# Research Papers — 2025-12 · bundle page 51 of 175 > Full-text markdown of papers #2501–2550 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-12/page/51 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/50.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/52.md) ### Is There a Better Source Distribution than Gaussian? Exploring Source Distributions for Image Flow Matching Authors: Junho Lee, Kwanseok Kim, Joonseok Lee Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18184v1 Flow matching has emerged as a powerful generative modeling approach with flexible choices of source distribution. While Gaussian distributions are commonly used, the potential for better alternatives in high-dimensional data generation remains largely unexplored. In this paper, we propose a novel 2D simulation that captures high-dimensional geometric properties in an interpretable 2D setting, enabling us to analyze the learning dynamics of flow matching during training. Based on this analysis, we derive several key insights about flow matching behavior: (1) density approximation can paradoxically degrade performance due to mode discrepancy, (2) directional alignment suffers from path entanglement when overly concentrated, (3) Gaussian's omnidirectional coverage ensures robust learning, and (4) norm misalignment incurs substantial learning costs. Building on these insights, we propose a practical framework that combines norm-aligned training with directionally-pruned sampling. This approach maintains the robust omnidirectional supervision essential for stable flow learning, while eliminating initializations in data-sparse regions during inference. Importantly, our pruning strategy can be applied to any flow matching model trained with a Gaussian source, providing immediate performance gains without the need for retraining. Empirical evaluations demonstrate consistent improvements in both generation quality and sampling efficiency. Our findings provide practical insights and guidelines for source distribution design and introduce a readily applicable technique for improving existing flow matching models. Our code is available at https://github.com/kwanseokk/SourceFM. --- ### MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation Authors: Kaixing Yang, Jiashu Zhu, Xulong Tang, Ziqiao Peng, Xiangyue Zhang, Puwei Wang, Jiahong Wu, Xiangxiang Chu, Hongyan Liu, Jun He Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18181v3 With the rise of online dance-video platforms and rapid advances in AI-generated content (AIGC), music-driven dance generation has emerged as a compelling research direction. Despite substantial progress in related domains such as music-driven 3D dance generation, pose-driven image animation, and audio-driven talking-head synthesis, existing methods cannot be directly adapted to this task. Moreover, the limited studies in this area still struggle to jointly achieve high-quality visual appearance and realistic human motion. Accordingly, we present MACE-Dance, a music-driven dance video generation framework with cascaded Mixture-of-Experts (MoE). The Motion Expert performs music-to-3D motion generation while enforcing kinematic plausibility and artistic expressiveness, whereas the Appearance Expert carries out motion- and reference-conditioned video synthesis, preserving visual identity with spatiotemporal coherence. Specifically, the Motion Expert adopts a diffusion model with a BiMamba-Transformer hybrid architecture and a Guidance-Free Training (GFT) strategy, achieving state-of-the-art (SOTA) performance in 3D dance generation. The Appearance Expert employs a decoupled kinematic-aesthetic fine-tuning strategy, achieving state-of-the-art (SOTA) performance in pose-driven image animation. To better benchmark this task, we curate a large-scale and diverse dataset and design a motion-appearance evaluation protocol. Based on this protocol, MACE-Dance also achieves state-of-the-art performance. Code is available at https://github.com/AMAP-ML/MACE-Dance. --- ### FairExpand: Individual Fairness on Graphs with Partial Similarity Information Authors: Rebecca Salganik, Yibin Wang, Guillaume Salha-Galvan, Jian Kang Published: 2025-12-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.18180v1 Individual fairness, which requires that similar individuals should be treated similarly by algorithmic systems, has become a central principle in fair machine learning. Individual fairness has garnered traction in graph representation learning due to its practical importance in high-stakes Web areas such as user modeling, recommender systems, and search. However, existing methods assume the existence of predefined similarity information over all node pairs, an often unrealistic requirement that prevents their operationalization in practice. In this paper, we assume the similarity information is only available for a limited subset of node pairs and introduce FairExpand, a flexible framework that promotes individual fairness in this more realistic partial information scenario. FairExpand follows a two-step pipeline that alternates between refining node representations using a backbone model (e.g., a graph neural network) and gradually propagating similarity information, which allows fairness enforcement to effectively expand to the entire graph. Extensive experiments show that FairExpand consistently enhances individual fairness while preserving performance, making it a practical solution for enabling graph-based individual fairness in real-world applications with partial similarity information. --- ### NEURO-GUARD: Neuro-Symbolic Generalization and Unbiased Adaptive Routing for Diagnostics -- Explainable Medical AI Authors: Midhat Urooj, Ayan Banerjee, Sandeep Gupta Published: 2025-12-20 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.18177v1 Accurate yet interpretable image-based diagnosis remains a central challenge in medical AI, particularly in settings characterized by limited data, subtle visual cues, and high-stakes clinical decision-making. Most existing vision models rely on purely data-driven learning and produce black-box predictions with limited interpretability and poor cross-domain generalization, hindering their real-world clinical adoption. We present NEURO-GUARD, a novel knowledge-guided vision framework that integrates Vision Transformers (ViTs) with language-driven reasoning to improve performance, transparency, and domain robustness. NEURO-GUARD employs a retrieval-augmented generation (RAG) mechanism for self-verification, in which a large language model (LLM) iteratively generates, evaluates, and refines feature-extraction code for medical images. By grounding this process in clinical guidelines and expert knowledge, the framework progressively enhances feature detection and classification beyond purely data-driven baselines. Extensive experiments on diabetic retinopathy classification across four benchmark datasets APTOS, EyePACS, Messidor-1, and Messidor-2 demonstrate that NEURO-GUARD improves accuracy by 6.2% over a ViT-only baseline (84.69% vs. 78.4%) and achieves a 5% gain in domain generalization. Additional evaluations on MRI-based seizure detection further confirm its cross-domain robustness, consistently outperforming existing methods. Overall, NEURO-GUARD bridges symbolic medical reasoning with subsymbolic visual learning, enabling interpretable, knowledge-aware, and generalizable medical image diagnosis while achieving state-of-the-art performance across multiple datasets. --- ### Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation Authors: Ziyu Zhang, Yi Yu, Simeng Zhu, Ahmed Aly, Yunhe Gao, Ning Gu, Yuan Xue Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18176v2 Accurate segmentation of anatomical structures in medical images is essential for diagnosis and treatment planning. While recent interactive segmentation foundation models enhance generalization through large-scale multimodal pretraining, they still depend on precise prompts and can fail in underrepresented clinical contexts (e.g., small organs-at-risk). We present AtlasSegFM, an atlas-guided framework that customizes off-the-shelf foundation models to new clinical contexts with a single annotated example. AtlasSegFM 1) performs atlas-query registration to generate context-aware prompts, 2) refines the segmentation with a frozen foundation model, and 3) applies a lightweight adaptive fusion module to combine atlas priors with foundation-model inputs and predictions. Extensive experiments on six public and in-house datasets across radiotherapy and vascular scenarios show consistent gains, with the largest improvements on small and delicate structures. AtlasSegFM provides a lightweight, deployable solution for one-shot customization of segmentation foundation models in real-world clinical workflows. --- ### Conscious Data Contribution via Community-Driven Chain-of-Thought Distillation Authors: Lena Libon, Meghana Bhange, Rushabh Solanki, Elliot Creager, Ulrich Aïvodji Published: 2025-12-20 Categories: cs.LG, cs.CR, cs.CY arXiv: https://arxiv.org/abs/2512.18174v1 The current era of AI development places a heavy emphasis on training large models on increasingly scaled-up datasets. This paradigm has catalyzed entirely new product categories, such as LLM chatbots, while also raising concerns about data privacy and consumer choice. In this paper, we consider questions of data portability and user autonomy in the context of LLMs that "reason" using chain-of-thought (CoT) traces, computing intermediate text artifacts from user input before producing a final output. We first interpret recent data privacy and portability law to argue that these intermediate computations qualify as users' personal data. Then, building on the existing framework of Conscious Data Contribution, we show how communities who receive low utility from an available model can aggregate and distill their shared knowledge into an alternate model better aligned with their goals. We verify this approach empirically and investigate the effects of community diversity, reasoning granularity, and community size on distillation performance. --- ### Local Patches Meet Global Context: Scalable 3D Diffusion Priors for Computed Tomography Reconstruction Authors: Taewon Yang, Jason Hu, Jeffrey A. Fessler, Liyue Shen Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18161v1 Diffusion models learn strong image priors that can be leveraged to solve inverse problems like medical image reconstruction. However, for real-world applications such as 3D Computed Tomography (CT) imaging, directly training diffusion models on 3D data presents significant challenges due to the high computational demands of extensive GPU resources and large-scale datasets. Existing works mostly reuse 2D diffusion priors to address 3D inverse problems, but fail to fully realize and leverage the generative capacity of diffusion models for high-dimensional data. In this study, we propose a novel 3D patch-based diffusion model that can learn a fully 3D diffusion prior from limited data, enabling scalable generation of high-resolution 3D images. Our core idea is to learn the prior of 3D patches to achieve scalable efficiency, while coupling local and global information to guarantee high-quality 3D image generation, by modeling the joint distribution of position-aware 3D local patches and downsampled 3D volume as global context. Our approach not only enables high-quality 3D generation, but also offers an unprecedentedly efficient and accurate solution to high-resolution 3D inverse problems. Experiments on 3D CT reconstruction across multiple datasets show that our method outperforms state-of-the-art methods in both performance and efficiency, notably achieving high-resolution 3D reconstruction of $512 \times 512 \times 256$ ($\sim$20 mins). --- ### Propose, Solve, Verify: Self-Play Through Formal Verification Authors: Alex Wilf, Pranjal Aggarwal, Bryan Parno, Daniel Fried, Louis-Philippe Morency, Paul Pu Liang, Sean Welleck Published: 2025-12-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.18160v1 Training models through self-play alone (without any human data) has been a longstanding goal in AI, but its effectiveness for training large language models remains unclear, particularly in code generation where rewards based on unit tests are brittle and prone to error propagation. We study self-play in the verified code generation setting, where formal verification provides reliable correctness signals. We introduce Propose, Solve, Verify (PSV) a simple self-play framework where formal verification signals are used to create a proposer capable of generating challenging synthetic problems and a solver trained via expert iteration. We use PSV to train PSV-Verus, which across three benchmarks improves pass@1 by up to 9.6x over inference-only and expert-iteration baselines. We show that performance scales with the number of generated questions and training iterations, and through ablations identify formal verification and difficulty-aware proposal as essential ingredients for successful self-play. --- ### EndoStreamDepth: Temporally Consistent Monocular Depth Estimation for Endoscopic Video Streams Authors: Hao Li, Daiwei Lu, Jiacheng Wang, Robert J. Webster, Ipek Oguz Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18159v2 This work presents EndoStreamDepth, a monocular depth estimation framework for endoscopic video streams. It provides accurate depth maps with sharp anatomical boundaries for each frame, temporally consistent predictions across frames, and real-time throughput. Unlike prior work that uses batched inputs, EndoStreamDepth processes individual frames with a temporal module to propagate inter-frame information. The framework contains three main components: (1) a single-frame depth network with endoscopy-specific transformation to produce accurate depth maps, (2) multi-level Mamba temporal modules that leverage inter-frame information to improve accuracy and stabilize predictions, and (3) a hierarchical design with comprehensive multi-scale supervision, where complementary loss terms jointly improve local boundary sharpness and global geometric consistency. We conduct comprehensive evaluations on two publicly available colonoscopy depth estimation datasets. Compared to state-of-the-art monocular depth estimation methods, EndoStreamDepth substantially improves performance, and it produces depth maps with sharp, anatomically aligned boundaries, which are essential to support downstream tasks such as automation for robotic surgery. The code is publicly available at https://github.com/MedICL-VU/EndoStreamDepth --- ### Estimating Solvation Free Energies with Boltzmann Generators Authors: Maximilian Schebek, Nikolas M. Froböse, Bettina G. Keller, Jutta Rogal Published: 2025-12-20 Categories: cond-mat.stat-mech, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2512.18147v2 Accurate calculations of solvation free energies remain a central challenge in molecular simulations, often requiring extensive sampling and numerous alchemical intermediates to ensure sufficient overlap between phase-space distributions of a solute in the gas phase and in solution. Here, we introduce a computational framework based on normalizing flows that directly maps solvent configurations between solutes of different sizes, and compare the accuracy and efficiency to conventional free energy estimates. For a Lennard-Jones solvent, we demonstrate that this approach yields acceptable accuracy in estimating free energy differences for challenging transformations, such as solute growth or increased solute-solute separation, which typically demand multiple intermediate simulation steps along the transformation. Analysis of radial distribution functions indicates that the flow generates physically meaningful solvent rearrangements, substantially enhancing configurational overlap between states in configuration space. These results suggest flow-based models as a promising alternative to traditional free energy estimation methods. --- ### On Swarm Leader Identification using Probing Policies Authors: Stergios E. Bachoumas, Panagiotis Artemiadis Published: 2025-12-20 Categories: cs.RO, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2512.18146v1 Identifying the leader within a robotic swarm is crucial, especially in adversarial contexts where leader concealment is necessary for mission success. This work introduces the interactive Swarm Leader Identification (iSLI) problem, a novel approach where an adversarial probing agent identifies a swarm's leader by physically interacting with its members. We formulate the iSLI problem as a Partially Observable Markov Decision Process (POMDP) and employ Deep Reinforcement Learning, specifically Proximal Policy Optimization (PPO), to train the prober's policy. The proposed approach utilizes a novel neural network architecture featuring a Timed Graph Relationformer (TGR) layer combined with a Simplified Structured State Space Sequence (S5) model. The TGR layer effectively processes graph-based observations of the swarm, capturing temporal dependencies and fusing relational information using a learned gating mechanism to generate informative representations for policy learning. Extensive simulations demonstrate that our TGR-based model outperforms baseline graph neural network architectures and exhibits significant zero-shot generalization capabilities across varying swarm sizes and speeds different from those used during training. The trained prober achieves high accuracy in identifying the leader, maintaining performance even in out-of-training distribution scenarios, and showing appropriate confidence levels in its predictions. Real-world experiments with physical robots further validate the approach, confirming successful sim-to-real transfer and robustness to dynamic changes, such as unexpected agent disconnections. --- ### Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool use Authors: Shreyas Subramanian, Adewale Akinfaderin, Yanyan Zhang, Ishan Singh, Mani Khanuja, Sandeep Singh, Maira Ladeira Tanke Published: 2025-12-19 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.23368v1 While Retrieval-Augmented Generation (RAG) has proven effective for generating accurate, context-based responses based on existing knowledge bases, it presents several challenges including retrieval quality dependencies, integration complexity and cost. Recent advances in agentic-RAG and tool-augmented LLM architectures have introduced alternative approaches to information retrieval and processing. We question how much additional value vector databases and semantic search bring to RAG over simple, agentic keyword search in documents for question-answering. In this study, we conducted a systematic comparison between RAG-based systems and tool-augmented LLM agents, specifically evaluating their retrieval mechanisms and response quality when the agent only has access to basic keyword search tools. Our empirical analysis demonstrates that tool-based keyword search implementations within an agentic framework can attain over $90\%$ of the performance metrics compared to traditional RAG systems without using a standing vector database. Our approach is simple to implement, cost effective, and is particularly useful in scenarios requiring frequent updates to knowledge bases. --- ### Perceptions of AI-CBT: Trust and Barriers in Chinese Postgrads Authors: Chan-in Sio, Alex Mann, Lingxi Fan, Andrew Cheung, Lik-hang Lee Published: 2025-12-19 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2602.03852v1 The mental well-being of graduate students is an increasing concern, yet the adoption of scalable support remains uneven. Artificial intelligence-powered cognitive behavioral therapy chatbots (AI-CBT) offer low barrier help, but little is known about how Chinese postgraduates perceive and use them. This qualitative study explored perceptions and experiences of AI-CBT chatbots among ten Chinese graduate students recruited through social media. Semi-structured Zoom interviews were conducted and analyzed using reflexive thematic analysis, with the Health Belief Model (HBM) and the Theory of Planned Behavior (TPB) as sensitizing frameworks. The findings indicate a cautious openness to AI-CBT chatbots: perceived usefulness and 24/7 access supported favorable attitudes, while data privacy, emotional safety, and uncertainty about `fit' for complex problems restricted the intention to use. Social norms (e.g., stigma and peer views) and perceived control (digital literacy, language quality) further shaped adoption. The study offers context-specific information to guide the culturally sensitive design, communication, and deployment of AI mental well-being tools for student populations in China and outlines the design implications around transparency, safeguards, and graduated care pathways. --- ### WebAccessVL: Violation-Aware VLM for Web Accessibility Authors: Amber Yijia Zheng, Jae Joong Lee, Bedrich Benes, Raymond A. Yeh Published: 2025-12-19 Categories: cs.HC, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.03850v3 We present a vision-language model (VLM) that automatically edits website HTML to address violations of the Web Content Accessibility Guidelines 2 (WCAG2) while preserving the original design. We formulate this as a supervised image-conditioned program synthesis task, where the model learns to correct HTML given both the code and its visual rendering. We create WebAccessVL, a website dataset with manually corrected accessibility violations. We then propose a violation-conditioned VLM that further takes the detected violations' descriptions from a checker as input. This conditioning enables an iterative checker-in-the-loop refinement strategy at test time. We conduct extensive evaluation on both open API and open-weight models. Empirically, our method achieves 0.211 violations per website, a 96.0\% reduction from the 5.34 violations in raw data and 87\% better than GPT-5. A perceptual study also confirms that our edited websites better maintain the original visual appearance and content. --- ### Triples and Knowledge-Infused Embeddings for Clustering and Classification of Scientific Documents Authors: Mihael Arcan Published: 2025-12-19 Categories: cs.CL, cs.AI, cs.DL arXiv: https://arxiv.org/abs/2601.08841v2 The increasing volume and complexity of scientific literature demand robust methods for organizing and understanding research documents. In this study, we investigate whether structured knowledge, specifically, subject-predicate-object triples-improves clustering and classification of scientific papers. We present a modular pipeline that combines unsupervised clustering and supervised classification across four document representations: abstract, triples, abstract+triples, and hybrid. Using a filtered arXiv corpus, we evaluate four transformer embeddings (MiniLM, MPNet, SciBERT, SPECTER) with KMeans, GMM, and HDBSCAN, and then train downstream classifiers for subject prediction. Across a five-seed benchmark (seeds 40-44), abstract-only inputs provide the strongest and most stable classification performance, reaching 0.923 accuracy and 0.923 macro-F1 (mean). Triple-only and knowledge-infused variants do not consistently outperform this baseline. In clustering, KMeans/GMM generally outperform HDBSCAN on external validity metrics, while HDBSCAN exhibits higher noise sensitivity. We observe that adding extracted triples naively does not guarantee gains and can reduce performance depending on representation choice. These results refine the role of knowledge infusion in scientific document modeling: structured triples are informative but not universally beneficial, and their impact is strongly configuration-dependent. Our findings provide a reproducible benchmark and practical guidance for when knowledge-augmented representations help, and when strong text-only baselines remain preferable. --- ### Consistency-Aware Editing for Entity-level Unlearning in Language Models Authors: Xiaoqi Han, Víctor Gutiérrez-Basulto, Ru Li, Xiaoli Li, Jiye Liang, Jeff Z. Pan Published: 2025-12-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.08840v1 Large language models (LLMs) risk retaining sensitive, copyrighted, or harmful information from their training data. Entity-level unlearning addresses this issue by removing all knowledge of a specific entity while preserving the model's overall capabilities. Existing approaches typically rely on full-model fine-tuning or prompt-based interventions, which can be computationally expensive or brittle when handling paraphrased queries. Recently, model editing has emerged as an efficient alternative for updating knowledge in LLMs, offering a promising direction for unlearning. However, existing editing techniques are typically designed for instance-level updates, modifying responses to specific attributes of an entity rather than eliminating all knowledge associated with the entity. In this paper, we investigate how editing techniques can be adapted for effective and efficient entity-level unlearning. To this end, we introduce a novel consistency-aware editing (CAE) framework. CAE aggregates a diverse set of prompts related to a target entity, including its attributes, relations, and adversarial paraphrases. It then jointly learns a low-rank update guided by a consistency regularizer that aligns the editing directions across prompts. This promotes robust and comprehensive forgetting while minimizing interference with unrelated knowledge. We further examine where different entities are stored within the model and how many diverse prompts are needed for successful unlearning. We evaluate CAE on two challenging benchmarks, RWKU and ToFU, and demonstrate that it (i) provides insights into how entity-level knowledge is internally represented and deleted in LLMs, (ii) significantly improves forgetting accuracy and robustness over traditional unlearning and editing baselines, and (iii) enables scalable entity removal using only tens of carefully selected prompts. --- ### Hierarchical Sparse Plus Low Rank Compression of LLM Authors: Pawan Kumar, Aditi Gupta Published: 2025-12-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.07839v1 Modern large language models (LLMs) place extraordinary pressure on memory and compute budgets, making principled compression indispensable for both deployment and continued training. We present Hierarchical Sparse Plus Low-Rank (HSS) compression, a two-stage scheme that (i) removes the largest-magnitude weights into a sparse matrix S and (ii) applies a recursive Hierarchically Sparse Separable (HSS) low-rank factorisation to the dense residual matrix. A recursive rank-reducing strategy and a reverse Cuthill-Mckee (RCM) permutation are introduced to align high weights towards the diagonal with the block-diagonal hierarchy, maximising off-diagonal compressibility (because they are touched only once). HSS is hardware-friendly: its matrix-vector multiply reduces to one sparse and a sequence of thin-matrix multiplications and can be trained end-to-end with standard optimisers. Experiments on LLaMA-7B show that targeting only the self-attention projections (1.6 B parameters of Q, K, and V matrices out of a total 7B parameters) suffices to yield large memory savings while retaining comparable state-of-the-art perplexity scores on test samples of the WikiText dataset. For example, with a 30\% sparsity budget and an outer rank of 512, sHSS-RCM achieves a perplexity of 1.64, outperforming dense baselines and classical sparse-plus-SVD variants, while also achieving significant memory savings. --- ### A Multi-Stage Workflow for the Review of Marketing Content with Reasoning Large Language Models Authors: Alberto Purpura, Emily Chen, Swapnil Shinde Published: 2025-12-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.06054v1 Reasoning Large Language Models (LLMs) have shown promising results when tasked with solving complex problems. In this paper, we propose and evaluate a multi-stage workflow that leverages the capabilities of fine-tuned reasoning LLMs to assist in the review process of marketing content, making sure they comply with a given list of requirements. The contributions of this paper are the following: (i) we present a novel approach -- that does not rely on any external knowledge representation -- for the automatic identification of compliance issues in textual content; (ii) compare the effectiveness of different fine-tuning strategies like Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO) in training models to solve this problem; (iii) we evaluate the effectiveness of training small LLMs to generate reasoning tokens before providing their final response; (iv) we evaluate how the choice and combinations of different reward functions affects the performance of a model trained with GRPO. --- ### Sports Business Administration and New Age Technology: Role of AI Authors: Sahibpreet Singh, Pawan Kumar Published: 2025-12-19 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2601.06053v1 This chapter explores the complexities of sports governance, taxation, dispute resolution, and the impact of digital transformation within the sports sector. This study identifies a critical research gap regarding the integration of innovative technologies to enhance governance and talent identification in sports law. The objective is to evaluate how data-driven approaches and AI can optimize recruitment processes; also ensuring compliance with existing regulations. A comprehensive analysis of current governance structures and taxation policies,(ie Income Tax Act and GST Act), reveals preliminary results indicating that reform is necessary to support sustainable growth in the sports economy. Key findings demonstrate that AI enhances player evaluation by minimizing biases and expanding access to diverse talent pools. While the Court of Arbitration for Sport provides an efficient mechanism for dispute resolution. The implications emphasize the need for regulatory reforms that align taxation policies with international best practices, promoting transparency and accountability in sports organizations. This research contributes valuable insights into the evolving dynamics of sports management, aiming to foster innovation and integrity in the industry. --- ### Reinforcement Learning for Chain of Thought Compression with One-Domain-to-All Generalization Authors: Hanyu Li, Jiangshan Duo, Bofei Gao, Hailin Zhang, Sujian Li, Xiaotie Deng, Liang Zhao Published: 2025-12-19 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.06052v2 Chain-of-thought reasoning in large language models can trigger an "overthinking trap": longer rollouts raise cost and latency yet often yield unreliable accuracy gains. Existing methods use global, static controls that may suppress needed reasoning. We propose mastery-gated, sample-level, soft reinforcement learning compression that penalizes long rollouts only when the model already solves the problem and has produced a shorter rollout. Across benchmarks, it cuts response length by 20-40% with comparable or higher accuracy and generalizes across domains: a model trained on math spontaneously shortens unseen tasks (code, instruction following, general-knowledge QA) without hurting accuracy. We further show two-way transfer between non-agent CoT and tool-use agents: non-agent training reduces SWE-Bench Verified rounds by 13%, while compressing a thinking agent cuts SWE trajectories by 67% tokens and 52% rounds and shortens non-agent outputs by up to 44%. Compression is thus not cosmetic brevity, but an inherent computation policy -- what to keep, and what to forget. --- ### Advances and Challenges in Semantic Textual Similarity: A Comprehensive Survey Authors: Lokendra Kumar, Neelesh S. Upadhye, Kannan Piedy Published: 2025-12-19 Categories: cs.CL, cs.AI, math.OC arXiv: https://arxiv.org/abs/2601.03270v1 Semantic Textual Similarity (STS) research has expanded rapidly since 2021, driven by advances in transformer architectures, contrastive learning, and domain-specific techniques. This survey reviews progress across six key areas: transformer-based models, contrastive learning, domain-focused solutions, multi-modal methods, graph-based approaches, and knowledge-enhanced techniques. Recent transformer models such as FarSSiBERT and DeBERTa-v3 have achieved remarkable accuracy, while contrastive methods like AspectCSE have established new benchmarks. Domain-adapted models, including CXR-BERT for medical texts and Financial-STS for finance, demonstrate how STS can be effectively customized for specialized fields. Moreover, multi-modal, graph-based, and knowledge-integrated models further enhance semantic understanding and representation. By organizing and analyzing these developments, the survey provides valuable insights into current methods, practical applications, and remaining challenges. It aims to guide researchers and practitioners alike in navigating rapid advancements, highlighting emerging trends and future opportunities in the evolving field of STS. --- ### The Instruction Gap: LLMs get lost in Following Instruction Authors: Vishesh Tripathi, Uday Allu, Biddwan Ahmed Published: 2025-12-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.03269v1 Large Language Models (LLMs) have shown remarkable capabilities in natural language understanding and generation, yet their deployment in enterprise environments reveals a critical limitation: inconsistent adherence to custom instructions. This study presents a comprehensive evaluation of 13 leading LLMs across instruction compliance, response accuracy, and performance metrics in realworld RAG (Retrieval-Augmented Generation) scenarios. Through systematic testing with samples and enterprise-grade evaluation protocols, we demonstrate that instruction following varies dramatically across models, with Claude-Sonnet-4 and GPT-5 achieving the highest results. Our findings reveal the "instruction gap" - a fundamental challenge where models excel at general tasks but struggle with precise instruction adherence required for enterprise deployment. This work provides practical insights for organizations deploying LLM-powered solutions and establishes benchmarks for instruction-following capabilities across major model families. --- ### WRAVAL -- WRiting Assist eVALuation Authors: Gabriel Benedict, Matthew Butler, Naved Merchant, Eetu Salama-Laine Published: 2025-12-19 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.03268v1 The emergence of Large Language Models (LLMs) has shifted language model evaluation toward reasoning and problem-solving tasks as measures of general intelligence. Small Language Models (SLMs) -- defined here as models under 10B parameters -- typically score 3-4 times lower than LLMs on these metrics. However, we demonstrate that these evaluations fail to capture SLMs' effectiveness in common industrial applications, such as tone modification tasks (e.g., funny, serious, professional). We propose an evaluation framework specifically designed to highlight SLMs' capabilities in non-reasoning tasks where predefined evaluation datasets don't exist. Our framework combines novel approaches in data generation, prompt-tuning, and LLM-based evaluation to demonstrate the potential of task-specific finetuning. This work provides practitioners with tools to effectively benchmark both SLMs and LLMs for practical applications, particularly in edge and private computing scenarios. Our implementation is available at: https://github.com/amazon-science/wraval. --- ### OpenAI GPT-5 System Card Authors: Aaditya Singh, Adam Fry, Adam Perelman, Adam Tart, Adi Ganesh, Ahmed El-Kishky, Aidan McLaughlin, Aiden Low, AJ Ostrow, Akhila Ananthram, Akshay Nathan, Alan Luo et al. Published: 2025-12-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.03267v2 This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits are reached, a mini version of each model handles remaining queries. This system card focuses primarily on gpt-5-thinking and gpt-5-main, while evaluations for other models are available in the appendix. The GPT-5 system not only outperforms previous models on benchmarks and answers questions more quickly, but -- more importantly -- is more useful for real-world queries. We've made significant advances in reducing hallucinations, improving instruction following, and minimizing sycophancy, and have leveled up GPT-5's performance in three of ChatGPT's most common uses: writing, coding, and health. All of the GPT-5 models additionally feature safe-completions, our latest approach to safety training to prevent disallowed content. Similarly to ChatGPT agent, we have decided to treat gpt-5-thinking as High capability in the Biological and Chemical domain under our Preparedness Framework, activating the associated safeguards. While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm -- our defined threshold for High capability -- we have chosen to take a precautionary approach. --- ### Spike-Timing-Dependent Plasticity for Bernoulli Message Passing Authors: Sepideh Adamiat, Wouter M. Kouw, Bert de Vries Published: 2025-12-19 Categories: q-bio.NC, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2512.23728v1 Bayesian inference provides a principled framework for understanding brain function, while neural activity in the brain is inherently spike-based. This paper bridges these two perspectives by designing spiking neural networks that simulate Bayesian inference through message passing for Bernoulli messages. To train the networks, we employ spike-timing-dependent plasticity, a biologically plausible mechanism for synaptic plasticity which is based on the Hebbian rule. Our results demonstrate that the network's performance closely matches the true numerical solution. We further demonstrate the versatility of our approach by implementing a factor graph example from coding theory, illustrating signal transmission over an unreliable channel. --- ### q3-MuPa: Quick, Quiet, Quantitative Multi-Parametric MRI using Physics-Informed Diffusion Models Authors: Shishuai Wang, Florian Wiesinger, Noemi Sgambelluri, Carolin Pirkl, Stefan Klein, Juan A. Hernandez-Tamames, Dirk H. J. Poot Published: 2025-12-19 Categories: physics.med-ph, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.23726v2 The 3D fast silent multi-parametric mapping sequence with zero echo time (MuPa-ZTE) is a novel quantitative MRI (qMRI) acquisition that enables nearly silent scanning by using a 3D phyllotaxis sampling scheme. MuPa-ZTE improves patient comfort and motion robustness, and generates quantitative maps of T1, T2, and proton density using the acquired weighted image series. In this work, we propose a diffusion model-based qMRI mapping method that leverages both a deep generative model and physics-based data consistency to further improve the mapping performance. Furthermore, our method enables additional acquisition acceleration, allowing high-quality qMRI mapping from a fourfold-accelerated MuPa-ZTE scan (approximately 1 minute). Specifically, we trained a denoising diffusion probabilistic model (DDPM) to map MuPa-ZTE image series to qMRI maps, and we incorporated the MuPa-ZTE forward signal model as an explicit data consistency (DC) constraint during inference. We compared our mapping method against a baseline dictionary matching approach and a purely data-driven diffusion model. The diffusion models were trained entirely on synthetic data generated from digital brain phantoms, eliminating the need for large real-scan datasets. We evaluated on synthetic data, a NISM/ISMRM phantom, healthy volunteers, and a patient with brain metastases. The results demonstrated that our method produces 3D qMRI maps with high accuracy, reduced noise and better preservation of structural details. Notably, it generalised well to real scans despite training on synthetic data alone. The combination of the MuPa-ZTE acquisition and our physics-informed diffusion model is termed q3-MuPa, a quick, quiet, and quantitative multi-parametric mapping framework, and our findings highlight its strong clinical potential. --- ### AI-Enhanced Virtual Biopsies for Brain Tumor Diagnosis in Low Resource Settings Authors: Areeb Ehsan Published: 2025-12-19 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2512.22184v1 Timely brain tumor diagnosis remains challenging in low-resource clinical environments where expert neuroradiology interpretation, high-end MRI hardware, and invasive biopsy procedures may be limited. Although deep learning has achieved strong performance in brain tumor analysis, real-world adoption is constrained by computational demands, dataset shift across scanners, and limited interpretability. This paper presents a prototype virtual biopsy pipeline for four-class classification of 2D brain MRI images using a lightweight convolutional neural network (CNN) and complementary radiomics-style handcrafted features. A MobileNetV2-based CNN is trained for classification, while an interpretable radiomics branch extracts eight features capturing lesion shape, intensity statistics, and gray-level co-occurrence matrix (GLCM) texture descriptors. A late fusion strategy concatenates CNN embeddings with radiomics features and trains a RandomForest classifier on the fused representation. Explainability is provided via Grad-CAM visualizations and radiomics feature importance analysis. Experiments on a public Kaggle brain tumor MRI dataset show improved validation performance for fusion relative to single-branch baselines, while robustness tests under reduced resolution and additive noise highlight sensitivity relevant to low-resource imaging conditions. The system is framed as decision support and not a substitute for clinical diagnosis or histopathology. --- ### Unbiased Visual Reasoning with Controlled Visual Inputs Authors: Zhaonan Li, Shijie Lu, Fei Wang, Jacob Dineen, Xiao Ye, Zhikun Xu, Siyi Liu, Young Min Cho, Bangzheng Li, Daniel Chang, Kenny Nguyen, Qizheng Yang et al. Published: 2025-12-19 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.22183v1 End-to-end Vision-language Models (VLMs) often answer visual questions by exploiting spurious correlations instead of causal visual evidence, and can become more shortcut-prone when fine-tuned. We introduce VISTA (Visual-Information Separation for Text-based Analysis), a modular framework that decouples perception from reasoning via an explicit information bottleneck. A frozen VLM sensor is restricted to short, objective perception queries, while a text-only LLM reasoner decomposes each question, plans queries, and aggregates visual facts in natural language. This controlled interface defines a reward-aligned environment for training unbiased visual reasoning with reinforcement learning. Instantiated with Qwen2.5-VL and Llama3.2-Vision sensors, and trained with GRPO from only 641 curated multi-step questions, VISTA significantly improves robustness to real-world spurious correlations on SpuriVerse (+16.29% with Qwen-2.5-VL-7B and +6.77% with Llama-3.2-Vision-11B), while remaining competitive on MMVP and a balanced SeedBench subset. VISTA transfers robustly across unseen VLM sensors and is able to recognize and recover from VLM perception failures. Human analysis further shows that VISTA's reasoning traces are more neutral, less reliant on spurious attributes, and more explicitly grounded in visual evidence than end-to-end VLM baselines. --- ### Enhancing Medical Data Analysis through AI-Enhanced Locally Linear Embedding: Applications in Medical Point Location and Imagery Authors: Hassan Khalid, Muhammad Mahad Khaliq, Muhammad Jawad Bashir Published: 2025-12-19 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.22182v1 The rapid evolution of Artificial intelligence in healthcare has opened avenues for enhancing various processes, including medical billing and transcription. This paper introduces an innovative approach by integrating AI with Locally Linear Embedding (LLE) to revolutionize the handling of high-dimensional medical data. This AI-enhanced LLE model is specifically tailored to improve the accuracy and efficiency of medical billing systems and transcription services. By automating these processes, the model aims to reduce human error and streamline operations, thereby facilitating faster and more accurate patient care documentation and financial transactions. This paper provides a comprehensive mathematical model of AI-enhanced LLE, demonstrating its application in real-world healthcare scenarios through a series of experiments. The results indicate a significant improvement in data processing accuracy and operational efficiency. This study not only underscores the potential of AI-enhanced LLE in medical data analysis but also sets a foundation for future research into broader healthcare applications. --- ### Interpretable Link Prediction in AI-Driven Cancer Research: Uncovering Co-Authorship Patterns Authors: Shahab Mosallaie, Andrea Schiffauerova, Ashkan Ebadi Published: 2025-12-19 Categories: cs.DL, cs.AI arXiv: https://arxiv.org/abs/2512.22181v1 Artificial intelligence (AI) is transforming cancer diagnosis and treatment. The intricate nature of this disease necessitates the collaboration of diverse stakeholders with varied expertise to ensure the effectiveness of cancer research. Despite its importance, forming effective interdisciplinary research teams remains challenging. Understanding and predicting collaboration patterns can help researchers, organizations, and policymakers optimize resources and foster impactful research. We examined co-authorship networks as a proxy for collaboration within AI-driven cancer research. Using 7,738 publications (2000-2017) from Scopus, we constructed 36 overlapping co-authorship networks representing new, persistent, and discontinued collaborations. We engineered both attribute-based and structure-based features and built four machine learning classifiers. Model interpretability was performed using Shapley Additive Explanations (SHAP). Random forest achieved the highest recall for all three types of examined collaborations. The discipline similarity score emerged as a crucial factor, positively affecting new and persistent patterns while negatively impacting discontinued collaborations. Additionally, high productivity and seniority were positively associated with discontinued links. Our findings can guide the formation of effective research teams, enhance interdisciplinary cooperation, and inform strategic policy decisions. --- ### iOS as Acceleration Authors: Alexander K. Chen Published: 2025-12-19 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2512.22180v1 Practical utilization of large-scale machine learning requires a powerful compute setup, a necessity which poses a significant barrier to engagement with such artificial intelligence in more restricted system environments. While cloud computing offers a solution to weaker local environments, certain situations like training involving private or sensitive data, physical environments not available through the cloud, or higher anticipated usage costs, necessitate computing locally. We explore the potential to improve weaker local compute systems at zero additional cost by taking advantage of ubiquitous yet underutilized resources: mobile phones. Specifically, recent iOS phones are equipped with surprisingly powerful processors, but they also face limitations like memory constraints, thermal throttling, and OS sandboxing. We present a proof-of-concept system demonstrating a novel approach to harness an iOS device via distributed pipeline parallelism, achieving significant benefits in a lesser compute environment by accelerating modest model training, batch inference, and agentic LRM tool-usage. We discuss practical use-cases, limitations, and directions for future work. The findings of this paper highlight the potential for the improving commonplace mobile devices to provide greater contributions to machine learning. --- ### Latent Sculpting for Zero-Shot Generalization: A Manifold Learning Approach to Out-of-Distribution Anomaly Detection Authors: Rajeeb Thapa Chhetri, Saurab Thapa, Avinash Kumar, Zhixiong Chen Published: 2025-12-19 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2512.22179v3 Detecting previously unseen attacks remains a major challenge for machine learning-based intrusion detection systems. Deep models trained on network traffic often achieve high accuracy on known attacks but fail under distributional shift because their decision boundaries are tightly coupled to the training data distribution. We introduce Latent Sculpting, a two-stage anomaly detection framework that improves robustness by explicitly structuring the latent representation before density estimation. The first stage trains a Transformer-based tabular encoder using a novel Binary Latent Sculpting loss, which encourages benign traffic to form a compact latent cluster while enforcing separation from anomalous patterns. The second stage fits a Masked Autoregressive Flow to the resulting latent space to produce calibrated probabilistic anomaly scores. Under a strict zero-shot evaluation protocol on the CIC-IDS-2017 benchmark, Stage 1 attains an F1-score of 0.98 on known attacks, while Stage 2 -- evaluated at the balanced threshold (85th-percentile) -- achieves a zero-shot OOD F1-score of 0.867 and AUROC of 0.913. The model successfully detects difficult distribution shifts including stealthy infiltration attacks (78.7% recall, peaking at 97.2%) and low-volume DoS variants (>94% recall), scenarios where conventional approaches often fail. Our results suggest that explicitly separating latent geometry learning from density modeling provides a stable approach for detecting zero-day cyber threats. --- ### Wireless Traffic Prediction with Large Language Model Authors: Chuanting Zhang, Haixia Zhang, Jingping Qiao, Zongzhang Li, Mohamed-Slim Alouini Published: 2025-12-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.22178v1 The growing demand for intelligent, adaptive resource management in next-generation wireless networks has underscored the importance of accurate and scalable wireless traffic prediction. While recent advancements in deep learning and foundation models such as large language models (LLMs) have demonstrated promising forecasting capabilities, they largely overlook the spatial dependencies inherent in city-scale traffic dynamics. In this paper, we propose TIDES (Traffic Intelligence with DeepSeek-Enhanced Spatial-temporal prediction), a novel LLM-based framework that captures spatial-temporal correlations for urban wireless traffic prediction. TIDES first identifies heterogeneous traffic patterns across regions through a clustering mechanism and trains personalized models for each region to balance generalization and specialization. To bridge the domain gap between numerical traffic data and language-based models, we introduce a prompt engineering scheme that embeds statistical traffic features as structured inputs. Furthermore, we design a DeepSeek module that enables spatial alignment via cross-domain attention, allowing the LLM to leverage information from spatially related regions. By fine-tuning only lightweight components while freezing core LLM layers, TIDES achieves efficient adaptation to domain-specific patterns without incurring excessive training overhead. Extensive experiments on real-world cellular traffic datasets demonstrate that TIDES significantly outperforms state-of-the-art baselines in both prediction accuracy and robustness. Our results indicate that integrating spatial awareness into LLM-based predictors is the key to unlocking scalable and intelligent network management in future 6G systems. --- ### Real-Time American Sign Language Recognition Using 3D Convolutional Neural Networks and LSTM: Architecture, Training, and Deployment Authors: Dawnena Key Published: 2025-12-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22177v1 This paper presents a real-time American Sign Language (ASL) recognition system utilizing a hybrid deep learning architecture combining 3D Convolutional Neural Networks (3D CNN) with Long Short-Term Memory (LSTM) networks. The system processes webcam video streams to recognize word-level ASL signs, addressing communication barriers for over 70 million deaf and hard-of-hearing individuals worldwide. Our architecture leverages 3D convolutions to capture spatial-temporal features from video frames, followed by LSTM layers that model sequential dependencies inherent in sign language gestures. Trained on the WLASL dataset (2,000 common words), ASL-LEX lexical database (~2,700 signs), and a curated set of 100 expert-annotated ASL signs, the system achieves F1-scores ranging from 0.71 to 0.99 across sign classes. The model is deployed on AWS infrastructure with edge deployment capability on OAK-D cameras for real-time inference. We discuss the architecture design, training methodology, evaluation metrics, and deployment considerations for practical accessibility applications. --- ### Fairness Is Not Just Ethical: Performance Trade-Off via Data Correlation Tuning to Mitigate Bias in ML Software Authors: Ying Xiao, Shangwen Wang, Sicen Liu, Dingyuan Xue, Xian Zhan, Yepang Liu, Jie M. Zhang Published: 2025-12-19 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.21348v1 Traditional software fairness research typically emphasizes ethical and social imperatives, neglecting that fairness fundamentally represents a core software quality issue arising directly from performance disparities across sensitive user groups. Recognizing fairness explicitly as a software quality dimension yields practical benefits beyond ethical considerations, notably improved predictive performance for unprivileged groups, enhanced out-of-distribution generalization, and increased geographic transferability in real-world deployments. Nevertheless, existing bias mitigation methods face a critical dilemma: while pre-processing methods offer broad applicability across model types, they generally fall short in effectiveness compared to post-processing techniques. To overcome this challenge, we propose Correlation Tuning (CoT), a novel pre-processing approach designed to mitigate bias by adjusting data correlations. Specifically, CoT introduces the Phi-coefficient, an intuitive correlation measure, to systematically quantify correlation between sensitive attributes and labels, and employs multi-objective optimization to address the proxy biases. Extensive evaluations demonstrate that CoT increases the true positive rate of unprivileged groups by an average of 17.5% and reduces three key bias metrics, including statistical parity difference (SPD), average odds difference (AOD), and equal opportunity difference (EOD), by more than 50% on average. CoT outperforms state-of-the-art methods by three and ten percentage points in single attribute and multiple attributes scenarios, respectively. We will publicly release our experimental results and source code to facilitate future research. --- ### Query Carefully: Detecting the Unanswerables in Text-to-SQL Tasks Authors: Jasmin Saxer, Isabella Maria Aigner, Luise Linzmeier, Andreas Weiler, Kurt Stockinger Published: 2025-12-19 Categories: cs.DB, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.21345v1 Text-to-SQL systems allow non-SQL experts to interact with relational databases using natural language. However, their tendency to generate executable SQL for ambiguous, out-of-scope, or unanswerable queries introduces a hidden risk, as outputs may be misinterpreted as correct. This risk is especially serious in biomedical contexts, where precision is critical. We therefore present Query Carefully, a pipeline that integrates LLM-based SQL generation with explicit detection and handling of unanswerable inputs. Building on the OncoMX component of ScienceBenchmark, we construct OncoMX-NAQ (No-Answer Questions), a set of 80 no-answer questions spanning 8 categories (non-SQL, out-of-schema/domain, and multiple ambiguity types). Our approach employs llama3.3:70b with schema-aware prompts, explicit No-Answer Rules (NAR), and few-shot examples drawn from both answerable and unanswerable questions. We evaluate SQL exact match, result accuracy, and unanswerable-detection accuracy. On the OncoMX dev split, few-shot prompting with answerable examples increases result accuracy, and adding unanswerable examples does not degrade performance. On OncoMX-NAQ, balanced prompting achieves the highest unanswerable-detection accuracy (0.8), with near-perfect results for structurally defined categories (non-SQL, missing columns, out-of-domain) but persistent challenges for missing-value queries (0.5) and column ambiguity (0.3). A lightweight user interface surfaces interim SQL, execution results, and abstentions, supporting transparent and reliable text-to-SQL in biomedical applications. --- ### Bridging the AI Trustworthiness Gap between Functions and Norms Authors: Daan Di Scala, Sophie Lathouwers, Michael van Bekkum Published: 2025-12-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.20671v1 Trustworthy Artificial Intelligence (TAI) is gaining traction due to regulations and functional benefits. While Functional TAI (FTAI) focuses on how to implement trustworthy systems, Normative TAI (NTAI) focuses on regulations that need to be enforced. However, gaps between FTAI and NTAI remain, making it difficult to assess trustworthiness of AI systems. We argue that a bridge is needed, specifically by introducing a conceptual language which can match FTAI and NTAI. Such a semantic language can assist developers as a framework to assess AI systems in terms of trustworthiness. It can also help stakeholders translate norms and regulations into concrete implementation steps for their systems. In this position paper, we describe the current state-of-the-art and identify the gap between FTAI and NTAI. We will discuss starting points for developing a semantic language and the envisioned effects of it. Finally, we provide key considerations and discuss future actions towards assessment of TAI. --- ### Disentangling Fact from Sentiment: A Dynamic Conflict-Consensus Framework for Multimodal Fake News Detection Authors: Weilin Zhou, Zonghao Ying, Rongchen Zhao, Chunlei Meng, Quanchen Zou, Deyue Zhang, Enhao Gu, Mingze Liu, Dongdong Yang, Xiangzheng Zhang Published: 2025-12-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.20670v2 Prevalent multimodal fake news detection relies on consistency-based fusion, yet this paradigm fundamentally misinterprets critical cross-modal discrepancies as noise, leading to over-smoothing, which dilutes critical evidence of fabrication. Mainstream consistency-based fusion inherently minimizes feature discrepancies to align modalities, yet this approach fundamentally fails because it inadvertently smoothes out the subtle cross-modal contradictions that serve as the primary evidence of fabrication. To address this, we propose the Dynamic Conflict-Consensus Framework (DCCF), an inconsistency-seeking paradigm designed to amplify rather than suppress contradictions. First, DCCF decouples inputs into independent Fact and Sentiment spaces to distinguish objective mismatches from emotional dissonance. Second, we employ physics-inspired feature dynamics to iteratively polarize these representations, actively extracting maximally informative conflicts. Finally, a conflict-consensus mechanism standardizes these local discrepancies against the global context for robust deliberative judgment.Extensive experiments conducted on three real world datasets demonstrate that DCCF consistently outperforms state-of-the-art baselines, achieving an average accuracy improvement of 3.52\%. --- ### Improving Cardiac Risk Prediction Using Data Generation Techniques Authors: Alexandre Cabodevila, Pedro Gamallo-Fernandez, Juan C. Vidal, Manuel Lama Published: 2025-12-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.20669v1 Cardiac rehabilitation constitutes a structured clinical process involving multiple interdependent phases, individualized medical decisions, and the coordinated participation of diverse healthcare professionals. This sequential and adaptive nature enables the program to be modeled as a business process, thereby facilitating its analysis. Nevertheless, studies in this context face significant limitations inherent to real-world medical databases: data are often scarce due to both economic costs and the time required for collection; many existing records are not suitable for specific analytical purposes; and, finally, there is a high prevalence of missing values, as not all patients undergo the same diagnostic tests. To address these limitations, this work proposes an architecture based on a Conditional Variational Autoencoder (CVAE) for the synthesis of realistic clinical records that are coherent with real-world observations. The primary objective is to increase the size and diversity of the available datasets in order to enhance the performance of cardiac risk prediction models and to reduce the need for potentially hazardous diagnostic procedures, such as exercise stress testing. The results demonstrate that the proposed architecture is capable of generating coherent and realistic synthetic data, whose use improves the accuracy of the various classifiers employed for cardiac risk detection, outperforming state-of-the-art deep learning approaches for synthetic data generation. --- ### Forward Only Learning for Orthogonal Neural Networks of any Depth Authors: Paul Caillon, Alex Colagrande, Erwan Fagnou, Blaise Delattre, Alexandre Allauzen Published: 2025-12-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.20668v1 Backpropagation is still the de facto algorithm used today to train neural networks. With the exponential growth of recent architectures, the computational cost of this algorithm also becomes a burden. The recent PEPITA and forward-only frameworks have proposed promising alternatives, but they failed to scale up to a handful of hidden layers, yet limiting their use. In this paper, we first analyze theoretically the main limitations of these approaches. It allows us the design of a forward-only algorithm, which is equivalent to backpropagation under the linear and orthogonal assumptions. By relaxing the linear assumption, we then introduce FOTON (Forward-Only Training of Orthogonal Networks) that bridges the gap with the backpropagation algorithm. Experimental results show that it outperforms PEPITA, enabling us to train neural networks of any depth, without the need for a backward pass. Moreover its performance on convolutional networks clearly opens up avenues for its application to more advanced architectures. The code is open-sourced at https://github.com/p0lcAi/FOTON . --- ### Dominant vs. Dominated: Concept-Level Generative Collapse in Diffusion Models Authors: Hayeon Jeong, Jong-Seok Lee Published: 2025-12-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.20666v2 Text-to-image diffusion models have attracted significant attention for their ability to generate diverse, high-fidelity images. However, in multi-concept generation, one concept token often dominates the output while others are suppressed-a phenomenon we term the Dominant-vs-Dominated (DvD) imbalance. To systematically study this failure mode, we introduce DominanceBench and examine its underlying causes from both data and internal-mechanistic perspectives. Our controlled fine-tuning study, which mimics concept learning during diffusion-model training, shows that concepts learned from visually homogeneous (low-variation) concept-specific training images exhibit stronger dominance when composed with others. Cross-attention analysis indicates that dominant tokens concentrate attention in early denoising steps, followed by reduced representation of competing concepts. Head-ablation analysis further shows that this dominance is distributed across attention heads rather than localized. Overall, these findings characterize DvD as a systematic concept-level failure mode and provide a basis for more reliable and controllable multi-concept generation. DominanceBench will be released upon publication. --- ### Eidoku: A Neuro-Symbolic Verification Gate for LLM Reasoning via Structural Constraint Satisfaction Authors: Shinobu Miya Published: 2025-12-19 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2512.20664v1 Large Language Models (LLMs) frequently produce hallucinated statements that are assigned high likelihood by the model itself, exposing a fundamental limitation of probability-based verification. This suggests that hallucination is often not a low-confidence phenomenon, but a failure of structural consistency. In this work, we reformulate the verification of LLM reasoning as a Constraint Satisfaction Problem (CSP) operating independently of the generation likelihood. Rather than optimizing for statistical plausibility, we model verification as a feasibility check based on structural violation cost -- the computational cost required to embed a candidate reasoning step into the contextual graph structure. We define a total cost function composed of three proxies: (i) graph connectivity (structural), (ii) feature space consistency (geometric), and (iii) logical entailment (symbolic). Crucially, verification is performed via a lightweight System-2 gate, Eidoku, which rejects candidates exceeding a context-calibrated cost threshold. The threshold is not learned but is derived from the intrinsic statistics of the context, avoiding ad hoc heuristics. We demonstrate that this approach successfully rejects ``smooth falsehoods'' -- statements that are highly probable yet structurally disconnected -- that probability-based verifiers are principally incapable of detecting. Our experiments on a controlled diagnostic dataset show that explicitly enforcing structural constraints allows for the deterministic rejection of this specific class of hallucinations, serving as a neuro-symbolic sanity check for generative reasoning. --- ### Quantifying Laziness, Decoding Suboptimality, and Context Degradation in Large Language Models Authors: Yiqing Ma, Jung-Hua Liu Published: 2025-12-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.20662v1 Large Language Models (LLMs) often exhibit behavioral artifacts such as laziness (premature truncation of responses or partial compliance with multi-part requests), decoding suboptimality (failure to select higher-quality sequences due to myopic decoding), and context degradation (forgetting or ignoring core instructions over long conversations). We conducted three controlled experiments (A, B, and C) to quantify these phenomena across several advanced LLMs (OpenAI GPT-4 variant, DeepSeek). Our results indicate widespread laziness in satisfying complex multi-part instructions: models frequently omitted required sections or failed to meet length requirements despite explicit prompting. However, we found limited evidence of decoding suboptimality in a simple reasoning task (the models' greedy answers appeared to align with their highest-confidence solution), and we observed surprising robustness against context degradation in a 200-turn chaotic conversation test - the models maintained key facts and instructions far better than expected. These findings suggest that while compliance with detailed instructions remains an open challenge, modern LLMs may internally mitigate some hypothesized failure modes (such as context forgetting) in straightforward retrieval scenarios. We discuss implications for reliability, relate our findings to prior work on instruction-following and long-context processing, and recommend strategies (such as self-refinement and dynamic prompting) to reduce laziness and bolster multi-instruction compliance. --- ### Calibrating Transformer Attention via Task-Space Sensitivity Feedback Authors: Yawei Liu Published: 2025-12-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.20661v2 Transformer-based pre-trained language models (PLMs) excel in text classification but suffer from attention dilution and attention sink effects, forcing models to over-focus on task-irrelevant tokens. Existing attention supervision methods rely on costly token-level human annotations or static heuristics, which fail to scale or capture context-dependent token importance. To address this, we propose AttCal, a self-supervised, annotation-free attention calibration framework via task-space sensitivity feedback. AttCal treats attention distributions as stochastic policies to guide token deletion perturbations, infers context-dependent token importance from semantic shifts, and optimizes attention parameters via policy gradient. Critically, AttCal freezes the PLM backbone and updates only attention projection layers to ensure training efficiency. Benchmarks across five datasets demonstrate that AttCal significantly outperforms vanilla PLMs-yielding up to a 15.8% accuracy lift for Llama3-8B-and surpasses SOTA supervised baselines in both classification and interpretability. --- ### Attention Distance: A Novel Metric for Directed Fuzzing with Large Language Models Authors: Wang Bin, Ao Yang, Kedan Li, Aofan Liu, Hui Li, Guibo Luo, Weixiang Huang, Yan Zhuang Published: 2025-12-19 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.19758v1 In the domain of software security testing, Directed Grey-Box Fuzzing (DGF) has garnered widespread attention for its efficient target localization and excellent detection performance. However, existing approaches measure only the physical distance between seed execution paths and target locations, overlooking logical relationships among code segments. This omission can yield redundant or misleading guidance in complex binaries, weakening DGF's real-world effectiveness. To address this, we introduce \textbf{attention distance}, a novel metric that leverages a large language model's contextual analysis to compute attention scores between code elements and reveal their intrinsic connections. Under the same AFLGo configuration -- without altering any fuzzing components other than the distance metric -- replacing physical distances with attention distances across 38 real vulnerability reproduction experiments delivers a \textbf{3.43$\times$} average increase in testing efficiency over the traditional method. Compared to state-of-the-art directed fuzzers DAFL and WindRanger, our approach achieves \textbf{2.89$\times$} and \textbf{7.13$\times$} improvements, respectively. To further validate the generalizability of attention distance, we integrate it into DAFL and WindRanger, where it also consistently enhances their original performance. All related code and datasets are publicly available at https://github.com/TheBinKing/Attention\_Distance.git. --- ### QMBench: A Research Level Benchmark for Quantum Materials Research Authors: Yanzhen Wang, Yiyang Jiang, Diana Golovanova, Kamal Das, Hyeonhu Bae, Yufei Zhao, Huu-Thong Le, Abhinava Chatterjee, Yunzhe Liu, Chao-Xing Liu, Felipe H. da Jornada, Binghai Yan et al. Published: 2025-12-19 Categories: cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2512.19753v1 We introduce QMBench, a comprehensive benchmark designed to evaluate the capability of large language model agents in quantum materials research. This specialized benchmark assesses the model's ability to apply condensed matter physics knowledge and computational techniques such as density functional theory to solve research problems in quantum materials science. QMBench encompasses different domains of the quantum material research, including structural properties, electronic properties, thermodynamic and other properties, symmetry principle and computational methodologies. By providing a standardized evaluation framework, QMBench aims to accelerate the development of an AI scientist capable of making creative contributions to quantum materials research. We expect QMBench to be developed and constantly improved by the research community. --- ### Unifying Causal Reinforcement Learning: Survey, Taxonomy, Algorithms and Applications Authors: Cristiano da Costa Cunha, Wei Liu, Tim French, Ajmal Mian Published: 2025-12-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.18135v1 Integrating causal inference (CI) with reinforcement learning (RL) has emerged as a powerful paradigm to address critical limitations in classical RL, including low explainability, lack of robustness and generalization failures. Traditional RL techniques, which typically rely on correlation-driven decision-making, struggle when faced with distribution shifts, confounding variables, and dynamic environments. Causal reinforcement learning (CRL), leveraging the foundational principles of causal inference, offers promising solutions to these challenges by explicitly modeling cause-and-effect relationships. In this survey, we systematically review recent advancements at the intersection of causal inference and RL. We categorize existing approaches into causal representation learning, counterfactual policy optimization, offline causal RL, causal transfer learning, and causal explainability. Through this structured analysis, we identify prevailing challenges, highlight empirical successes in practical applications, and discuss open problems. Finally, we provide future research directions, underscoring the potential of CRL for developing robust, generalizable, and interpretable artificial intelligence systems. --- ### Optimal Software Pipelining and Warp Specialization for Tensor Core GPUs Authors: Rupanshu Soi, Rohan Yadav, Fredrik Kjolstad, Alex Aiken, Maryam Mehri Dehnavi, Michael Garland, Michael Bauer Published: 2025-12-19 Categories: cs.PL, cs.AR, cs.LG arXiv: https://arxiv.org/abs/2512.18134v1 GPU architectures have continued to grow in complexity, with recent incarnations introducing increasingly powerful fixed-function units for matrix multiplication and data movement to accompany highly parallel general-purpose cores. To fully leverage these machines, software must use sophisticated schedules that maximally utilize all hardware resources. Since realizing such schedules is complex, both programmers and compilers routinely employ program transformations, such as software pipelining (SWP) and warp specialization (WS), to do so in practice. However, determining how best to use SWP and WS in combination is a challenging problem that is currently handled through a mix of brittle compilation heuristics and fallible human intuition, with little insight into the space of solutions. To remedy this situation, we introduce a novel formulation of SWP and WS as a joint optimization problem that can be solved holistically by off-the-shelf constraint solvers. We reify our approach in Twill, the first system that automatically derives optimal SWP and WS schedules for a large class of iterative programs. Twill is heuristic-free, easily extensible to new GPU architectures, and guaranteed to produce optimal schedules. We show that Twill can rediscover, and thereby prove optimal, the SWP and WS schedules manually developed by experts for Flash Attention on both the NVIDIA Hopper and Blackwell GPU architectures. --- ### Grad: Guided Relation Diffusion Generation for Graph Augmentation in Graph Fraud Detection Authors: Jie Yang, Rui Zhang, Ziyang Cheng, Dawei Cheng, Guang Yang, Bo Wang Published: 2025-12-19 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2512.18133v1 Nowadays, Graph Fraud Detection (GFD) in financial scenarios has become an urgent research topic to protect online payment security. However, as organized crime groups are becoming more professional in real-world scenarios, fraudsters are employing more sophisticated camouflage strategies. Specifically, fraudsters disguise themselves by mimicking the behavioral data collected by platforms, ensuring that their key characteristics are consistent with those of benign users to a high degree, which we call Adaptive Camouflage. Consequently, this narrows the differences in behavioral traits between them and benign users within the platform's database, thereby making current GFD models lose efficiency. To address this problem, we propose a relation diffusion-based graph augmentation model Grad. In detail, Grad leverages a supervised graph contrastive learning module to enhance the fraud-benign difference and employs a guided relation diffusion generator to generate auxiliary homophilic relations from scratch. Based on these, weak fraudulent signals would be enhanced during the aggregation process, thus being obvious enough to be captured. Extensive experiments have been conducted on two real-world datasets provided by WeChat Pay, one of the largest online payment platforms with billions of users, and three public datasets. The results show that our proposed model Grad outperforms SOTA methods in both various scenarios, achieving at most 11.10% and 43.95% increases in AUC and AP, respectively. Our code is released at https://github.com/AI4Risk/antifraud and https://github.com/Muyiiiii/WWW25-Grad. --- ### Holistic Evaluation of State-of-the-Art LLMs for Code Generation Authors: Le Zhang, Suresh Kothari Published: 2025-12-19 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.18131v1 This study presents a comprehensive empirical evaluation of six state-of-the-art large language models (LLMs) for code generation, including both general-purpose and code-specialized models. Using a dataset of 944 real-world LeetCode problems across five programming languages, we assess model performance using rigorous metrics: compile-time errors, runtime errors, functional failures, and algorithmic suboptimalities. The results reveal significant performance variations, with DeepSeek-R1 and GPT-4.1 consistently outperform others in terms of correctness, efficiency, and robustness. Through detailed case studies, we identify common failure scenarios such as syntax errors, logical flaws, and suboptimal algorithms, highlighting the critical role of prompt engineering and human oversight in improving results. Based on these findings, we provide actionable recommendations for developers and practitioners, emphasizing that successful LLM deployment depends on careful model selection, effective prompt design, and context-aware usage to ensure reliable code generation in real-world software development tasks. ---