Junhao Wang

Jiawei Liu, Songrun Xie, Junhao Wang et al.

We introduce Differential Performance Evaluation (DPE), a framework designed to reliably evaluate Large Language Models (LLMs) for efficient code generation. Traditional coding benchmarks often fail to provide reliable insights into code efficiency, due to their reliance on simplistic test inputs and the absence of effective compound metrics. DPE addresses these issues by focusing on efficiency-demanding programming tasks and establishing an insightful compound metric for performance evaluation. DPE operates in two phases: To curate efficiency datasets, it selects efficiency-demanding tasks from existing coding benchmarks and generates computationally expensive inputs to stress the efficiency of LLM solutions. To assess the code efficiency, DPE profiles the new solution and compares it globally against a set of reference solutions that exhibit distinct efficiency levels, where the matched level defines its efficiency score. As a proof of concept, we use DPE to create EvalPerf, a benchmark with 121 performance-challenging coding tasks. Our comprehensive evaluation draws interesting findings on the efficiency impact of model sizes, instruction tuning, and prompting. For example, while the scaling law fails to account for code efficiency, general instruction tuning benefits both code correctness and efficiency. We also evaluate the evaluation by examining the effectiveness of DPE, showing that EvalPerf is reliable and convenient to use even across platforms.

Xing Zhang, Jiaheng Wen, Fangkai Yang et al.

The advancement of large language models has intensified the need to modernize enterprise applications and migrate legacy systems to secure, versatile languages. However, existing code translation benchmarks primarily focus on individual functions, overlooking the complexities involved in translating entire repositories, such as maintaining inter-module coherence and managing dependencies. While some recent repository-level translation benchmarks attempt to address these challenges, they still face limitations, including poor maintainability and overly coarse evaluation granularity, which make them less developer-friendly. We introduce Skeleton-Guided-Translation, a framework for repository-level Java to C# code translation with fine-grained quality evaluation. It uses a two-step process: first translating the repository's structural "skeletons", then translating the full repository guided by these skeletons. Building on this, we present TRANSREPO-BENCH, a benchmark of high quality open-source Java repositories and their corresponding C# skeletons, including matching unit tests and build configurations. Our unit tests are fixed and can be applied across multiple or incremental translations without manual adjustments, enhancing automation and scalability in evaluations. Additionally, we develop fine-grained evaluation metrics that assess translation quality at the individual test case level, addressing traditional binary metrics' inability to distinguish when build failures cause all tests to fail. Evaluations using TRANSREPO-BENCH highlight key challenges and advance more accurate repository level code translation.

Linghao Zhang, Shilin He, Chaoyun Zhang et al.

The issue-resolving task, where a model generates patches to fix real-world bugs, has emerged as a critical benchmark for evaluating the capabilities of large language models (LLMs). While SWE-bench and its variants have become standard in this domain, they suffer from key limitations: they have not been updated since their initial releases, cover a narrow set of repositories, and depend heavily on manual effort for instance construction and environment setup. These factors hinder scalability and introduce risks of overfitting and data contamination. In this work, we present SWE-bench-Live, a live-updatable benchmark designed to overcome these challenges. Our initial release consists of 1,319 tasks derived from real GitHub issues created since 2024, spanning 93 repositories. Each task is accompanied by a dedicated Docker image to ensure reproducible execution. Central to our benchmark is \method, an automated curation pipeline that streamlines the entire process from instance creation to environment setup, removing manual bottlenecks and enabling scalability and continuous updates. We evaluate a range of state-of-the-art agent frameworks and LLMs on SWE-bench-Live, revealing a substantial performance gap compared to static benchmarks like SWE-bench, even under controlled evaluation conditions. To better understand this discrepancy, we perform detailed analyses across repository origin, issue recency, and task difficulty. By providing a fresh, diverse, and executable benchmark grounded in live repository activity, SWE-bench-Live facilitates rigorous, contamination-resistant evaluation of LLMs and agents in dynamic, real-world software development settings.

Linghao Zhang, Junhao Wang, Shilin He et al.

Large Language Models have advanced automated software development, however, it remains a challenge to correctly infer dependencies, namely, identifying the internal components and external packages required for a repository to successfully run. Existing studies highlight that dependency-related issues cause over 40\% of observed runtime errors on the generated repository. To address this, we introduce DI-BENCH, a large-scale benchmark and evaluation framework specifically designed to assess LLMs' capability on dependency inference. The benchmark features 581 repositories with testing environments across Python, C#, Rust, and JavaScript. Extensive experiments with textual and execution-based metrics reveal that the current best-performing model achieves only a 42.9% execution pass rate, indicating significant room for improvement. DI-BENCH establishes a new viewpoint for evaluating LLM performance on repositories, paving the way for more robust end-to-end software synthesis.

Arsenii Gorin, Cem Subakan, Sajjad Abdoli et al.

In this paper, we explore self-supervised learning (SSL) for analyzing a first-of-its-kind database of cry recordings containing clinical indications of more than a thousand newborns. Specifically, we target cry-based detection of neurological injury as well as identification of cry triggers such as pain, hunger, and discomfort. Annotating a large database in the medical setting is expensive and time-consuming, typically requiring the collaboration of several experts over years. Leveraging large amounts of unlabeled audio data to learn useful representations can lower the cost of building robust models and, ultimately, clinical solutions. In this work, we experiment with self-supervised pre-training of a convolutional neural network on large audio datasets. We show that pre-training with SSL contrastive loss (SimCLR) performs significantly better than supervised pre-training for both neuro injury and cry triggers. In addition, we demonstrate further performance gains through SSL-based domain adaptation using unlabeled infant cries. We also show that using such SSL-based pre-training for adaptation to cry sounds decreases the need for labeled data of the overall system.

David Venuto, Jhelum Chakravorty, Leonard Boussioux et al.

Explicit engineering of reward functions for given environments has been a major hindrance to reinforcement learning methods. While Inverse Reinforcement Learning (IRL) is a solution to recover reward functions from demonstrations only, these learned rewards are generally heavily \textit{entangled} with the dynamics of the environment and therefore not portable or \emph{robust} to changing environments. Modern adversarial methods have yielded some success in reducing reward entanglement in the IRL setting. In this work, we leverage one such method, Adversarial Inverse Reinforcement Learning (AIRL), to propose an algorithm that learns hierarchical disentangled rewards with a policy over options. We show that this method has the ability to learn \emph{generalizable} policies and reward functions in complex transfer learning tasks, while yielding results in continuous control benchmarks that are comparable to those of the state-of-the-art methods.

Junhao Wang, Sacha Levy, Ren Wang et al.

Recent events have led to a burgeoning awareness on the misuse of social media sites to affect political events, sway public opinion, and confuse the voters. Such serious, hostile mass manipulation has motivated a large body of works on bots/troll detection and fake news detection, which mostly focus on classifying at the user level based on the content generated by the users. In this study, we jointly analyze the connections among the users, as well as the content generated by them to Spot Coordinated Groups (SCG), sets of users that are likely to be organized towards impacting the general discourse. Given their tiny size (relative to the whole data), detecting these groups is computationally hard. Our proposed method detects these tiny-clusters effectively and efficiently. We deploy our SCG method to summarize and explain the coordinated groups on Twitter around the 2019 Canadian Federal Elections, by analyzing over 60 thousand user accounts with 3.4 million followership connections, and 1.3 million unique hashtags in the content of their tweets. The users in the detected coordinated groups are over 4x more likely to get suspended, whereas the hashtags which characterize their creed are linked to misinformation campaigns.