FireBench: Evaluating Instruction Following in Enterprise and API-Driven LLM Applications

Instruction following is critical for LLMs deployed in enterprise and API-driven settings, where strict adherence to output formats, content constraints, and procedural requirements is essential for enabling reliable LLM-assisted workflows. However, existing instruction following benchmarks predominantly evaluate natural language generation constraints that reflect the needs of chat assistants rather than enterprise users. To bridge this gap, we introduce FireBench, an LLM instruction following benchmark grounded in real-world enterprise and API usage patterns. FireBench evaluates six core capability dimensions across diverse applications including information extraction, customer support, and coding agents, comprising over 2,400 samples. We evaluate 11 LLMs and present key findings on their instruction following behavior in enterprise scenarios. We open-source FireBench at fire-bench.com to help users assess model suitability, support model developers in diagnosing performance, and invite community contributions.

LiveNewsBench: Evaluating LLM Web Search Capabilities with Freshly Curated News

Large Language Models (LLMs) with agentic web search capabilities show strong potential for tasks requiring real-time information access and complex fact retrieval, yet evaluating such systems remains challenging. We introduce \bench, a rigorous and regularly updated benchmark designed to assess the agentic web search abilities of LLMs. \bench automatically generates fresh question-answer pairs from recent news articles, ensuring that questions require information beyond an LLM's training data and enabling clear separation between internal knowledge and search capability. The benchmark features intentionally difficult questions requiring multi-hop search queries, page visits, and reasoning, making it well-suited for evaluating agentic search behavior. Our automated data curation and question generation pipeline enables frequent benchmark updates and supports construction of a large-scale training dataset for agentic web search models, addressing the scarcity of such data in the research community. To ensure reliable evaluation, we include a subset of human-verified samples in the test set. We evaluate a broad range of systems using \bench, including commercial and open-weight LLMs as well as LLM-based web search APIs. The leaderboard, datasets, and code are publicly available at livenewsbench.com.

Forecasting Communication Derailments Through Conversation Generation

Forecasting communication derailment can be useful in real-world settings such as online content moderation, conflict resolution, and business negotiations. However, despite language models' success at identifying offensive speech present in conversations, they struggle to forecast future communication derailments. In contrast to prior work that predicts conversation outcomes solely based on the past conversation history, our approach samples multiple future conversation trajectories conditioned on existing conversation history using a fine-tuned LLM. It predicts the communication outcome based on the consensus of these trajectories. We also experimented with leveraging socio-linguistic attributes, which reflect turn-level conversation dynamics, as guidance when generating future conversations. Our method of future conversation trajectories surpasses state-of-the-art results on English communication derailment prediction benchmarks and demonstrates significant accuracy gains in ablation studies.

Deep Learning Waveform Modeling for Wideband Optical Fiber Channel Transmission: Challenges and Potential Solutions

Fast and accurate optical fiber communication simulation system are crucial for optimizing optical networks, developing digital signal processing algorithms, and performing end-to-end (E2E) optimization. Deep learning (DL) has emerged as a valuable tool to reduce the complexity of traditional waveform simulation methods, such as split-step Fourier method (SSFM). DL-based schemes have achieved high accuracy and low complexity fiber channel waveform modeling as its strong nonlinear fitting ability and high efficiency in parallel computation. However, DL-based schemes are mainly utilized in single-channel and few-channel wavelength division multiplexing (WDM) systems. The applicability of DL-based schemes in wideband WDM systems remains uncertain due to the lack of comparison under consistent standards and scenarios. In this paper, we propose a DSP-assisted accuracy evaluation method to evaluate the performance for DL-based schemes, from the aspects of waveform and quality of transmission (QoT) errors. We compare the performance of five various DL-based schemes and valid the effectiveness of DSP-assisted method in WDM systems. Results suggest that feature decoupled distributed (FDD) achieves the better accuracy, especially in large-channel and high-rate scenarios. Furthermore, we find that the accuracy of FDD still exhibit significant degradation with the number of WDM channels and transmission rates exceeds 15 and 100 GBaud, indicating challenges for wideband applications. We further analyze the reasons of performance degradation from the perspective of increased linearity and nonlinearity and discuss potential solutions including further decoupling scheme designs and improvement in DL models. Despite DL-based schemes remain challenges in wideband WDM systems, they have strong potential for high-accuracy and low-complexity optical fiber channel waveform modeling.

Asynchronous Federated Clustering with Unknown Number of Clusters

Federated Clustering (FC) is crucial to mining knowledge from unlabeled non-Independent Identically Distributed (non-IID) data provided by multiple clients while preserving their privacy. Most existing attempts learn cluster distributions at local clients, and then securely pass the desensitized information to the server for aggregation. However, some tricky but common FC problems are still relatively unexplored, including the heterogeneity in terms of clients' communication capacity and the unknown number of proper clusters $k^*$. To further bridge the gap between FC and real application scenarios, this paper first shows that the clients' communication asynchrony and unknown $k^*$ are complex coupling problems, and then proposes an Asynchronous Federated Cluster Learning (AFCL) method accordingly. It spreads the excessive number of seed points to the clients as a learning medium and coordinates them across the clients to form a consensus. To alleviate the distribution imbalance cumulated due to the unforeseen asynchronous uploading from the heterogeneous clients, we also design a balancing mechanism for seeds updating. As a result, the seeds gradually adapt to each other to reveal a proper number of clusters. Extensive experiments demonstrate the efficacy of AFCL.

SketchFill: Sketch-Guided Code Generation for Imputing Derived Missing Values

Missing value is a critical issue in data science, significantly impacting the reliability of analyses and predictions. Missing value imputation (MVI) is a longstanding problem because it highly relies on domain knowledge. Large language models (LLMs) have emerged as a promising tool for data cleaning, including MVI for tabular data, offering advanced capabilities for understanding and generating content. However, despite their promise, existing LLM techniques such as in-context learning and Chain-of-Thought (CoT) often fall short in guiding LLMs to perform complex reasoning for MVI, particularly when imputing derived missing values, which require mathematical formulas and data relationships across rows and columns. This gap underscores the need for further advancements in LLM methodologies to enhance their reasoning capabilities for more reliable imputation outcomes. To fill this gap, we propose SketchFill, a novel sketch-based method to guide LLMs in generating accurate formulas to impute missing numerical values. Our experimental results demonstrate that SketchFill significantly outperforms state-of-the-art methods, achieving 56.2% higher accuracy than CoT-based methods and 78.8% higher accuracy than MetaGPT. This sets a new standard for automated data cleaning and advances the field of MVI for numerical values.

Improve the Fitting Accuracy of Deep Learning for the Nonlinear Schrödinger Equation Using Linear Feature Decoupling Method

We utilize the Feature Decoupling Distributed (FDD) method to enhance the capability of deep learning to fit the Nonlinear Schrodinger Equation (NLSE), significantly reducing the NLSE loss compared to non decoupling model.

Multi-modal Learnable Queries for Image Aesthetics Assessment

Image aesthetics assessment (IAA) is attracting wide interest with the prevalence of social media. The problem is challenging due to its subjective and ambiguous nature. Instead of directly extracting aesthetic features solely from the image, user comments associated with an image could potentially provide complementary knowledge that is useful for IAA. With existing large-scale pre-trained models demonstrating strong capabilities in extracting high-quality transferable visual and textual features, learnable queries are shown to be effective in extracting useful features from the pre-trained visual features. Therefore, in this paper, we propose MMLQ, which utilizes multi-modal learnable queries to extract aesthetics-related features from multi-modal pre-trained features. Extensive experimental results demonstrate that MMLQ achieves new state-of-the-art performance on multi-modal IAA, beating previous methods by 7.7% and 8.3% in terms of SRCC and PLCC, respectively.

Style-Consistent 3D Indoor Scene Synthesis with Decoupled Objects

Controllable 3D indoor scene synthesis stands at the forefront of technological progress, offering various applications like gaming, film, and augmented/virtual reality. The capability to stylize and de-couple objects within these scenarios is a crucial factor, providing an advanced level of control throughout the editing process. This control extends not just to manipulating geometric attributes like translation and scaling but also includes managing appearances, such as stylization. Current methods for scene stylization are limited to applying styles to the entire scene, without the ability to separate and customize individual objects. Addressing the intricacies of this challenge, we introduce a unique pipeline designed for synthesis 3D indoor scenes. Our approach involves strategically placing objects within the scene, utilizing information from professionally designed bounding boxes. Significantly, our pipeline prioritizes maintaining style consistency across multiple objects within the scene, ensuring a cohesive and visually appealing result aligned with the desired aesthetic. The core strength of our pipeline lies in its ability to generate 3D scenes that are not only visually impressive but also exhibit features like photorealism, multi-view consistency, and diversity. These scenes are crafted in response to various natural language prompts, demonstrating the versatility and adaptability of our model.

iComMa: Inverting 3D Gaussians Splatting for Camera Pose Estimation via Comparing and Matching

We present a method named iComMa to address the 6D pose estimation problem in computer vision. The conventional pose estimation methods typically rely on the target's CAD model or necessitate specific network training tailored to particular object classes. Some existing methods address mesh-free 6D pose estimation by employing the inversion of a Neural Radiance Field (NeRF), aiming to overcome the aforementioned constraints. However, it still suffers from adverse initializations. By contrast, we model the pose estimation as the problem of inverting the 3D Gaussian Splatting (3DGS) with both the comparing and matching loss. In detail, a render-and-compare strategy is adopted for the precise estimation of poses. Additionally, a matching module is designed to enhance the model's robustness against adverse initializations by minimizing the distances between 2D keypoints. This framework systematically incorporates the distinctive characteristics and inherent rationale of render-and-compare and matching-based approaches. This comprehensive consideration equips the framework to effectively address a broader range of intricate and challenging scenarios, including instances with substantial angular deviations, all while maintaining a high level of prediction accuracy. Experimental results demonstrate the superior precision and robustness of our proposed jointly optimized framework when evaluated on synthetic and complex real-world data in challenging scenarios.