Related papers: ShIOEnv: A Command Evaluation Environment for Gram…

With the growing complexity of deep learning methods adopted in practical applications, there is an increasing and stringent need to explain and interpret the decisions of such methods. In this work, we focus on explainable AI and propose a…

Simulated environments play an essential role in embodied AI, functionally analogous to test cases in software engineering. However, existing environment generation methods often emphasize visual realism (e.g., object diversity and layout…

We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised,…

As Large Language Models (LLMs) are increasingly deployed as task-oriented agents in enterprise environments, ensuring their strict adherence to complex, domain-specific operational guidelines is critical. While utilizing an LLM-as-a-Judge…

Effective static analyses have been proposed which infer bounds on the number of resolutions or reductions. These have the advantage of being independent from the platform on which the programs are executed and have been shown to be useful…

Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimization primarily in the prompt space. In other words, these methods mainly search for better…

The complexity of modern software has led to a drastic increase in the time and cost associated with detecting and rectifying software bugs. In response, researchers have explored various methods to automatically generate fixes for buggy…

Current clinical agent built on small LLMs, such as TxAgent suffer from a \textit{Context Utilization Failure}, where models successfully retrieve biomedical evidence due to supervised finetuning but fail to ground their diagnosis in that…

Event-driven scheduling policies are increasingly deployed in industrial environments, where decisions are made under asynchronous and partially observed system states. As a result, decision states are not temporally consistent, action…

In an era of human-computer interaction with increasingly agentic AI systems capable of connecting with users conversationally, speech is an important modality for commanding agents. By recognizing and using speech emotions (i.e., how a…

Speech language models (Speech LMs) enable end-to-end speech-text modeling within a single model, offering a promising direction for spoken dialogue systems. The choice of speech-text jointly decoding paradigm plays a critical role in…

Interactive agent benchmarks face a tension between scalable construction and realistic workflow evaluation. Hand-authored tasks are expensive to extend and revise, while static prompt evaluation misses failures that only appear when agents…

This paper explores the instruction fine-tuning technique for speech-to-semantic tasks by introducing a unified end-to-end (E2E) framework that generates target text conditioned on a task-related prompt for audio data. We pre-train the…

Reliably ensuring Large Language Models (LLMs) follow complex instructions is a critical challenge, as existing benchmarks often fail to reflect real-world use or isolate compliance from task success. We introduce MOSAIC (MOdular Synthetic…

Static analysis, the process of examining code without executing it, is crucial for identifying software issues. Yet, static analysis is hampered by its complexity and the need for customization for different targets. Traditional static…

In this paper, we propose an effective yet efficient model PAIE for both sentence-level and document-level Event Argument Extraction (EAE), which also generalizes well when there is a lack of training data. On the one hand, PAIE utilizes…

While large language models (LLMs) have exhibited impressive instruction-following capabilities, it is still unclear whether and to what extent they can respond to explicit constraints that might be entailed in various instructions. As a…

As the complexity of System-on-Chip (SoC) designs grows, the shift-left paradigm necessitates the rapid development of high-fidelity reference models (typically written in SystemC) for early architecture exploration and verification. While…

Post-training GUI agents in interactive environments is critical for developing generalization and long-horizon planning capabilities. However, training on real-world applications is hindered by high latency, poor reproducibility, and…

Identifying the root cause of a bug remains difficult for many developers because bug reports often lack a bug reproducing test case that reliably triggers the failure. Manually writing such test cases is time-consuming and requires…