methods, however, typically rely on manually specified task automata,…
Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcement Learning (RL) effectively preserves general capabilities.…
Existing literature heavily relies on static analysis tools to evaluate LLMs for secure code generation and vulnerability detection. We reviewed 1,080 LLM-generated code samples, built a human-validated ground-truth, and compared the…
The rapid adoption of large language models (LLMs), such as GPT-4 and Claude 3.5, underscores the need to distinguish LLM-generated text from human-written content to mitigate the spread of misinformation and misuse in education. One…
Recent advancements in Large Language Models (LLMs) have sparked interest in their application to Static Application Security Testing (SAST), primarily due to their superior contextual reasoning capabilities compared to traditional symbolic…
General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achieved by distilling the chain-of-thought of a larger model at…
Machine learning models are commonly used for malware classification; however, they suffer from performance degradation over time due to concept drift. Adapting these models to changing data distributions requires frequent updates, which…
The fundamental challenge of using Large Language Models (LLMs) for reliable, enterprise-grade analytics, such as sentiment prediction, is the conflict between the LLMs' inherent stochasticity (generative, non-deterministic nature) and the…
Most existing sign language translation (SLT) datasets are limited in scale, lack multilingual coverage, and are costly to curate due to their reliance on expert annotation and controlled recording setup. Recently, Vision Language Models…
Eliminating vulnerabilities from low-level code is vital for securing software. Static analysis is a promising approach for discovering vulnerabilities since it can provide developers early feedback on the code they write. But, it presents…
Traditional approaches to test case generation often involve manual effort and incur significant computational overhead. Additionally, these approaches are not scalable, and hence, unsuitable for complex software systems. Recently, Large…
Automated theorem proving is essential for the formal verification of safety-critical systems. As the corpus of formal proofs grows, a natural paradigm is to learn from existing proofs. However, current learning-based approaches…