COREval: A Comprehensive and Objective Benchmark for Evaluating the Remote Sensing Capabilities of Large Vision-Language Models

With the rapid development of Large Vision-Language Models (VLMs), both general-domain models and those specifically tailored for remote sensing Earth observation, have demonstrated exceptional perception and reasoning abilities within this specific field. However, the current absence of a comprehensive benchmark for holistically evaluating the remote sensing capabilities of these VLMs represents a significant gap. To bridge this gap, we propose COREval, the first benchmark designed to comprehensively and objectively evaluate the hierarchical remote sensing capabilities of VLMs. Concentrating on 2 primary capability dimensions essential to remote sensing: perception and reasoning, we further categorize 6 secondary dimensions and 22 leaf tasks to ensure a well-rounded assessment coverage for this specific field. COREval guarantees the quality of the total of 6,263 problems through a rigorous process of data collection from 50 globally distributed cities, question construction and quality control, and the format of multiple-choice questions with definitive answers allows for an objective and straightforward evaluation of VLM performance. We conducted a holistic evaluation of 13 prominent open-source VLMs from both the general and remote sensing domains, highlighting current shortcomings in their remote sensing capabilities and providing directions for improvements in their application within this specialized context. We hope that COREval will serve as a valuable resource and offer deeper insights into the challenges and potential of VLMs in the field of remote sensing.

MapEval: Towards Unified, Robust and Efficient SLAM Map Evaluation Framework

Evaluating massive-scale point cloud maps in Simultaneous Localization and Mapping (SLAM) remains challenging, primarily due to the absence of unified, robust and efficient evaluation frameworks. We present MapEval, an open-source framework for comprehensive quality assessment of point cloud maps, specifically addressing SLAM scenarios where ground truth map is inherently sparse compared to the mapped environment. Through systematic analysis of existing evaluation metrics in SLAM applications, we identify their fundamental limitations and establish clear guidelines for consistent map quality assessment. Building upon these insights, we propose a novel Gaussian-approximated Wasserstein distance in voxelized space, enabling two complementary metrics under the same error standard: Voxelized Average Wasserstein Distance (AWD) for global geometric accuracy and Spatial Consistency Score (SCS) for local consistency evaluation. This theoretical foundation leads to significant improvements in both robustness against noise and computational efficiency compared to conventional metrics. Extensive experiments on both simulated and real-world datasets demonstrate that MapEval achieves at least \SI{100}{}-\SI{500}{} times faster while maintaining evaluation integrity. The MapEval library\footnote{\texttt{https://github.com/JokerJohn/Cloud\_Map\_Evaluation}} will be publicly available to promote standardized map evaluation practices in the robotics community.

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Training large language models (LLMs) to spend more time thinking and reflection before responding is crucial for effectively solving complex reasoning tasks in fields such as science, coding, and mathematics. However, the effectiveness of mechanisms like self-reflection and self-correction depends on the model's capacity to accurately assess its own performance, which can be limited by factors such as initial accuracy, question difficulty, and the lack of external feedback. In this paper, we delve into a two-player paradigm that separates the roles of reasoning and critique models, where the critique model provides step-level feedback to supervise the reasoning (actor) model during both test-time and train-time. We first propose AutoMathCritique, an automated and scalable framework for collecting critique data, resulting in a dataset of $76,321$ responses paired with step-level feedback. Fine-tuning language models with this dataset enables them to generate natural language feedback for mathematical reasoning. We demonstrate that the critique models consistently improve the actor's performance on difficult queries at test-time, especially when scaling up inference-time computation. Motivated by these findings, we introduce the critique-based supervision to the actor's self-training process, and propose a critique-in-the-loop self-improvement method. Experiments show that the method improves the actor's exploration efficiency and solution diversity, especially on challenging queries, leading to a stronger reasoning model. Lastly, we take the preliminary step to explore training self-talk reasoning models via critique supervision and showcase its potential. Our code and datasets are at \href{https://mathcritique.github.io/}{https://mathcritique.github.io/}.

Investigating Idiomaticity in Word Representations

Idiomatic expressions are an integral part of human languages, often used to express complex ideas in compressed or conventional ways (e.g. eager beaver as a keen and enthusiastic person). However, their interpretations may not be straightforwardly linked to the meanings of their individual components in isolation and this may have an impact for compositional approaches. In this paper, we investigate to what extent word representation models are able to go beyond compositional word combinations and capture multiword expression idiomaticity and some of the expected properties related to idiomatic meanings. We focus on noun compounds of varying levels of idiomaticity in two languages (English and Portuguese), presenting a dataset of minimal pairs containing human idiomaticity judgments for each noun compound at both type and token levels, their paraphrases and their occurrences in naturalistic and sense-neutral contexts, totalling 32,200 sentences. We propose this set of minimal pairs for evaluating how well a model captures idiomatic meanings, and define a set of fine-grained metrics of Affinity and Scaled Similarity, to determine how sensitive the models are to perturbations that may lead to changes in idiomaticity. The results obtained with a variety of representative and widely used models indicate that, despite superficial indications to the contrary in the form of high similarities, idiomaticity is not yet accurately represented in current models. Moreover, the performance of models with different levels of contextualisation suggests that their ability to capture context is not yet able to go beyond more superficial lexical clues provided by the words and to actually incorporate the relevant semantic clues needed for idiomaticity.

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling

Self-improvement methods enable large language models (LLMs) to generate solutions themselves and iteratively train on filtered, high-quality rationales. This process proves effective and reduces the reliance on human supervision in LLMs' reasoning, but the performance soon plateaus. We delve into the process and find that models tend to over-sample on easy queries and under-sample on queries they have yet to master. As iterations proceed, this imbalance in sampling is exacerbated, leading to a long-tail distribution where solutions to difficult queries almost diminish. This phenomenon limits the performance gain of self-improving models. A straightforward solution is brute-force sampling to balance the distribution, which significantly raises computational costs. In this paper, we introduce Guided Self-Improvement (GSI), a strategy aimed at improving the efficiency of sampling challenging heavy-tailed data. It leverages Socratic-style guidance signals to help LLM reasoning with complex queries, reducing the exploration effort and minimizing computational overhead. Experiments on four models across diverse mathematical tasks show that GSI strikes a balance between performance and efficiency, while also being effective on held-out tasks.

Distill Visual Chart Reasoning Ability from LLMs to MLLMs

Solving complex chart Q&A tasks requires advanced visual reasoning abilities in multimodal large language models (MLLMs). Recent studies highlight that these abilities consist of two main parts: recognizing key information from visual inputs and conducting reasoning over it. Thus, a promising approach to enhance MLLMs is to construct relevant training data focusing on the two aspects. However, collecting and annotating complex charts and questions is costly and time-consuming, and ensuring the quality of annotated answers remains a challenge. In this paper, we propose Code-as-Intermediary Translation (CIT), a cost-effective, efficient and easily scalable data synthesis method for distilling visual reasoning abilities from LLMs to MLLMs. The code serves as an intermediary that translates visual chart representations into textual representations, enabling LLMs to understand cross-modal information. Specifically, we employ text-based synthesizing techniques to construct chart-plotting code and produce ReachQA, a dataset containing 3k reasoning-intensive charts and 20k Q&A pairs to enhance both recognition and reasoning abilities. Experiments show that when fine-tuned with our data, models not only perform well on chart-related benchmarks, but also demonstrate improved multimodal reasoning abilities on general mathematical benchmarks like MathVista. The code and dataset are publicly available at https://github.com/hewei2001/ReachQA.

Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs

Vision-language large models have achieved remarkable success in various multi-modal tasks, yet applying them to video understanding remains challenging due to the inherent complexity and computational demands of video data. While training-based video-LLMs deliver high performance, they often require substantial resources for training and inference. Conversely, training-free approaches offer a more efficient alternative by adapting pre-trained image-LLMs models for video tasks without additional training, but they face inference efficiency bottlenecks due to the large number of visual tokens generated from video frames. In this work, we present a novel prompt-guided visual perception framework (abbreviated as \emph{Free Video-LLM}) for efficient inference of training-free video LLMs. The proposed framework decouples spatial-temporal dimension and performs temporal frame sampling and spatial RoI cropping respectively based on task-specific prompts. Our method effectively reduces the number of visual tokens while maintaining high performance across multiple video question-answering benchmarks. Extensive experiments demonstrate that our approach achieves competitive results with significantly fewer tokens, offering an optimal trade-off between accuracy and computational efficiency compared to state-of-the-art video LLMs. The code will be available at \url{https://github.com/contrastive/FreeVideoLLM}.

Advancing H&E-to-IHC Stain Translation in Breast Cancer: A Multi-Magnification and Attention-Based Approach

Breast cancer presents a significant healthcare challenge globally, demanding precise diagnostics and effective treatment strategies, where histopathological examination of Hematoxylin and Eosin (H&E) stained tissue sections plays a central role. Despite its importance, evaluating specific biomarkers like Human Epidermal Growth Factor Receptor 2 (HER2) for personalized treatment remains constrained by the resource-intensive nature of Immunohistochemistry (IHC). Recent strides in deep learning, particularly in image-to-image translation, offer promise in synthesizing IHC-HER2 slides from H\&E stained slides. However, existing methodologies encounter challenges, including managing multiple magnifications in pathology images and insufficient focus on crucial information during translation. To address these issues, we propose a novel model integrating attention mechanisms and multi-magnification information processing. Our model employs a multi-magnification processing strategy to extract and utilize information from various magnifications within pathology images, facilitating robust image translation. Additionally, an attention module within the generative network prioritizes critical information for image distribution translation while minimizing less pertinent details. Rigorous testing on a publicly available breast cancer dataset demonstrates superior performance compared to existing methods, establishing our model as a state-of-the-art solution in advancing pathology image translation from H&E to IHC staining.

CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models

Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging and domain-specific task, such as finance, has not been fully explored. In this paper, we present CFinBench: a meticulously crafted, the most comprehensive evaluation benchmark to date, for assessing the financial knowledge of LLMs under Chinese context. In practice, to better align with the career trajectory of Chinese financial practitioners, we build a systematic evaluation from 4 first-level categories: (1) Financial Subject: whether LLMs can memorize the necessary basic knowledge of financial subjects, such as economics, statistics and auditing. (2) Financial Qualification: whether LLMs can obtain the needed financial qualified certifications, such as certified public accountant, securities qualification and banking qualification. (3) Financial Practice: whether LLMs can fulfill the practical financial jobs, such as tax consultant, junior accountant and securities analyst. (4) Financial Law: whether LLMs can meet the requirement of financial laws and regulations, such as tax law, insurance law and economic law. CFinBench comprises 99,100 questions spanning 43 second-level categories with 3 question types: single-choice, multiple-choice and judgment. We conduct extensive experiments of 50 representative LLMs with various model size on CFinBench. The results show that GPT4 and some Chinese-oriented models lead the benchmark, with the highest average accuracy being 60.16%, highlighting the challenge presented by CFinBench. The dataset and evaluation code are available at https://cfinbench.github.io/.

Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Loss

Accurately modeling idiomatic or non-compositional language has been a longstanding challenge in Natural Language Processing (NLP). This is partly because these expressions do not derive their meanings solely from their constituent words, but also due to the scarcity of relevant data resources, and their impact on the performance of downstream tasks such as machine translation and simplification. In this paper we propose an approach to model idiomaticity effectively using a triplet loss that incorporates the asymmetric contribution of components words to an idiomatic meaning for training language models by using adaptive contrastive learning and resampling miners to build an idiomatic-aware learning objective. Our proposed method is evaluated on a SemEval challenge and outperforms previous alternatives significantly in many metrics.