# Research Papers — 2025-12 · bundle page 47 of 175

> Full-text markdown of papers #2301–2350 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/47
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/46.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/48.md)

### Rectification Reimagined: A Unified Mamba Model for Image Correction and Rectangling with Prompts

Authors: Linwei Qiu, Gongzhe Li, Xiaozhe Zhang, Qilin Sun, Fengying Xie
Published: 2025-12-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.18718v3

Image correction and rectangling are valuable tasks in practical photography systems such as smartphones. Recent remarkable advancements in deep learning have undeniably brought about substantial performance improvements in these fields. Nevertheless, existing methods mainly rely on task-specific architectures. This significantly restricts their generalization ability and effective application across a wide range of different tasks. In this paper, we introduce the Unified Rectification Framework (UniRect), a comprehensive approach that addresses these practical tasks from a consistent distortion rectification perspective. Our approach incorporates various task-specific inverse problems into a general distortion model by simulating different types of lenses. To handle diverse distortions, UniRect adopts one task-agnostic rectification framework with a dual-component structure: a {Deformation Module}, which utilizes a novel Residual Progressive Thin-Plate Spline (RP-TPS) model to address complex geometric deformations, and a subsequent Restoration Module, which employs Residual Mamba Blocks (RMBs) to counteract the degradation caused by the deformation process and enhance the fidelity of the output image. Moreover, a Sparse Mixture-of-Experts (SMoEs) structure is designed to circumvent heavy task competition in multi-task learning due to varying distortions. Extensive experiments demonstrate that our models have achieved state-of-the-art performance compared with other up-to-date methods.

---

### KeenKT: Knowledge Mastery-State Disambiguation for Knowledge Tracing

Authors: Zhifei Li, Lifan Chen, Jiali Yi, Xiaoju Hou, Yue Zhao, Wenxin Huang, Miao Zhang, Kui Xiao, Bing Yang
Published: 2025-12-21
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.18709v1

Knowledge Tracing (KT) aims to dynamically model a student's mastery of knowledge concepts based on their historical learning interactions. Most current methods rely on single-point estimates, which cannot distinguish true ability from outburst or carelessness, creating ambiguity in judging mastery. To address this issue, we propose a Knowledge Mastery-State Disambiguation for Knowledge Tracing model (KeenKT), which represents a student's knowledge state at each interaction using a Normal-Inverse-Gaussian (NIG) distribution, thereby capturing the fluctuations in student learning behaviors. Furthermore, we design an NIG-distance-based attention mechanism to model the dynamic evolution of the knowledge state. In addition, we introduce a diffusion-based denoising reconstruction loss and a distributional contrastive learning loss to enhance the model's robustness. Extensive experiments on six public datasets demonstrate that KeenKT outperforms SOTA KT models in terms of prediction accuracy and sensitivity to behavioral fluctuations. The proposed method yields the maximum AUC improvement of 5.85% and the maximum ACC improvement of 6.89%.

---

### CauTraj: A Causal-Knowledge-Guided Framework for Lane-Changing Trajectory Planning of Autonomous Vehicles

Authors: Cailin Lei, Haiyang Wu, Yuxiong Ji, Xiaoyu Cai, Yuchuan Du
Published: 2025-12-21
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.18703v1

Enhancing the performance of trajectory planners for lane - changing vehicles is one of the key challenges in autonomous driving within human - machine mixed traffic. Most existing studies have not incorporated human drivers' prior knowledge when designing trajectory planning models. To address this issue, this study proposes a novel trajectory planning framework that integrates causal prior knowledge into the control process. Both longitudinal and lateral microscopic behaviors of vehicles are modeled to quantify interaction risk, and a staged causal graph is constructed to capture causal dependencies in lane-changing scenarios. Causal effects between the lane-changing vehicle and surrounding vehicles are then estimated using causal inference, including average causal effects (ATE) and conditional average treatment effects (CATE). These causal priors are embedded into a model predictive control (MPC) framework to enhance trajectory planning. The proposed approach is validated on naturalistic vehicle trajectory datasets. Experimental results show that: (1) causal inference provides interpretable and stable quantification of vehicle interactions; (2) individual causal effects reveal driver heterogeneity; and (3) compared with the baseline MPC, the proposed method achieves a closer alignment with human driving behaviors, reducing maximum trajectory deviation from 1.2 m to 0.2 m, lateral velocity fluctuation by 60%, and yaw angle variability by 50%. These findings provide methodological support for human-like trajectory planning and practical value for improving safety, stability, and realism in autonomous vehicle testing and traffic simulation platforms.

---

### Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis

Authors: Pengchao Feng, Yao Xiao, Ziyang Ma, Zhikang Niu, Shuai Fan, Yao Li, Sheng Wang, Xie Chen
Published: 2025-12-21
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2512.18699v1

Recent advances in text-to-speech (TTS) have yielded remarkable improvements in naturalness and intelligibility. Building on these achievements, research has increasingly shifted toward enhancing the expressiveness of generated speech, such as dialectal and emotional TTS. However, cross-style synthesis combining both dialect and emotion remains challenging and largely unexplored, mainly due to the scarcity of dialectal data with emotional labels. To address this, we propose Hierarchical Expressive Vector (HE-Vector), a two-stage method for Emotional Dialectal TTS. In the first stage, we construct different task vectors to model dialectal and emotional styles independently, and then enhance single-style synthesis by adjusting their weights, a method we refer to as Expressive Vector (E-Vector). For the second stage, we hierarchically integrate these vectors to achieve controllable emotionally expressive dialect synthesis without requiring jointly labeled data, corresponding to Hierarchical Expressive Vector (HE-Vector). Experimental results demonstrate that HE-Vectors achieve superior performance in dialect synthesis, and promising results in synthesizing emotionally expressive dialectal speech in a zero-shot setting.

---

### EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images

Authors: Jongmin Park, Minh-Quan Viet Bui, Juan Luis Gonzalez Bello, Jaeho Moon, Jihyong Oh, Munchurl Kim
Published: 2025-12-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.18692v1

Feed-forward 3D Gaussian Splatting (3DGS) enables efficient one-pass scene reconstruction, providing 3D representations for novel view synthesis without per-scene optimization. However, existing methods typically predict pixel-aligned primitives per-view, producing an excessive number of primitives in dense-view settings and offering no explicit control over the number of predicted Gaussians. To address this, we propose EcoSplat, the first efficiency-controllable feed-forward 3DGS framework that adaptively predicts the 3D representation for any given target primitive count at inference time. EcoSplat adopts a two-stage optimization process. The first stage is Pixel-aligned Gaussian Training (PGT) where our model learns initial primitive prediction. The second stage is Importance-aware Gaussian Finetuning (IGF) stage where our model learns rank primitives and adaptively adjust their parameters based on the target primitive count. Extensive experiments across multiple dense-view settings show that EcoSplat is robust and outperforms state-of-the-art methods under strict primitive-count constraints, making it well-suited for flexible downstream rendering tasks.

---

### Fusion of Multiscale Features Via Centralized Sparse-attention Network for EEG Decoding

Authors: Xiangrui Cai, Shaocheng Ma, Lei Cao, Jie Li, Tianyu Liu, Yilin Dong
Published: 2025-12-21
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.18689v3

Electroencephalography (EEG) signal decoding is a key technology that translates brain activity into executable commands, laying the foundation for direct brain-machine interfacing and intelligent interaction. To address the inherent spatiotemporal heterogeneity of EEG signals, this paper proposes a multi-branch parallel architecture, where each temporal scale is equipped with an independent spatial feature extraction module. To further enhance multi-branch feature fusion, we propose a Fusion of Multiscale Features via Centralized Sparse-attention Network (EEG-CSANet), a centralized sparse-attention network. It employs a main-auxiliary branch architecture, where the main branch models core spatiotemporal patterns via multiscale self-attention, and the auxiliary branch facilitates efficient local interactions through sparse cross-attention. Experimental results show that EEG-CSANet achieves state-of-the-art (SOTA) performance across five public datasets (BCIC-IV-2A, BCIC-IV-2B, HGD, SEED, and SEED-VIG), with accuracies of 88.54%, 91.09%, 97.15%, 96.03%, and 90.56%, respectively. Such performance demonstrates its strong adaptability and robustness across various EEG decoding tasks. Moreover, extensive ablation studies are conducted to enhance the interpretability of EEG-CSANet. In the future, we hope that EEG-CSANet could serve as a promising baseline model in the field of EEG signal decoding. The source code is publicly available at: https://github.com/Xiangrui-Cai/EEG-CSANet

---

### Social Comparison without Explicit Inference of Others' Reward Values: A Constructive Approach Using a Probabilistic Generative Model

Authors: Yosuke Taniuchi, Chie Hieida, Atsushi Noritake, Kazushi Ikeda, Masaki Isoda
Published: 2025-12-21
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.18687v4

Social comparison$\unicode{x2014}$the process of evaluating one's rewards relative to others$\unicode{x2014}$is an essential feature of social emotions such as envy and plays a fundamental role in primate social cognition. However, it remains unknown how information about others' rewards affects one's own reward valuation. This study examines whether monkeys merely recognize objective differences in reward or instead infer others' subjective reward valuations. To address this issue, a constructive approach$\unicode{x2014}$one that replicates target emotions in artificial systems and extracts knowledge from them$\unicode{x2014}$was employed, owing to its potential to simulate how the monkey interacts with social contexts, specifically social comparison. We developed three computational models with varying degrees of social information processing: an Internal Prediction Model (IPM), which infers the partner's subjective values; a No Comparison Model (NCM), which disregards partner information; and an External Comparison Model (ECM), which directly incorporates the partner's objective rewards. We trained the models on a dataset containing the behavior of a pair of monkeys, their rewards, and the conditioned stimuli, and then evaluated the models' ability to classify subjective values across pre-defined experimental conditions. The ECM achieved the best classification result (0.88 for the ECM vs. 0.85 for the IPM on the Rand index), suggesting that, in our modeling framework, social comparison relies on objective differences in reward rather than on inferences about subjective reward values.

---

### A Study of Finetuning Video Transformers for Multi-view Geometry Tasks

Authors: Huimin Wu, Kwang-Ting Cheng, Stephen Lin, Zhirong Wu
Published: 2025-12-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.18684v1

This paper presents an investigation of vision transformer learning for multi-view geometry tasks, such as optical flow estimation, by fine-tuning video foundation models. Unlike previous methods that involve custom architectural designs and task-specific pretraining, our research finds that general-purpose models pretrained on videos can be readily transferred to multi-view problems with minimal adaptation. The core insight is that general-purpose attention between patches learns temporal and spatial information for geometric reasoning. We demonstrate that appending a linear decoder to the Transformer backbone produces satisfactory results, and iterative refinement can further elevate performance to stateof-the-art levels. This conceptually simple approach achieves top cross-dataset generalization results for optical flow estimation with end-point error (EPE) of 0.69, 1.78, and 3.15 on the Sintel clean, Sintel final, and KITTI datasets, respectively. Our method additionally establishes a new record on the online test benchmark with EPE values of 0.79, 1.88, and F1 value of 3.79. Applications to 3D depth estimation and stereo matching also show strong performance, illustrating the versatility of video-pretrained models in addressing geometric vision tasks.

---

### Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Design

Authors: Yuchen Li, Handing Wang, Bing Xue, Mengjie Zhang, Yaochu Jin
Published: 2025-12-21
Categories: cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2512.18682v2

In the high-cost simulation-driven design domain, translating ambiguous design requirements into a mathematical optimization formulation is a bottleneck for optimizing product performance. This process is time-consuming and heavily reliant on expert knowledge. While large language models (LLMs) offer potential for automating this task, existing approaches either suffer from poor formalization that fails to accurately align with the design intent or rely on solver feedback for data filtering, which is unavailable due to the high simulation costs. To address this challenge, we propose APF, a framework for solver-independent, automated problem formulation via LLMs designed to automatically convert engineers' natural language requirements into executable optimization models. The core of this framework is an innovative pipeline for automatically generating high-quality data, which overcomes the difficulty of constructing suitable fine-tuning datasets in the absence of high-cost solver feedback with the help of data generation and test instance annotation. The generated high-quality dataset is used to perform supervised fine-tuning on LLMs, significantly enhancing their ability to generate accurate and executable optimization problem formulations. Experimental results on antenna design demonstrate that APF significantly outperforms the existing methods in both the accuracy of requirement formalization and the quality of resulting radiation efficiency curves in meeting the design goals.

---

### brat: Aligned Multi-View Embeddings for Brain MRI Analysis

Authors: Maxime Kayser, Maksim Gridnev, Wanting Wang, Max Bain, Aneesh Rangnekar, Avijit Chatterjee, Aleksandr Petrov, Harini Veeraraghavan, Nathaniel C. Swinburne
Published: 2025-12-21
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2512.18679v1

We present brat (brain report alignment transformer), a multi-view representation learning framework for brain magnetic resonance imaging (MRI) trained on MRIs paired with clinical reports. Brain MRIs present unique challenges due to the presence of numerous, highly varied, and often subtle abnormalities that are localized to a few slices within a 3D volume. To address these challenges, we introduce a brain MRI dataset $10\times$ larger than existing ones, containing approximately 80,000 3D scans with corresponding radiology reports, and propose a multi-view pre-training approach inspired by advances in document retrieval. We develop an implicit query-feature matching mechanism and adopt concepts from quality-diversity to obtain multi-view embeddings of MRIs that are aligned with the clinical features given by report sentences. We evaluate our approach across multiple vision-language and vision tasks, demonstrating substantial performance improvements. The brat foundation models are publicly released.

---

### AsyncDiff: Asynchronous Timestep Conditioning for Enhanced Text-to-Image Diffusion Inference

Authors: Longhuan Xu, Feng Yin, Cunjian Chen
Published: 2025-12-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.18675v1

Text-to-image diffusion inference typically follows synchronized schedules, where the numerical integrator advances the latent state to the same timestep at which the denoiser is conditioned. We propose an asynchronous inference mechanism that decouples these two, allowing the denoiser to be conditioned at a different, learned timestep while keeping image update schedule unchanged. A lightweight timestep prediction module (TPM), trained with Group Relative Policy Optimization (GRPO), selects a more feasible conditioning timestep based on the current state, effectively choosing a desired noise level to control image detail and textural richness. At deployment, a scaling hyper-parameter can be used to interpolate between the original and de-synchronized timesteps, enabling conservative or aggressive adjustments. To keep the study computationally affordable, we cap the inference at 15 steps for SD3.5 and 10 steps for Flux. Evaluated on Stable Diffusion 3.5 Medium and Flux.1-dev across MS-COCO 2014 and T2I-CompBench datasets, our method optimizes a composite reward that averages Image Reward, HPSv2, CLIP Score and Pick Score, and shows consistent improvement.

---

### Remoe: Towards Efficient and Low-Cost MoE Inference in Serverless Computing

Authors: Wentao Liu, Yuhao Hu, Ruiting Zhou, Baochun Li, Ne Wang
Published: 2025-12-21
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2512.18674v1

Mixture-of-Experts (MoE) has become a dominant architecture in large language models (LLMs) due to its ability to scale model capacity via sparse expert activation. Meanwhile, serverless computing, with its elasticity and pay-per-use billing, is well-suited for deploying MoEs with bursty workloads. However, the large number of experts in MoE models incurs high inference costs due to memory-intensive parameter caching. These costs are difficult to mitigate via simple model partitioning due to input-dependent expert activation. To address these issues, we propose Remoe, a heterogeneous MoE inference system tailored for serverless computing. Remoe assigns non-expert modules to GPUs and expert modules to CPUs, and further offloads infrequently activated experts to separate serverless functions to reduce memory overhead and enable parallel execution. We incorporate three key techniques: (1) a Similar Prompts Searching (SPS) algorithm to predict expert activation patterns based on semantic similarity of inputs; (2) a Main Model Pre-allocation (MMP) algorithm to ensure service-level objectives (SLOs) via worst-case memory estimation; and (3) a joint memory and replica optimization framework leveraging Lagrangian duality and the Longest Processing Time (LPT) algorithm. We implement Remoe on Kubernetes and evaluate it across multiple LLM benchmarks. Experimental results show that Remoe reduces inference cost by up to 57% and cold start latency by 47% compared to state-of-the-art baselines.

---

### Improving Pattern Recognition of Scheduling Anomalies through Structure-Aware and Semantically-Enhanced Graphs

Authors: Ning Lyu, Junjie Jiang, Lu Chang, Chihui Shao, Feng Chen, Chong Zhang
Published: 2025-12-21
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.18673v1

This paper proposes a structure-aware driven scheduling graph modeling method to improve the accuracy and representation capability of anomaly identification in scheduling behaviors of complex systems. The method first designs a structure-guided scheduling graph construction mechanism that integrates task execution stages, resource node states, and scheduling path information to build dynamically evolving scheduling behavior graphs, enhancing the model's ability to capture global scheduling relationships. On this basis, a multi-scale graph semantic aggregation module is introduced to achieve semantic consistency modeling of scheduling features through local adjacency semantic integration and global topology alignment, thereby strengthening the model's capability to capture abnormal features in complex scenarios such as multi-task concurrency, resource competition, and stage transitions. Experiments are conducted on a real scheduling dataset with multiple scheduling disturbance paths set to simulate different types of anomalies, including structural shifts, resource changes, and task delays. The proposed model demonstrates significant performance advantages across multiple metrics, showing a sensitive response to structural disturbances and semantic shifts. Further visualization analysis reveals that, under the combined effect of structure guidance and semantic aggregation, the scheduling behavior graph exhibits stronger anomaly separability and pattern representation, validating the effectiveness and adaptability of the method in scheduling anomaly detection tasks.

---

### SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse

Authors: Yiming Sun, Mi Zhang, Feifei Li, Geng Hong, Min Yang
Published: 2025-12-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.18671v1

Despite Video Large Language Models having rapidly advanced in recent years, perceptual hallucinations pose a substantial safety risk, which severely restricts their real-world applicability. While several methods for hallucination mitigation have been proposed, they often compromise the model's capacity for video understanding and reasoning. In this work, we propose SmartSight, a pioneering step to address this issue in a training-free manner by leveraging the model's own introspective capabilities. Specifically, SmartSight generates multiple candidate responses to uncover low-hallucinated outputs that are often obscured by standard greedy decoding. It assesses the hallucination of each response using the Temporal Attention Collapse score, which measures whether the model over-focuses on trivial temporal regions of the input video when generating the response. To improve efficiency, SmartSight identifies the Visual Attention Vanishing point, enabling more accurate hallucination estimation and early termination of hallucinated responses, leading to a substantial reduction in decoding cost. Experiments show that SmartSight substantially lowers hallucinations for Qwen2.5-VL-7B by 10.59% on VRIPT-HAL, while simultaneously enhancing video understanding and reasoning, boosting performance on VideoMMMU by up to 8.86%. These results highlight SmartSight's effectiveness in improving the reliability of open-source Video-LLMs.

---

### Demonstration-Guided Continual Reinforcement Learning in Dynamic Environments

Authors: Xue Yang, Michael Schukat, Junlin Lu, Patrick Mannion, Karl Mason, Enda Howley
Published: 2025-12-21
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.18670v1

Reinforcement learning (RL) excels in various applications but struggles in dynamic environments where the underlying Markov decision process evolves. Continual reinforcement learning (CRL) enables RL agents to continually learn and adapt to new tasks, but balancing stability (preserving prior knowledge) and plasticity (acquiring new knowledge) remains challenging. Existing methods primarily address the stability-plasticity dilemma through mechanisms where past knowledge influences optimization but rarely affects the agent's behavior directly, which may hinder effective knowledge reuse and efficient learning. In contrast, we propose demonstration-guided continual reinforcement learning (DGCRL), which stores prior knowledge in an external, self-evolving demonstration repository that directly guides RL exploration and adaptation. For each task, the agent dynamically selects the most relevant demonstration and follows a curriculum-based strategy to accelerate learning, gradually shifting from demonstration-guided exploration to fully self-exploration. Extensive experiments on 2D navigation and MuJoCo locomotion tasks demonstrate its superior average performance, enhanced knowledge transfer, mitigation of forgetting, and training efficiency. The additional sensitivity analysis and ablation study further validate its effectiveness.

---

### IntelliCode: A Multi-Agent LLM Tutoring System with Centralized Learner Modeling

Authors: Jones David, Shreya Ghosh
Published: 2025-12-21
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.18669v1

LLM-based tutors are typically single-turn assistants that lack persistent representations of learner knowledge, making it difficult to provide principled, transparent, and long-term pedagogical support. We introduce IntelliCode, a multi-agent LLM tutoring system built around a centralized, versioned learner state that integrates mastery estimates, misconceptions, review schedules, and engagement signals. A StateGraph Orchestrator coordinates six specialized agents: skill assessment, learner profiling, graduated hinting, curriculum selection, spaced repetition, and engagement monitoring, each operating as a pure transformation over the shared state under a single-writer policy. This architecture enables auditable mastery updates, proficiency-aware hints, dependency-aware curriculum adaptation, and safety-aligned prompting. The demo showcases an end-to-end tutoring workflow: a learner attempts a DSA problem, receives a conceptual hint when stuck, submits a corrected solution, and immediately sees mastery updates and a personalized review interval. We report validation results with simulated learners, showing stable state updates, improved task success with graduated hints, and diverse curriculum coverage. IntelliCode demonstrates how persistent learner modeling, orchestrated multi-agent reasoning, and principled instructional design can be combined to produce transparent and reliable LLM-driven tutoring.

---

### Automatic Adaptation to Concept Complexity and Subjective Natural Concepts: A Cognitive Model based on Chunking

Authors: Dmitry Bennett, Fernand Gobet
Published: 2025-12-21
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.18665v1

A key issue in cognitive science concerns the fundamental psychological processes that underlie the formation and retrieval of multiple types of concepts in short-term and long-term memory (STM and LTM, respectively). We propose that chunking mechanisms play an essential role and show how the CogAct computational model grounds concept learning in fundamental cognitive processes and structures (such as chunking, attention, STM and LTM). First are the in-principle demonstrations, with CogAct automatically adapting to learn a range of categories from simple logical functions, to artificial categories, to natural raw (as opposed to natural pre-processed) concepts in the dissimilar domains of literature, chess and music. This kind of adaptive learning is difficult for most other psychological models, e.g., with cognitive models stopping at modelling artificial categories and (non-GPT) models based on deep learning requiring task-specific changes to the architecture. Secondly, we offer novel ways of designing human benchmarks for concept learning experiments and simulations accounting for subjectivity, ways to control for individual human experiences, all while keeping to real-life complex categories. We ground CogAct in simulations of subjective conceptual spaces of individual human participants, capturing humans subjective judgements in music, with the models learning from raw music score data without bootstrapping to pre-built knowledge structures. The CogAct simulations are compared to those obtained by a deep-learning model. These findings integrate concept learning and adaptation to complexity into the broader theories of cognitive psychology. Our approach may also be used in psychological applications that move away from modelling the average participant and towards capturing subjective concept space.

---

### Pseudo-Expert Regularized Offline RL for End-to-End Autonomous Driving in Photorealistic Closed-Loop Environments

Authors: Chihiro Noguchi, Takaki Yamamoto
Published: 2025-12-21
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2512.18662v2

End-to-end (E2E) autonomous driving models that take only camera images as input and directly predict a future trajectory are appealing for their computational efficiency and potential for improved generalization via unified optimization; however, persistent failure modes remain due to reliance on imitation learning (IL). While online reinforcement learning (RL) could mitigate IL-induced issues, the computational burden of neural rendering-based simulation and large E2E networks renders iterative reward and hyperparameter tuning costly. We introduce a camera-only E2E offline RL framework that performs no additional exploration and trains solely on a fixed simulator dataset. Offline RL offers strong data efficiency and rapid experimental iteration, yet is susceptible to instability from overestimation on out-of-distribution (OOD) actions. To address this, we construct pseudo ground-truth trajectories from expert driving logs and use them as a behavior regularization signal, suppressing imitation of unsafe or suboptimal behavior while stabilizing value learning. Training and closed-loop evaluation are conducted in a neural rendering environment learned from the public nuScenes dataset. Empirically, the proposed method achieves substantial improvements in collision rate and route completion compared with IL baselines. Our code is available at https://github.com/ToyotaInfoTech/PEBC.

---

### ASTIF: Adaptive Semantic-Temporal Integration for Cryptocurrency Price Forecasting

Authors: Hafiz Saif Ur Rehman, Ling Liu, Kaleem Ullah Qasim
Published: 2025-12-21
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.18661v1

Financial time series forecasting is fundamentally an information fusion challenge, yet most existing models rely on static architectures that struggle to integrate heterogeneous knowledge sources or adjust to rapid regime shifts. Conventional approaches, relying exclusively on historical price sequences, often neglect the semantic drivers of volatility such as policy uncertainty and market narratives. To address these limitations, we propose the ASTIF (Adaptive Semantic-Temporal Integration for Cryptocurrency Price Forecasting), a hybrid intelligent system that adapts its forecasting strategy in real time through confidence-based meta-learning. The framework integrates three complementary components. A dual-channel Small Language Model using MirrorPrompt extracts semantic market cues alongside numerical trends. A hybrid LSTM Random Forest model captures sequential temporal dependencies. A confidence-aware meta-learner functions as an adaptive inference layer, modulating each predictor's contribution based on its real-time uncertainty. Experimental evaluation on a diverse dataset of AI-focused cryptocurrencies and major technology stocks from 2020 to 2024 shows that ASTIF outperforms leading deep learning and Transformer baselines (e.g., Informer, TFT). The ablation studies further confirm the critical role of the adaptive meta-learning mechanism, which successfully mitigates risk by shifting reliance between semantic and temporal channels during market turbulence. The research contributes a scalable, knowledge-based solution for fusing quantitative and qualitative data in non-stationary environments.

---

### PMPGuard: Catching Pseudo-Matched Pairs in Remote Sensing Image-Text Retrieval

Authors: Pengxiang Ouyang, Qing Ma, Zheng Wang, Cong Bai
Published: 2025-12-21
Categories: cs.CV, cs.LG, cs.MM
arXiv: https://arxiv.org/abs/2512.18660v1

Remote sensing (RS) image-text retrieval faces significant challenges in real-world datasets due to the presence of Pseudo-Matched Pairs (PMPs), semantically mismatched or weakly aligned image-text pairs, which hinder the learning of reliable cross-modal alignments. To address this issue, we propose a novel retrieval framework that leverages Cross-Modal Gated Attention and a Positive-Negative Awareness Attention mechanism to mitigate the impact of such noisy associations. The gated module dynamically regulates cross-modal information flow, while the awareness mechanism explicitly distinguishes informative (positive) cues from misleading (negative) ones during alignment learning. Extensive experiments on three benchmark RS datasets, i.e., RSICD, RSITMD, and RS5M, demonstrate that our method consistently achieves state-of-the-art performance, highlighting its robustness and effectiveness in handling real-world mismatches and PMPs in RS image-text retrieval tasks.

---

### Does It Tie Out? Towards Autonomous Legal Agents in Venture Capital

Authors: Pierre Colombo, Malik Boudiaf, Allyn Sweet, Michael Desa, Hongxi Wang, Kevin Candra, Syméon del Marmol
Published: 2025-12-21
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.18658v1

Before closing venture capital financing rounds, lawyers conduct diligence that includes tying out the capitalization table: verifying that every security (for example, shares, options, warrants) and issuance term (for example, vesting schedules, acceleration triggers, transfer restrictions) is supported by large sets of underlying legal documentation. While LLMs continue to improve on legal benchmarks, specialized legal workflows, such as capitalization tie-out, remain out of reach even for strong agentic systems. The task requires multi-document reasoning, strict evidence traceability, and deterministic outputs that current approaches fail to reliably deliver. We characterize capitalization tie-out as an instance of a real-world benchmark for legal AI, analyze and compare the performance of existing agentic systems, and propose a world model architecture toward tie-out automation-and more broadly as a foundation for applied legal intelligence.

---

### SplatBright: Generalizable Low-Light Scene Reconstruction from Sparse Views via Physically-Guided Gaussian Enhancement

Authors: Yue Wen, Liang Song, Hesheng Wang
Published: 2025-12-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.18655v1

Low-light 3D reconstruction from sparse views remains challenging due to exposure imbalance and degraded color fidelity. While existing methods struggle with view inconsistency and require per-scene training, we propose SplatBright, which is, to our knowledge, the first generalizable 3D Gaussian framework for joint low-light enhancement and reconstruction from sparse sRGB inputs. Our key idea is to integrate physically guided illumination modeling with geometry-appearance decoupling for consistent low-light reconstruction. Specifically, we adopt a dual-branch predictor that provides stable geometric initialization of 3D Gaussian parameters. On the appearance side, illumination consistency leverages frequency priors to enable controllable and cross-view coherent lighting, while an appearance refinement module further separates illumination, material, and view-dependent cues to recover fine texture. To tackle the lack of large-scale geometrically consistent paired data, we synthesize dark views via a physics-based camera model for training. Extensive experiments on public and self-collected datasets demonstrate that SplatBright achieves superior novel view synthesis, cross-view consistency, and better generalization to unseen low-light scenes compared with both 2D and 3D methods.

---

### Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilities

Authors: Zhiyuan Peng, Zihan Ye, Shreyank N Gowda, Yuping Yan, Haotian Xu, Ling Shao
Published: 2025-12-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.18651v1

Zero-shot Learning (ZSL) aims to enable image classifiers to recognize images from unseen classes that were not included during training. Unlike traditional supervised classification, ZSL typically relies on learning a mapping from visual features to predefined, human-understandable class concepts. While ZSL models promise to improve generalization and interpretability, their robustness under systematic input perturbations remain unclear. In this study, we present an empirical analysis about the robustness of existing ZSL methods at both classlevel and concept-level. Specifically, we successfully disrupted their class prediction by the well-known non-target class attack (clsA). However, in the Generalized Zero-shot Learning (GZSL) setting, we observe that the success of clsA is only at the original best-calibrated point. After the attack, the optimal bestcalibration point shifts, and ZSL models maintain relatively strong performance at other calibration points, indicating that clsA results in a spurious attack success in the GZSL. To address this, we propose the Class-Bias Enhanced Attack (CBEA), which completely eliminates GZSL accuracy across all calibrated points by enhancing the gap between seen and unseen class probabilities.Next, at concept-level attack, we introduce two novel attack modes: Class-Preserving Concept Attack (CPconA) and NonClass-Preserving Concept Attack (NCPconA). Our extensive experiments evaluate three typical ZSL models across various architectures from the past three years and reveal that ZSL models are vulnerable not only to the traditional class attack but also to concept-based attacks. These attacks allow malicious actors to easily manipulate class predictions by erasing or introducing concepts. Our findings highlight a significant performance gap between existing approaches, emphasizing the need for improved adversarial robustness in current ZSL models.

---

### Geometric-Photometric Event-based 3D Gaussian Ray Tracing

Authors: Kai Kohyama, Yoshimitsu Aoki, Guillermo Gallego, Shintaro Shiba
Published: 2025-12-21
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2512.18640v3

Event cameras offer a high temporal resolution over traditional frame-based cameras, which makes them suitable for motion and structure estimation. However, it has been unclear how event-based 3D Gaussian Splatting (3DGS) approaches could leverage fine-grained temporal information of sparse events. This work proposes GPERT, a framework to address the trade-off between accuracy and temporal resolution in event-based 3DGS. Our key idea is to decouple the rendering into two branches: event-by-event geometry (depth) rendering and snapshot-based radiance (intensity) rendering, by using ray-tracing and the image of warped events. The extensive evaluation shows that our method achieves state-of-the-art performance on the real-world datasets and competitive performance on the synthetic dataset. Also, the proposed method works without prior information (e.g., pretrained image reconstruction models) or COLMAP-based initialization, is more flexible in the event selection number, and achieves sharp reconstruction on scene edges with fast training time. We hope that this work deepens our understanding of the sparse nature of events for 3D reconstruction. https://github.com/e3ai/gpert

---

### Uni-Neur2Img: Unified Neural Signal-Guided Image Generation, Editing, and Stylization via Diffusion Transformers

Authors: Xiyue Bai, Ronghao Yu, Jia Xiu, Pengfei Zhou, Jie Xia, Peng Ji
Published: 2025-12-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.18635v1

Generating or editing images directly from Neural signals has immense potential at the intersection of neuroscience, vision, and Brain-computer interaction. In this paper, We present Uni-Neur2Img, a unified framework for neural signal-driven image generation and editing. The framework introduces a parameter-efficient LoRA-based neural signal injection module that independently processes each conditioning signal as a pluggable component, facilitating flexible multi-modal conditioning without altering base model parameters. Additionally, we employ a causal attention mechanism accommodate the long-sequence modeling demands of conditional generation tasks. Existing neural-driven generation research predominantly focuses on textual modalities as conditions or intermediate representations, resulting in limited exploration of visual modalities as direct conditioning signals. To bridge this research gap, we introduce the EEG-Style dataset. We conduct comprehensive evaluations across public benchmarks and self-collected neural signal datasets: (1) EEG-driven image generation on the public CVPR40 dataset; (2) neural signal-guided image editing on the public Loongx dataset for semantic-aware local modifications; and (3) EEG-driven style transfer on our self-collected EEG-Style dataset. Extensive experimental results demonstrate significant improvements in generation fidelity, editing consistency, and style transfer quality while maintaining low computational overhead and strong scalability to additional modalities. Thus, Uni-Neur2Img offers a unified, efficient, and extensible solution for bridging neural signals and visual content generation.

---

### From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers

Authors: Ryotaro Kawata, Yujin Song, Alberto Bietti, Naoki Nishikawa, Taiji Suzuki, Samuel Vaiter, Denny Wu
Published: 2025-12-21
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.18634v1

Transformers can implement both generalizable algorithms (e.g., induction heads) and simple positional shortcuts (e.g., memorizing fixed output positions). In this work, we study how the choice of pretraining data distribution steers a shallow transformer toward one behavior or the other. Focusing on a minimal trigger-output prediction task -- copying the token immediately following a special trigger upon its second occurrence -- we present a rigorous analysis of gradient-based training of a single-layer transformer. In both the infinite and finite sample regimes, we prove a transition in the learned mechanism: if input sequences exhibit sufficient diversity, measured by a low ``max-sum'' ratio of trigger-to-trigger distances, the trained model implements an induction head and generalizes to unseen contexts; by contrast, when this ratio is large, the model resorts to a positional shortcut and fails to generalize out-of-distribution (OOD). We also reveal a trade-off between the pretraining context length and OOD generalization, and derive the optimal pretraining distribution that minimizes computational cost per sample. Finally, we validate our theoretical predictions with controlled synthetic experiments, demonstrating that broadening context distributions robustly induces induction heads and enables OOD generalization. Our results shed light on the algorithmic biases of pretrained transformers and offer conceptual guidelines for data-driven control of their learned behaviors.

---

### ARC: Leveraging Compositional Representations for Cross-Problem Learning on VRPs

Authors: Han-Seul Jeong, Youngjoon Park, Hyungseok Song, Woohyung Lim
Published: 2025-12-21
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.18633v1

Vehicle Routing Problems (VRPs) with diverse real-world attributes have driven recent interest in cross-problem learning approaches that efficiently generalize across problem variants. We propose ARC (Attribute Representation via Compositional Learning), a cross-problem learning framework that learns disentangled attribute representations by decomposing them into two complementary components: an Intrinsic Attribute Embedding (IAE) for invariant attribute semantics and a Contextual Interaction Embedding (CIE) for attribute-combination effects. This disentanglement is achieved by enforcing analogical consistency in the embedding space to ensure the semantic transformation of adding an attribute (e.g., a length constraint) remains invariant across different problem contexts. This enables our model to reuse invariant semantics across trained variants and construct representations for unseen combinations. ARC achieves state-of-the-art performance across in-distribution, zero-shot generalization, few-shot adaptation, and real-world benchmarks.

---

### LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction

Authors: Jensen Zhang, Ningyuan Liu, Yijia Fan, Zihao Huang, Qinglin Zeng, Kaitong Cai, Jian Wang, Keze Wang
Published: 2025-12-21
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.18623v1

Large language models (LLMs) often generate hallucinated content that lacks factual or contextual grounding, limiting their reliability in critical applications. Existing approaches such as supervised fine-tuning and reinforcement learning from human feedback are data intensive and computationally expensive, while static parameter editing methods struggle with context dependent errors and catastrophic forgetting. We propose LLM-CAS, a framework that formulates real-time hallucination correction as a hierarchical reinforcement learning problem. LLM-CAS trains an agent to learn a policy that dynamically selects temporary neuron perturbations during inference based on the current context. Unlike prior dynamic approaches that rely on heuristic or predefined adjustments, this policy driven mechanism enables adaptive and fine grained correction without permanent parameter modification. Experiments across multiple language models demonstrate that LLM-CAS consistently improves factual accuracy, achieving gains of 10.98 percentage points on StoryCloze, 2.71 points on TriviaQA, and 2.06 points on the MC1 score of TruthfulQA. These results outperform both static editing methods such as ITI and CAA and the dynamic SADI framework. Overall, LLM-CAS provides an efficient and context aware solution for improving the reliability of LLMs, with promising potential for future multimodal extensions.

---

### A Multi-agent Text2SQL Framework using Small Language Models and Execution Feedback

Authors: Thanh Dat Hoang, Thanh Trung Huynh, Matthias Weidlich, Thanh Tam Nguyen, Tong Chen, Hongzhi Yin, Quoc Viet Hung Nguyen
Published: 2025-12-21
Categories: cs.DB, cs.AI, cs.CL, cs.HC, cs.MA
arXiv: https://arxiv.org/abs/2512.18622v1

Text2SQL, the task of generating SQL queries from natural language text, is a critical challenge in data engineering. Recently, Large Language Models (LLMs) have demonstrated superior performance for this task due to their advanced comprehension and generation capabilities. However, privacy and cost considerations prevent companies from using Text2SQL solutions based on external LLMs offered as a service. Rather, small LLMs (SLMs) that are openly available and can hosted in-house are adopted. These SLMs, in turn, lack the generalization capabilities of larger LLMs, which impairs their effectiveness for complex tasks such as Text2SQL. To address these limitations, we propose MATS, a novel Text2SQL framework designed specifically for SLMs. MATS uses a multi-agent mechanism that assigns specialized roles to auxiliary agents, reducing individual workloads and fostering interaction. A training scheme based on reinforcement learning aligns these agents using feedback obtained during execution, thereby maintaining competitive performance despite a limited LLM size. Evaluation results using on benchmark datasets show that MATS, deployed on a single- GPU server, yields accuracy that are on-par with large-scale LLMs when using significantly fewer parameters. Our source code and data are available at https://github.com/thanhdath/mats-sql.

---

### ChronoDreamer: Action-Conditioned World Model as an Online Simulator for Robotic Planning

Authors: Zhenhao Zhou, Dan Negrut
Published: 2025-12-21
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2512.18619v1

We present ChronoDreamer, an action-conditioned world model for contact-rich robotic manipulation. Given a history of egocentric RGB frames, contact maps, actions, and joint states, ChronoDreamer predicts future video frames, contact distributions, and joint angles via a spatial-temporal transformer trained with MaskGIT-style masked prediction. Contact is encoded as depth-weighted Gaussian splat images that render 3D forces into a camera-aligned format suitable for vision backbones. At inference, predicted rollouts are evaluated by a vision-language model that reasons about collision likelihood, enabling rejection sampling of unsafe actions before execution. We train and evaluate on DreamerBench, a simulation dataset generated with Project Chrono that provides synchronized RGB, contact splat, proprioception, and physics annotations across rigid and deformable object scenarios. Qualitative results demonstrate that the model preserves spatial coherence during non-contact motion and generates plausible contact predictions, while the LLM-based judge distinguishes collision from non-collision trajectories.

---

### Assignment-Routing Optimization: Solvers for Problems Under Constraints

Authors: Yuan Qilong, Michal Pavelka
Published: 2025-12-21
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.18618v1

We study the Joint Routing-Assignment (JRA) problem in which items must be assigned one-to-one to placeholders while simultaneously determining a Hamiltonian cycle visiting all nodes exactly once. Extending previous exact MIP solvers with Gurobi and cutting-plane subtour elimination, we develop a solver tailored for practical packaging-planning scenarios with richer constraints.These include multiple placeholder options, time-frame restrictions, and multi-class item packaging. Experiments on 46 mobile manipulation datasets demonstrate that the proposed MIP approach achieves global optima with stable and low computation times, significantly outperforming the shaking-based exact solver by up to an orders of magnitude. Compared to greedy baselines, the MIP solutions achieve consistent optimal distances with an average deviation of 14% for simple heuristics, confirming both efficiency and solution quality. The results highlight the practical applicability of MIP-based JRA optimization for robotic packaging, motion planning, and complex logistics .

---

### DASH: Deception-Augmented Shared Mental Model for a Human-Machine Teaming System

Authors: Zelin Wan, Han Jun Yoon, Nithin Alluru, Terrence J. Moore, Frederica F. Nelson, Seunghyun Yoon, Hyuk Lim, Dan Dongseong Kim, Jin-Hee Cho
Published: 2025-12-21
Categories: cs.HC, cs.AI, cs.CR, cs.MA
arXiv: https://arxiv.org/abs/2512.18616v1

We present DASH (Deception-Augmented Shared mental model for Human-machine teaming), a novel framework that enhances mission resilience by embedding proactive deception into Shared Mental Models (SMM). Designed for mission-critical applications such as surveillance and rescue, DASH introduces "bait tasks" to detect insider threats, e.g., compromised Unmanned Ground Vehicles (UGVs), AI agents, or human analysts, before they degrade team performance. Upon detection, tailored recovery mechanisms are activated, including UGV system reinstallation, AI model retraining, or human analyst replacement. In contrast to existing SMM approaches that neglect insider risks, DASH improves both coordination and security. Empirical evaluations across four schemes (DASH, SMM-only, no-SMM, and baseline) show that DASH sustains approximately 80% mission success under high attack rates, eight times higher than the baseline. This work contributes a practical human-AI teaming framework grounded in shared mental models, a deception-based strategy for insider threat detection, and empirical evidence of enhanced robustness under adversarial conditions. DASH establishes a foundation for secure, adaptive human-machine teaming in contested environments.

---

### PTTA: A Pure Text-to-Animation Framework for High-Quality Creation

Authors: Ruiqi Chen, Kaitong Cai, Yijia Fan, Keze Wang
Published: 2025-12-21
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.18614v1

Traditional animation production involves complex pipelines and significant manual labor cost. While recent video generation models such as Sora, Kling, and CogVideoX achieve impressive results on natural video synthesis, they exhibit notable limitations when applied to animation generation. Recent efforts, such as AniSora, demonstrate promising performance by fine-tuning image-to-video models for animation styles, yet analogous exploration in the text-to-video setting remains limited. In this work, we present PTTA, a pure text-to-animation framework for high-quality animation creation. We first construct a small-scale but high-quality paired dataset of animation videos and textual descriptions. Building upon the pretrained text-to-video model HunyuanVideo, we perform fine-tuning to adapt it to animation-style generation. Extensive visual evaluations across multiple dimensions show that the proposed approach consistently outperforms comparable baselines in animation video synthesis.

---

### Text2Graph VPR: A Text-to-Graph Expert System for Explainable Place Recognition in Changing Environments

Authors: Saeideh Yousefzadeh, Hamidreza Pourreza
Published: 2025-12-21
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.18613v1

Visual Place Recognition (VPR) in long-term deployment requires reasoning beyond pixel similarity: systems must make transparent, interpretable decisions that remain robust under lighting, weather and seasonal change. We present Text2Graph VPR, an explainable semantic localization system that converts image sequences into textual scene descriptions, parses those descriptions into structured scene graphs, and reasons over the resulting graphs to identify places. Scene graphs capture objects, attributes and pairwise relations; we aggregate per-frame graphs into a compact place representation and perform retrieval with a dual-similarity mechanism that fuses learned Graph Attention Network (GAT) embeddings and a Shortest-Path (SP) kernel for structural matching. This hybrid design enables both learned semantic matching and topology-aware comparison, and -- critically -- produces human-readable intermediate representations that support diagnostic analysis and improve transparency in the decision process. We validate the system on Oxford RobotCar and MSLS (Amman/San Francisco) benchmarks and demonstrate robust retrieval under severe appearance shifts, along with zero-shot operation using human textual queries. The results illustrate that semantic, graph-based reasoning is a viable and interpretable alternative for place recognition, particularly suited to safety-sensitive and resource-constrained settings.

---

### The Procrustean Bed of Time Series: The Optimization Bias in Point-wise Loss Functions

Authors: Rongyao Cai, Yuxi Wan, Kexin Zhang, Ming Jin, Zhiqiang Ge, Daoyi Dong, Hang Yu, Yong Liu, Qingsong Wen
Published: 2025-12-21
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.18610v3

Intuitively, a more deterministic time series should be easier to forecast. However, point-wise loss functions (e.g., MSE and MAE), serving as differentiable surrogates for the ideal optimization target, score each timestamp independently and therefore disregard temporal dependence. This mismatch induces a systematic optimization bias that cannot be eliminated merely by improving model expressiveness or optimizer. To formalize this issue, we define the Expectation of Optimization Bias (EOB) as the Kullback--Leibler divergence between the true joint distribution and the factorized i.i.d. surrogate induced by the point-wise paradigm. Under covariance-stationary Gaussian assumptions, we derive closed-form expressions for the stochastic component of EOB, establishing it as an irreducible lower bound on the total bias in linear systems, and further extend it to nonlinear regimes through a Gaussian mixture model lower bound. Crucially, we prove this bias is governed intrinsically by two data properties, i.e., sequence length and Structural Signal-to-Noise Ratio (SSNR), regardless of specific model architecture, optimizer, or point-wise loss forms. This theory motivates a principled debiasing program based on sequence length reduction and structural orthogonalization, which we instantiate through DFT/DWT combined with a novel harmonized $\ell_p$ norm. Extensive experiments validate the predicted SSNR--horizon dynamics, resolve the classic trigonometric fitting failure as an objective-induced pathology, and demonstrate substantial plug-and-play gains. Notably, on iTransformer, our proposed objective reduces average MSE/MAE by 5.2%/5.0% in forecasting across 11 datasets and by 27.4%/19.4% in imputation across 9 datasets.

---

### A Comparative Study of Light-weight Language Models for PII Masking and their Deployment for Real Conversational Texts

Authors: Prabigya Acharya, Liza Shrestha
Published: 2025-12-21
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.18608v1

Automated masking of Personally Identifiable Information (PII) is critical for privacy-preserving conversational systems. While current frontier large language models demonstrate strong PII masking capabilities, concerns about data handling and computational costs motivate exploration of whether lightweight models can achieve comparable performance. We compare encoder-decoder and decoder-only architectures by fine-tuning T5-small and Mistral-Instruct-v0.3 on English datasets constructed from the AI4Privacy benchmark. We create different dataset variants to study label standardization and PII representation, covering 24 standardized PII categories and higher-granularity settings. Evaluation using entity-level and character-level metrics, type accuracy, and exact match shows that both lightweight models achieve performance comparable to frontier LLMs for PII masking tasks. Label normalization consistently improves performance across architectures. Mistral achieves higher F1 and recall with greater robustness across PII types but incurs significantly higher generation latency. T5, while less robust in conversational text, offers more controllable structured outputs and lower inference cost, motivating its use in a real-time Discord bot for real-world PII redaction. Evaluation on live messages reveals performance degradation under informal inputs. These results clarify trade-offs between accuracy, robustness, and computational efficiency, demonstrating that lightweight models can provide effective PII masking while addressing data handling concerns associated with frontier LLMs.

---

### The Interaction Bottleneck of Deep Neural Networks: Discovery, Proof, and Modulation

Authors: Huiqi Deng, Qihan Ren, Zhuofan Chen, Zhenyuan Cui, Wen Shen, Peng Zhang, Hongbin Pei, Quanshi Zhang
Published: 2025-12-21
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.18607v1

Understanding what kinds of cooperative structures deep neural networks (DNNs) can represent remains a fundamental yet insufficiently understood problem. In this work, we treat interactions as the fundamental units of such structure and investigate a largely unexplored question: how DNNs encode interactions under different levels of contextual complexity, and how these microscopic interaction patterns shape macroscopic representation capacity. To quantify this complexity, we use multi-order interactions (57), where each order reflects the amount of contextual information required to evaluate the joint interaction utility of a variable pair. This formulation enables a stratified analysis of cooperative patterns learned by DNNs. Building on this formulation, we develop a comprehensive study of interaction structure in DNNs. (i) We empirically discover a universal interaction bottleneck: across architectures and tasks, DNNs easily learn low-order and high-order interactions but consistently under-represent mid-order ones. (ii) We theoretically explain this bottleneck by proving that mid-order interactions incur the highest contextual variability, yielding large gradient variance and making them intrinsically difficult to learn. (iii) We further modulate the bottleneck by introducing losses that steer models toward emphasizing interactions of selected orders. Finally, we connect microscopic interaction structures with macroscopic representational behavior: low-order-emphasized models exhibit stronger generalization and robustness, whereas high-order-emphasized models demonstrate greater structural modeling and fitting capability. Together, these results uncover an inherent representational bias in modern DNNs and establish interaction order as a powerful lens for interpreting and guiding deep representations.

---

### Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction

Authors: Qinglin Zeng, Jing Yang, Keze Wang
Published: 2025-12-21
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.18605v1

Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency. However, ensemble-based approaches, especially self-consistency which relies on multiple reasoning trajectories, often incur substantial computational overhead. To improve efficiency, prior work has leveraged internal confidence signals, where early stopping strategies such as DeepConf reduce cost by terminating low-confidence trajectories. However, this strategy discards incomplete reasoning paths and wastes partial computation. We propose reflective confidence, a novel reasoning framework that transforms low-confidence signals from termination indicators into reflection triggers. When confidence falls below a threshold, instead of stopping generation, the model produces a reflection prompt to analyze the current reasoning state, identify potential errors, and continue generation along a corrected trajectory. Experiments on mathematical reasoning benchmarks, including AIME 2025, demonstrate significant accuracy improvements over advanced early-stopping baselines at comparable computational cost, validating the effectiveness of proactive self-correction over passive discarding.

---

### Trajectory Planning for UAV-Based Smart Farming Using Imitation-Based Triple Deep Q-Learning

Authors: Wencan Mao, Quanxi Zhou, Tomas Couso Coddou, Manabu Tsukada, Yunling Liu, Yusheng Ji
Published: 2025-12-21
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.18604v1

Unmanned aerial vehicles (UAVs) have emerged as a promising auxiliary platform for smart agriculture, capable of simultaneously performing weed detection, recognition, and data collection from wireless sensors. However, trajectory planning for UAV-based smart agriculture is challenging due to the high uncertainty of the environment, partial observations, and limited battery capacity of UAVs. To address these issues, we formulate the trajectory planning problem as a Markov decision process (MDP) and leverage multi-agent reinforcement learning (MARL) to solve it. Furthermore, we propose a novel imitation-based triple deep Q-network (ITDQN) algorithm, which employs an elite imitation mechanism to reduce exploration costs and utilizes a mediator Q-network over a double deep Q-network (DDQN) to accelerate and stabilize training and improve performance. Experimental results in both simulated and real-world environments demonstrate the effectiveness of our solution. Moreover, our proposed ITDQN outperforms DDQN by 4.43\% in weed recognition rate and 6.94\% in data collection rate.

---

### On Finding Inconsistencies in Documents

Authors: Charles J. Lovering, Seth Ebner, Brandon Smock, Michael Krumdick, Saad Rabbani, Ahmed Muhammad, Varshini Reddy, Chris Tanner
Published: 2025-12-21
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.18601v1

Professionals in academia, law, and finance audit their documents because inconsistencies can result in monetary, reputational, and scientific costs. Language models (LMs) have the potential to dramatically speed up this auditing process. To understand their abilities, we introduce a benchmark, FIND (Finding INconsistencies in Documents), where each example is a document with an inconsistency inserted manually by a domain expert. Despite the documents being long, technical, and complex, the best-performing model (gpt-5) recovered 64% of the inserted inconsistencies. Surprisingly, gpt-5 also found undiscovered inconsistencies present in the original documents. For example, on 50 arXiv papers, we judged 136 out of 196 of the model's suggestions to be legitimate inconsistencies missed by the original authors. However, despite these findings, even the best models miss almost half of the inconsistencies in FIND, demonstrating that inconsistency detection is still a challenging task.

---

### Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback

Authors: Jianglin Lu, Yuanwei Wu, Ziyi Zhao, Hongcheng Wang, Felix Jimenez, Abrar Majeedi, Yun Fu
Published: 2025-12-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.18599v2

Complex image restoration aims to recover high-quality images from inputs affected by multiple degradations such as blur, noise, rain, and compression artifacts. Recent restoration agents, powered by vision-language models and large language models, offer promising restoration capabilities but suffer from significant efficiency bottlenecks due to reflection, rollback, and iterative tool searching. Moreover, their performance heavily depends on degradation recognition models that require extensive annotations for training, limiting their applicability in label-free environments. To address these limitations, we propose a policy optimization-based restoration framework that learns an lightweight agent to determine tool-calling sequences. The agent operates in a sequential decision process, selecting the most appropriate restoration operation at each step to maximize final image quality. To enable training within label-free environments, we introduce a novel reward mechanism driven by multimodal large language models, which act as human-aligned evaluator and provide perceptual feedback for policy improvement. Once trained, our agent executes a deterministic restoration plans without redundant tool invocations, significantly accelerating inference while maintaining high restoration quality. Extensive experiments show that despite using no supervision, our method matches SOTA performance on full-reference metrics and surpasses existing approaches on no-reference metrics across diverse degradation scenarios.

---

### Commercial Vehicle Braking Optimization: A Robust SIFT-Trajectory Approach

Authors: Zhe Li, Kun Cheng, Hanyue Mo, Jintao Lu, Ziwen Kuang, Jianwen Ye, Lixu Xu, Xinya Meng, Jiahui Zhao, Shengda Ji, Shuyuan Liu, Mengyu Wang
Published: 2025-12-21
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2512.18597v1

A vision-based trajectory analysis solution is proposed to address the "zero-speed braking" issue caused by inaccurate Controller Area Network (CAN) signals in commercial vehicle Automatic Emergency Braking (AEB) systems during low-speed operation. The algorithm utilizes the NVIDIA Jetson AGX Xavier platform to process sequential video frames from a blind spot camera, employing self-adaptive Contrast Limited Adaptive Histogram Equalization (CLAHE)-enhanced Scale-Invariant Feature Transform (SIFT) feature extraction and K-Nearest Neighbors (KNN)-Random Sample Consensus (RANSAC) matching. This allows for precise classification of the vehicle's motion state (static, vibration, moving). Key innovations include 1) multiframe trajectory displacement statistics (5-frame sliding window), 2) a dual-threshold state decision matrix, and 3) OBD-II driven dynamic Region of Interest (ROI) configuration. The system effectively suppresses environmental interference and false detection of dynamic objects, directly addressing the challenge of low-speed false activation in commercial vehicle safety systems. Evaluation in a real-world dataset (32,454 video segments from 1,852 vehicles) demonstrates an F1-score of 99.96% for static detection, 97.78% for moving state recognition, and a processing delay of 14.2 milliseconds (resolution 704x576). The deployment on-site shows an 89% reduction in false braking events, a 100% success rate in emergency braking, and a fault rate below 5%.

---

### EIA-SEC: Improved Actor-Critic Framework for Multi-UAV Collaborative Control in Smart Agriculture

Authors: Quanxi Zhou, Wencan Mao, Yilei Liang, Manabu Tsukada, Yunling Liu, Jon Crowcroft
Published: 2025-12-21
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.18596v1

The widespread application of wireless communication technology has promoted the development of smart agriculture, where unmanned aerial vehicles (UAVs) play a multifunctional role. We target a multi-UAV smart agriculture system where UAVs cooperatively perform data collection, image acquisition, and communication tasks. In this context, we model a Markov decision process to solve the multi-UAV trajectory planning problem. Moreover, we propose a novel Elite Imitation Actor-Shared Ensemble Critic (EIA-SEC) framework, where agents adaptively learn from the elite agent to reduce trial-and-error costs, and a shared ensemble critic collaborates with each agent's local critic to ensure unbiased objective value estimates and prevent overestimation. Experimental results demonstrate that EIA-SEC outperforms state-of-the-art baselines in terms of reward performance, training stability, and convergence speed.

---

### Benchmarking neural surrogates on realistic spatiotemporal multiphysics flows

Authors: Runze Mao, Rui Zhang, Xuan Bai, Tianhao Wu, Teng Zhang, Zhenyi Chen, Minqi Lin, Bocheng Zeng, Yangchen Xu, Yingxuan Xiang, Haoze Zhang, Shubham Goswami et al.
Published: 2025-12-21
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.18595v2

Predicting multiphysics dynamics is computationally expensive and challenging due to the severe coupling of multi-scale, heterogeneous physical processes. While neural surrogates promise a paradigm shift, the field currently suffers from an "illusion of mastery", as repeatedly emphasized in top-tier commentaries: existing evaluations overly rely on simplified, low-dimensional proxies, which fail to expose the models' inherent fragility in realistic regimes. To bridge this critical gap, we present REALM (REalistic AI Learning for Multiphysics), a rigorous benchmarking framework designed to test neural surrogates on challenging, application-driven reactive flows. REALM features 11 high-fidelity datasets spanning from canonical multiphysics problems to complex propulsion and fire safety scenarios, alongside a standardized end-to-end training and evaluation protocol that incorporates multiphysics-aware preprocessing and a robust rollout strategy. Using this framework, we systematically benchmark over a dozen representative surrogate model families, including spectral operators, convolutional models, Transformers, pointwise operators, and graph/mesh networks, and identify three robust trends: (i) a scaling barrier governed jointly by dimensionality, stiffness, and mesh irregularity, leading to rapidly growing rollout errors; (ii) performance primarily controlled by architectural inductive biases rather than parameter count; and (iii) a persistent gap between nominal accuracy metrics and physically trustworthy behavior, where models with high correlations still miss key transient structures and integral quantities. Taken together, REALM exposes the limits of current neural surrogates on realistic multiphysics flows and offers a rigorous testbed to drive the development of next-generation physics-aware architectures.

---

### From Scratch to Fine-Tuned: A Comparative Study of Transformer Training Strategies for Legal Machine Translation

Authors: Amit Barman, Atanu Mandal, Sudip Kumar Naskar
Published: 2025-12-21
Categories: cs.CL, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2512.18593v1

In multilingual nations like India, access to legal information is often hindered by language barriers, as much of the legal and judicial documentation remains in English. Legal Machine Translation (L-MT) offers a scalable solution to this challenge by enabling accurate and accessible translations of legal documents. This paper presents our work for the JUST-NLP 2025 Legal MT shared task, focusing on English-Hindi translation using Transformer-based approaches. We experiment with 2 complementary strategies, fine-tuning a pre-trained OPUS-MT model for domain-specific adaptation and training a Transformer model from scratch using the provided legal corpus. Performance is evaluated using standard MT metrics, including SacreBLEU, chrF++, TER, ROUGE, BERTScore, METEOR, and COMET. Our fine-tuned OPUS-MT model achieves a SacreBLEU score of 46.03, significantly outperforming both baseline and from-scratch models. The results highlight the effectiveness of domain adaptation in enhancing translation quality and demonstrate the potential of L-MT systems to improve access to justice and legal transparency in multilingual contexts.

---

### SD2AIL: Adversarial Imitation Learning from Synthetic Demonstrations via Diffusion Models

Authors: Pengcheng Li, Qiang Fang, Tong Zhao, Yixing Lan, Xin Xu
Published: 2025-12-21
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2512.18583v2

Adversarial Imitation Learning (AIL) is a dominant framework in imitation learning that infers rewards from expert demonstrations to guide policy optimization. Although providing more expert demonstrations typically leads to improved performance and greater stability, collecting such demonstrations can be challenging in certain scenarios. Inspired by the success of diffusion models in data generation, we propose SD2AIL, which utilizes synthetic demonstrations via diffusion models. We first employ a diffusion model in the discriminator to generate synthetic demonstrations as pseudo-expert data that augment the expert demonstrations. To selectively replay the most valuable demonstrations from the large pool of (pseudo-) expert demonstrations, we further introduce a prioritized expert demonstration replay strategy (PEDR). The experimental results on simulation tasks demonstrate the effectiveness and robustness of our method. In particular, in the Hopper task, our method achieves an average return of 3441, surpassing the state-of-the-art method by 89. Our code will be available at https://github.com/positron-lpc/SD2AIL.

---

### Modality-Dependent Memory Mechanisms in Cross-Modal Neuromorphic Computing

Authors: Effiong Blessing, Chiung-Yi Tseng, Somshubhra Roy, Junaid Rehman, Isaac Nkrumah
Published: 2025-12-21
Categories: cs.LG, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2512.18575v1

Memory-augmented spiking neural networks (SNNs) promise energy-efficient neuromorphic computing, yet their generalization across sensory modalities remains unexplored. We present the first comprehensive cross-modal ablation study of memory mechanisms in SNNs, evaluating Hopfield networks, Hierarchical Gated Recurrent Networks (HGRNs), and supervised contrastive learning (SCL) across visual (N-MNIST) and auditory (SHD) neuromorphic datasets. Our systematic evaluation of five architectures reveals striking modality-dependent performance patterns: Hopfield networks achieve 97.68% accuracy on visual tasks but only 76.15% on auditory tasks (21.53 point gap), revealing severe modality-specific specialization, while SCL demonstrates more balanced cross-modal performance (96.72% visual, 82.16% audio, 14.56 point gap). These findings establish that memory mechanisms exhibit task-specific benefits rather than universal applicability. Joint multi-modal training with HGRN achieves 94.41% visual and 79.37% audio accuracy (88.78% average), matching parallel HGRN performance through unified deployment. Quantitative engram analysis confirms weak cross-modal alignment (0.038 similarity), validating our parallel architecture design. Our work provides the first empirical evidence for modality-specific memory optimization in neuromorphic systems, achieving 603x energy efficiency over traditional neural networks.

---

### Placenta Accreta Spectrum Detection Using an MRI-based Hybrid CNN-Transformer Model

Authors: Sumaiya Ali, Areej Alhothali, Ohoud Alzamzami, Sameera Albasri, Ahmed Abduljabbar, Muhammad Alwazzan
Published: 2025-12-21
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.18573v1

Placenta Accreta Spectrum (PAS) is a serious obstetric condition that can be challenging to diagnose with Magnetic Resonance Imaging (MRI) due to variability in radiologists' interpretations. To overcome this challenge, a hybrid 3D deep learning model for automated PAS detection from volumetric MRI scans is proposed in this study. The model integrates a 3D DenseNet121 to capture local features and a 3D Vision Transformer (ViT) to model global spatial context. It was developed and evaluated on a retrospective dataset of 1,133 MRI volumes. Multiple 3D deep learning architectures were also evaluated for comparison. On an independent test set, the DenseNet121-ViT model achieved the highest performance with a five-run average accuracy of 84.3%. These results highlight the strength of hybrid CNN-Transformer models as a computer-aided diagnosis tool. The model's performance demonstrates a clear potential to assist radiologists by providing a robust decision support to improve diagnostic consistency across interpretations, and ultimately enhance the accuracy and timeliness of PAS diagnosis.

---

### ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning

Authors: Weijie Zhou, Xuangtang Xiong, Ye Tian, Lijun Yue, Xinyu Wu, Wei Li, Chaoyang Zhao, Honghui Dong, Ming Tang, Jinqiao Wang, Zhengyou Zhang
Published: 2025-12-21
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2512.18571v1

Multimodal Large Language Models (MLLMs) have empowered embodied agents with remarkable capabilities in planning and reasoning. However, when facing ambiguous natural language instructions (e.g., "fetch the tool" in a cluttered room), current agents often fail to balance the high cost of physical exploration against the cognitive cost of human interaction. They typically treat disambiguation as a passive perception problem, lacking the strategic reasoning to minimize total task execution costs. To bridge this gap, we propose ESearch-R1, a cost-aware embodied reasoning framework that unifies interactive dialogue (Ask), episodic memory retrieval (GetMemory), and physical navigation (Navigate) into a single decision process. We introduce HC-GRPO (Heterogeneous Cost-Aware Group Relative Policy Optimization). Unlike traditional PPO which relies on a separate value critic, HC-GRPO optimizes the MLLM by sampling groups of reasoning trajectories and reinforcing those that achieve the optimal trade-off between information gain and heterogeneous costs (e.g., navigate time, and human attention). Extensive experiments in AI2-THOR demonstrate that ESearch-R1 significantly outperforms standard ReAct-based agents. It improves task success rates while reducing total operational costs by approximately 50\%, validating the effectiveness of GRPO in aligning MLLM agents with physical world constraints.

---

### AI Code in the Wild: Measuring Security Risks and Ecosystem Shifts of AI-Generated Code in Modern Software

Authors: Bin Wang, Wenjie Yu, Yilu Zhong, Hao Yu, Keke Lian, Chaohua Lu, Hongfang Zheng, Dong Zhang, Hui Li
Published: 2025-12-21
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2512.18567v1

Large language models (LLMs) for code generation are becoming integral to modern software development, but their real-world prevalence and security impact remain poorly understood. We present the first large-scale empirical study of AI-generated code (AIGCode) in the wild. We build a high-precision detection pipeline and a representative benchmark to distinguish AIGCode from human-written code, and apply them to (i) development commits from the top 1,000 GitHub repositories (2022-2025) and (ii) 7,000+ recent CVE-linked code changes. This lets us label commits, files, and functions along a human/AI axis and trace how AIGCode moves through projects and vulnerability life cycles. Our measurements show three ecological patterns. First, AIGCode is already a substantial fraction of new code, but adoption is structured: AI concentrates in glue code, tests, refactoring, documentation, and other boilerplate, while core logic and security-critical configurations remain mostly human-written. Second, adoption has security consequences: some CWE families are overrepresented in AI-tagged code, and near-identical insecure templates recur across unrelated projects, suggesting "AI-induced vulnerabilities" propagated by shared models rather than shared maintainers. Third, in human-AI edit chains, AI introduces high-throughput changes while humans act as security gatekeepers; when review is shallow, AI-introduced defects persist longer, remain exposed on network-accessible surfaces, and spread to more files and repositories. We will open-source the complete dataset and release analysis artifacts and fine-grained documentation of our methodology and findings.

---