Text-to-Image Retrieval (T2IR) is a highly valuable task that aims to match a given textual query to images in a gallery. Existing benchmarks primarily focus on textual queries describing overall image semantics or foreground salient objects, possibly overlooking inconspicuous small objects, especially in complex environments. Such small object retrieval is crucial, as in real-world applications, the targets of interest are not always prominent in the image. Thus, we introduce SORCE (Small Object Retrieval in Complex Environments), a new subfield of T2IR, focusing on retrieving small objects in complex images with textual queries. We propose a new benchmark, SORCE-1K, consisting of images with complex environments and textual queries describing less conspicuous small objects with minimal contextual cues from other salient objects. Preliminary analysis on SORCE-1K finds that existing T2IR methods struggle to capture small objects and encode all the semantics into a single embedding, leading to poor retrieval performance on SORCE-1K. Therefore, we propose to represent each image with multiple distinctive embeddings. We leverage Multimodal Large Language Models (MLLMs) to extract multiple embeddings for each image instructed by a set of Regional Prompts (ReP). Experimental results show that our multi-embedding approach through MLLM and ReP significantly outperforms existing T2IR methods on SORCE-1K. Our experiments validate the effectiveness of SORCE-1K for benchmarking SORCE performances, highlighting the potential of multi-embedding representation and text-customized MLLM features for addressing this task.
In knowledge distillation (KD), logit distillation (LD) aims to transfer class-level knowledge from a more powerful teacher network to a small student model via accurate teacher-student alignment at the logits level. Since high-confidence object classes usually dominate the distillation process, low-probability classes which also contain discriminating information are downplayed in conventional methods, leading to insufficient knowledge transfer. To address this issue, we propose a simple yet effective LD method termed Progressive Class-level Distillation (PCD). In contrast to existing methods which perform all-class ensemble distillation, our PCD approach performs stage-wise distillation for step-by-step knowledge transfer. More specifically, we perform ranking on teacher-student logits difference for identifying distillation priority from scratch, and subsequently divide the entire LD process into multiple stages. Next, bidirectional stage-wise distillation incorporating fine-to-coarse progressive learning and reverse coarse-to-fine refinement is conducted, allowing comprehensive knowledge transfer via sufficient logits alignment within separate class groups in different distillation stages. Extension experiments on public benchmarking datasets demonstrate the superiority of our method compared to state-of-the-arts for both classification and detection tasks.
Multimodal large language models have demonstrated remarkable capabilities in visual understanding, but their application to long-term Earth observation analysis remains limited, primarily focusing on single-temporal or bi-temporal imagery. To address this gap, we introduce DVL-Suite, a comprehensive framework for analyzing long-term urban dynamics through remote sensing imagery. Our suite comprises 15,063 high-resolution (1.0m) multi-temporal images spanning 42 megacities in the U.S. from 2005 to 2023, organized into two components: DVL-Bench and DVL-Instruct. The DVL-Bench includes seven urban understanding tasks, from fundamental change detection (pixel-level) to quantitative analyses (regional-level) and comprehensive urban narratives (scene-level), capturing diverse urban dynamics including expansion/transformation patterns, disaster assessment, and environmental challenges. We evaluate 17 state-of-the-art multimodal large language models and reveal their limitations in long-term temporal understanding and quantitative analysis. These challenges motivate the creation of DVL-Instruct, a specialized instruction-tuning dataset designed to enhance models' capabilities in multi-temporal Earth observation. Building upon this dataset, we develop DVLChat, a baseline model capable of both image-level question-answering and pixel-level segmentation, facilitating a comprehensive understanding of city dynamics through language interactions.
Recent advancements in text-to-image (T2I) generation have enabled models to produce high-quality images from textual descriptions. However, these models often struggle with complex instructions involving multiple objects, attributes, and spatial relationships. Existing benchmarks for evaluating T2I models primarily focus on general text-image alignment and fail to capture the nuanced requirements of complex, multi-faceted prompts. Given this gap, we introduce LongBench-T2I, a comprehensive benchmark specifically designed to evaluate T2I models under complex instructions. LongBench-T2I consists of 500 intricately designed prompts spanning nine diverse visual evaluation dimensions, enabling a thorough assessment of a model's ability to follow complex instructions. Beyond benchmarking, we propose an agent framework (Plan2Gen) that facilitates complex instruction-driven image generation without requiring additional model training. This framework integrates seamlessly with existing T2I models, using large language models to interpret and decompose complex prompts, thereby guiding the generation process more effectively. As existing evaluation metrics, such as CLIPScore, fail to adequately capture the nuances of complex instructions, we introduce an evaluation toolkit that automates the quality assessment of generated images using a set of multi-dimensional metrics. The data and code are released at https://github.com/yczhou001/LongBench-T2I.
Recent advancements in Large Language Models (LLMs) have transformed natural language understanding and generation, leading to extensive benchmarking across diverse tasks. However, cryptanalysis a critical area for data security and encryption has not yet been thoroughly explored in LLM evaluations. To address this gap, we evaluate cryptanalytic potential of state of the art LLMs on encrypted texts generated using a range of cryptographic algorithms. We introduce a novel benchmark dataset comprising diverse plain texts spanning various domains, lengths, writing styles, and topics paired with their encrypted versions. Using zero-shot and few shot settings, we assess multiple LLMs for decryption accuracy and semantic comprehension across different encryption schemes. Our findings reveal key insights into the strengths and limitations of LLMs in side-channel communication while raising concerns about their susceptibility to jailbreaking attacks. This research highlights the dual-use nature of LLMs in security contexts and contributes to the ongoing discussion on AI safety and security.
Cultural content poses challenges for machine translation systems due to the differences in conceptualizations between cultures, where language alone may fail to convey sufficient context to capture region-specific meanings. In this work, we investigate whether images can act as cultural context in multimodal translation. We introduce CaMMT, a human-curated benchmark of over 5,800 triples of images along with parallel captions in English and regional languages. Using this dataset, we evaluate five Vision Language Models (VLMs) in text-only and text+image settings. Through automatic and human evaluations, we find that visual context generally improves translation quality, especially in handling Culturally-Specific Items (CSIs), disambiguation, and correct gender usage. By releasing CaMMT, we aim to support broader efforts in building and evaluating multimodal translation systems that are better aligned with cultural nuance and regional variation.
Automated radiology report generation from chest X-ray (CXR) images has the potential to improve clinical efficiency and reduce radiologists' workload. However, most datasets, including the publicly available MIMIC-CXR and CheXpert Plus, consist entirely of free-form reports, which are inherently variable and unstructured. This variability poses challenges for both generation and evaluation: existing models struggle to produce consistent, clinically meaningful reports, and standard evaluation metrics fail to capture the nuances of radiological interpretation. To address this, we introduce Structured Radiology Report Generation (SRRG), a new task that reformulates free-text radiology reports into a standardized format, ensuring clarity, consistency, and structured clinical reporting. We create a novel dataset by restructuring reports using large language models (LLMs) following strict structured reporting desiderata. Additionally, we introduce SRR-BERT, a fine-grained disease classification model trained on 55 labels, enabling more precise and clinically informed evaluation of structured reports. To assess report quality, we propose F1-SRR-BERT, a metric that leverages SRR-BERT's hierarchical disease taxonomy to bridge the gap between free-text variability and structured clinical reporting. We validate our dataset through a reader study conducted by five board-certified radiologists and extensive benchmarking experiments.
In this paper, we aim to establish a simple, effective, and theoretically grounded benchmark for rigorously probing abstract reasoning in Large Language Models (LLMs). To achieve this, we first develop a mathematic framework that defines abstract reasoning as the ability to: (i) extract essential patterns independent of surface representations, and (ii) apply consistent rules to these abstract patterns. Based on this framework, we introduce two novel complementary metrics: \(\scoreGamma\) measures basic reasoning accuracy, while \(\scoreDelta\) quantifies a model's reliance on specific symbols rather than underlying patterns - a key indicator of true abstraction versus mere memorization. To implement this measurement, we design a benchmark: systematic symbol remapping in rule-based tasks, which forces models to demonstrate genuine pattern recognition beyond superficial token matching. Extensive LLM evaluations using this benchmark (commercial API models, 7B-70B, multi-agent) reveal:1) critical limitations in non-decimal arithmetic and symbolic reasoning; 2) persistent abstraction gaps despite chain-of-thought prompting; and 3) \(\scoreDelta\)'s effectiveness in robustly measuring memory dependence by quantifying performance degradation under symbol remapping, particularly highlighting operand-specific memorization. These findings underscore that current LLMs, despite domain-specific strengths, still lack robust abstract reasoning, highlighting key areas for future improvement.
A critical component in the trustworthiness of LLMs is reliable uncertainty communication, yet LLMs often use assertive language when conveying false claims, leading to over-reliance and eroded trust. We present the first systematic study of $\textit{faithful confidence calibration}$ of LLMs, benchmarking models' ability to use linguistic expressions of uncertainty that $\textit{faithfully reflect}$ their intrinsic uncertainty, across a comprehensive array of models, datasets, and prompting strategies. Our results demonstrate that LLMs largely fail at this task, and that existing interventions are insufficient: standard prompt approaches provide only marginal gains, and existing, factuality-based calibration techniques can even harm faithful calibration. To address this critical gap, we introduce MetaFaith, a novel prompt-based calibration approach inspired by human metacognition. We show that MetaFaith robustly improves faithful calibration across diverse models and task domains, enabling up to 61% improvement in faithfulness and achieving an 83% win rate over original generations as judged by humans.
We present ByzFL, an open-source Python library for developing and benchmarking robust federated learning (FL) algorithms. ByzFL provides a unified and extensible framework that includes implementations of state-of-the-art robust aggregators, a suite of configurable attacks, and tools for simulating a variety of FL scenarios, including heterogeneous data distributions, multiple training algorithms, and adversarial threat models. The library enables systematic experimentation via a single JSON-based configuration file and includes built-in utilities for result visualization. Compatible with PyTorch tensors and NumPy arrays, ByzFL is designed to facilitate reproducible research and rapid prototyping of robust FL solutions. ByzFL is available at https://byzfl.epfl.ch/, with source code hosted on GitHub: https://github.com/LPD-EPFL/byzfl.
Foundation Models (FMs) are large-scale, pre-trained AI systems that have revolutionized natural language processing and computer vision, and are now advancing geospatial analysis and Earth Observation (EO). They promise improved generalization across tasks, scalability, and efficient adaptation with minimal labeled data. However, despite the rapid proliferation of geospatial FMs, their real-world utility and alignment with global sustainability goals remain underexplored. We introduce SustainFM, a comprehensive benchmarking framework grounded in the 17 Sustainable Development Goals with extremely diverse tasks ranging from asset wealth prediction to environmental hazard detection. This study provides a rigorous, interdisciplinary assessment of geospatial FMs and offers critical insights into their role in attaining sustainability goals. Our findings show: (1) While not universally superior, FMs often outperform traditional approaches across diverse tasks and datasets. (2) Evaluating FMs should go beyond accuracy to include transferability, generalization, and energy efficiency as key criteria for their responsible use. (3) FMs enable scalable, SDG-grounded solutions, offering broad utility for tackling complex sustainability challenges. Critically, we advocate for a paradigm shift from model-centric development to impact-driven deployment, and emphasize metrics such as energy efficiency, robustness to domain shifts, and ethical considerations.
Large language models (LLMs) have rapidly advanced and are increasingly capable of tackling complex scientific problems, including those in physics. Despite this progress, current LLMs often fail to emulate the concise, principle-based reasoning characteristic of human experts, instead generating lengthy and opaque solutions. This discrepancy highlights a crucial gap in their ability to apply core physical principles for efficient and interpretable problem solving. To systematically investigate this limitation, we introduce PhySense, a novel principle-based physics reasoning benchmark designed to be easily solvable by experts using guiding principles, yet deceptively difficult for LLMs without principle-first reasoning. Our evaluation across multiple state-of-the-art LLMs and prompt types reveals a consistent failure to align with expert-like reasoning paths, providing insights for developing AI systems with efficient, robust and interpretable principle-based scientific reasoning.
The availability of Large Language Models (LLMs) presents a unique opportunity to reinvigorate research on Knowledge Engineering (KE) automation, a trend already evident in recent efforts developing LLM-based methods and tools for the automatic generation of Competency Questions (CQs). However, the evaluation of these tools lacks standardisation. This undermines the methodological rigour and hinders the replication and comparison of results. To address this gap, we introduce Bench4KE, an extensible API-based benchmarking system for KE automation. Its first release focuses on evaluating tools that generate CQs automatically. CQs are natural language questions used by ontology engineers to define the functional requirements of an ontology. Bench4KE provides a curated gold standard consisting of CQ datasets from four real-world ontology projects. It uses a suite of similarity metrics to assess the quality of the CQs generated. We present a comparative analysis of four recent CQ generation systems, which are based on LLMs, establishing a baseline for future research. Bench4KE is also designed to accommodate additional KE automation tasks, such as SPARQL query generation, ontology testing and drafting. Code and datasets are publicly available under the Apache 2.0 license.
The advent of foundation models, particularly Vision-Language Models (VLMs) and Multi-modal Large Language Models (MLLMs), has redefined the frontiers of artificial intelligence, enabling remarkable generalization across diverse tasks with minimal or no supervision. Yet, their potential in biometric recognition and analysis remains relatively underexplored. In this work, we introduce a comprehensive benchmark that evaluates the zero-shot and few-shot performance of state-of-the-art publicly available VLMs and MLLMs across six biometric tasks spanning the face and iris modalities: face verification, soft biometric attribute prediction (gender and race), iris recognition, presentation attack detection (PAD), and face manipulation detection (morphs and deepfakes). A total of 41 VLMs were used in this evaluation. Experiments show that embeddings from these foundation models can be used for diverse biometric tasks with varying degrees of success. For example, in the case of face verification, a True Match Rate (TMR) of 96.77 percent was obtained at a False Match Rate (FMR) of 1 percent on the Labeled Face in the Wild (LFW) dataset, without any fine-tuning. In the case of iris recognition, the TMR at 1 percent FMR on the IITD-R-Full dataset was 97.55 percent without any fine-tuning. Further, we show that applying a simple classifier head to these embeddings can help perform DeepFake detection for faces, Presentation Attack Detection (PAD) for irides, and extract soft biometric attributes like gender and ethnicity from faces with reasonably high accuracy. This work reiterates the potential of pretrained models in achieving the long-term vision of Artificial General Intelligence.
CAPTCHAs have been a critical bottleneck for deploying web agents in real-world applications, often blocking them from completing end-to-end automation tasks. While modern multimodal LLM agents have demonstrated impressive performance in static perception tasks, their ability to handle interactive, multi-step reasoning challenges like CAPTCHAs is largely untested. To address this gap, we introduce Open CaptchaWorld, the first web-based benchmark and platform specifically designed to evaluate the visual reasoning and interaction capabilities of MLLM-powered agents through diverse and dynamic CAPTCHA puzzles. Our benchmark spans 20 modern CAPTCHA types, totaling 225 CAPTCHAs, annotated with a new metric we propose: CAPTCHA Reasoning Depth, which quantifies the number of cognitive and motor steps required to solve each puzzle. Experimental results show that humans consistently achieve near-perfect scores, state-of-the-art MLLM agents struggle significantly, with success rates at most 40.0% by Browser-Use Openai-o3, far below human-level performance, 93.3%. This highlights Open CaptchaWorld as a vital benchmark for diagnosing the limits of current multimodal agents and guiding the development of more robust multimodal reasoning systems. Code and Data are available at this https URL.
The recent rapid adoption of large language models (LLMs) highlights the critical need for benchmarking their fairness. Conventional fairness metrics, which focus on discrete accuracy-based evaluations (i.e., prediction correctness), fail to capture the implicit impact of model uncertainty (e.g., higher model confidence about one group over another despite similar accuracy). To address this limitation, we propose an uncertainty-aware fairness metric, UCerF, to enable a fine-grained evaluation of model fairness that is more reflective of the internal bias in model decisions compared to conventional fairness measures. Furthermore, observing data size, diversity, and clarity issues in current datasets, we introduce a new gender-occupation fairness evaluation dataset with 31,756 samples for co-reference resolution, offering a more diverse and suitable dataset for evaluating modern LLMs. We establish a benchmark, using our metric and dataset, and apply it to evaluate the behavior of ten open-source LLMs. For example, Mistral-7B exhibits suboptimal fairness due to high confidence in incorrect predictions, a detail overlooked by Equalized Odds but captured by UCerF. Overall, our proposed LLM benchmark, which evaluates fairness with uncertainty awareness, paves the way for developing more transparent and accountable AI systems.
Despite recent advances in large language models (LLMs) for materials science, there is a lack of benchmarks for evaluating their domain-specific knowledge and complex reasoning abilities. To bridge this gap, we introduce MSQA, a comprehensive evaluation benchmark of 1,757 graduate-level materials science questions in two formats: detailed explanatory responses and binary True/False assessments. MSQA distinctively challenges LLMs by requiring both precise factual knowledge and multi-step reasoning across seven materials science sub-fields, such as structure-property relationships, synthesis processes, and computational modeling. Through experiments with 10 state-of-the-art LLMs, we identify significant gaps in current LLM performance. While API-based proprietary LLMs achieve up to 84.5% accuracy, open-source (OSS) LLMs peak around 60.5%, and domain-specific LLMs often underperform significantly due to overfitting and distributional shifts. MSQA represents the first benchmark to jointly evaluate the factual and reasoning capabilities of LLMs crucial for LLMs in advanced materials science.
We present Yambda-5B, a large-scale open dataset sourced from the Yandex.Music streaming platform. Yambda-5B contains 4.79 billion user-item interactions from 1 million users across 9.39 million tracks. The dataset includes two primary types of interactions: implicit feedback (listening events) and explicit feedback (likes, dislikes, unlikes and undislikes). In addition, we provide audio embeddings for most tracks, generated by a convolutional neural network trained on audio spectrograms. A key distinguishing feature of Yambda-5B is the inclusion of the is_organic flag, which separates organic user actions from recommendation-driven events. This distinction is critical for developing and evaluating machine learning algorithms, as Yandex.Music relies on recommender systems to personalize track selection for users. To support rigorous benchmarking, we introduce an evaluation protocol based on a Global Temporal Split, allowing recommendation algorithms to be assessed in conditions that closely mirror real-world use. We report benchmark results for standard baselines (ItemKNN, iALS) and advanced models (SANSA, SASRec) using a variety of evaluation metrics. By releasing Yambda-5B to the community, we aim to provide a readily accessible, industrial-scale resource to advance research, foster innovation, and promote reproducible results in recommender systems.
Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect prompt injection. Current evaluations of this threat either lack support realistic but controlled environments or ignore hybrid web-OS attack scenarios involving both interfaces. To address this, we propose RedTeamCUA, an adversarial testing framework featuring a novel hybrid sandbox that integrates a VM-based OS environment with Docker-based web platforms. Our sandbox supports key features tailored for red teaming, such as flexible adversarial scenario configuration, and a setting that decouples adversarial evaluation from navigational limitations of CUAs by initializing tests directly at the point of an adversarial injection. Using RedTeamCUA, we develop RTC-Bench, a comprehensive benchmark with 864 examples that investigate realistic, hybrid web-OS attack scenarios and fundamental security vulnerabilities. Benchmarking current frontier CUAs identifies significant vulnerabilities: Claude 3.7 Sonnet | CUA demonstrates an ASR of 42.9%, while Operator, the most secure CUA evaluated, still exhibits an ASR of 7.6%. Notably, CUAs often attempt to execute adversarial tasks with an Attempt Rate as high as 92.5%, although failing to complete them due to capability limitations. Nevertheless, we observe concerning ASRs of up to 50% in realistic end-to-end settings, with the recently released frontier Claude 4 Opus | CUA showing an alarming ASR of 48%, demonstrating that indirect prompt injection presents tangible risks for even advanced CUAs despite their capabilities and safeguards. Overall, RedTeamCUA provides an essential framework for advancing realistic, controlled, and systematic analysis of CUA vulnerabilities, highlighting the urgent need for robust defenses to indirect prompt injection prior to real-world deployment.
Process Reward Models (PRMs) are crucial in complex reasoning and problem-solving tasks (e.g., LLM agents with long-horizon decision-making) by verifying the correctness of each intermediate reasoning step. In real-world scenarios, LLMs may apply various reasoning patterns (e.g., decomposition) to solve a problem, potentially suffering from errors under various reasoning patterns. Therefore, PRMs are required to identify errors under various reasoning patterns during the reasoning process. However, existing benchmarks mainly focus on evaluating PRMs with stepwise correctness, ignoring a systematic evaluation of PRMs under various reasoning patterns. To mitigate this gap, we introduce Socratic-PRMBench, a new benchmark to evaluate PRMs systematically under six reasoning patterns, including Transformation, Decomposition, Regather, Deduction, Verification, and Integration. Socratic-PRMBench}comprises 2995 reasoning paths with flaws within the aforementioned six reasoning patterns. Through our experiments on both PRMs and LLMs prompted as critic models, we identify notable deficiencies in existing PRMs. These observations underscore the significant weakness of current PRMs in conducting evaluations on reasoning steps under various reasoning patterns. We hope Socratic-PRMBench can serve as a comprehensive testbed for systematic evaluation of PRMs under diverse reasoning patterns and pave the way for future development of PRMs.