As AI systems are increasingly used to conduct research autonomously, misaligned systems could introduce subtle flaws that produce misleading results while evading detection. We introduce ASMR-Bench (Auditing for Sabotage in ML Research), a benchmark for evaluating the ability of auditors to detect sabotage in ML research codebases. ASMR-Bench consists of 9 ML research codebases with sabotaged variants that produce qualitatively different experimental results. Each sabotage modifies implementation details, such as hyperparameters, training data, or evaluation code, while preserving the high-level methodology described in the paper. We evaluated frontier LLMs and LLM-assisted human auditors on ASMR-Bench and found that both struggled to reliably detect sabotage: the best performance was an AUROC of 0.77 and a top-1 fix rate of 42%, achieved by Gemini 3.1 Pro. We also tested LLMs as red teamers and found that LLM-generated sabotages were weaker than human-generated ones but still sometimes evaded same-capability LLM auditors. We release ASMR-Bench to support research on monitoring and auditing techniques for AI-conducted research.

Explaining Machine Learning (ML) results in a transparent and user-friendly manner remains a challenging task of Explainable Artificial Intelligence (XAI). In this paper, we present a method to enhance the interpretability of ML models by using a Knowledge Graph (KG). We store domain-specific data along with ML results and their corresponding explanations, establishing a structured connection between domain knowledge and ML insights. To make these insights accessible to users, we designed a selective retrieval method in which relevant triplets are extracted from the KG and processed by a Large Language Model (LLM) to generate user-friendly explanations of ML results. We evaluated our method in a manufacturing environment using the XAI Question Bank. Beyond standard questions, we introduce more complex, tailored questions that highlight the strengths of our approach. We evaluated 33 questions, analyzing responses using quantitative metrics such as accuracy and consistency, as well as qualitative ones such as clarity and usefulness. Our contribution is both theoretical and practical: from a theoretical perspective, we present a novel approach for effectively enabling LLMs to dynamically access a KG in order to improve the explainability of ML results. From a practical perspective, we provide empirical evidence showing that such explanations can be successfully applied in real-world manufacturing environments, supporting better decision-making in manufacturing processes.

Although most of the automated theorem-proving approaches depend on formal proof systems, informal theorem proving can align better with large language models' (LLMs) strength in natural language processing. In this work, we identify a primary bottleneck in informal theorem proving as a lack of insight, namely the difficulty of recognizing the core techniques required to solve complex problems. To address this, we propose a novel framework designed to cultivate this essential reasoning skill and enable LLMs to perform insightful reasoning. We propose $\mathtt{DeepInsightTheorem}$, a hierarchical dataset that structures informal proofs by explicitly extracting core techniques and proof sketches alongside the final proof. To fully exploit this dataset, we design a Progressive Multi-Stage SFT strategy that mimics the human learning process, guiding the model from basic proof writing to insightful thinking. Our experiments on challenging mathematical benchmarks demonstrate that this insight-aware generation strategy significantly outperforms baselines. These results demonstrate that teaching models to identify and apply core techniques can substantially improve their mathematical reasoning.

This paper explores the response of Large Language Models (LLMs) to user prompts with different degrees of politeness and impoliteness. The Politeness Theory by Brown and Levinson and the Impoliteness Framework by Culpeper form the basis of experiments conducted across three languages (English, Hindi, Spanish), five models (Gemini-Pro, GPT-4o Mini, Claude 3.7 Sonnet, DeepSeek-Chat, and Llama 3), and three interaction histories between users (raw, polite, and impolite). Our sample consists of 22,500 pairs of prompts and responses of various types, evaluated across five levels of politeness using an eight-factor assessment framework: coherence, clarity, depth, responsiveness, context retention, toxicity, conciseness, and readability. The findings show that model performance is highly influenced by tone, dialogue history, and language. While polite prompts enhance the average response quality by up to ~11% and impolite tones worsen it, these effects are neither consistent nor universal across languages and models. English is best served by courteous or direct tones, Hindi by deferential and indirect tones, and Spanish by assertive tones. Among the models, Llama is the most tone-sensitive (11.5% range), whereas GPT is more robust to adversarial tone. These results indicate that politeness is a quantifiable computational variable that affects LLM behaviour, though its impact is language- and model-dependent rather than universal. To support reproducibility and future work, we additionally release PLUM (Politeness Levels in Utterances, Multilingual), a publicly available corpus of 1,500 human-validated prompts across three languages and five politeness categories, and provide a formal supplementary analysis of six falsifiable hypotheses derived from politeness theory, empirically assessed against the dataset.

As AI-assisted video creation becomes increasingly practical, instruction-guided video editing has become essential for refining generated or captured footage to meet professional requirements. Yet the field still lacks both a large-scale human-annotated dataset with complete editing examples and a standardized evaluator for comparing editing systems. Existing resources are limited by small scale, missing edited outputs, or the absence of human quality labels, while current evaluation often relies on expensive manual inspection or generic vision-language model judges that are not specialized for editing quality. We introduce VEFX-Dataset, a human-annotated dataset containing 5,049 video editing examples across 9 major editing categories and 32 subcategories, each labeled along three decoupled dimensions: Instruction Following, Rendering Quality, and Edit Exclusivity. Building on VEFX-Dataset, we propose VEFX-Reward, a reward model designed specifically for video editing quality assessment. VEFX-Reward jointly processes the source video, the editing instruction, and the edited video, and predicts per-dimension quality scores via ordinal regression. We further release VEFX-Bench, a benchmark of 300 curated video-prompt pairs for standardized comparison of editing systems. Experiments show that VEFX-Reward aligns more strongly with human judgments than generic VLM judges and prior reward models on both standard IQA/VQA metrics and group-wise preference evaluation. Using VEFX-Reward as an evaluator, we benchmark representative commercial and open-source video editing systems, revealing a persistent gap between visual plausibility, instruction following, and edit locality in current models.

The complexity of Vietnam's legal texts presents a significant barrier to public access to justice. While Large Language Models offer a promising solution for legal text simplification, evaluating their true capabilities requires a multifaceted approach that goes beyond surface-level metrics. This paper introduces a comprehensive dual-aspect evaluation framework to address this need. First, we establish a performance benchmark for four state-of-the-art large language models (GPT-4o, Claude 3 Opus, Gemini 1.5 Pro, and Grok-1) across three key dimensions: Accuracy, Readability, and Consistency. Second, to understand the "why" behind these performance scores, we conduct a large-scale error analysis on a curated dataset of 60 complex Vietnamese legal articles, using a novel, expert-validated error typology. Our results reveal a crucial trade-off: models like Grok-1 excel in Readability and Consistency but compromise on fine-grained legal Accuracy, while models like Claude 3 Opus achieve high Accuracy scores that mask a significant number of subtle but critical reasoning errors. The error analysis pinpoints \textit{Incorrect Example} and \textit{Misinterpretation} as the most prevalent failures, confirming that the primary challenge for current LLMs is not summarization but controlled, accurate legal reasoning. By integrating a quantitative benchmark with a qualitative deep dive, our work provides a holistic and actionable assessment of LLMs for legal applications.

Recent advances in language models have substantially improved Natural Language Understanding (NLU). Although widely used benchmarks suggest that Large Language Models (LLMs) can effectively disambiguate, their practical applicability in real-world narrative contexts remains underexplored. SemEval-2026 Task 5 addresses this gap by introducing a task that predicts the human-perceived plausibility of a word sense within a short story. In this work, we propose an LLM-based framework for plausibility scoring of homonymous word senses in narrative texts using a structured reasoning mechanism. We examine the impact of fine-tuning low-parameter LLMs with diverse reasoning strategies, alongside dynamic few-shot prompting for large-parameter models, on accurate sense identification and plausibility estimation. Our results show that commercial large-parameter LLMs with dynamic few-shot prompting closely replicate human-like plausibility judgments. Furthermore, model ensembling slightly improves performance, better simulating the agreement patterns of five human annotators compared to single-model predictions

Frontier models have demonstrated exceptional capabilities following the integration of task-reward-based reinforcement learning (RL) into their training pipelines, enabling systems to evolve from pure reasoning models into sophisticated agents. However, debate persists regarding whether RL genuinely instills new skills within a base model or merely sharpens its existing distribution to elicit latent capabilities. To address this dichotomy, we present an explicit comparison between distribution sharpening and task-reward-based learning, utilizing RL as a tool to implement both paradigms. Our analysis reveals the inherent limitations of distribution sharpening, demonstrating from first principles how and why the optima can be unfavorable and the approach fundamentally unstable. Furthermore, our experiments using Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct and Qwen3-4B-Instruct-2507 on math datasets confirm that sharpening yields limited gains, whereas incorporating task-based reward signal can greatly help achieve robust performance improvements and stable learning.

Competency Questions (CQs) are a cornerstone of requirement elicitation in ontology engineering. CQs represent requirements as a set of natural language questions that an ontology should satisfy; they are traditionally modelled by ontology engineers together with domain experts as part of a human-centred, manual elicitation process. The use of Generative AI automates CQ creation at scale, therefore democratising the process of generation, widening stakeholder engagement, and ultimately broadening access to ontology engineering. However, given the large and heterogeneous landscape of LLMs, varying in dimensions such as parameter scale, task and domain specialisation, and accessibility, it is crucial to characterise and understand the intrinsic, observable properties of the CQs they produce (e.g., readability, structural complexity) through a systematic, cross-domain analysis. This paper introduces a set of quantitative measures for the systematic comparison of CQs across multiple dimensions. Using CQs generated from well defined use cases and scenarios, we identify their salient properties, including readability, relevance with respect to the input text and structural complexity of the generated questions. We conduct our experiments over a set of use cases and requirements using a range of LLMs, including both open (KimiK2-1T, LLama3.1-8B, LLama3.2-3B) and closed models (Gemini 2.5 Pro, GPT 4.1). Our analysis demonstrates that LLM performance reflects distinct generation profiles shaped by the use case.

Reasoning in vision-language models (VLMs) has recently attracted significant attention due to its broad applicability across diverse downstream tasks. However, it remains unclear whether the superior performance of VLMs stems from genuine vision-grounded reasoning or relies predominantly on the reasoning capabilities of their textual backbones. To systematically measure this, we introduce CrossMath, a novel multimodal reasoning benchmark designed for controlled cross-modal comparisons. Specifically, we construct each problem in text-only, image-only, and image+text formats guaranteeing identical task-relevant information, verified by human annotators. This rigorous alignment effectively isolates modality-specific reasoning differences while eliminating confounding factors such as information mismatch. Extensive evaluation of state-of-the-art VLMs reveals a consistent phenomenon: a substantial performance gap between textual and visual reasoning. Notably, VLMs excel with text-only inputs, whereas incorporating visual data (image+text) frequently degrades performance compared to the text-only baseline. These findings indicate that current VLMs conduct reasoning primarily in the textual space, with limited genuine reliance on visual evidence. To mitigate this limitation, we curate a CrossMath training set for VLM fine-tuning. Empirical evaluations demonstrate that fine-tuning on this training set significantly boosts reasoning performance across all individual and joint modalities, while yielding robust gains on two general visual reasoning tasks. Source code is available at https://github.com/xuyige/CrossMath.

We propose HILBERT (HIerarchical Long-sequence Balanced Embedding with Reciprocal contrastive Training), a cross-attentive multimodal framework for learning document-level audio-text representations from long, segmented sequences in low-resource data settings. HILBERT leverages frozen pre-trained speech and language encoders to extract segment-level features, which are aggregated via cross-modal attention and self-attentive pooling to form modality-specific document representations and a joint cross-attentive embedding. To align modalities while preserving modality-specific structure under severe audio-text dimensional imbalance, we introduce a reciprocal dual contrastive objective that simultaneously aligns audio-to-joint and text-to-joint representations, rather than directly contrasting audio and text alone. Two auxiliary regularizers further stabilize long-sequence fusion: a Centered Kernel Alignment (CKA) loss that preserves structural consistency between each modality and the joint embedding, and a mutual information balancing loss that prevents dominance of a single modality by equalizing information flow from audio and text into the joint space. For downstream prediction, HILBERT employs a Mixture-of-Experts (MoE) classifier over concatenated audio, text, and joint representations to accommodate heterogeneous label regimes. Extensive evaluation across multiple audio-text backbone combinations demonstrates that HILBERT learns semantically meaningful long-sequence representations and achieves superior performance on highly imbalanced multi-class settings.

Reinforcement learning with verifiable rewards (RLVR) typically optimizes for outcome rewards without imposing constraints on intermediate reasoning. This leaves training susceptible to reward hacking, where models exploit loopholes (e.g., spurious patterns in training data) in the reward function to achieve high scores without solving the intended task. These reward-hacking behaviors are often implicit, as the intermediate chain-of-thought (CoT) may appear plausible on the surface, limiting the effectiveness of purely text-based monitoring. We propose Gradient Fingerprint (GRIFT), a method for detecting reward hacking using models' internal computations. Given a prompt and a model-generated CoT, GRIFT computes gradients of the CoT conditioned on the prompt and compresses them into a compact representation, which is then used to assess whether the CoT reflects reward hacking behavior. Across verifiable reasoning benchmarks spanning math, code, and logical reasoning, GRIFT substantially outperforms strong baselines, including CoT Monitor and TRACE, achieving over 25% relative improvement in detecting reward hacking behavior. Moreover, integrating GRIFT into the rejection fine-tuning pipeline for reasoning tasks reduces reward hacking and improves performance on the true task objective. Our results highlight a promising direction of leveraging gradient level representations for assessing the quality of CoT reasoning traces. Our code is available at: https://github.com/songtao-x/reward_hack.

Large language models have shown strong performance on broad-domain knowledge and reasoning benchmarks, but it remains unclear how well language models handle specialized animal-related knowledge under a unified closed-book evaluation protocol. We introduce BAGEL, a benchmark for evaluating animal knowledge expertise in language models. BAGEL is constructed from diverse scientific and reference sources, including bioRxiv, Global Biotic Interactions, Xeno-canto, and Wikipedia, using a combination of curated examples and automatically generated closed-book question-answer pairs. The benchmark covers multiple aspects of animal knowledge, including taxonomy, morphology, habitat, behavior, vocalization, geographic distribution, and species interactions. By focusing on closed-book evaluation, BAGEL measures animal-related knowledge of models without external retrieval at inference time. BAGEL further supports fine-grained analysis across source domains, taxonomic groups, and knowledge categories, enabling a more precise characterization of model strengths and systematic failure modes. Our benchmark provides a new testbed for studying domain-specific knowledge generalization in language models and for improving their reliability in biodiversity-related applications.

This paper presents a systematic benchmark of state-of-the-art multilingual large language models (LLMs) adapted via token pruning - a compression technique that eliminates tokens and embedding parameters corresponding to languages irrelevant to the target application. Focusing on Korean-centric natural language processing (NLP) tasks, we evaluate architectures including Qwen3, Gemma-3, Llama-3, and Aya across three vocabulary configurations: Original, English-Korean (EnKo), and English-Korean-Chinese (EnKoZh). Performance is assessed using established benchmarks for general aptitude, cultural literacy, instruction following, and machine translation. Our findings indicate that token pruning significantly improves generation stability by eliminating language confusion, and in the case of machine translation, frequently enhances performance on Korean-specific tasks. While instruction-following capabilities display architecture-dependent variance linked to latent cross-lingual representations, the significant reduction in vocabulary size validates token pruning as a highly effective optimization strategy for memory-constrained, domain-specific deployments, despite modest gains in inference latency.

Academic integrity continues to face the persistent challenge of examination cheating. Traditional invigilation relies on human observation, which is inefficient, costly, and prone to errors at scale. Although some existing AI-powered monitoring systems have been deployed and trusted, many lack transparency or require multi-layered architectures to achieve the desired performance. To overcome these challenges, we propose an improvement over a simple two-stage framework for exam cheating detection that integrates object detection and behavioral analysis using well-known technologies. First, the state-of-the-art YOLOv8n model is used to localize students in exam-room images. Each detected region is cropped and preprocessed, then classified by a fine-tuned RexNet-150 model as either normal or cheating behavior. The system is trained on a dataset compiled from 10 independent sources with a total of 273,897 samples, achieving 0.95 accuracy, 0.94 recall, 0.96 precision, and 0.95 F1-score - a 13\% increase over a baseline accuracy of 0.82 in video-based cheating detection. In addition, with an average inference time of 13.9 ms per sample, the proposed approach demonstrates robustness and scalability for deployment in large-scale environments. Beyond the technical contribution, the AI-assisted monitoring system also addresses ethical concerns by ensuring that final outcomes are delivered privately to individual students after the examination, for example, via personal email. This prevents public exposure or shaming and offers students an opportunity to reflect on their behavior. For further improvement, it is possible to incorporate additional factors, such as audio data and consecutive frames, to achieve greater accuracy. This study provides a foundation for developing real-time, scalable, ethical, and open-source solutions.

Understanding natural and engineered systems often relies on symbolic formulations, such as differential equations, which provide interpretability and transferability beyond black-box models. We introduce Latent Grammar Flow (LGF), a neuro-symbolic generative framework for discovering ordinary differential equations from data. LGF embeds equations as grammar-based representations into a discrete latent space and forces semantically similar equations to be positioned closer together with a behavioural loss. Then, a discrete flow model guides the sampling process to recursively generate candidate equations that best fit the observed data. Domain knowledge and constraints, such as stability, can be either embedded into the rules or used as conditional predictors.

As a relatively new forum, ACM FAccT has become a key space for activists and scholars to critically examine emerging AI and ML technologies. It brings together academics, civil society members, and government representatives from diverse fields to explore the broader societal impacts of both deployed and proposed technologies. We report a large-scale participatory design (PD) process for reflexive conference governance, which combined an in-person CRAFT session, an asynchronous Polis poll and the synthesis of a governance-facing report for the FAccT leadership. Participants shaped the substantive agenda by authoring seed statements, adding new statements and making patterns of agreement, disagreement and uncertainty made visible through voting.Our endeavors represent one of the the first instances of applying PD to a venue that critically interrogates the societal impacts of AI, fostering a niche in which critical scholars are free to voice their concerns. Finally, this work advances large-scale PD theory by providing an effective case study of a co-design paradigm that can readily scale temporally and epistemologically.

Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilities, entropy, and self-consistency can become brittle under calibration--deployment mismatch. Conformal prediction provides finite-sample validity under exchangeability, but its practical usefulness depends on the quality of the nonconformity score. We propose a conformal framework for LLM question answering that uses internal representations rather than output-facing statistics: specifically, we introduce Layer-Wise Information (LI) scores, which measure how conditioning on the input reshapes predictive entropy across model depth, and use them as nonconformity scores within a standard split conformal pipeline. Across closed-ended and open-domain QA benchmarks, with the clearest gains under cross-domain shift, our method achieves a better validity--efficiency trade-off than strong text-level baselines while maintaining competitive in-domain reliability at the same nominal risk level. These results suggest that internal representations can provide more informative conformal scores when surface-level uncertainty is unstable under distribution shift.

Secondary school students enrolled in the AP Computer Science Principles (CSP) course commonly utilize web resources (e.g., tutorials, Q\&A sites) to better understand key concepts in the curriculum. The primary obstacle to using these resources is finding information appropriate for the learning task and student's background. In addition to web search, conversational agents are increasingly a viable alternative for CSP students. In this paper, we study the potential of conversational agents to aid secondary school students as they acquire knowledge on CSP concepts. We explore general purpose, generative conversational agents (e.g., ChatGPT) and custom, fixed-response conversational agents built specifically to aid CSP students. We present results from classroom use by 45 high school students in grades 9-11 (ages 14-17) across six CSP sections. Our main contributions are in better understanding how conversational agents can help CSP students and an evaluation of the effectiveness and engagement of different approaches for CSP exploratory search.

Software engineering research has experienced rapid growth in both output and participation over the past decades. Yet concerns persist about the field's ability to accumulate, integrate, and reuse knowledge in ways that support long-term progress. To better understand how the community itself perceives these challenges, we analyze responses from the ICSE 2026 Future of Software Engineering pre-survey, which captures perspectives from 280 globally distributed and highly experienced researchers. Our analysis reveals a tension between increasing research productivity and the limited mechanisms available for synthesizing results, tracking evolving claims, and supporting cumulative understanding over time. Building on these observations, we diagnose four interrelated structural breakdowns: papers function as isolated knowledge units with claims embedded in prose; context and provenance are lost as knowledge moves through the publication pipeline; claims evolve without systematic tracking; and incentive structures favor novelty over consolidation. We argue that addressing these barriers requires rethinking the fundamental properties of research artifacts. We articulate four technology-agnostic principles for future research artifacts: structured and interpretable representations of claims and evidence; inspectable and provenance-aware documentation of methodological decisions; long-lived and reusable substrates that evolve beyond publication; and governance mechanisms that align individual incentives with collective knowledge-building goals. We discuss implications for research practice, publication norms, and community infrastructure, positioning FOSE as a venue for experimenting with alternative artifact designs that support cumulative scientific progress.

As forgery types continue to emerge consistently, Incremental Face Forgery Detection (IFFD) has become a crucial paradigm. However, existing methods typically rely on data replay or coarse binary supervision, which fails to explicitly constrain the feature space, leading to severe feature drift and catastrophic forgetting. To address this, we propose AIFIND, Artifact-Aware Interpreting Fine-Grained Alignment for Incremental Face Forgery Detection, which leverages semantic anchors to stabilize incremental learning. We design the Artifact-Driven Semantic Prior Generator to instantiate invariant semantic anchors, establishing a fixed coordinate system from low-level artifact cues. These anchors are injected into the image encoder via Artifact-Probe Attention, which explicitly constrains volatile visual features to align with stable semantic anchors. Adaptive Decision Harmonizer harmonizes the classifiers by preserving angular relationships of semantic anchors, maintaining geometric consistency across tasks. Extensive experiments on multiple incremental protocols validate the superiority of AIFIND.

Computational X-ray absorption near-edge structure (XANES) is widely used to probe local coordination environments, oxidation states, and electronic structure in chemically complex systems. However, the use of computational XANES at scale is constrained more by workflow complexity than by the underlying simulation method itself. To address this challenge, we present ChemGraph-XANES, an agentic framework for automated XANES simulation and analysis that unifies natural-language task specification, structure acquisition, FDMNES input generation, task-parallel execution, spectral normalization, and provenance-aware data curation. Built on ASE, FDMNES, Parsl, and a LangGraph/LangChain-based tool interface, the framework exposes XANES workflow operations as typed Python tools that can be orchestrated by large language model (LLM) agents. In multi-agent mode, a retrieval-augmented expert agent consults the FDMNES manual to ground parameter selection, while executor agents translate user requests into structured tool calls. We demonstrate documentation-grounded parameter retrieval and show that the same workflow supports both explicit structure-file inputs and chemistry-level natural-language requests. Because independent XANES calculations are naturally task-parallel, the framework is well suited for high-throughput deployment on high-performance computing (HPC) systems, enabling scalable XANES database generation for downstream analysis and machine-learning applications. ChemGraph-XANES thus provides a reproducible and extensible workflow layer for physics-based XANES simulation, spectral curation, and agent-compatible computational spectroscopy.

Code generation refers to automatically producing executable programs from user requirements. Recently, researchers have explored approaches to enhance the correctness of generated code with advanced large language models. Although achieving improvements, existing approaches focus on designing reasoning strategies or post-refinement methods to enhance code generation performance. Despite their differences, all these methods share a common assumption: the LLM can correctly understand the given requirement. However, this assumption does not always hold. To fill this gap, we propose REA-Coder, a requirement alignment approach to enhance the code generation performance of LLMs. REA-Coder involves first identifying the requirement content that does not align with LLMs and aligning the requirements. Then, based on the aligned requirements, LLMs generate code and further verify whether the generated code aligns with the requirements, iterating this process of requirement alignment and code generation until generating correct code or achieving the maximum number of iterations. Experimental results show that REA-Coder outperforms all advanced baselines on four LLMs across five programming benchmarks. Concretely, REA-Coder achieves average improvements of 7.93%, 30.25%, 26.75%, 8.59%, and 8.64% on the five benchmark datasets, demonstrating the effectiveness of requirement alignment for improving the code generation performance of LLMs.

Data plays a fundamental role in consolidating markets, services, and products in the digital financial ecosystem. However, the use of real data, especially in the financial context, can lead to privacy risks and access restrictions, affecting institutions, research, and modeling processes. Although not all financial datasets present such limitations, this work proposes the use of deep learning techniques for generating synthetic data applied to cryptocurrency price time series. The approach is based on Conditional Generative Adversarial Networks (CGANs), combining an LSTM-type recurrent generator and an MLP discriminator to produce statistically consistent synthetic data. The experiments consider different crypto-assets and demonstrate that the model is capable of reproducing relevant temporal patterns, preserving market trends and dynamics. The generation of synthetic series through GANs is an efficient alternative for simulating financial data, showing potential for applications such as market behavior analysis and anomaly detection, with lower computational cost compared to more complex generative approaches.

Automated 3D radiology report generation often suffers from clinical hallucinations and a lack of the iterative verification found in human practice. While recent Vision-Language Models (VLMs) have advanced the field, they typically operate as monolithic "black-box" systems without the collaborative oversight characteristic of clinical workflows. To address these challenges, we propose MARCH (Multi-Agent Radiology Clinical Hierarchy), a multi-agent framework that emulates the professional hierarchy of radiology departments and assigns specialized roles to distinct agents. MARCH utilizes a Resident Agent for initial drafting with multi-scale CT feature extraction, multiple Fellow Agents for retrieval-augmented revision, and an Attending Agent that orchestrates an iterative, stance-based consensus discourse to resolve diagnostic discrepancies. On the RadGenome-ChestCT dataset, MARCH significantly outperforms state-of-the-art baselines in both clinical fidelity and linguistic accuracy. Our work demonstrates that modeling human-like organizational structures enhances the reliability of AI in high-stakes medical domains.

Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by sequentially learning a low-rank update matrix for each task. To mitigate catastrophic forgetting, state-of-the-art approaches impose constraints on new adapters with respect to the previous ones, by targeting either subspace or coordinate-wise interference. In this paper, we propose JumpLoRA, a novel framework to adaptively induce sparsity in the Low-Rank Adaptation (LoRA) blocks through the use of JumpReLU gating. The method achieves dynamic parameter isolation, which helps prevent task interference. We demonstrate that our method is highly modular and compatible with LoRA-based CL approaches. Specifically, it significantly boosts the performance of IncLoRA and outperforms the leading state-of-the-art CL method, ELLA.

Large language models (LLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex tasks. Yet ensuring that the reasoning trace both contributes to and faithfully reflects the processes underlying the model's final answer, rather than merely accompanying it, remains challenging. We introduce AtManRL, a method that leverages differentiable attention manipulation to learn more faithful reasoning through reinforcement learning. By training an additive attention mask that identifies tokens in the CoT crucial for producing correct answers, we derive a saliency reward signal that encourages the model to generate reasoning traces that genuinely influence its final predictions. We integrate this saliency reward with outcome-based rewards within the GRPO framework to jointly optimize for correctness and interpretability. Experiments on GSM8K and MMLU with Llama-3.2-3B-Instruct demonstrate that our approach can identify influential reasoning tokens and enable training more transparent reasoning models.

This paper presents SWNet, a bimodal end-to-end cross-spectral network specifically engineered for the detection of camouflaged weeds in dense agricultural environments. Plant camouflage, characterized by homochromatic blending where invasive species mimic the phenotypic traits of primary crops, poses a significant challenge for traditional computer vision systems. To overcome these limitations, SWNet utilizes a Pyramid Vision Transformer v2 backbone to capture long-range dependencies and a Bimodal Gated Fusion Module to dynamically integrate Visible and Near-Infrared information. By leveraging the physiological differences in chlorophyll reflectance captured in the NIR spectrum, the proposed architecture effectively discriminates targets that are otherwise indistinguishable in the visible range. Furthermore, an Edge-Aware Refinement module is employed to produce sharper object boundaries and reduce structural ambiguity. Experimental results on the Weeds-Banana dataset indicate that SWNet outperforms ten state-of-the-art methods. The study demonstrates that the integration of cross-spectral data and boundary-guided refinement is essential for high segmentation accuracy in complex crop canopies. The code is available on GitHub: https://cod-espol.github.io/SWNet/

Recent works proposed test-time alignment methods that rely on a small aligned model as a proxy that guides the generation of a larger base (unaligned) model. The implicit reward approach skews the large model distribution, whereas the nudging approach defers the generation of the next token to the small aligned model when the large base one is unconfident about its outcome. In this work, we first show that both approaches can be reduced to sampling from similar graphical models, where they differ only in the definition of a rejection criterion (or distribution). Moreover, we argue that the confidence criterion is ill-motivated due to linguistic phenomena like ambiguous phrasing. We propose a novel rejection criterion based on a conservative confidence bet. Experimentally, our novel approach outperforms previous work on several datasets.

Accurate prediction of training time in distributed deep learning is crucial for resource allocation, cost estimation, and job scheduling. We observe that the floating-point precision setting is a key determinant of training time, leading to training time variations of ~2.4x over its minimum. However, existing studies on distributed training time prediction rely on static model computation graphs that do not capture precision variations, including mixed precision. According to our experiments, training time prediction without considering precision results in significant prediction errors - reaching up to 147.85% in mean absolute percentage error (MAPE). To address this issue, we propose a precision-aware distributed training time predictor that achieves robust accuracy across diverse precision settings, including mixed precision, with 9.8% MAPE.