# Research Papers — 2025-12 · bundle page 129 of 175 > Full-text markdown of papers #6401–6450 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/129 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/128.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/130.md) ### Enhancing knowledge tracing robustness for new question cold start in Intelligent Tutoring Systems Authors: Wonbeen Lee, Channyoung Lee, Junho Sohn, Hansam Cho Published: 2025-12-08 Categories: cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2512.07179v2 Intelligent Tutoring Systems (ITS) provide personalized learning paths by diagnosing learners' proficiency. Knowledge Tracing (KT) models play a central role in this diagnosis by estimating learners' evolving knowledge states. However, in real-world ITS services, diagnostic reliability may decrease when newly introduced questions have no prior interaction history. This study aims to empirically identify the key features that support KT model robustness under the question cold start situation. To this end, we designed Practical Integrated Cross-consistent Knowledge Tracing (PICKT), which integrates multiple types of features, and examined which feature contributes to robustness under the question cold start situation. Among these features, we further analyzed difficulty, texts, and relational information derived from the knowledge map, which have been identified as important factors in prior KT research, to examine how each contributes to robustness under the question cold start situation. The results showed that difficulty feature was particularly informative for highly challenging questions, where the likelihood of a correct response rate was remarkably low. Meanwhile, the fused texts and knowledge map features supported robustness by enabling the model to estimate the representation of unseen questions by leveraging semantically and structurally similar questions observed during training. These findings suggest that maintaining KT robustness in ITS applications requires prioritization of feature annotation aligned with the characteristics of educational services. --- ### ContextualSHAP : Enhancing SHAP Explanations Through Contextual Language Generation Authors: Latifa Dwiyanti, Sergio Ryan Wibisono, Hidetaka Nambo Published: 2025-12-08 Categories: cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2512.07178v1 Explainable Artificial Intelligence (XAI) has become an increasingly important area of research, particularly as machine learning models are deployed in high-stakes domains. Among various XAI approaches, SHAP (SHapley Additive exPlanations) has gained prominence due to its ability to provide both global and local explanations across different machine learning models. While SHAP effectively visualizes feature importance, it often lacks contextual explanations that are meaningful for end-users, especially those without technical backgrounds. To address this gap, we propose a Python package that extends SHAP by integrating it with a large language model (LLM), specifically OpenAI's GPT, to generate contextualized textual explanations. This integration is guided by user-defined parameters (such as feature aliases, descriptions, and additional background) to tailor the explanation to both the model context and the user perspective. We hypothesize that this enhancement can improve the perceived understandability of SHAP explanations. To evaluate the effectiveness of the proposed package, we applied it in a healthcare-related case study and conducted user evaluations involving real end-users. The results, based on Likert-scale surveys and follow-up interviews, indicate that the generated explanations were perceived as more understandable and contextually appropriate compared to visual-only outputs. While the findings are preliminary, they suggest that combining visualization with contextualized text may support more user-friendly and trustworthy model explanations. --- ### SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models Authors: Yibo Wang, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Lijun Zhang Published: 2025-12-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.07175v1 Self-play fine-tuning has demonstrated promising abilities in adapting large language models (LLMs) to downstream tasks with limited real-world data. The basic principle is to iteratively refine the model with real samples and synthetic ones generated from itself. However, the existing methods primarily focus on the relative gaps between the rewards for two types of data, neglecting their absolute values. Through theoretical analysis, we identify that the gap-based methods suffer from unstable evolution, due to the potentially degenerated objectives. To address this limitation, we introduce a novel self-play fine-tuning method, namely Self-PlAy via Noise Contrastive Estimation (SPACE), which leverages noise contrastive estimation to capture the real-world data distribution. Specifically, SPACE treats synthetic samples as auxiliary components, and discriminates them from the real ones in a binary classification manner. As a result, SPACE independently optimizes the absolute reward values for each type of data, ensuring a consistently meaningful objective and thereby avoiding the instability issue. Theoretically, we show that the optimal solution of the objective in SPACE aligns with the underlying distribution of real-world data, and SPACE guarantees a provably stable convergence to the optimal distribution. Empirically, we show that SPACE significantly improves the performance of LLMs over various tasks, and outperforms supervised fine-tuning that employs much more real-world samples. Compared to gap-based self-play fine-tuning methods, SPACE exhibits remarkable superiority and stable evolution. --- ### Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration Authors: Jucheng Shen, Gaurav Sarkar, Yeonju Ro, Sharath Nittur Sridhar, Zhangyang Wang, Aditya Akella, Souvik Kundu Published: 2025-12-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.07173v4 We present CadLLM, a training-free method to accelerate the inference throughput of diffusion-based LLMs (dLLMs). We first investigate the dynamic nature of token unmasking confidence across blocks and steps. Based on this observation, we present a lightweight adaptive approach that controls the generation block size, step size, and threshold based on the average confidence of unmasked tokens. We further reduce softmax overhead by dynamically leveraging a subset of the vocabulary to regulate sampling breadth. CadLLM is a plug-and-play, model-agnostic method compatible with KV-cache-based dLLMs. Extensive experiments on four popular tasks demonstrate that CadLLM yields up to 1.1-2.28x throughput improvement over the state-of-the-art baseline with competitive accuracy. --- ### TIDE: Two-Stage Inverse Degradation Estimation with Guided Prior Disentanglement for Underwater Image Restoration Authors: Shravan Venkatraman, Rakesh Raj Madavan, Pavan Kumar S, Muthu Subash Kavitha Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07171v1 Underwater image restoration is essential for marine applications ranging from ecological monitoring to archaeological surveys, but effectively addressing the complex and spatially varying nature of underwater degradations remains a challenge. Existing methods typically apply uniform restoration strategies across the entire image, struggling to handle multiple co-occurring degradations that vary spatially and with water conditions. We introduce TIDE, a $\underline{t}$wo stage $\underline{i}$nverse $\underline{d}$egradation $\underline{e}$stimation framework that explicitly models degradation characteristics and applies targeted restoration through specialized prior decomposition. Our approach disentangles the restoration process into multiple specialized hypotheses that are adaptively fused based on local degradation patterns, followed by a progressive refinement stage that corrects residual artifacts. Specifically, TIDE decomposes underwater degradations into four key factors, namely color distortion, haze, detail loss, and noise, and designs restoration experts specialized for each. By generating specialized restoration hypotheses, TIDE balances competing degradation factors and produces natural results even in highly degraded regions. Extensive experiments across both standard benchmarks and challenging turbid water conditions show that TIDE achieves competitive performance on reference based fidelity metrics while outperforming state of the art methods on non reference perceptual quality metrics, with strong improvements in color correction and contrast enhancement. Our code is available at: https://rakesh-123-cryp.github.io/TIDE. --- ### Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach Authors: Jiayang Li, Chengjie Jiang, Junjun Jiang, Pengwei Liang, Jiayi Ma, Liqiang Nie Published: 2025-12-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.07170v1 Image fusion aims to blend complementary information from multiple sensing modalities, yet existing approaches remain limited in robustness, adaptability, and controllability. Most current fusion networks are tailored to specific tasks and lack the ability to flexibly incorporate user intent, especially in complex scenarios involving low-light degradation, color shifts, or exposure imbalance. Moreover, the absence of ground-truth fused images and the small scale of existing datasets make it difficult to train an end-to-end model that simultaneously understands high-level semantics and performs fine-grained multimodal alignment. We therefore present DiTFuse, instruction-driven Diffusion-Transformer (DiT) framework that performs end-to-end, semantics-aware fusion within a single model. By jointly encoding two images and natural-language instructions in a shared latent space, DiTFuse enables hierarchical and fine-grained control over fusion dynamics, overcoming the limitations of pre-fusion and post-fusion pipelines that struggle to inject high-level semantics. The training phase employs a multi-degradation masked-image modeling strategy, so the network jointly learns cross-modal alignment, modality-invariant restoration, and task-aware feature selection without relying on ground truth images. A curated, multi-granularity instruction dataset further equips the model with interactive fusion capabilities. DiTFuse unifies infrared-visible, multi-focus, and multi-exposure fusion-as well as text-controlled refinement and downstream tasks-within a single architecture. Experiments on public IVIF, MFF, and MEF benchmarks confirm superior quantitative and qualitative performance, sharper textures, and better semantic retention. The model also supports multi-level user control and zero-shot generalization to other multi-image fusion scenarios, including instruction-conditioned segmentation. --- ### JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention Authors: Georgios Ioannides, Christos Constantinou, Aman Chadha, Aaron Elkins, Linsey Pang, Ravid Shwartz-Ziv, Yann LeCun Published: 2025-12-08 Categories: cs.SD, cs.AI, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2512.07168v1 We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning robust speech representations. Stage~1 uses JEPA with DAAM to learn semantic audio features via masked prediction in latent space, fully decoupled from waveform reconstruction. Stage~2 leverages these representations for efficient tokenization using Finite Scalar Quantization (FSQ) and a mixed-radix packing scheme, followed by high-fidelity waveform reconstruction with a HiFi-GAN decoder. By integrating Gaussian mixture-based density-adaptive gating into the JEPA encoder, the model performs adaptive temporal feature selection and discovers hierarchical speech structure at a low frame rate of 2.5~Hz. The resulting tokens (47.5 tokens/sec) provide a reversible, highly compressed, and language-model-friendly representation that is competitive with, and often more efficient than, existing neural audio codecs. --- ### When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM Editing Authors: Siyuan Xu, Yibing Liu, Peilin Chen, Yung-Hui Li, Shiqi Wang, Sam Kwong Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07166v1 Privacy leakage in Multimodal Large Language Models (MLLMs) has long been an intractable problem. Existing studies, though effectively obscure private information in MLLMs, often overlook the evaluation of the authenticity and recovery quality of user privacy. To this end, this work uniquely focuses on the critical challenge of how to restore surrogate-driven protected data in diverse MLLM scenarios. We first bridge this research gap by contributing the SPPE (Surrogate Privacy Protected Editable) dataset, which includes a wide range of privacy categories and user instructions to simulate real MLLM applications. This dataset offers protected surrogates alongside their various MLLM-edited versions, thus enabling the direct assessment of privacy recovery quality. By formulating privacy recovery as a guided generation task conditioned on complementary multimodal signals, we further introduce a unified approach that reliably reconstructs private content while preserving the fidelity of MLLM-generated edits. The experiments on both SPPE and InstructPix2Pix further show that our approach generalizes well across diverse visual content and editing tasks, achieving a strong balance between privacy protection and MLLM usability. --- ### MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale Adaptation Authors: Muyu Xu, Fangneng Zhan, Xiaoqin Zhang, Ling Shao, Shijian Lu Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07165v1 Sparse-view 3D Gaussian splatting seeks to render high-quality novel views of 3D scenes from a limited set of input images. While recent pose-free feed-forward methods leveraging pre-trained 3D priors have achieved impressive results, most of them rely on full fine-tuning of large Vision Transformer (ViT) backbones and incur substantial GPU costs. In this work, we introduce MuSASplat, a novel framework that dramatically reduces the computational burden of training pose-free feed-forward 3D Gaussian splats models with little compromise of rendering quality. Central to our approach is a lightweight Multi-Scale Adapter that enables efficient fine-tuning of ViT-based architectures with only a small fraction of training parameters. This design avoids the prohibitive GPU overhead associated with previous full-model adaptation techniques while maintaining high fidelity in novel view synthesis, even with very sparse input views. In addition, we introduce a Feature Fusion Aggregator that integrates features across input views effectively and efficiently. Unlike widely adopted memory banks, the Feature Fusion Aggregator ensures consistent geometric integration across input views and meanwhile mitigates the memory usage, training complexity, and computational costs significantly. Extensive experiments across diverse datasets show that MuSASplat achieves state-of-the-art rendering quality but has significantly reduced parameters and training resource requirements as compared with existing methods. --- ### DeepSVM: Learning Stochastic Volatility Models with Physics-Informed Deep Operator Networks Authors: Kieran A. Malandain, Selim Kalici, Hakob Chakhoyan Published: 2025-12-08 Categories: q-fin.CP, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.07162v1 Real-time calibration of stochastic volatility models (SVMs) is computationally bottlenecked by the need to repeatedly solve coupled partial differential equations (PDEs). In this work, we propose DeepSVM, a physics-informed Deep Operator Network (PI-DeepONet) designed to learn the solution operator of the Heston model across its entire parameter space. Unlike standard data-driven deep learning (DL) approaches, DeepSVM requires no labelled training data. Rather, we employ a hard-constrained ansatz that enforces terminal payoffs and static no-arbitrage conditions by design. Furthermore, we use Residual-based Adaptive Refinement (RAR) to stabilize training in difficult regions subject to high gradients. Overall, DeepSVM achieves a final training loss of $10^{-5}$ and predicts highly accurate option prices across a range of typical market dynamics. While pricing accuracy is high, we find that the model's derivatives (Greeks) exhibit noise in the at-the-money (ATM) regime, highlighting the specific need for higher-order regularization in physics-informed operator learning. --- ### CHIMERA: Adaptive Cache Injection and Semantic Anchor Prompting for Zero-shot Image Morphing with Morphing-oriented Metrics Authors: Dahyeon Kye, Jeahun Sung, Minkyu Jeon, Jihyong Oh Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07155v9 Recent diffusion-based image morphing methods typically interpolate inverted latents and reuse limited conditioning signals, which often yields unstable intermediates for heterogeneous endpoint pairs. In particular, (i) feature reuse is usually partial or non-adaptive, leading to abrupt structural changes or over-smoothing, and (ii) text conditions are commonly obtained independently per endpoint and then interpolated, which can introduce incompatible semantics. We present CHIMERA, a novel zero-shot diffusion morphing framework that addresses both issues via inversion-guided denoising with complementary feature reuse and text conditioning. Adaptive Cache Injection (ACI) caches a broader set of multi-scale diffusion features beyond Key-Value-only reuse during DDIM inversion, and re-injects them with layer- and timestep-aware scheduling to stabilize denoising and enable gradual fusion. Semantic Anchor Prompting (SAP) uses a VLM to generate a shared anchor-prompt and anchor-conditioned endpoint prompts, and injects the anchor into cross-attention to improve intermediate semantic coherence. Finally, we propose Global-Local Consistency Score (GLCS), a morphing-oriented metric that jointly captures global domain harmonization and local transition smoothness. Extensive experiments and a user study show that CHIMERA produces smoother and more semantically consistent morphing results than prior methods, while remaining efficient and applicable across diverse diffusion backbones without retraining. --- ### FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solvers Authors: Jonghyun Park, Jong Chul Ye Published: 2025-12-08 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.07150v2 Deep generative models are powerful priors for imaging inverse problems, but training-free solvers for latent flow models face a practical finite-step trade-off. Optimization-heavy methods quickly improve measurement consistency, but in highly nonlinear latent spaces, their results can depend strongly on where local refinement is initialized, often degrading perceptual realism. In contrast, stochastic sampling methods better preserve posterior exploration, but often require many iterations to obtain sharp, measurement-consistent reconstructions. To address this trade-off, we propose FlowLPS, a training-free latent flow inverse solver based on Langevin-Proximal Sampling. At each reverse step, FlowLPS uses a few Langevin updates to perturb the model-predicted clean estimate in posterior-oriented directions, providing stochastic initializations for local refinement. It then applies local MAP-style proximal refinement to rapidly improve measurement consistency from the Langevin-updated estimate. We additionally use controlled pCN-style re-noising to stabilize the reverse trajectory while retaining trajectory coherence. Experiments on FFHQ and DIV2K across five linear inverse problems show that FlowLPS achieves a strong balance between measurement fidelity and perceptual quality, with additional experiments on pixel-space inverse problems and phase retrieval. --- ### Winning the Lottery by Preserving Network Training Dynamics with Concrete Ticket Search Authors: Tanay Arora, Christof Teuscher Published: 2025-12-08 Categories: cs.LG, cs.AI, cs.CV, cs.NE arXiv: https://arxiv.org/abs/2512.07142v1 The Lottery Ticket Hypothesis asserts the existence of highly sparse, trainable subnetworks ('winning tickets') within dense, randomly initialized neural networks. However, state-of-the-art methods of drawing these tickets, like Lottery Ticket Rewinding (LTR), are computationally prohibitive, while more efficient saliency-based Pruning-at-Initialization (PaI) techniques suffer from a significant accuracy-sparsity trade-off and fail basic sanity checks. In this work, we argue that PaI's reliance on first-order saliency metrics, which ignore inter-weight dependencies, contributes substantially to this performance gap, especially in the sparse regime. To address this, we introduce Concrete Ticket Search (CTS), an algorithm that frames subnetwork discovery as a holistic combinatorial optimization problem. By leveraging a Concrete relaxation of the discrete search space and a novel gradient balancing scheme (GRADBALANCE) to control sparsity, CTS efficiently identifies high-performing subnetworks near initialization without requiring sensitive hyperparameter tuning. Motivated by recent works on lottery ticket training dynamics, we further propose a knowledge distillation-inspired family of pruning objectives, finding that minimizing the reverse Kullback-Leibler divergence between sparse and dense network outputs (CTS-KL) is particularly effective. Experiments on varying image classification tasks show that CTS produces subnetworks that robustly pass sanity checks and achieve accuracy comparable to or exceeding LTR, while requiring only a small fraction of the computation. For example, on ResNet-20 on CIFAR10, it reaches 99.3% sparsity with 74.0% accuracy in 7.9 minutes, while LTR attains the same sparsity with 68.3% accuracy in 95.2 minutes. CTS's subnetworks outperform saliency-based methods across all sparsities, but its advantage over LTR is most pronounced in the highly sparse regime. --- ### Think-Reflect-Revise: A Policy-Guided Reflective Framework for Safety Alignment in Large Vision Language Models Authors: Fenghua Weng, Chaochao Lu, Xia Hu, Wenqi Shao, Wenjie Wang Published: 2025-12-08 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2512.07141v1 As multimodal reasoning improves the overall capabilities of Large Vision Language Models (LVLMs), recent studies have begun to explore safety-oriented reasoning, aiming to enhance safety awareness by analyzing potential safety risks during the reasoning process before generating the final response. Although such approaches improve safety awareness and interpretability, this single-pass think-then-answer paradigm remains vulnerable to contextual or visual jailbreak attacks. This reveals a critical flaw: single-pass reasoning may overlook explicit harmful content in its own output. Our key insight is to exploit this wasted signal through reflection, which can effectively leverage the malicious content revealed in the first-pass reasoning to enable genuine self-correction and prevent unsafe generations. Motivated by this, we propose Think-Reflect-Revise (TRR), a three-stage training framework designed to enhance the safety alignment of LVLMs through policy-guided self-reflection. We first build a Reflective Safety Reasoning (ReSafe) dataset with 5,000 examples that follow a think-reflect-revise process. We then fine-tune the target model using the ReSafe dataset to initialize reflective behavior, and finally reinforce policy-guided reflection through reinforcement learning. Experimental results show that TRR substantially improves the safety performance of LVLMs across both safety-awareness benchmarks and jailbreak attack evaluations, increasing the overall safe response rate from 42.8% to 87.7% on Qwen2.5-VL-7B, while preserving stable performance on general benchmarks such as MMMU and MMStar. The project page is available at https://think-reflect-revise.github.io/. --- ### A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning Authors: Siyang Jiang, Mu Yuan, Xiang Ji, Bufang Yang, Zeyu Liu, Lilin Xu, Yang Li, Yuting He, Liran Dong, Wenrui Lu, Zhenyu Yan, Xiaofan Jiang et al. Published: 2025-12-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.07136v1 Multimodal human action recognition (HAR) leverages complementary sensors for activity classification. Beyond recognition, recent advances in large language models (LLMs) enable detailed descriptions and causal reasoning, motivating new tasks: human action understanding (HAU) and human action reasoning (HARn). However, most LLMs, especially large vision language models (LVLMs), struggle with non-RGB modalities such as depth, IMU, and mmWave due to the lack of large-scale data-caption resources. Existing HAR datasets mainly provide coarse data-label annotations, which are insufficient to capture fine-grained action dynamics needed for HAU and HARn. We consider two ground-truth pair types: (1) data label (discrete category) and (2) data caption (textual description). Naively generating captions from labels often lacks logical and spatiotemporal consistency. We introduce CUHK-X, a large-scale multimodal dataset and benchmark suite for HAR, HAU, and HARn. CUHK-X contains 58,445 samples covering 40 actions performed by 30 participants across two indoor environments. To improve caption consistency, we propose a prompt-based scene creation method that leverages LLMs to generate logically connected activity sequences, followed by human validation. CUHK-X includes three benchmarks with six evaluation tasks. Experiments report average accuracies of 76.52% (HAR), 40.76% (HAU), and 70.25% (HARn). CUHK-X aims to enable the community to apply and develop data-intensive learning methods for robust, multimodal human activity analysis. Project page and code: https://openaiotlab.github.io/CUHK-X/ and https://github.com/openaiotlab/CUHK-X. --- ### TrajMoE: Scene-Adaptive Trajectory Planning with Mixture of Experts and Reinforcement Learning Authors: Zebin Xing, Pengxuan Yang, Linbo Wang, Yichen Zhang, Yiming Hu, Yupeng Zheng, Junli Wang, Yinfeng Gao, Guang Li, Kun Ma, Long Chen, Zhongpu Xia et al. Published: 2025-12-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.07135v2 Current autonomous driving systems often favor end-to-end frameworks, which take sensor inputs like images and learn to map them into trajectory space via neural networks. Previous work has demonstrated that models can achieve better planning performance when provided with a prior distribution of possible trajectories. However, these approaches often overlook two critical aspects: 1) The appropriate trajectory prior can vary significantly across different driving scenarios. 2) Their trajectory evaluation mechanism lacks policy-driven refinement, remaining constrained by the limitations of one-stage supervised training. To address these issues, we explore improvements in two key areas. For problem 1, we employ MoE to apply different trajectory priors tailored to different scenarios. For problem 2, we utilize Reinforcement Learning to fine-tune the trajectory scoring mechanism. Additionally, we integrate models with different perception backbones to enhance perceptual features. Our integrated model achieved a score of 51.08 on the navsim ICCV benchmark, securing third place. --- ### GUMBridge: a Corpus for Varieties of Bridging Anaphora Authors: Lauren Levine, Amir Zeldes Published: 2025-12-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.07134v2 Bridging is an anaphoric phenomenon where the referent of an entity in a discourse is dependent on a previous, non-identical entity for interpretation, such as in "There is 'a house'. 'The door' is red," where the door is specifically understood to be the door of the aforementioned house. While there are several existing resources in English for bridging anaphora, most are small, provide limited coverage of the phenomenon, and/or provide limited genre coverage. In this paper, we introduce GUMBridge, a new resource for bridging, which includes 16 diverse genres of English, providing both broad coverage for the phenomenon and granular annotations for the subtype categorization of bridging varieties. We also present an evaluation of annotation quality and report on baseline performance using open and closed source contemporary LLMs on three tasks underlying our data, showing that bridging resolution and subtype classification remain difficult NLP tasks in the age of LLMs. --- ### DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning Authors: Nithin Sivakumaran, Justin Chih-Yao Chen, David Wan, Yue Zhang, Jaehong Yoon, Elias Stengel-Eskin, Mohit Bansal Published: 2025-12-08 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.07132v1 Specialized visual tools can augment large language models or vision language models with expert knowledge (e.g., grounding, spatial reasoning, medical knowledge, etc.), but knowing which tools to call (and when to call them) can be challenging. We introduce DART, a multi-agent framework that uses disagreements between multiple debating visual agents to identify useful visual tools (e.g., object detection, OCR, spatial reasoning, etc.) that can resolve inter-agent disagreement. These tools allow for fruitful multi-agent discussion by introducing new information, and by providing tool-aligned agreement scores that highlight agents in agreement with expert tools, thereby facilitating discussion. We utilize an aggregator agent to select the best answer by providing the agent outputs and tool information. We test DART on four diverse benchmarks and show that our approach improves over multi-agent debate as well as over single agent tool-calling frameworks, beating the next-strongest baseline (multi-agent debate with a judge model) by 3.4% and 2.4% on A-OKVQA and MMMU respectively. We also find that DART adapts well to new tools in applied domains, with a 1.3% improvement on the M3D medical dataset over other strong tool-calling, single agent, and multi-agent baselines. Additionally, we measure text overlap across rounds to highlight the rich discussion in DART compared to existing multi-agent methods. Finally, we study the tool call distribution, finding that diverse tools are reliably used to help resolve disagreement. --- ### Mimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Driving Authors: Zebin Xing, Yupeng Zheng, Qichao Zhang, Zhixing Ding, Pengxuan Yang, Songen Gu, Zhongpu Xia, Dongbin Zhao Published: 2025-12-08 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.07130v1 End-to-end autonomous driving has emerged as a pivotal direction in the field of autonomous systems. Recent works have demonstrated impressive performance by incorporating high-level guidance signals to steer low-level trajectory planners. However, their potential is often constrained by inaccurate high-level guidance and the computational overhead of complex guidance modules. To address these limitations, we propose Mimir, a novel hierarchical dual-system framework capable of generating robust trajectories relying on goal points with uncertainty estimation: (1) Unlike previous approaches that deterministically model, we estimate goal point uncertainty with a Laplace distribution to enhance robustness; (2) To overcome the slow inference speed of the guidance system, we introduce a multi-rate guidance mechanism that predicts extended goal points in advance. Validated on challenging Navhard and Navtest benchmarks, Mimir surpasses previous state-of-the-art methods with a 20% improvement in the driving score EPDMS, while achieving 1.6 times improvement in high-level module inference speed without compromising accuracy. The code and models will be released soon to promote reproducibility and further development. The code is available at https://github.com/ZebinX/Mimir-Uncertainty-Driving --- ### MulCLIP: A Multi-level Alignment Framework for Enhancing Fine-grained Long-context CLIP Authors: Chau Truong, Hieu Ta Quang, Dung D. Le Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07128v1 Vision-language models like CLIP show impressive ability to align images and text, but their training on short, concise captions makes them struggle with lengthy, detailed descriptions. Recent advances mitigate this challenge by leveraging region-proposal information to map visual regions with corresponding sentences from lengthy captions, yet incurring notable deployment costs. We introduce MulCLIP, a novel end-to-end multi-level alignment framework that bridges natural long-text structures with image components. MulCLIP first preserves global contrastive alignment between images and both summary and long captions, while extending positional embeddings for longer text sequences. To further enhance fine-grained understanding, we propose two novel strategies: (1) a token reconstruction alignment over locally calibrated features to strengthen semantic connections between words and image patches, and (2) a subcaption-aggregated patch alignment that automatically extracts and aggregates context-rich patches for each subcaption. Experimental results across diverse benchmarks demonstrate our method consistently improves downstream performance, while ablation studies confirm its multi-scale alignment is the key factor driving better fine-grained capability than region-proposal-assisted approaches, making it particularly suitable for diverse real-world applications. --- ### Training-free Clothing Region of Interest Self-correction for Virtual Try-On Authors: Shengjie Lu, Zhibin Wan, Jiejie Liu, Quan Zhang, Mingjie Sun Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07126v1 VTON (Virtual Try-ON) aims at synthesizing the target clothing on a certain person, preserving the details of the target clothing while keeping the rest of the person unchanged. Existing methods suffer from the discrepancies between the generated clothing results and the target ones, in terms of the patterns, textures and boundaries. Therefore, we propose to use an energy function to impose constraints on the attention map extracted through the generation process. Thus, at each generation step, the attention can be more focused on the clothing region of interest, thereby influencing the generation results to be more consistent with the target clothing details. Furthermore, to address the limitation that existing evaluation metrics concentrate solely on image realism and overlook the alignment with target elements, we design a new metric, Virtual Try-on Inception Distance (VTID), to bridge this gap and ensure a more comprehensive assessment. On the VITON-HD and DressCode datasets, our approach has outperformed the previous state-of-the-art (SOTA) methods by 1.4%, 2.3%, 12.3%, and 5.8% in the traditional metrics of LPIPS, FID, KID, and the new VTID metrics, respectively. Additionally, by applying the generated data to downstream Clothing-Change Re-identification (CC-Reid) methods, we have achieved performance improvements of 2.5%, 1.1%, and 1.6% on the LTCC, PRCC, VC-Clothes datasets in the metrics of Rank-1. The code of our method is public at https://github.com/MrWhiteSmall/CSC-VTON.git. --- ### RisConFix: LLM-based Automated Repair of Risk-Prone Drone Configurations Authors: Liping Han, Tingting Nie, Le Yu, Mingzhe Hu, Tao Yue Published: 2025-12-08 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.07122v1 Flight control software is typically designed with numerous configurable parameters governing multiple functionalities, enabling flexible adaptation to mission diversity and environmental uncertainty. Although developers and manufacturers usually provide recommendations for these parameters to ensure safe and stable operations, certain combinations of parameters with recommended values may still lead to unstable flight behaviors, thereby degrading the drone's robustness. To this end, we propose a Large Language Model (LLM) based approach for real-time repair of risk-prone configurations (named RisConFix) that degrade drone robustness. RisConFix continuously monitors the drone's operational state and automatically triggers a repair mechanism once abnormal flight behaviors are detected. The repair mechanism leverages an LLM to analyze relationships between configuration parameters and flight states, and then generates corrective parameter updates to restore flight stability. To ensure the validity of the updated configuration, RisConFix operates as an iterative process; it continuously monitors the drone's flight state and, if an anomaly persists after applying an update, automatically triggers the next repair cycle. We evaluated RisConFix through a case study of ArduPilot (with 1,421 groups of misconfigurations). Experimental results show that RisConFix achieved a best repair success rate of 97% and an optimal average number of repairs of 1.17, demonstrating its capability to effectively and efficiently repair risk-prone configurations in real time. --- ### Chromatic Feature Vectors for 2-Trees: Exact Formulas for Partition Enumeration with Network Applications Authors: J. Allagan, G. Morgan, S. Langley, R. Lopez-Bonilla, V. Deriglazov Published: 2025-12-08 Categories: cs.DS, cs.LG arXiv: https://arxiv.org/abs/2512.07120v1 We establish closed-form enumeration formulas for chromatic feature vectors of 2-trees under the bichromatic triangle constraint. These efficiently computable structural features derive from constrained graph colorings where each triangle uses exactly two colors, forbidding monochromatic and rainbow triangles, a constraint arising in distributed systems where components avoid complete concentration or isolation. For theta graphs Theta_n, we prove r_k(Theta_n) = S(n-2, k-1) for k >= 3 (Stirling numbers of the second kind) and r_2(Theta_n) = 2^(n-2) + 1, computable in O(n) time. For fan graphs Phi_n, we establish r_2(Phi_n) = F_{n+1} (Fibonacci numbers) and derive explicit formulas r_k(Phi_n) = sum_{t=k-1}^{n-1} a_{n-1,t} * S(t, k-1) with efficiently computable binomial coefficients, achieving O(n^2) computation per component. Unlike classical chromatic polynomials, which assign identical features to all n-vertex 2-trees, bichromatic constraints provide informative structural features. While not complete graph invariants, these features capture meaningful structural properties through connections to Fibonacci polynomials, Bell numbers, and independent set enumeration. Applications include Byzantine fault tolerance in hierarchical networks, VM allocation in cloud computing, and secret-sharing protocols in distributed cryptography. --- ### PlantBiMoE: A Bidirectional Foundation Model with SparseMoE for Plant Genomes Authors: Kepeng Lin, Qizhe Zhang, Rui Wang, Xuehai Hu, Wei Xu Published: 2025-12-08 Categories: cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2512.07113v1 Understanding the underlying linguistic rules of plant genomes remains a fundamental challenge in computational biology. Recent advances including AgroNT and PDLLMs have made notable progress although, they suffer from excessive parameter size and limited ability to model the bidirectional nature of DNA strands respectively. To address these limitations, we propose PlantBiMoE, a lightweight and expressive plant genome language model that integrates bidirectional Mamba and a Sparse Mixture-of-Experts (SparseMoE) framework. The bidirectional Mamba enables the model to effectively capture structural dependencies across both the forward and reverse DNA strands, while SparseMoE significantly reduces the number of active parameters, improving computational efficiency without sacrificing modeling capacity. We evaluated and tested our model on the Modified Plants Genome Benchmark (MPGB), an enhanced genomic benchmark, which consolidates 31 datasets across 11 representative tasks, with input sequence lengths ranging from 50 to 6,000 bp. Experimental results demonstrate that PlantBiMoE achieves the best performance on 20 out of 31 datasets and the average best when comparing with existing models. In summary, all above results demonstrate that our model can effectively represent plant genomic sequences, serving as a robust computational tool for diverse genomic tasks, while making substantive contributions to plant genomics, gene editing, and synthetic biology. The code is available at: https://github.com/HUST-Keep-Lin/PlantBiMoE --- ### FOAM: Blocked State Folding for Memory-Efficient LLM Training Authors: Ziqing Wen, Jiahuan Wang, Ping Luo, Dongsheng Li, Tao Sun Published: 2025-12-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.07112v2 Large language models (LLMs) have demonstrated remarkable performance due to their large parameter counts and extensive training data. However, their scale leads to significant memory bottlenecks during training, especially when using memory-intensive optimizers like Adam. Existing memory-efficient approaches often rely on techniques such as singular value decomposition (SVD), projections, or weight freezing, which can introduce substantial computational overhead, require additional memory for projections, or degrade model performance. In this paper, we propose Folded Optimizer with Approximate Moment (FOAM), a method that compresses optimizer states by computing block-wise gradient means and incorporates a residual correction to recover lost information. Theoretically, FOAM achieves convergence rates equivalent to vanilla Adam under standard non-convex optimization settings. Empirically, FOAM eliminates up to 90\% of the memory overhead of optimizer states and accelerates convergence. Furthermore, FOAM is compatible with other memory-efficient optimizers, delivering performance and throughput that match or surpass both full-rank and existing memory-efficient baselines. Code is available at https://github.com/zqOuO/FOAM. --- ### MSN: Multi-directional Similarity Network for Hand-crafted and Deep-synthesized Copy-Move Forgery Detection Authors: Liangwei Jiang, Jinluo Xie, Yecheng Huang, Hua Zhang, Hongyu Yang, Di Huang Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07110v1 Copy-move image forgery aims to duplicate certain objects or to hide specific contents with copy-move operations, which can be achieved by a sequence of manual manipulations as well as up-to-date deep generative network-based swapping. Its detection is becoming increasingly challenging for the complex transformations and fine-tuned operations on the tampered regions. In this paper, we propose a novel two-stream model, namely Multi-directional Similarity Network (MSN), to accurate and efficient copy-move forgery detection. It addresses the two major limitations of existing deep detection models in \textbf{representation} and \textbf{localization}, respectively. In representation, an image is hierarchically encoded by a multi-directional CNN network, and due to the diverse augmentation in scales and rotations, the feature achieved better measures the similarity between sampled patches in two streams. In localization, we design a 2-D similarity matrix based decoder, and compared with the current 1-D similarity vector based one, it makes full use of spatial information in the entire image, leading to the improvement in detecting tampered regions. Beyond the method, a new forgery database generated by various deep neural networks is presented, as a new benchmark for detecting the growing deep-synthesized copy-move. Extensive experiments are conducted on two classic image forensics benchmarks, \emph{i.e.} CASIA CMFD and CoMoFoD, and the newly presented one. The state-of-the-art results are reported, which demonstrate the effectiveness of the proposed approach. --- ### A Neural Affinity Framework for Abstract Reasoning: Diagnosing the Compositional Gap in Transformer Architectures via Procedural Task Taxonomy Authors: Miguel Ingram, Arthur Joseph Merritt Published: 2025-12-08 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.07109v1 Responding to Hodel et al.'s (2024) call for a formal definition of task relatedness in re-arc, we present the first 9-category taxonomy of all 400 tasks, validated at 97.5% accuracy via rule-based code analysis. We prove the taxonomy's visual coherence by training a CNN on raw grid pixels (95.24% accuracy on S3, 36.25% overall, 3.3x chance), then apply the taxonomy diagnostically to the original ARC-AGI-2 test set. Our curriculum analysis reveals 35.3% of tasks exhibit low neural affinity for Transformers--a distributional bias mirroring ARC-AGI-2. To probe this misalignment, we fine-tuned a 1.7M-parameter Transformer across 302 tasks, revealing a profound Compositional Gap: 210 of 302 tasks (69.5%) achieve >80% cell accuracy (local patterns) but <10% grid accuracy (global synthesis). This provides direct evidence for a Neural Affinity Ceiling Effect, where performance is bounded by architectural suitability, not curriculum. Applying our framework to Li et al.'s independent ViTARC study (400 specialists, 1M examples each) confirms its predictive power: Very Low affinity tasks achieve 51.9% versus 77.7% for High affinity (p<0.001), with a task at 0% despite massive data. The taxonomy enables precise diagnosis: low-affinity tasks (A2) hit hard ceilings, while high-affinity tasks (C1) reach 99.8%. These findings indicate that progress requires hybrid architectures with affinity-aligned modules. We release our validated taxonomy, --- ### COREA: Coupled Relightable 3D Gaussians and SDFs for Efficient Normal Alignment Authors: Jaeyoon Lee, Hojoon Jung, Sungtae Hwang, Jihyong Oh, Jongwon Choi Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07107v3 We present COREA, the first unified three-tasks framework that couples an SDF and relightable 3D Gaussians (3DGS) to jointly support SH-based novel-view synthesis (NVS), surface reconstruction, and inverse physically-based rendering (inverse PBR). While recent relightable 3DGS methods have progressed, inverse PBR remains bottlenecked by normal estimation, as the discrete nature of 3DGS often yields oversmoothed and unstable normals. To address this limitation, COREA couples the complementary geometric properties of an SDF and relightable 3DGS on a shared underlying surface, where geometry-constrained relightable 3DGS provides reliable depth signals to anchor SDF geometry and the continuous SDF normal field provides spatially consistent supervision for Gaussian normal learning. We couple these signals through depth-guided alignment and normal supervision with normal-aware densification, and introduce Dual-Density Control to regulate densification by balancing photometric and geometric gradients for stable, memory-efficient training. Experiments on standard benchmarks show that COREA is the only framework that supports all three tasks, achieving competitive performance overall, with particularly superior results in inverse PBR. --- ### Dual Refinement Cycle Learning: Unsupervised Text Classification of Mamba and Community Detection on Text Attributed Graph Authors: Hong Wang, Yinglong Zhang, Hanhan Guo, Xuewen Xia, Xing Xu Published: 2025-12-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.07100v2 Pretrained language models offer strong text understanding capabilities but remain difficult to deploy in real-world text-attributed networks due to their heavy dependence on labeled data. Meanwhile, community detection methods typically ignore textual semantics, limiting their usefulness in downstream applications such as content organization, recommendation, and risk monitoring. To overcome these limitations, we present Dual Refinement Cycle Learning (DRCL), a fully unsupervised framework designed for practical scenarios where no labels or category definitions are available. DRCL integrates structural and semantic information through a warm-start initialization and a bidirectional refinement cycle between a GCN-based Community Detection Module (GCN-CDM) and a Text Semantic Modeling Module (TSMM). The two modules iteratively exchange pseudo-labels, allowing semantic cues to enhance structural clustering and structural patterns to guide text representation learning without manual supervision. Across several text-attributed graph datasets, DRCL consistently improves the structural and semantic quality of discovered communities. Moreover, a Mamba-based classifier trained solely from DRCL's community signals achieves accuracy comparable to supervised models, demonstrating its potential for deployment in large-scale systems where labeled data are scarce or costly. The code is available at https://github.com/wuanghoong/DRCL.git. --- ### VIGIL: A Reflective Runtime for Self-Healing Agents Authors: Christopher Cruz Published: 2025-12-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.07094v2 Agentic LLM frameworks promise autonomous behavior via task decomposition, tool use, and iterative planning, but most deployed systems remain brittle. They lack runtime introspection, cannot diagnose their own failure modes, and do not improve over time without human intervention. In practice, many agent stacks degrade into decorated chains of LLM calls with no structural mechanisms for reliability. We present VIGIL (Verifiable Inspection and Guarded Iterative Learning), a reflective runtime that supervises a sibling agent and performs autonomous maintenance rather than task execution. VIGIL ingests behavioral logs, appraises each event into a structured emotional representation, maintains a persistent EmoBank with decay and contextual policies, and derives an RBT diagnosis that sorts recent behavior into strengths, opportunities, and failures. From this analysis, VIGIL generates both guarded prompt updates that preserve core identity semantics and read only code proposals produced by a strategy engine that operates on log evidence and code hotspots. VIGIL functions as a state gated pipeline. Illegal transitions produce explicit errors rather than allowing the LLM to improvise. In a reminder latency case study, VIGIL identified elevated lag, proposed prompt and code repairs, and when its own diagnostic tool failed due to a schema conflict, it surfaced the internal error, produced a fallback diagnosis, and emitted a repair plan. This demonstrates meta level self repair in a deployed agent runtime. --- ### The Geometry of Persona: Disentangling Personality from Reasoning in Large Language Models Authors: Zhixiang Wang Published: 2025-12-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.07092v1 Background: The deployment of personalized Large Language Models (LLMs) is currently constrained by the stability-plasticity dilemma. Prevailing alignment methods, such as Supervised Fine-Tuning (SFT), rely on stochastic weight updates that often incur an "alignment tax" -- degrading general reasoning capabilities. Methods: We propose the Soul Engine, a framework based on the Linear Representation Hypothesis, which posits that personality traits exist as orthogonal linear subspaces. We introduce SoulBench, a dataset constructed via dynamic contextual sampling. Using a dual-head architecture on a frozen Qwen-2.5 base, we extract disentangled personality vectors without modifying the backbone weights. Results: Our experiments demonstrate three breakthroughs. First, High-Precision Profiling: The model achieves a Mean Squared Error (MSE) of 0.011 against psychological ground truth. Second, Geometric Orthogonality: T-SNE visualization confirms that personality manifolds are distinct and continuous, allowing for "Zero-Shot Personality Injection" that maintains original model intelligence. Third, Deterministic Steering: We achieve robust control over behavior via vector arithmetic, validated through extensive ablation studies. Conclusion: This work challenges the necessity of fine-tuning for personalization. By transitioning from probabilistic prompting to deterministic latent intervention, we provide a mathematically rigorous foundation for safe, controllable AI personalization. --- ### Leveraging KV Similarity for Online Structured Pruning in LLMs Authors: Jungmin Lee, Gwangeun Byeon, Yulhwa Kim, Seokin Hong Published: 2025-12-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.07090v1 Pruning has emerged as a promising direction for accelerating large language model (LLM) inference, yet existing approaches often suffer from instability because they rely on offline calibration data that may not generalize across inputs. In this work, we introduce Token Filtering, a lightweight online structured pruning technique that makes pruning decisions directly during inference without any calibration data. The key idea is to measure token redundancy via joint key-value similarity and skip redundant attention computations, thereby reducing inference cost while preserving critical information. To further enhance stability, we design a variance-aware fusion strategy that adaptively weights key and value similarity across heads, ensuring that informative tokens are retained even under high pruning ratios. This design introduces no additional memory overhead and provides a more reliable criterion for token importance. Extensive experiments on LLaMA-2 (7B/13B), LLaMA-3 (8B), and Mistral (7B) demonstrate that Token Filtering consistently outperforms prior structured pruning methods, preserving accuracy on commonsense reasoning benchmarks and maintaining strong performance on challenging tasks such as MMLU, even with 50% pruning. --- ### ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking Authors: Yunzhe Li, Jianan Wang, Hongzi Zhu, James Lin, Shan Chang, Minyi Guo Published: 2025-12-08 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.07086v1 Large Language Models (LLMs) have become foundational components in a wide range of applications, including natural language understanding and generation, embodied intelligence, and scientific discovery. As their computational requirements continue to grow, these models are increasingly deployed as cloud-based services, allowing users to access powerful LLMs via the Internet. However, this deployment model introduces a new class of threat: denial-of-service (DoS) attacks via unbounded reasoning, where adversaries craft specially designed inputs that cause the model to enter excessively long or infinite generation loops. These attacks can exhaust backend compute resources, degrading or denying service to legitimate users. To mitigate such risks, many LLM providers adopt a closed-source, black-box setting to obscure model internals. In this paper, we propose ThinkTrap, a novel input-space optimization framework for DoS attacks against LLM services even in black-box environments. The core idea of ThinkTrap is to first map discrete tokens into a continuous embedding space, then undertake efficient black-box optimization in a low-dimensional subspace exploiting input sparsity. The goal of this optimization is to identify adversarial prompts that induce extended or non-terminating generation across several state-of-the-art LLMs, achieving DoS with minimal token overhead. We evaluate the proposed attack across multiple commercial, closed-source LLM services. Our results demonstrate that, even far under the restrictive request frequency limits commonly enforced by these platforms, typically capped at ten requests per minute (10 RPM), the attack can degrade service throughput to as low as 1% of its original capacity, and in some cases, induce complete service failure. --- ### TRACE: A Generalizable Drift Detector for Streaming Data-Driven Optimization Authors: Yuan-Ting Zhong, Ting Huang, Xiaolin Xiao, Yue-Jiao Gong Published: 2025-12-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.07082v1 Many optimization tasks involve streaming data with unknown concept drifts, posing a significant challenge as Streaming Data-Driven Optimization (SDDO). Existing methods, while leveraging surrogate model approximation and historical knowledge transfer, are often under restrictive assumptions such as fixed drift intervals and fully environmental observability, limiting their adaptability to diverse dynamic environments. We propose TRACE, a TRAnsferable C}oncept-drift Estimator that effectively detects distributional changes in streaming data with varying time scales. TRACE leverages a principled tokenization strategy to extract statistical features from data streams and models drift patterns using attention-based sequence learning, enabling accurate detection on unseen datasets and highlighting the transferability of learned drift patterns. Further, we showcase TRACE's plug-and-play nature by integrating it into a streaming optimizer, facilitating adaptive optimization under unknown drifts. Comprehensive experimental results on diverse benchmarks demonstrate the superior generalization, robustness, and effectiveness of our approach in SDDO scenarios. --- ### ClinNoteAgents: An LLM Multi-Agent System for Predicting and Interpreting Heart Failure 30-Day Readmission from Clinical Notes Authors: Rongjia Zhou, Chengzhuo Li, Carl Yang, Jiaying Lu Published: 2025-12-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.07081v2 Heart failure (HF) is one of the leading causes of rehospitalization among older adults in the United States. Although clinical notes contain rich, detailed patient information and make up a large portion of electronic health records (EHRs), they remain underutilized for HF readmission risk analysis. Traditional computational models for HF readmission often rely on expert-crafted rules, medical thesauri, and ontologies to interpret clinical notes, which are typically written under time pressure and may contain misspellings, abbreviations, and domain-specific jargon. We present ClinNoteAgents, an LLM-based multi-agent framework that transforms free-text clinical notes into (1) structured representations of clinical and social risk factors for association analysis and (2) clinician-style abstractions for HF 30-day readmission prediction. We evaluate ClinNoteAgents on 3,544 notes from 2,065 patients (readmission rate=35.16%), demonstrating high extraction fidelity for clinical variables (conditional accuracy >= 90% for multiple vitals), key risk factor identification, and preservation of predictive signal despite 60 to 90% text reduction. By reducing reliance on structured fields and minimizing manual annotation and model training, ClinNoteAgents provides a scalable and interpretable approach to note-based HF readmission risk modeling in data-limited healthcare systems. --- ### Procrustean Bed for AI-Driven Retrosynthesis: A Unified Framework for Reproducible Evaluation Authors: Anton Morgunov, Victor S. Batista Published: 2025-12-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.07079v1 Progress in computer-aided synthesis planning (CASP) is obscured by the lack of standardized evaluation infrastructure and the reliance on metrics that prioritize topological completion over chemical validity. We introduce RetroCast, a unified evaluation suite that standardizes heterogeneous model outputs into a common schema to enable statistically rigorous, apples-to-apples comparison. The framework includes a reproducible benchmarking pipeline with stratified sampling and bootstrapped confidence intervals, accompanied by SynthArena, an interactive platform for qualitative route inspection. We utilize this infrastructure to evaluate leading search-based and sequence-based algorithms on a new suite of standardized benchmarks. Our analysis reveals a divergence between "solvability" (stock-termination rate) and route quality; high solvability scores often mask chemical invalidity or fail to correlate with the reproduction of experimental ground truths. Furthermore, we identify a "complexity cliff" in which search-based methods, despite high solvability rates, exhibit a sharp performance decay in reconstructing long-range synthetic plans compared to sequence-based approaches. We release the full framework, benchmark definitions, and a standardized database of model predictions to support transparent and reproducible development in the field. --- ### DFIR-DETR: Frequency-Domain Iterative Refinement and Dynamic Feature Aggregation for Small Object Detection Authors: Bo Gao, Jingcheng Tong, Xingsheng Chen, Han Yu, Zichen Li Published: 2025-12-08 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.07078v4 Small object detection in complex scenes exposes a fundamental tension in neural network design: backbone attention distributes computation uniformly regardless of content, pyramid necks inflate activation magnitudes during upsampling without norm compensation, and bottleneck convolutions progressively smooth high-frequency edge components through accumulated spatial filtering. In response, we develop DFIR-DETR by tracing each proposed module back to a specific, measurable deficiency in the RT-DETR baseline: uniform attention that ignores spatial complexity, norm drift that destabilises upsampled features, and spatial convolutions that progressively suppress the high-frequency components small objects depend on. On NEU-DET and VisDrone, DFIR-DETR achieves 92.9% and 51.6% mAP50 with only 11.7M parameters and 47.2 GFLOPs, demonstrating consistent gains across two qualitatively different detection domains. --- ### Context-measure: Contextualizing Metric for Camouflage Authors: Chen-Yang Wang, Ge-Peng Ji, Song Shao, Ming-Ming Cheng, Deng-Ping Fan Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07076v5 Camouflage relies heavily on context, but current metrics used in camouflaged object segmentation ignore contextual cues. We identify two major drawbacks of these metrics: first, the Dimension Flaw - a predicted foreground map usually contains both pixel labels and probability scores, whereas ground truth provides only one-dimensional binary labels; second, the Range Flaw - these metrics struggle to capture full-range pixel dependencies. Thus, we propose Context-measure, a novel context-aware evaluation paradigm built on a probabilistic pixel correlation framework. It augments the ground truth with pixel-level contextual affinity and builds a perception cycle, achieving greater consistency with human perception. Extensive experiments using four meta-measures show that our Context-measure comprehensively outperforms all widely adopted metrics for camouflaged object segmentation. To our knowledge, this is the first metric designed for camouflaged scenarios. Code is available at https://github.com/pursuitxi/Context-measure. --- ### Do Large Language Models Truly Understand Cross-cultural Differences? Authors: Shiwei Guo, Sihang Jiang, Qianxi He, Yanghua Xiao, Jiaqing Liang, Bi Yude, Minggui He, Shimin Tao, Li Zhang Published: 2025-12-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.07075v1 In recent years, large language models (LLMs) have demonstrated strong performance on multilingual tasks. Given its wide range of applications, cross-cultural understanding capability is a crucial competency. However, existing benchmarks for evaluating whether LLMs genuinely possess this capability suffer from three key limitations: a lack of contextual scenarios, insufficient cross-cultural concept mapping, and limited deep cultural reasoning capabilities. To address these gaps, we propose SAGE, a scenario-based benchmark built via cross-cultural core concept alignment and generative task design, to evaluate LLMs' cross-cultural understanding and reasoning. Grounded in cultural theory, we categorize cross-cultural capabilities into nine dimensions. Using this framework, we curated 210 core concepts and constructed 4530 test items across 15 specific real-world scenarios, organized under four broader categories of cross-cultural situations, following established item design principles. The SAGE dataset supports continuous expansion, and experiments confirm its transferability to other languages. It reveals model weaknesses across both dimensions and scenarios, exposing systematic limitations in cross-cultural reasoning. While progress has been made, LLMs are still some distance away from reaching a truly nuanced cross-cultural understanding. In compliance with the anonymity policy, we include data and code in the supplement materials. In future versions, we will make them publicly available online. --- ### Machine Learning-based Unfolding for Cross Section Measurements in the Presence of Nuisance Parameters Authors: Huanbiao Zhu, Krish Desai, Mikael Kuusela, Vinicius Mikuni, Benjamin Nachman, Larry Wasserman Published: 2025-12-08 Categories: stat.AP, hep-ex, hep-ph, physics.data-an, stat.ML arXiv: https://arxiv.org/abs/2512.07074v3 Statistically correcting measured cross sections for detector effects is an important step across many applications. In particle physics, this inverse problem is known as unfolding. In cases with complex instruments, the distortions they introduce are often known only implicitly through simulations of the detector. Modern machine learning has enabled efficient simulation-based approaches for unfolding high-dimensional data. Among these, one of the first methods successfully deployed on experimental data is the OmniFold algorithm, a classifier-based Expectation-Maximization procedure. In practice, however, the forward model is only approximately specified, and the corresponding uncertainty is encoded through nuisance parameters. Building on the well-studied OmniFold algorithm, we show how to extend machine learning-based unfolding to incorporate nuisance parameters. Our new algorithm, called Profile OmniFold, is demonstrated using a Gaussian example as well as a particle physics case study using simulated data from the CMS Experiment at the Large Hadron Collider. --- ### SETUP: Sentence-level English-To-Uniform Meaning Representation Parser Authors: Emma Markle, Javier Gutierrez Bach, Shira Wein Published: 2025-12-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.07068v3 Uniform Meaning Representation (UMR) is a novel graph-based semantic representation which captures the core meaning of a text, with flexibility incorporated into the annotation schema such that the breadth of the world's languages can be annotated (including low-resource languages). While UMR shows promise in enabling language documentation, improving low-resource language technologies, and adding interpretability, the downstream applications of UMR can only be fully explored when text-to-UMR parsers enable the automatic large-scale production of accurate UMR graphs at test time. Prior work on text-to-UMR parsing is limited to date. In this paper, we introduce two methods for English text-to-UMR parsing, one of which fine-tunes existing parsers for Abstract Meaning Representation and the other, which leverages a converter from Universal Dependencies, using prior work as a baseline. Our best-performing model, which we call SETUP, achieves an AnCast score of 84 and a SMATCH++ score of 91, indicating substantial gains towards automatic UMR parsing. --- ### Persistent Homology-Guided Frequency Filtering for Image Compression Authors: Anil Chintapalli, Peter Tenholder, Henry Chen, Arjun Rao Published: 2025-12-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.07065v1 Feature extraction in noisy image datasets presents many challenges in model reliability. In this paper, we use the discrete Fourier transform in conjunction with persistent homology analysis to extract specific frequencies that correspond with certain topological features of an image. This method allows the image to be compressed and reformed while ensuring that meaningful data can be differentiated. Our experimental results show a level of compression comparable to that of using JPEG using six different metrics. The end goal of persistent homology-guided frequency filtration is its potential to improve performance in binary classification tasks (when augmenting a Convolutional Neural Network) compared to traditional feature extraction and compression methods. These findings highlight a useful end result: enhancing the reliability of image compression under noisy conditions. --- ### Self-Supervised Learning on Molecular Graphs: A Systematic Investigation of Masking Design Authors: Jiannan Yang, Veronika Thost, Tengfei Ma Published: 2025-12-08 Categories: cs.LG, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2512.07064v1 Self-supervised learning (SSL) plays a central role in molecular representation learning. Yet, many recent innovations in masking-based pretraining are introduced as heuristics and lack principled evaluation, obscuring which design choices are genuinely effective. This work cast the entire pretrain-finetune workflow into a unified probabilistic framework, enabling a transparent comparison and deeper understanding of masking strategies. Building on this formalism, we conduct a controlled study of three core design dimensions: masking distribution, prediction target, and encoder architecture, under rigorously controlled settings. We further employ information-theoretic measures to assess the informativeness of pretraining signals and connect them to empirically benchmarked downstream performance. Our findings reveal a surprising insight: sophisticated masking distributions offer no consistent benefit over uniform sampling for common node-level prediction tasks. Instead, the choice of prediction target and its synergy with the encoder architecture are far more critical. Specifically, shifting to semantically richer targets yields substantial downstream improvements, particularly when paired with expressive Graph Transformer encoders. These insights offer practical guidance for developing more effective SSL methods for molecular graphs. --- ### $\mathrm{D}^\mathrm{3}$-Predictor: Noise-Free Deterministic Diffusion for Dense Prediction Authors: Changliang Xia, Chengyou Jia, Minnan Luo, Zhuohang Dang, Xin Shen, Bowen Ping Published: 2025-12-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.07062v4 Although diffusion models with strong visual priors have emerged as powerful dense prediction backbones, they overlook a core limitation: the stochastic noise at the core of diffusion sampling is inherently misaligned with dense prediction that requires a deterministic mapping from image to geometry. In this paper, we show that this stochastic noise corrupts fine-grained spatial cues and pushes the model toward timestep-specific noise objectives, consequently destroying meaningful geometric structure mappings. To address this, we introduce $\mathrm{D}^\mathrm{3}$-Predictor, a noise-free deterministic diffusion-based dense prediction model built by reformulating a pretrained diffusion model without stochasticity noise. Instead of relying on noisy inputs to leverage diffusion priors, $\mathrm{D}^\mathrm{3}$-Predictor views the pretrained diffusion network as an ensemble of timestep-dependent visual experts and self-supervisedly aggregates their heterogeneous priors into a single, clean, and complete geometric prior. Meanwhile, we utilize task-specific supervision to seamlessly adapt this noise-free prior to dense prediction tasks. Extensive experiments on various dense prediction tasks demonstrate that $\mathrm{D}^\mathrm{3}$-Predictor achieves competitive or state-of-the-art performance in diverse scenarios. In addition, it requires less than half the training data previously used and efficiently performs inference in a single step. Our code, data, and checkpoints are publicly available at https://x-gengroup.github.io/HomePage_D3-Predictor/. --- ### Replicating TEMPEST at Scale: Multi-Turn Adversarial Attacks Against Trillion-Parameter Frontier Models Authors: Richard Young Published: 2025-12-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.07059v1 Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is unknown. This study employed the TEMPEST multi-turn attack framework to evaluate ten frontier models from eight vendors across 1,000 harmful behaviors, generating over 97,000 API queries across adversarial conversations with automated evaluation by independent safety classifiers. Results demonstrated a spectrum of vulnerability: six models achieved 96% to 100% attack success rate (ASR), while four showed meaningful resistance, with ASR ranging from 42% to 78%; enabling extended reasoning on identical architecture reduced ASR from 97% to 42%. These findings indicate that safety alignment quality varies substantially across vendors, that model scale does not predict adversarial robustness, and that thinking mode provides a deployable safety enhancement. Collectively, this work establishes that current alignment techniques remain fundamentally vulnerable to adaptive multi-turn attacks regardless of model scale, while identifying deliberative inference as a promising defense direction. --- ### Uniqueness ratio as a predictor of a privacy leakage Authors: Danah A. AlSalem AlKhashti Published: 2025-12-07 Categories: cs.DB, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2601.11550v1 Identity leakage can emerge when independent databases are joined, even when each dataset is anonymized individually. While previous work focuses on post-join detection or complex privacy models, little attention has been given to simple, interpretable pre-join indicators that can warn data engineers and database administrators before integration occurs. This study investigates the uniqueness ratio of candidate join attributes as an early predictor of re-identification risk. Using synthetic multi-table datasets, we compute the uniqueness ratio of attribute combinations within each database and examine how these ratios correlate with identity exposure after the join. Experimental results show a strong relationship between high pre-join uniqueness and increased post-join leakage, measured by the proportion of records that become uniquely identifiable or fall into very small groups. Our findings demonstrate that uniqueness ratio offers an explainable and practical signal for assessing join induced privacy risk, providing a foundation for developing more comprehensive pre-join risk estimation models. --- ### Enhancing Admission Inquiry Responses with Fine-Tuned Models and Retrieval-Augmented Generation Authors: Aram Virabyan Published: 2025-12-07 Categories: cs.CL, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2601.04206v1 University admissions offices face the significant challenge of managing high volumes of inquiries efficiently while maintaining response quality, which critically impacts prospective students' perceptions. This paper addresses the issues of response time and information accuracy by proposing an AI system integrating a fine-tuned language model with Retrieval-Augmented Generation (RAG). While RAG effectively retrieves relevant information from large datasets, its performance in narrow, complex domains like university admissions can be limited without adaptation, potentially leading to contextually inadequate responses due to the intricate rules and specific details involved. To overcome this, we fine-tuned the model on a curated dataset specific to admissions processes, enhancing its ability to interpret RAG-provided data accurately and generate domain-relevant outputs. This hybrid approach leverages RAG's ability to access up-to-date information and fine-tuning's capacity to embed nuanced domain understanding. We further explored optimization strategies for the response generation logic, experimenting with settings to balance response quality and speed, aiming for consistently high-quality outputs that meet the specific requirements of admissions communications. --- ### STaRR: Spatial-Temporal Token-Dynamics-Aware Responsive Remasking for Diffusion Language Models Authors: Xinhao Sun, Huaijin Zhao, Maoliang Li, Zihao Zheng, Jiayu Chen, Yun Liang, Xiang Chen Published: 2025-12-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.04205v2 Diffusion Language Models (DLMs) enable parallel decoding via iterative denoising, where remasking strategies play a critical role in balancing inference speed and output quality. Existing methods predominantly rely on static confidence thresholds, overlooking the spatial-temporal dynamics of token confidence, causing unnecessary remasking. We propose Spatial-Temporal Token-Dynamics-Aware Responsive Remasking (STaRR), a training-free framework that dynamically adapts remasking decisions based on token confidence evolution. STaRR introduces two metrics, temporal variance and spatial deviance, to guide fine-grained, step-wise dynamic thresholding. We further introduce a step-wise dynamic thresholding strategy, further enhanced with responsiveness optimizations for scalability and robustness. Experiments show that STaRR achieves an average speedup of 4.1 and up to 8.9 while maintaining comparable accuracy. --- ### TeachMaster: Generative Teaching via Code Authors: Yuheng Wang, Runde Yang, Lin Wu, Jie Zhang, Jingru Fan, Tianle Zhou, Ruoyu Fu, Huatao Li, Ruijie Shi, Siheng Chen, Weinan E, Chen Qian Published: 2025-12-07 Categories: cs.CY, cs.AI, cs.CL, cs.HC, cs.MA arXiv: https://arxiv.org/abs/2601.04204v2 The scalability of high-quality online education is hindered by the high costs and slow cycles of manual content creation. Despite advancements in video generation, current approaches often fail to ensure pedagogical structure and precise control due to their pixel-level, black-box nature. In this paper, we propose Generative Teaching, a novel paradigm shifting educators from manual creators to high-level directors who focus on pedagogical intents while agents handle the execution. To realize this vision, we introduce TeachMaster, a multi-agent framework that leverages code as an intermediate semantic medium. Unlike traditional video generation methods, TeachMaster orchestrates a collaborative team of agents, spanning planning, design, and rendering, to automate the production of interpretable, editable, and curriculum-ready educational videos. Experiments validate that TeachMaster significantly boosts production efficiency without compromising structural coherence or visual fidelity, slashing production costs to only 0.3% of traditional online course videos and providing a robust solution for scalable education. --- ### Permission Manifests for Web Agents Authors: Samuele Marro, Alan Chan, Xinxing Ren, Lewis Hammond, Jesse Wright, Gurjyot Wanga, Tiziano Piccardi, Nuno Campos, Tobin South, Jialin Yu, Sunando Sengupta, Eric Sommerlade et al. Published: 2025-12-07 Categories: cs.CY, cs.AI, cs.MA, cs.NI arXiv: https://arxiv.org/abs/2601.02371v2 The rise of Large Language Model (LLM)-based web agents represents a significant shift in automated interactions with the web. Unlike traditional crawlers that follow simple conventions, such as robots$.$txt, modern agents engage with websites in sophisticated ways: navigating complex interfaces, extracting structured information, and completing end-to-end tasks. Existing governance mechanisms were not designed for these capabilities. Without a way to specify what interactions are and are not allowed, website owners increasingly rely on blanket blocking and CAPTCHAs, which undermine beneficial applications such as efficient automation, convenient use of e-commerce services, and accessibility tools. We introduce agent-permissions$.$json, a robots$.$txt-style lightweight manifest where websites specify allowed interactions, complemented by API references where available. This framework provides a low-friction coordination mechanism: website owners only need to write a simple JSON file, while agents can easily parse and automatically implement the manifest's provisions. Website owners can then focus on blocking non-compliant agents, rather than agents as a whole. By extending the spirit of robots$.$txt to the era of LLM-mediated interaction, and complementing data use initiatives such as AIPref, the manifest establishes a compliance framework that enables beneficial agent interactions while respecting site owners' preferences. ---