The effective management of wastewater and stormwater systems is crucial for urban sustainability and environmental protection. These systems, which form an integral part of public infrastructure, require structured information for monitoring, planning, and maintenance. However, much of the relevant information exists in unstructured textual formats, such as technical reports, regulatory documents, and maintenance logs. Extracting information from these sources is a key challenge, due to domain-specific terminology and the multilingual nature of regulatory and operational contexts. Typically a wastewater management information extraction application will require domain-specific entity recognition, followed by the extraction of relations between entities to support decision-making, automated reasoning, and linking to existing knowledge bases. The recent progresses in domain-specific Named Entity Recognition (NER) have the potential to greatly facilitate the development of such applications. However, to effectively evaluate this first and crucial step of the extraction pipeline, it is essential to establish a clearly defined set of extractable entities and construct a multilingual benchmark corpus . Building on previous work - carried out within the framework of a national project on just one language - we propose the following contributions: The starwars corpus, an aligned French-Italian corpus containing domain-specific texts.

Humans naturally process real-world multimodal information in a full-duplex manner. In artificial intelligence, replicating this capability is essential for advancing model development and deployment, particularly in embodied contexts. The development of multimodal models faces two primary challenges: (1) effectively handling more than three modalities-such as vision, audio, and text; and (2) delivering full-duplex responses to rapidly evolving human instructions. To facilitate research on models that support both omnimodal processing and full duplexity, we present RoboEgo (alias: FLM-Ego), a unified model system designed to address both challenges. RoboEgo incorporates a backbone architecture and algorithms that natively support full duplexity, achieving a theoretical duplex latency of 80 ms. In streaming visually grounded conversations under real-world conditions, RoboEgo exhibits superior responsiveness and speech naturalness, while maintaining comparable content qualities to state-of-the-art semi-duplex omnimodal models-a feat previously considered unattainable by native full-duplex systems.

This paper addresses critical gaps in Arabic language model evaluation by establishing comprehensive theoretical guidelines and introducing a novel evaluation framework. We first analyze existing Arabic evaluation datasets, identifying significant issues in linguistic accuracy, cultural alignment, and methodological rigor. To address these limitations in LLMs, we present the Arabic Depth Mini Dataset (ADMD), a carefully curated collection of 490 challenging questions spanning ten major domains (42 sub-domains, see Figure 1. Using ADMD, we evaluate five leading language models: GPT-4, Claude 3.5 Sonnet, Gemini Flash 1.5, CommandR 100B, and Qwen-Max. Our results reveal significant variations in model performance across different domains, with particular challenges in areas requiring deep cultural understanding and specialized knowledge. Claude 3.5 Sonnet demonstrated the highest overall accuracy at 30\%, showing relative strength in mathematical theory in Arabic, Arabic language, and islamic domains. This work provides both theoretical foundations and practical insights for improving Arabic language model evaluation, emphasizing the importance of cultural competence alongside technical capabilities.

As machine learning algorithms are shown to be an increasingly valuable tool, the demand for their access has grown accordingly. Oftentimes, it is infeasible to run inference with larger models without an accelerator, which may be unavailable in environments that have constraints such as energy consumption, security, or cost. To increase the availability of these models, we aim to improve the LLM inference speed on a CPU-only environment by modifying the cache architecture. To determine what improvements could be made, we conducted two experiments using Llama.cpp and the QWEN model: running various cache configurations and evaluating their performance, and outputting a trace of the memory footprint. Using these experiments, we investigate the memory access patterns and performance characteristics to identify potential optimizations.

Recent advances in large language models (LLMs) have propelled research in natural language interfaces to databases. However, most state-of-the-art text-to-SQL systems still depend on complex, multi-stage pipelines. This work proposes a novel agentic framework that unifies schema linking, query generation, and iterative refinement within a single, end-to-end component. By leveraging the intrinsic reasoning abilities of LLMs, our method emulates how humans answer questions when working with unfamiliar databases: understanding the data by formulating hypotheses, running dynamic queries to validate them, reasoning over the results, and revising outputs based on observed results. Crucially, our approach introduces a new strategy for scaling test-time computation in text-to-SQL: we scale the depth of interactive database exploration and reflection. This shift enables the model to allocate computation dynamically to better understand the data, especially useful in ambiguous and underspecified scenarios. Our experiments show that it improved the Execution Accuracy (EX) from 44.8% to 56.5% on the challenging BIRD dataset using DeepSeek-R1-Distill-Llama-70B. Furthermore, when equipped with steps to add more diversity to the answers, our agent achieves a Best-of-N accuracy of 81.8% with 8 rounds of candidate generation, rivaling the 82.79% achieved by the top-ranked published solution, while reducing engineering complexity. These findings position our unified framework as a promising alternative for building natural language interfaces to databases.

Molecular Relational Learning (MRL) aims to understand interactions between molecular pairs, playing a critical role in advancing biochemical research. With the recent development of large language models (LLMs), a growing number of studies have explored the integration of MRL with LLMs and achieved promising results. However, the increasing availability of diverse LLMs and molecular structure encoders has significantly expanded the model space, presenting major challenges for benchmarking. Currently, there is no LLM framework that supports both flexible molecular input formats and dynamic architectural switching. To address these challenges, reduce redundant coding, and ensure fair model comparison, we propose ModuLM, a framework designed to support flexible LLM-based model construction and diverse molecular representations. ModuLM provides a rich suite of modular components, including 8 types of 2D molecular graph encoders, 11 types of 3D molecular conformation encoders, 7 types of interaction layers, and 7 mainstream LLM backbones. Owing to its highly flexible model assembly mechanism, ModuLM enables the dynamic construction of over 50,000 distinct model configurations. In addition, we provide comprehensive results to demonstrate the effectiveness of ModuLM in supporting LLM-based MRL tasks.

We present SwingArena, a competitive evaluation framework for Large Language Models (LLMs) that closely mirrors real-world software development workflows. Unlike traditional static benchmarks, SwingArena models the collaborative process of software iteration by pairing LLMs as submitters, who generate patches, and reviewers, who create test cases and verify the patches through continuous integration (CI) pipelines. To support these interactive evaluations, we introduce a retrieval-augmented code generation (RACG) module that efficiently handles long-context challenges by providing syntactically and semantically relevant code snippets from large codebases, supporting multiple programming languages (C++, Python, Rust, and Go). This enables the framework to scale across diverse tasks and contexts while respecting token limitations. Our experiments, using over 400 high-quality real-world GitHub issues selected from a pool of 2,300 issues, show that models like GPT-4o excel at aggressive patch generation, whereas DeepSeek and Gemini prioritize correctness in CI validation. SwingArena presents a scalable and extensible methodology for evaluating LLMs in realistic, CI-driven software development settings. More details are available on our project page: swing-bench.github.io

We introduce PHYSICS, a comprehensive benchmark for university-level physics problem solving. It contains 1297 expert-annotated problems covering six core areas: classical mechanics, quantum mechanics, thermodynamics and statistical mechanics, electromagnetism, atomic physics, and optics. Each problem requires advanced physics knowledge and mathematical reasoning. We develop a robust automated evaluation system for precise and reliable validation. Our evaluation of leading foundation models reveals substantial limitations. Even the most advanced model, o3-mini, achieves only 59.9% accuracy, highlighting significant challenges in solving high-level scientific problems. Through comprehensive error analysis, exploration of diverse prompting strategies, and Retrieval-Augmented Generation (RAG)-based knowledge augmentation, we identify key areas for improvement, laying the foundation for future advancements.

Supervised fine-tuning (SFT) on domain-specific data is the dominant approach for adapting foundation models to specialized tasks. However, it has been observed that SFT models tend to forget knowledge acquired during pretraining. In vision models, ensembling a pretrained model with its fine-tuned counterpart has been shown to mitigate this issue. In this work, we demonstrate that the same holds for language models, and, more strikingly, we observe an overadaptation phenomenon: the ensemble model not only retains general knowledge from the foundation model but also outperforms the fine-tuned model even on the fine-tuning domain itself. Despite the empirical success of ensembling, a theoretical understanding of its benefits remains underexplored. We develop a formal theoretical analysis of the overadaptation phenomenon. Ensembling mitigates this by balancing two primary sources of error: bias, caused by insufficient fine-tuning, and variance, introduced by overfitting to fine-tuning data. While regularization techniques aim to address this trade-off, we show that ensembling provides a more effective solution. We analyze this phenomenon in over-parameterized linear settings and demonstrate that interpolating between pretrained and fine-tuned weights significantly improves performance. These findings offer theoretical justification for the observed advantages of model ensembling, supported by empirical experiments consistent with our analysis.

Dense retrievers encode texts into embeddings to efficiently retrieve relevant documents from large databases in response to user queries. However, real-world corpora continually evolve, leading to a shift from the original training distribution of the retriever. Without timely updates or retraining, indexing newly emerging documents can degrade retrieval performance for future queries. Thus, identifying when a dense retriever requires an update is critical for maintaining robust retrieval systems. In this paper, we propose a novel task of predicting whether a corpus is out-of-distribution (OOD) relative to a dense retriever before indexing. Addressing this task allows us to proactively manage retriever updates, preventing potential retrieval failures. We introduce GradNormIR, an unsupervised approach that leverages gradient norms to detect OOD corpora effectively. Experiments on the BEIR benchmark demonstrate that GradNormIR enables timely updates of dense retrievers in evolving document collections, significantly enhancing retrieval robustness and efficiency.