Despite recent progress in 3D-LLMs, they remain limited in accurately grounding language to visual and spatial elements in 3D environments. This limitation stems in part from training data that focuses on language reasoning rather than spatial understanding due to scarce 3D resources, leaving inherent grounding biases unresolved. T o address this, we propose 3D scene editing as a key mechanism to generate precise visual counterfactuals that mitigate these biases through fine-grained spatial manipulation, without requiring costly scene reconstruction or large-scale 3D data collection. Furthermore, to make these edits targeted and directly address the specific weaknesses of the model, we introduce DEER-3D, an error-driven framework following a structured "Decompose, Diagnostic Evaluation, Edit, and Re-train" workflow, rather than broadly or randomly augmenting data as in conventional approaches. Specifically, upon identifying a grounding failure of the 3D-LLM, our framework first diagnoses the exact predicate-level error (e.g., attribute or spatial relation). It then executes minimal, predicate-aligned 3D scene edits, such as recoloring or repositioning, to produce targeted counterfactual supervision for iterative model fine-tuning, significantly enhancing grounding accuracy. W e evaluate our editing pipeline across multiple benchmarks for 3D grounding and scene understanding tasks, consistently demonstrating improvements across all evaluated datasets through iterative refinement. DEER-3D underscores the effectiveness of targeted, error-driven scene editing in bridging linguistic reasoning capabilities with spatial grounding in 3D LLMs.

Accurate segmentation of vestibular schwannoma (VS) on Magnetic Resonance Imaging (MRI) is essential for patient management but often requires time-intensive manual annotations by experts. While recent advances in deep learning (DL) have facilitated automated segmentation, challenges remain in achieving robust performance across diverse datasets and complex clinical cases. We present an annotated dataset stemming from a bootstrapped DL-based framework for iterative segmentation and quality refinement of VS in MRI. We combine data from multiple centres and rely on expert consensus for trustworthiness of the annotations. We show that our approach enables effective and resource-efficient generalisation of automated segmentation models to a target data distribution. The framework achieved a significant improvement in segmentation accuracy with a Dice Similarity Coefficient (DSC) increase from 0.9125 to 0.9670 on our target internal validation dataset, while maintaining stable performance on representative external datasets. Expert evaluation on 143 scans further highlighted areas for model refinement, revealing nuanced cases where segmentation required expert intervention. The proposed approach is estimated to enhance efficiency by approximately 37.4% compared to the conventional manual annotation process. Overall, our human-in-the-loop model training approach achieved high segmentation accuracy, highlighting its potential as a clinically adaptable and generalisable strategy for automated VS segmentation in diverse clinical settings. The dataset includes 190 patients, with tumour annotations available for 534 longitudinal contrast-enhanced T1-weighted (T1CE) scans from 184 patients, and non-annotated T2-weighted scans from 6 patients. This dataset is publicly accessible on The Cancer Imaging Archive (TCIA) (https://doi.org/10.7937/bq0z-xa62).

Large language models (LLMs) have recently enabled coding agents capable of generating, executing, and revising visualization code. However, existing models often fail in practical workflows due to limited language coverage, unreliable execution, and lack of iterative correction mechanisms. Progress has been constrained by narrow datasets and benchmarks that emphasize single-round generation and single-language tasks. To address these challenges, we introduce three complementary resources for advancing visualization coding agents. VisCode-Multi-679K is a large-scale, supervised dataset containing 679K validated and executable visualization samples with multi-turn correction dialogues across 12 programming languages. VisPlotBench is a benchmark for systematic evaluation, featuring executable tasks, rendered outputs, and protocols for both initial generation and multi-round self-debug. Finally, we present VisCoder2, a family of multi-language visualization models trained on VisCode-Multi-679K. Experiments show that VisCoder2 significantly outperforms strong open-source baselines and approaches the performance of proprietary models like GPT-4.1, with further gains from iterative self-debug, reaching 82.4% overall execution pass rate at the 32B scale, particularly in symbolic or compiler-dependent languages.

Large language models (LLMs) often struggle with visualization tasks like plotting diagrams, charts, where success depends on both code correctness and visual semantics. Existing instruction-tuning datasets lack execution-grounded supervision and offer limited support for iterative code correction, resulting in fragile and unreliable plot generation. We present VisCode-200K, a large-scale instruction tuning dataset for Python-based visualization and self-correction. It contains over 200K examples from two sources: (1) validated plotting code from open-source repositories, paired with natural language instructions and rendered plots; and (2) 45K multi-turn correction dialogues from Code-Feedback, enabling models to revise faulty code using runtime feedback. We fine-tune Qwen2.5-Coder-Instruct on VisCode-200K to create VisCoder, and evaluate it on PandasPlotBench. VisCoder significantly outperforms strong open-source baselines and approaches the performance of proprietary models like GPT-4o-mini. We further adopt a self-debug evaluation protocol to assess iterative repair, demonstrating the benefits of feedback-driven learning for executable, visually accurate code generation.

Large Vision Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet they also exhibit notable social biases. These biases often manifest as unintended associations between neutral concepts and sensitive human attributes, leading to disparate model behaviors across demographic groups. While existing studies primarily focus on detecting and quantifying such biases, they offer limited insight into the underlying mechanisms within the models. To address this gap, we propose an explanatory framework that combines information flow analysis with multi-round dialogue evaluation, aiming to understand the origin of social bias from the perspective of imbalanced internal information utilization. Specifically, we first identify high-contribution image tokens involved in the model's reasoning process for neutral questions via information flow analysis. Then, we design a multi-turn dialogue mechanism to evaluate the extent to which these key tokens encode sensitive information. Extensive experiments reveal that LVLMs exhibit systematic disparities in information usage when processing images of different demographic groups, suggesting that social bias is deeply rooted in the model's internal reasoning dynamics. Furthermore, we complement our findings from a textual modality perspective, showing that the model's semantic representations already display biased proximity patterns, thereby offering a cross-modal explanation of bias formation.

We introduce Fraud-R1, a benchmark designed to evaluate LLMs' ability to defend against internet fraud and phishing in dynamic, real-world scenarios. Fraud-R1 comprises 8,564 fraud cases sourced from phishing scams, fake job postings, social media, and news, categorized into 5 major fraud types. Unlike previous benchmarks, Fraud-R1 introduces a multi-round evaluation pipeline to assess LLMs' resistance to fraud at different stages, including credibility building, urgency creation, and emotional manipulation. Furthermore, we evaluate 15 LLMs under two settings: 1. Helpful-Assistant, where the LLM provides general decision-making assistance, and 2. Role-play, where the model assumes a specific persona, widely used in real-world agent-based interactions. Our evaluation reveals the significant challenges in defending against fraud and phishing inducement, especially in role-play settings and fake job postings. Additionally, we observe a substantial performance gap between Chinese and English, underscoring the need for improved multilingual fraud detection capabilities.

Large language models (LLMs) excel at answering questions but remain passive learners--absorbing static data without the ability to question and refine knowledge. This paper explores how LLMs can transition to interactive, question-driven learning through student-teacher dialogues. We introduce INTERACT (INTEReractive Learning for Adaptive Concept Transfer), a framework in which a "student" LLM engages a "teacher" LLM through iterative inquiries to acquire knowledge across 1,347 contexts, including song lyrics, news articles, movie plots, academic papers, and images. Our experiments show that across a wide range of scenarios and LLM architectures, interactive learning consistently enhances performance, achieving up to a 25% improvement, with 'cold-start' student models matching static learning baselines in as few as five dialogue turns. Interactive setups can also mitigate the disadvantages of weaker teachers, showcasing the robustness of question-driven learning.

In this paper, we address task-oriented (or goal-oriented) communications where an encoder at the transmitter learns compressed latent representations of data, which are then transmitted over a wireless channel. At the receiver, a decoder performs a machine learning task, specifically for classifying the received signals. The deep neural networks corresponding to the encoder-decoder pair are jointly trained, taking both channel and data characteristics into account. Our objective is to achieve high accuracy in completing the underlying task while minimizing the number of channel uses determined by the encoder's output size. To this end, we propose a multi-round, multi-task learning (MRMTL) approach for the dynamic update of channel uses in multi-round transmissions. The transmitter incrementally sends an increasing number of encoded samples over the channel based on the feedback from the receiver, and the receiver utilizes the signals from a previous round to enhance the task performance, rather than only considering the latest transmission. This approach employs multi-task learning to jointly optimize accuracy across varying number of channel uses, treating each configuration as a distinct task. By evaluating the confidence of the receiver in task decisions, MRMTL decides on whether to allocate additional channel uses in multiple rounds. We characterize both the accuracy and the delay (total number of channel uses) of MRMTL, demonstrating that it achieves the accuracy close to that of conventional methods requiring large numbers of channel uses, but with reduced delay by incorporating signals from a prior round. We consider the CIFAR-10 dataset, convolutional neural network architectures, and AWGN and Rayleigh channel models for performance evaluation. We show that MRMTL significantly improves the efficiency of task-oriented communications, balancing accuracy and latency effectively.

Traditional Semantic Table Interpretation (STI) methods rely primarily on the underlying table data to create semantic annotations. This year's SemTab challenge introduced the ``Metadata to KG'' track, which focuses on performing STI by using only metadata information, without access to the underlying data. In response to this new challenge, we introduce a new term: Column Vocabulary Association (CVA). This term refers to the task of semantic annotation of column headers solely based on metadata information. In this study, we evaluate the performance of various methods in executing the CVA task, including a Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) approach, as well as a more traditional similarity approach with SemanticBERT. Our methodology uses a zero-shot setting, with no pretraining or examples passed to the Large Language Models (LLMs), as we aim to avoid a domain-specific setting. We investigate a total of 7 different LLMs, of which three commercial GPT models (i.e. gpt-3.5-turbo-0.125, gpt-4o and gpt-4-turbo) and four open source models (i.e. llama3-80b, llama3-7b, gemma-7b and mixtral-8x7b). We integrate this models with RAG systems, and we explore how variations in temperature settings affect performances. Moreover, we continue our investigation by performing the CVA task utilizing SemanticBERT, analyzing how various metadata information influence its performance. Initial findings indicate that LLMs generally perform well at temperatures below 1.0, achieving an accuracy of 100\% in certain cases. Nevertheless, our investigation also reveal that the nature of the data significantly influences CVA task outcomes. In fact, in cases where the input data and glossary are related (for example by being created by the same organizations) traditional methods appear to surpass the performance of LLMs.

LiteEFG is an efficient library with easy-to-use Python bindings, which can solve multiplayer extensive-form games (EFGs). LiteEFG enables the user to express computation graphs in Python to define updates on the game tree structure. The graph is then executed by the C++ backend, leading to significant speedups compared to running the algorithm in Python. Moreover, in LiteEFG, the user needs to only specify the computation graph of the update rule in a decision node of the game, and LiteEFG will automatically distribute the update rule to each decision node and handle the structure of the imperfect-information game.