# Research Papers — 2025-12 · bundle page 23 of 175 > Full-text markdown of papers #1101–1150 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/23 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/22.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/24.md) ### Pruning as a Game: Equilibrium-Driven Sparsification of Neural Networks Authors: Zubair Shah, Noaman Khan Published: 2025-12-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.22106v1 Neural network pruning is widely used to reduce model size and computational cost. Yet, most existing methods treat sparsity as an externally imposed constraint, enforced through heuristic importance scores or training-time regularization. In this work, we propose a fundamentally different perspective: pruning as an equilibrium outcome of strategic interaction among model components. We model parameter groups such as weights, neurons, or filters as players in a continuous non-cooperative game, where each player selects its level of participation in the network to balance contribution against redundancy and competition. Within this formulation, sparsity emerges naturally when continued participation becomes a dominated strategy at equilibrium. We analyze the resulting game and show that dominated players collapse to zero participation under mild conditions, providing a principled explanation for pruning behavior. Building on this insight, we derive a simple equilibrium-driven pruning algorithm that jointly updates network parameters and participation variables without relying on explicit importance scores. This work focuses on establishing a principled formulation and empirical validation of pruning as an equilibrium phenomenon, rather than exhaustive architectural or large-scale benchmarking. Experiments on standard benchmarks demonstrate that the proposed approach achieves competitive sparsity-accuracy trade-offs while offering an interpretable, theory-grounded alternative to existing pruning methods. --- ### Learning Association via Track-Detection Matching for Multi-Object Tracking Authors: Momir Adžemović Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22105v2 Multi-object tracking aims to maintain object identities over time by associating detections across video frames. Two dominant paradigms exist in literature: tracking-by-detection methods, which are computationally efficient but rely on handcrafted association heuristics, and end-to-end approaches, which learn association from data at the cost of higher computational complexity. We propose Track-Detection Link Prediction (TDLP), a tracking-by-detection method that performs per-frame association via link prediction between tracks and detections, i.e., by predicting the correct continuation of each track at every frame. TDLP is architecturally designed primarily for geometric features such as bounding boxes, while optionally incorporating additional cues, including pose and appearance. Unlike heuristic-based methods, TDLP learns association directly from data without handcrafted rules, while remaining modular and computationally efficient compared to end-to-end trackers. Extensive experiments on multiple benchmarks demonstrate that TDLP consistently surpasses state-of-the-art performance across both tracking-by-detection and end-to-end methods. Finally, we provide a detailed analysis comparing link prediction with metric learning-based association and show that link prediction is more effective, particularly when handling heterogeneous features such as detection bounding boxes. Our code is available at \href{https://github.com/Robotmurlock/TDLP}{https://github.com/Robotmurlock/TDLP}. --- ### Explainable Multimodal Regression via Information Decomposition Authors: Zhaozhao Ma, Shujian Yu Published: 2025-12-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.22102v1 Multimodal regression aims to predict a continuous target from heterogeneous input sources and typically relies on fusion strategies such as early or late fusion. However, existing methods lack principled tools to disentangle and quantify the individual contributions of each modality and their interactions, limiting the interpretability of multimodal fusion. We propose a novel multimodal regression framework grounded in Partial Information Decomposition (PID), which decomposes modality-specific representations into unique, redundant, and synergistic components. The basic PID framework is inherently underdetermined. To resolve this, we introduce inductive bias by enforcing Gaussianity in the joint distribution of latent representations and the transformed response variable (after inverse normal transformation), thereby enabling analytical computation of the PID terms. Additionally, we derive a closed-form conditional independence regularizer to promote the isolation of unique information within each modality. Experiments on six real-world datasets, including a case study on large-scale brain age prediction from multimodal neuroimaging data, demonstrate that our framework outperforms state-of-the-art methods in both predictive accuracy and interpretability, while also enabling informed modality selection for efficient inference. Implementation is available at https://github.com/zhaozhaoma/PIDReg. --- ### A2P-Vis: an Analyzer-to-Presenter Agentic Pipeline for Visual Insights Generation and Reporting Authors: Shuyu Gan, Renxiang Wang, James Mooney, Dongyeop Kang Published: 2025-12-26 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.22101v1 Automating end-to-end data science pipeline with AI agents still stalls on two gaps: generating insightful, diverse visual evidence and assembling it into a coherent, professional report. We present A2P-Vis, a two-part, multi-agent pipeline that turns raw datasets into a high-quality data-visualization report. The Data Analyzer orchestrates profiling, proposes diverse visualization directions, generates and executes plotting code, filters low-quality figures with a legibility checker, and elicits candidate insights that are automatically scored for depth, correctness, specificity, depth and actionability. The Presenter then orders topics, composes chart-grounded narratives from the top-ranked insights, writes justified transitions, and revises the document for clarity and consistency, yielding a coherent, publication-ready report. Together, these agents convert raw data into curated materials (charts + vetted insights) and into a readable narrative without manual glue work. We claim that by coupling a quality-assured Analyzer with a narrative Presenter, A2P-Vis operationalizes co-analysis end-to-end, improving the real-world usefulness of automated data analysis for practitioners. For the complete dataset report, please see: https://www.visagent.org/api/output/f2a3486d-2c3b-4825-98d4-5af25a819f56. --- ### Introducing TrGLUE and SentiTurca: A Comprehensive Benchmark for Turkish General Language Understanding and Sentiment Analysis Authors: Duygu Altinok Published: 2025-12-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.22100v1 Evaluating the performance of various model architectures, such as transformers, large language models (LLMs), and other NLP systems, requires comprehensive benchmarks that measure performance across multiple dimensions. Among these, the evaluation of natural language understanding (NLU) is particularly critical as it serves as a fundamental criterion for assessing model capabilities. Thus, it is essential to establish benchmarks that enable thorough evaluation and analysis of NLU abilities from diverse perspectives. While the GLUE benchmark has set a standard for evaluating English NLU, similar benchmarks have been developed for other languages, such as CLUE for Chinese, FLUE for French, and JGLUE for Japanese. However, no comparable benchmark currently exists for the Turkish language. To address this gap, we introduce TrGLUE, a comprehensive benchmark encompassing a variety of NLU tasks for Turkish. In addition, we present SentiTurca, a specialized benchmark for sentiment analysis. To support researchers, we also provide fine-tuning and evaluation code for transformer-based models, facilitating the effective use of these benchmarks. TrGLUE comprises Turkish-native corpora curated to mirror the domains and task formulations of GLUE-style evaluations, with labels obtained through a semi-automated pipeline that combines strong LLM-based annotation, cross-model agreement checks, and subsequent human validation. This design prioritizes linguistic naturalness, minimizes direct translation artifacts, and yields a scalable, reproducible workflow. With TrGLUE, our goal is to establish a robust evaluation framework for Turkish NLU, empower researchers with valuable resources, and provide insights into generating high-quality semi-automated datasets. --- ### Yume-1.5: A Text-Controlled Interactive World Generation Model Authors: Xiaofeng Mao, Zhen Li, Chuanhao Li, Xiaojie Xu, Kaining Ying, Tong He, Jiangmiao Pang, Yu Qiao, Kaipeng Zhang Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22096v1 Recent approaches have demonstrated the promise of using diffusion models to generate interactive and explorable worlds. However, most of these methods face critical challenges such as excessively large parameter sizes, reliance on lengthy inference steps, and rapidly growing historical context, which severely limit real-time performance and lack text-controlled generation capabilities. To address these challenges, we propose \method, a novel framework designed to generate realistic, interactive, and continuous worlds from a single image or text prompt. \method achieves this through a carefully designed framework that supports keyboard-based exploration of the generated worlds. The framework comprises three core components: (1) a long-video generation framework integrating unified context compression with linear attention; (2) a real-time streaming acceleration strategy powered by bidirectional attention distillation and an enhanced text embedding scheme; (3) a text-controlled method for generating world events. We have provided the codebase in the supplementary material. --- ### Unifying Learning Dynamics and Generalization in Transformers Scaling Law Authors: Chiwun Yang Published: 2025-12-26 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.22088v3 The scaling law, a cornerstone of Large Language Model (LLM) development, predicts improvements in model performance with increasing computational resources. Yet, while empirically validated, its theoretical underpinnings remain poorly understood. This work formalizes the learning dynamics of transformer-based language models as an ordinary differential equation (ODE) system, then approximates this process to kernel behaviors. Departing from prior toy-model analyses, we rigorously analyze stochastic gradient descent (SGD) training for multi-layer transformers on sequence-to-sequence data with arbitrary data distribution, closely mirroring real-world conditions. Our analysis characterizes the convergence of generalization error to the irreducible risk as computational resources scale with data, especially during the optimization process. We establish matching upper and lower bounds on the excess risk, characterized by a distinct phase transition. In the initial optimization phase, the excess risk decays exponentially relative to the computational cost ${\sf C}$. However, once a specific resource allocation threshold is crossed, the system enters a statistical phase, where the generalization error follows a power-law decay of $Θ(\mathsf{C}^{-1/7})$. These rates are certified by complementary lower bounds -- statistical, via an information-theoretic two-point reduction, and optimization-side, via a first-order oracle argument -- rendering the two-stage law tight up to constants, logarithmic factors, and a condition-number gap. Beyond this unified framework, our theory derives isolated scaling laws for model size, training time, and dataset size, elucidating how each variable independently governs the bounds of generalization. --- ### Context as a Tool: Context Management for Long-Horizon SWE-Agents Authors: Shukai Liu, Jian Yang, Bo Jiang, Yizhi Li, Jinyang Guo, Xianglong Liu, Bryan Dai Published: 2025-12-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.22087v1 Agents based on large language models have recently shown strong potential on real-world software engineering (SWE) tasks that require long-horizon interaction with repository-scale codebases. However, most existing agents rely on append-only context maintenance or passively triggered compression heuristics, which often lead to context explosion, semantic drift, and degraded reasoning in long-running interactions. We propose CAT, a new context management paradigm that elevates context maintenance to a callable tool integrated into the decision-making process of agents. CAT formalizes a structured context workspace consisting of stable task semantics, condensed long-term memory, and high-fidelity short-term interactions, and enables agents to proactively compress historical trajectories into actionable summaries at appropriate milestones. To support context management for SWE-agents, we propose a trajectory-level supervision framework, CAT-GENERATOR, based on an offline data construction pipeline that injects context-management actions into complete interaction trajectories. Using this framework, we train a context-aware model, SWE-Compressor. Experiments on SWE-Bench-Verified demonstrate that SWE-Compressor reaches a 57.6% solved rate and significantly outperforms ReAct-based agents and static compression baselines, while maintaining stable and scalable long-horizon reasoning under a bounded context budget. --- ### A Frobenius-Optimal Projection for Enforcing Linear Conservation in Learned Dynamical Models Authors: John M. Mango, Ronald Katende Published: 2025-12-26 Categories: math.DS, cs.LG, math.NA arXiv: https://arxiv.org/abs/2512.22084v1 We consider the problem of restoring linear conservation laws in data-driven linear dynamical models. Given a learned operator $\widehat{A}$ and a full-rank constraint matrix $C$ encoding one or more invariants, we show that the matrix closest to $\widehat{A}$ in the Frobenius norm and satisfying $C^\top A = 0$ is the orthogonal projection $A^\star = \widehat{A} - C(C^\top C)^{-1}C^\top \widehat{A}$. This correction is uniquely defined, low rank and fully determined by the violation $C^\top \widehat{A}$. In the single-invariant case it reduces to a rank-one update. We prove that $A^\star$ enforces exact conservation while minimally perturbing the dynamics, and we verify these properties numerically on a Markov-type example. The projection provides an elementary and general mechanism for embedding exact invariants into any learned linear model. --- ### Scaling Adversarial Training via Data Selection Authors: Youran Ye, Dejin Wang, Ajinkya Bhandare Published: 2025-12-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.22069v1 Projected Gradient Descent (PGD) is a strong and widely used first-order adversarial attack, yet its computational cost scales poorly, as all training samples undergo identical iterative inner-loop optimization despite contributing unequally to robustness. Motivated by this inefficiency, we propose \emph{Selective Adversarial Training}, which perturbs only a subset of critical samples in each minibatch. Specifically, we introduce two principled selection criteria: (1) margin-based sampling, which prioritizes samples near the decision boundary, and (2) gradient-matching sampling, which selects samples whose gradients align with the dominant batch optimization direction. Adversarial examples are generated only for the selected subset, while the remaining samples are trained cleanly using a mixed objective. Experiments on MNIST and CIFAR-10 show that the proposed methods achieve robustness comparable to, or even exceeding, full PGD adversarial training, while reducing adversarial computation by up to $50\%$, demonstrating that informed sample selection is sufficient for scalable adversarial robustness. --- ### Prefill vs. Decode Bottlenecks: SRAM-Frequency Tradeoffs and the Memory-Bandwidth Ceiling Authors: Hannah Atmer, Yuan Yao, Thiemo Voigt, Stefanos Kaxiras Published: 2025-12-26 Categories: cs.AR, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2512.22066v1 Energy consumption dictates the cost and environmental impact of deploying Large Language Models. This paper investigates the impact of on-chip SRAM size and operating frequency on the energy efficiency and performance of LLM inference, focusing on the distinct behaviors of the compute-bound prefill and memory-bound decode phases. Our simulation methodology combines OpenRAM for energy modeling, LLMCompass for latency simulation, and ScaleSIM for systolic array operational intensity. Our findings show that total energy use is predominantly determined by SRAM size in both phases, with larger buffers significantly increasing static energy due to leakage, which is not offset by corresponding latency benefits. We quantitatively explore the memory-bandwidth bottleneck, demonstrating that while high operating frequencies reduce prefill latency, their positive impact on memory-bound decode latency is capped by the external memory bandwidth. Counter-intuitively, high compute frequency can reduce total energy by reducing execution time and consequently decreasing static energy consumption more than the resulting dynamic power increase. We identify an optimal hardware configuration for the simulated workload: high operating frequencies (1200MHz-1400MHz) and a small local buffer size of 32KB to 64KB. This combination achieves the best energy-delay product, balancing low latency with high energy efficiency. Furthermore, we demonstrate how memory bandwidth acts as a performance ceiling, and that increasing compute frequency only yields performance gains up to the point where the workload becomes memory-bound. This analysis provides concrete architectural insights for designing energy-efficient LLM accelerators, especially for datacenters aiming to minimize their energy overhead. --- ### StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars Authors: Zhiyao Sun, Ziqiao Peng, Yifeng Ma, Yi Chen, Zhengguang Zhou, Zixiang Zhou, Guozhen Zhang, Youliang Zhang, Yuan Zhou, Qinglin Lu, Yong-Jin Liu Published: 2025-12-26 Categories: cs.CV, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2512.22065v2 Real-time, streaming interactive avatars represent a critical yet challenging goal in digital human research. Although diffusion-based human avatar generation methods achieve remarkable success, their non-causal architecture and high computational costs make them unsuitable for streaming. Moreover, existing interactive approaches are typically restricted to the head-and-shoulder region, limiting their ability to produce gestures and body motions. To address these challenges, we propose a two-stage autoregressive adaptation and acceleration framework that applies autoregressive distillation and adversarial refinement to adapt a high-fidelity human video diffusion model for real-time, interactive streaming. To ensure long-term stability and consistency, we introduce three key components: a Reference Sink, a Reference-Anchored Positional Re-encoding (RAPR) strategy, and a Consistency-Aware Discriminator. Building on this framework, we develop a one-shot, interactive, human avatar model capable of generating both natural talking and listening behaviors with coherent gestures. Extensive experiments demonstrate that our method achieves state-of-the-art performance, surpassing existing approaches in generation quality, real-time efficiency, and interaction naturalness. Project page: https://streamavatar.github.io . --- ### Toward Secure and Compliant AI: Organizational Standards and Protocols for NLP Model Lifecycle Management Authors: Sunil Arora, John Hastings Published: 2025-12-26 Categories: cs.CR, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2512.22060v1 Natural Language Processing (NLP) systems are increasingly used in sensitive domains such as healthcare, finance, and government, where they handle large volumes of personal and regulated data. However, these systems introduce distinct risks related to security, privacy, and regulatory compliance that are not fully addressed by existing AI governance frameworks. This paper introduces the Secure and Compliant NLP Lifecycle Management Framework (SC-NLP-LMF), a comprehensive six-phase model designed to ensure the secure operation of NLP systems from development to retirement. The framework, developed through a systematic PRISMA-based review of 45 peer-reviewed and regulatory sources, aligns with leading standards, including NIST AI RMF, ISO/IEC 42001:2023, the EU AI Act, and MITRE ATLAS. It integrates established methods for bias detection, privacy protection (differential privacy, federated learning), secure deployment, explainability, and secure model decommissioning. A healthcare case study illustrates how SC-NLP-LMF detects emerging terminology drift (e.g., COVID-related language) and guides compliant model updates. The framework offers organizations a practical, lifecycle-wide structure for developing, deploying, and maintaining secure and accountable NLP systems in high-risk environments. --- ### Why Smooth Stability Assumptions Fail for ReLU Learning Authors: Ronald Katende Published: 2025-12-26 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2512.22055v1 Stability analyses of modern learning systems are frequently derived under smoothness assumptions that are violated by ReLU-type nonlinearities. In this note, we isolate a minimal obstruction by showing that no uniform smoothness-based stability proxy such as gradient Lipschitzness or Hessian control can hold globally for ReLU networks, even in simple settings where training trajectories appear empirically stable. We give a concrete counterexample demonstrating the failure of classical stability bounds and identify a minimal generalized derivative condition under which stability statements can be meaningfully restored. The result clarifies why smooth approximations of ReLU can be misleading and motivates nonsmooth-aware stability frameworks. --- ### MAI-UI Technical Report: Real-World Centric Foundation GUI Agents Authors: Hanzhang Zhou, Xu Zhang, Panrong Tong, Jianan Zhang, Liangyu Chen, Quyu Kong, Chenglin Cai, Chen Liu, Yue Wang, Jingren Zhou, Steven Hoi Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22047v1 The development of GUI agents could revolutionize the next generation of human-computer interaction. Motivated by this vision, we present MAI-UI, a family of foundation GUI agents spanning the full spectrum of sizes, including 2B, 8B, 32B, and 235B-A22B variants. We identify four key challenges to realistic deployment: the lack of native agent-user interaction, the limits of UI-only operation, the absence of a practical deployment architecture, and brittleness in dynamic environments. MAI-UI addresses these issues with a unified methodology: a self-evolving data pipeline that expands the navigation data to include user interaction and MCP tool calls, a native device-cloud collaboration system routes execution by task state, and an online RL framework with advanced optimizations to scale parallel environments and context length. MAI-UI establishes new state-of-the-art across GUI grounding and mobile navigation. On grounding benchmarks, it reaches 73.5% on ScreenSpot-Pro, 91.3% on MMBench GUI L2, 70.9% on OSWorld-G, and 49.2% on UI-Vision, surpassing Gemini-3-Pro and Seed1.8 on ScreenSpot-Pro. On mobile GUI navigation, it sets a new SOTA of 76.7% on AndroidWorld, surpassing UI-Tars-2, Gemini-2.5-Pro and Seed1.8. On MobileWorld, MAI-UI obtains 41.7% success rate, significantly outperforming end-to-end GUI models and competitive with Gemini-3-Pro based agentic frameworks. Our online RL experiments show significant gains from scaling parallel environments from 32 to 512 (+5.2 points) and increasing environment step budget from 15 to 50 (+4.3 points). Finally, the native device-cloud collaboration system improves on-device performance by 33%, reduces cloud model calls by over 40%, and preserves user privacy. --- ### Backdoor Attacks on Prompt-Driven Video Segmentation Foundation Models Authors: Zongmin Zhang, Zhen Sun, Yifan Liao, Wenhan Dong, Xinlei He, Xingshuo Han, Shengmin Xu, Xinyi Huang Published: 2025-12-26 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2512.22046v2 Prompt-driven Video Segmentation Foundation Models (VSFMs), such as SAM2, are increasingly used in applications including autonomous driving and digital pathology, yet their security risks remain underexplored. We study backdoor attacks against VSFMs and show that directly applying classic attacks such as BadNet is largely ineffective, yielding attack success rates (ASR) below 5%. Through gradient-similarity and attention-map analyses, we find that traditional backdoor training fails because clean and triggered samples induce aligned image-encoder gradients, while model attention remains focused on the prompt-specified object rather than the trigger. To address this limitation, we propose BadVSFM, the first backdoor attack framework tailored to prompt-driven VSFMs. BadVSFM uses a two-stage strategy that first learns trigger-specific encoder features and then trains the decoder to map triggered frame prompt representations to an attacker-specified target mask while preserving clean segmentation behavior. Experiments on five VSFMs and two datasets show that BadVSFM achieves strong, controllable backdoor effects across triggers and prompt types with limited clean-performance degradation. Ablations and interpretability analyses validate the necessity of the two-stage design, and five representative defenses remain largely ineffective. Our results reveal a practical and underexplored vulnerability of current VSFMs to backdoor threats. --- ### From In Silico to In Vitro: Evaluating Molecule Generative Models for Hit Generation Authors: Nagham Osman, Vittorio Lembo, Giovanni Bottegoni, Laura Toni Published: 2025-12-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.22031v1 Hit identification is a critical yet resource-intensive step in the drug discovery pipeline, traditionally relying on high-throughput screening of large compound libraries. Despite advancements in virtual screening, these methods remain time-consuming and costly. Recent progress in deep learning has enabled the development of generative models capable of learning complex molecular representations and generating novel compounds de novo. However, using ML to replace the entire drug-discovery pipeline is highly challenging. In this work, we rather investigate whether generative models can replace one step of the pipeline: hit-like molecule generation. To the best of our knowledge, this is the first study to explicitly frame hit-like molecule generation as a standalone task and empirically test whether generative models can directly support this stage of the drug discovery pipeline. Specifically, we investigate if such models can be trained to generate hit-like molecules, enabling direct incorporation into, or even substitution of, traditional hit identification workflows. We propose an evaluation framework tailored to this task, integrating physicochemical, structural, and bioactivity-related criteria within a multi-stage filtering pipeline that defines the hit-like chemical space. Two autoregressive and one diffusion-based generative models were benchmarked across various datasets and training settings, with outputs assessed using standard metrics and target-specific docking scores. Our results show that these models can generate valid, diverse, and biologically relevant compounds across multiple targets, with a few selected GSK-3$β$ hits synthesized and confirmed active in vitro. We also identify key limitations in current evaluation metrics and available training data. --- ### LibContinual: A Comprehensive Library towards Realistic Continual Learning Authors: Wenbin Li, Shangge Liu, Borui Kang, Yiyang Chen, KaXuan Lew, Yang Chen, Yinghuan Shi, Lei Wang, Yang Gao, Jiebo Luo Published: 2025-12-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.22029v1 A fundamental challenge in Continual Learning (CL) is catastrophic forgetting, where adapting to new tasks degrades the performance on previous ones. While the field has evolved with diverse methods, this rapid surge in diverse methodologies has culminated in a fragmented research landscape. The lack of a unified framework, including inconsistent implementations, conflicting dependencies, and varying evaluation protocols, makes fair comparison and reproducible research increasingly difficult. To address this challenge, we propose LibContinual, a comprehensive and reproducible library designed to serve as a foundational platform for realistic CL. Built upon a high-cohesion, low-coupling modular architecture, LibContinual integrates 19 representative algorithms across five major methodological categories, providing a standardized execution environment. Meanwhile, leveraging this unified framework, we systematically identify and investigate three implicit assumptions prevalent in mainstream evaluation: (1) offline data accessibility, (2) unregulated memory resources, and (3) intra-task semantic homogeneity. We argue that these assumptions often overestimate the real-world applicability of CL methods. Through our comprehensive analysis using strict online CL settings, a novel unified memory budget protocol, and a proposed category-randomized setting, we reveal significant performance drops in many representative CL methods when subjected to these real-world constraints. Our study underscores the necessity of resource-aware and semantically robust CL strategies, and offers LibContinual as a foundational toolkit for future research in realistic continual learning. The source code is available from \href{https://github.com/RL-VIG/LibContinual}{https://github.com/RL-VIG/LibContinual}. --- ### Patch-Discontinuity Mining for Generalized Deepfake Detection Authors: Huanhuan Yuan, Yang Ping, Zhengqin Xu, Junyi Cao, Shuai Jia, Chao Ma Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22027v1 The rapid advancement of generative artificial intelligence has enabled the creation of highly realistic fake facial images, posing serious threats to personal privacy and the integrity of online information. Existing deepfake detection methods often rely on handcrafted forensic cues and complex architectures, achieving strong performance in intra-domain settings but suffering significant degradation when confronted with unseen forgery patterns. In this paper, we propose GenDF, a simple yet effective framework that transfers a powerful large-scale vision model to the deepfake detection task with a compact and neat network design. GenDF incorporates deepfake-specific representation learning to capture discriminative patterns between real and fake facial images, feature space redistribution to mitigate distribution mismatch, and a classification-invariant feature augmentation strategy to enhance generalization without introducing additional trainable parameters. Extensive experiments demonstrate that GenDF achieves state-of-the-art generalization performance in cross-domain and cross-manipulation settings while requiring only 0.28M trainable parameters, validating the effectiveness and efficiency of the proposed framework. --- ### Direction Finding with Sparse Arrays Based on Variable Window Size Spatial Smoothing Authors: Wesley S. Leite, Rodrigo C. de Lamare, Yuriy Zakharov, Wei Liu, Martin Haardt Published: 2025-12-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.22024v1 In this work, we introduce a variable window size (VWS) spatial smoothing framework that enhances coarray-based direction of arrival (DOA) estimation for sparse linear arrays. By compressing the smoothing aperture, the proposed VWS Coarray MUSIC (VWS-CA-MUSIC) and VWS Coarray root-MUSIC (VWS-CA-rMUSIC) algorithms replace part of the perturbed rank-one outer products in the smoothed coarray data with unperturbed low-rank additional terms, increasing the separation between signal and noise subspaces, while preserving the signal subspace span. We also derive the bounds that guarantees identifiability, by limiting the values that can be assumed by the compression parameter. Simulations with sparse geometries reveal significant performance improvements and complexity savings relative to the fixed-window coarray MUSIC method. --- ### Meta-Learning-Based Handover Management in NextG O-RAN Authors: Michail Kalntis, George Iosifidis, José Suárez-Varela, Andra Lutu, Fernando A. Kuipers Published: 2025-12-26 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2512.22022v1 While traditional handovers (THOs) have served as a backbone for mobile connectivity, they increasingly suffer from failures and delays, especially in dense deployments and high-frequency bands. To address these limitations, 3GPP introduced Conditional Handovers (CHOs) that enable proactive cell reservations and user-driven execution. However, both handover (HO) types present intricate trade-offs in signaling, resource usage, and reliability. This paper presents unique, countrywide mobility management datasets from a top-tier mobile network operator (MNO) that offer fresh insights into these issues and call for adaptive and robust HO control in next-generation networks. Motivated by these findings, we propose CONTRA, a framework that, for the first time, jointly optimizes THOs and CHOs within the O-RAN architecture. We study two variants of CONTRA: one where users are a priori assigned to one of the HO types, reflecting distinct service or user-specific requirements, as well as a more dynamic formulation where the controller decides on-the-fly the HO type, based on system conditions and needs. To this end, it relies on a practical meta-learning algorithm that adapts to runtime observations and guarantees performance comparable to an oracle with perfect future information (universal no-regret). CONTRA is specifically designed for near-real-time deployment as an O-RAN xApp and aligns with the 6G goals of flexible and intelligent control. Extensive evaluations leveraging crowdsourced datasets show that CONTRA improves user throughput and reduces both THO and CHO switching costs, outperforming 3GPP-compliant and Reinforcement Learning (RL) baselines in dynamic and real-world scenarios. --- ### SketchPlay: Intuitive Creation of Physically Realistic VR Content with Gesture-Driven Sketching Authors: Xiangwen Zhang, Xiaowei Dai, Runnan Chen, Xiaoming Chen, Zeke Zexi Hu Published: 2025-12-26 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2512.22016v1 Creating physically realistic content in VR often requires complex modeling tools or predefined 3D models, textures, and animations, which present significant barriers for non-expert users. In this paper, we propose SketchPlay, a novel VR interaction framework that transforms humans' air-drawn sketches and gestures into dynamic, physically realistic scenes, making content creation intuitive and playful like drawing. Specifically, sketches capture the structure and spatial arrangement of objects and scenes, while gestures convey physical cues such as velocity, direction, and force that define movement and behavior. By combining these complementary forms of input, SketchPlay captures both the structure and dynamics of user-created content, enabling the generation of a wide range of complex physical phenomena, such as rigid body motion, elastic deformation, and cloth dynamics. Experimental results demonstrate that, compared to traditional text-driven methods, SketchPlay offers significant advantages in expressiveness, and user experience. By providing an intuitive and engaging creation process, SketchPlay lowers the entry barrier for non-expert users and shows strong potential for applications in education, art, and immersive storytelling. --- ### HWL-HIN: A Hypergraph-Level Hypergraph Isomorphism Network as Powerful as the Hypergraph Weisfeiler-Lehman Test with Application to Higher-Order Network Robustness Authors: Chengyu Tian, Wenbin Pei Published: 2025-12-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.22014v1 Robustness in complex systems is of significant engineering and economic importance. However, conventional attack-based a posteriori robustness assessments incur prohibitive computational overhead. Recently, deep learning methods, such as Convolutional Neural Networks (CNNs) and Graph Neural Networks (GNNs), have been widely employed as surrogates for rapid robustness prediction. Nevertheless, these methods neglect the complex higher-order correlations prevalent in real-world systems, which are naturally modeled as hypergraphs. Although Hypergraph Neural Networks (HGNNs) have been widely adopted for hypergraph learning, their topological expressive power has not yet reached the theoretical upper bound. To address this limitation, inspired by Graph Isomorphism Networks, this paper proposes a hypergraph-level Hypergraph Isomorphism Network framework. Theoretically, this approach is proven to possess an expressive power strictly equivalent to the Hypergraph Weisfeiler-Lehman test and is applied to predict hypergraph robustness. Experimental results demonstrate that while maintaining superior efficiency in training and prediction, the proposed method not only outperforms existing graph-based models but also significantly surpasses conventional HGNNs in tasks that prioritize topological structure representation. --- ### LongFly: Long-Horizon UAV Vision-and-Language Navigation with Spatiotemporal Context Integration Authors: Wen Jiang, Li Wang, Kangyao Huang, Wei Fan, Jinyuan Liu, Shaoyu Liu, Hongwei Duan, Bin Xu, Xiangyang Ji Published: 2025-12-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.22010v1 Unmanned aerial vehicles (UAVs) are crucial tools for post-disaster search and rescue, facing challenges such as high information density, rapid changes in viewpoint, and dynamic structures, especially in long-horizon navigation. However, current UAV vision-and-language navigation(VLN) methods struggle to model long-horizon spatiotemporal context in complex environments, resulting in inaccurate semantic alignment and unstable path planning. To this end, we propose LongFly, a spatiotemporal context modeling framework for long-horizon UAV VLN. LongFly proposes a history-aware spatiotemporal modeling strategy that transforms fragmented and redundant historical data into structured, compact, and expressive representations. First, we propose the slot-based historical image compression module, which dynamically distills multi-view historical observations into fixed-length contextual representations. Then, the spatiotemporal trajectory encoding module is introduced to capture the temporal dynamics and spatial structure of UAV trajectories. Finally, to integrate existing spatiotemporal context with current observations, we design the prompt-guided multimodal integration module to support time-based reasoning and robust waypoint prediction. Experimental results demonstrate that LongFly outperforms state-of-the-art UAV VLN baselines by 7.89\% in success rate and 6.33\% in success weighted by path length, consistently across both seen and unseen environments. --- ### iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perception Authors: Sarthak Mehrotra, Sairam V C Rebbapragada, Mani Hemanth Reddy Bonthu, Vineeth N Balasubramanian Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22009v1 Multimodal Large Language Models (MLLMs) show strong potential for interpreting and interacting with complex, pixel-rich Graphical User Interface (GUI) environments. However, building agents that are both efficient for high-level tasks and precise for fine-grained interactions remains challenging. GUI agents must perform routine actions efficiently while also handling tasks that demand exact visual grounding, yet existing approaches struggle when accuracy depends on identifying specific interface elements. These MLLMs also remain large and cannot adapt their reasoning depth to the task at hand. In this work, we introduce iSHIFT: Implicit Slow-fast Hybrid Inference with Flexible Tokens, a lightweight agent that integrates latent thinking (implicit chain-of-thought) with a perception control module. iSHIFT enables an MLLM to switch between a slow mode, which leverages detailed visual grounding for high precision and a fast mode that uses global cues for efficiency. Special perception tokens guide attention to relevant screen regions, allowing the model to decide both how to reason and where to focus. Despite its compact 2.5B size, iSHIFT matches state-of-the-art performance on multiple benchmark datasets. --- ### DuaDeep-SeqAffinity: Dual-Branch Deep Learning for Tri-Stream Sequence-Based Antibody--Antigen Affinity Prediction Authors: Aicha Boutorh, Soumia Bouyahiaoui, Manel Kara Laouar, Sara Belhadj, Nour El Yakine Guendouz, Asma Boutorh Published: 2025-12-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.22007v2 DuaDeep-SeqAffinity is a sequence-only deep learning framework that predicts antibody--antigen binding affinity directly from primary amino acid sequences, avoiding the cost and scarcity of resolved three-dimensional structures. The antigen and the antibody heavy and light chains are processed as three independent streams, each embedded with a frozen ESM-2 protein language model and passed through parallel Transformer and convolutional neural network (CNN) branches before late fusion, a decoupled design intended to preserve local complementarity-determining region (CDR) signal that monolithic encoders can dilute. On a sequence-disjoint split of the AbRank benchmark, the model achieves a Pearson correlation of 0.683, an R^2 of 0.460, and a pairwise ranking AUC of 0.895, significantly outperforming single-branch ablations (paired t-test, p < 0.05). Attention-map and gradient-based saliency analyses further show that the model preferentially attends to CDR loops and candidate epitope residues, supporting its use as a scalable, structure-free tool for high-throughput antibody screening. --- ### Look Closer! An Adversarial Parametric Editing Framework for Hallucination Mitigation in VLMs Authors: Jiayu Hu, Beibei Li, Jiangwei Xia, Yanjun Qin, Bing Ji, Zhongshi He Published: 2025-12-26 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.21999v1 While Vision-Language Models (VLMs) have garnered increasing attention in the AI community due to their promising practical applications, they exhibit persistent hallucination issues, generating outputs misaligned with visual inputs. Recent studies attribute these hallucinations to VLMs' over-reliance on linguistic priors and insufficient visual feature integration, proposing heuristic decoding calibration strategies to mitigate them. However, the non-trainable nature of these strategies inherently limits their optimization potential. To this end, we propose an adversarial parametric editing framework for Hallucination mitigation in VLMs, which follows an \textbf{A}ctivate-\textbf{L}ocate-\textbf{E}dit \textbf{A}dversarially paradigm. Specifically, we first construct an activation dataset that comprises grounded responses (positive samples attentively anchored in visual features) and hallucinatory responses (negative samples reflecting LLM prior bias and internal knowledge artifacts). Next, we identify critical hallucination-prone parameter clusters by analyzing differential hidden states of response pairs. Then, these clusters are fine-tuned using prompts injected with adversarial tuned prefixes that are optimized to maximize visual neglect, thereby forcing the model to prioritize visual evidence over inherent parametric biases. Evaluations on both generative and discriminative VLM tasks demonstrate the significant effectiveness of ALEAHallu in alleviating hallucinations. Our code is available at https://github.com/hujiayu1223/ALEAHallu. --- ### Region-Specific Calibration Achieves Excellent Inter-Device Reliability for Smartphone Dermatology: A Multi-Device Benchmark on Korean Facial Skin Authors: Sungwoo Kang, Jong-Kook Kim Published: 2025-12-26 Categories: eess.IV, cs.CV, q-bio.QM arXiv: https://arxiv.org/abs/2512.21988v4 Background: Smartphone-based dermatology requires inter-device colorimetric reliability that holds across calibration regimes, yet quantitative multi-device benchmarks remain scarce. Materials and Methods: We analyzed matched facial images from 965 Korean subjects captured by a digital single-lens reflex (DSLR) camera, a consumer tablet, and a consumer smartphone, and evaluated two calibration methods against the DSLR reference. The methods are standard global linear Color Correction Matrix (CCM) normalization and region-specific CCM trained per anatomical region, both applied in Commission Internationale de l'Eclairage Lab* (CIELAB) space. Results: Linear CCM reduced inter-device color differences by 61-74% and placed both Melanin Index (intraclass correlation coefficient (ICC) = 0.80) and Individual Typology Angle (ITA, ICC = 0.78) in the good reliability band. Region-specific CCM raised both indices into the excellent reliability band (MI ICC = 0.95, ITA ICC = 0.93), with anatomical region exceeding the source device as the largest pre-calibration variance contributor (analysis-of-variance $η^2 = 0.18$ versus 0.12). Conclusion: Consumer-device skin colorimetry therefore achieves clinically useful inter-device reliability using standard calibration, with region-aware calibration the largest remaining source of improvement. --- ### LVLM-Aided Alignment of Task-Specific Vision Models Authors: Alexander Koebler, Lukas Kuhn, Ingo Thon, Florian Buettner Published: 2025-12-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.21985v2 In high-stakes domains, small task-specific vision models are crucial due to their low computational requirements and the availability of numerous methods to explain their results. However, these explanations often reveal that the models do not align well with human domain knowledge, relying instead on spurious correlations. This might result in brittle behavior once deployed in the real-world. To address this issue, we introduce a novel and efficient method for aligning small task-specific vision models with human domain knowledge by leveraging the generalization capabilities of a Large Vision Language Model (LVLM). Our LVLM-Aided Visual Alignment (LVLM-VA) method provides a bidirectional interface that translates model behavior into natural language and maps human class-level specifications to image-level critiques, enabling effective interaction between domain experts and the model. Our method demonstrates substantial improvement in aligning model behavior with human specifications, as validated on both synthetic and real-world datasets. We show that it effectively reduces the model's dependence on spurious features and on group-specific biases, without requiring fine-grained feedback. --- ### A Lightweight Multi-Scale Attention Framework for Real-Time Spinal Endoscopic Instance Segmentation Authors: Qi Lai, JunYan Li, Qiang Cai, Lei Wang, Tao Yan, XiaoKun Liang Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21984v1 Real-time instance segmentation for spinal endoscopy is important for identifying and protecting critical anatomy during surgery, but it is difficult because of the narrow field of view, specular highlights, smoke/bleeding, unclear boundaries, and large scale changes. Deployment is also constrained by limited surgical hardware, so the model must balance accuracy and speed and remain stable under small-batch (even batch-1) training. We propose LMSF-A, a lightweight multi-scale attention framework co-designed across backbone, neck, and head. The backbone uses a C2f-Pro module that combines RepViT-style re-parameterized convolution (RVB) with efficient multi-scale attention (EMA), enabling multi-branch training while collapsing into a single fast path for inference. The neck improves cross-scale consistency and boundary detail using Scale-Sequence Feature Fusion (SSFF) and Triple Feature Encoding (TFE), which strengthens high-resolution features. The head adopts a Lightweight Multi-task Shared Head (LMSH) with shared convolutions and GroupNorm to reduce parameters and support batch-1 stability. We also release the clinically reviewed PELD dataset (61 patients, 610 images) with instance masks for adipose tissue, bone, ligamentum flavum, and nerve. Experiments show that LMSF-A is highly competitive (or even better than) in all evaluation metrics and much lighter than most instance segmentation methods requiring only 1.8M parameters and 8.8 GFLOPs, and it generalizes well to a public teeth benchmark. Code and dataset: https://github.com/hhwmortal/PELD-Instance-segmentation. --- ### RT-Focuser: A Real-Time Lightweight Model for Edge-side Image Deblurring Authors: Zhuoyu Wu, Wenhui Ou, Qiawei Zheng, Jiayan Yang, Quanjun Wang, Wenqi Fang, Zheng Wang, Yongkui Yang, Heshan Li Published: 2025-12-26 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2512.21975v1 Motion blur caused by camera or object movement severely degrades image quality and poses challenges for real-time applications such as autonomous driving, UAV perception, and medical imaging. In this paper, a lightweight U-shaped network tailored for real-time deblurring is presented and named RT-Focuser. To balance speed and accuracy, we design three key components: Lightweight Deblurring Block (LD) for edge-aware feature extraction, Multi-Level Integrated Aggregation module (MLIA) for encoder integration, and Cross-source Fusion Block (X-Fuse) for progressive decoder refinement. Trained on a single blurred input, RT-Focuser achieves 30.67 dB PSNR with only 5.85M parameters and 15.76 GMACs. It runs 6ms per frame on GPU and mobile, exceeds 140 FPS on both, showing strong potential for deployment on the edge. The official code and usage are available on: https://github.com/ReaganWu/RT-Focuser. --- ### Perceive and Calibrate: Analyzing and Enhancing Robustness of Medical Multi-Modal Large Language Models Authors: Dunyuan XU, Xikai Yang, Yaoqian Li, Juzheng Miao, Jinpeng Li, Pheng-Ann Heng Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21964v1 Medical Multi-modal Large Language Models (MLLMs) have shown promising clinical performance. However, their sensitivity to real-world input perturbations, such as imaging artifacts and textual errors, critically undermines their clinical applicability. Systematic analysis of such noise impact on medical MLLMs remains largely unexplored. Furthermore, while several works have investigated the MLLMs' robustness in general domains, they primarily focus on text modality and rely on costly fine-tuning. They are inadequate to address the complex noise patterns and fulfill the strict safety standards in medicine. To bridge this gap, this work systematically analyzes the impact of various perturbations on medical MLLMs across both visual and textual modalities. Building on our findings, we introduce a training-free Inherent-enhanced Multi-modal Calibration (IMC) framework that leverages MLLMs' inherent denoising capabilities following the perceive-and-calibrate principle for cross-modal robustness enhancement. For the visual modality, we propose a Perturbation-aware Denoising Calibration (PDC) which leverages MLLMs' own vision encoder to identify noise patterns and perform prototype-guided feature calibration. For text denoising, we design a Self-instantiated Multi-agent System (SMS) that exploits the MLLMs' self-assessment capabilities to refine noisy text through a cooperative hierarchy of agents. We construct a benchmark containing 11 types of noise across both image and text modalities on 2 datasets. Experimental results demonstrate our method achieves the state-of-the-art performance across multiple modalities, showing potential to enhance MLLMs' robustness in real clinical scenarios. --- ### Modeling high dimensional point clouds with the spherical cluster model Authors: Frédéric Cazals, Antoine Commaret, Louis Goldenberg Published: 2025-12-26 Categories: stat.ME, cs.LG arXiv: https://arxiv.org/abs/2512.21960v1 A parametric cluster model is a statistical model providing geometric insights onto the points defining a cluster. The {\em spherical cluster model} (SC) approximates a finite point set $P\subset \mathbb{R}^d$ by a sphere $S(c,r)$ as follows. Taking $r$ as a fraction $η\in(0,1)$ (hyper-parameter) of the std deviation of distances between the center $c$ and the data points, the cost of the SC model is the sum over all data points lying outside the sphere $S$ of their power distance with respect to $S$. The center $c$ of the SC model is the point minimizing this cost. Note that $η=0$ yields the celebrated center of mass used in KMeans clustering. We make three contributions. First, we show fitting a spherical cluster yields a strictly convex but not smooth combinatorial optimization problem. Second, we present an exact solver using the Clarke gradient on a suitable stratified cell complex defined from an arrangement of hyper-spheres. Finally, we present experiments on a variety of datasets ranging in dimension from $d=9$ to $d=10,000$, with two main observations. First, the exact algorithm is orders of magnitude faster than BFGS based heuristics for datasets of small/intermediate dimension and small values of $η$, and for high dimensional datasets (say $d>100$) whatever the value of $η$. Second, the center of the SC model behave as a parameterized high-dimensional median. The SC model is of direct interest for high dimensional multivariate data analysis, and the application to the design of mixtures of SC will be reported in a companion paper. --- ### Self-attention vector output similarities reveal how machines pay attention Authors: Tal Halevi, Yarden Tzach, Ronit D. Gross, Shalom Rosner, Ido Kanter Published: 2025-12-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21956v2 The self-attention mechanism has significantly advanced the field of natural language processing, facilitating the development of advanced language-learning machines. Although its utility is widely acknowledged, the precise mechanisms of self-attention underlying its advanced learning and the quantitative characterization of this learning process remains an open research question. This study introduces a new approach for quantifying information processing within the self-attention mechanism. The analysis conducted on the BERT-12 architecture reveals that, in the final layers, the attention map focuses on sentence separator tokens, suggesting a practical approach to text segmentation based on semantic features. Based on the vector space emerging from the self-attention heads, a context similarity matrix, measuring the scalar product between two token vectors was derived, revealing distinct similarities between different token vector pairs within each head and layer. The findings demonstrated that different attention heads within an attention block focused on different linguistic characteristics, such as identifying token repetitions in a given text or recognizing a token of common appearance in the text and its surrounding context. This specialization is also reflected in the distribution of distances between token vectors with high similarity as the architecture progresses. The initial attention layers exhibit substantially long-range similarities; however, as the layers progress, a more short-range similarity develops, culminating in a preference for attention heads to create strong similarities within the same sentence. Finally, the behavior of individual heads was analyzed by examining the uniqueness of their most common tokens in their high similarity elements. Each head tends to focus on a unique token from the text and builds similarity pairs centered around it. --- ### Interpretable Machine Learning-Derived Spectral Indices for Vegetation Monitoring Authors: Ali Lotfi, Adam Carter, Thuan Ha, Mohammad Meysami, Kwabena Nketia, Steve Shirtliffe Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21948v2 Spectral indices such as NDVI have driven vegetation monitoring for decades, yet their design remains largely manual and ad hoc. Their usefulness stems not only from their empirical performance, but also from algebraic forms that remain compact and biologically interpretable. However, the space of possible algebraic expressions relating spectral bands is effectively infinite, making systematic search impractical without structural constraints. We introduce the Spectral Feature Polynomial (SFP) framework, a general pipeline that automatically discovers compact, interpretable spectral indices from labeled multispectral imagery. SFP constructs a library of ratio-based spectral features that inherit illumination invariance by construction. It then applies cross-validated feature selection and continuous coefficient optimization to produce a single closed-form equation per task, transparent to domain experts and deployable on any remote sensing platform without requiring standardization statistics. We validate the framework on two agricultural applications. For Kochia (Bassia scoparia) detection in Sentinel-2 imagery near Lucky Lake of Saskatchewan over three growing seasons, the same two-term equation emerged in 44 of 46 independent cross-validation folds, achieving 98.6% mean accuracy, more than 4 percentage points above the best established index under year-held-out evaluation. For wheat plant classification from UAV multispectral imagery, stage-specific indices achieved 99.5%, 97.2%, and 93.5% across three growth stages, compared to 78% or below for the best established index at late season when NIR-based contrasts lose discriminatory power as wheat senesces. In both applications, SFP yielded a single transparent equation that generalized across held-out regions and outperformed established indices. --- ### Data relativistic uncertainty framework for low-illumination anime scenery image enhancement Authors: Yiquan Gao, John See Published: 2025-12-26 Categories: cs.CV, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2512.21944v3 By contrast with the prevailing works of low-light enhancement in natural images and videos, this study copes with the low-illumination quality degradation in anime scenery images to bridge the domain gap. For such an underexplored enhancement task, we first curate images from various sources and construct an unpaired anime scenery dataset with diverse environments and illumination conditions to address the data scarcity. To exploit the power of uncertainty information inherent with the diverse illumination conditions, we propose a Data Relativistic Uncertainty (DRU) framework, motivated by the idea from Relativistic GAN. By analogy with the wave-particle duality of light, our framework interpretably defines and quantifies the illumination uncertainty of dark/bright samples, which is leveraged to dynamically adjust the objective functions to recalibrate the model learning under data uncertainty. Extensive experiments demonstrate the effectiveness of DRU framework by training several versions of EnlightenGANs, yielding superior perceptual and aesthetic qualities beyond the state-of-the-art methods that are incapable of learning from data uncertainty perspective. We hope our framework can expose a novel paradigm of data-centric learning for potential visual and language domains. Code is available. --- ### Broken Words, Broken Performance: Effect of Tokenization on Performance of LLMs Authors: Sachin Pawar, Manoj Apte, Kshitij Jadhav, Girish Keshav Palshikar, Nitin Ramrakhiyani Published: 2025-12-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21933v1 Tokenization is the first step in training any Large Language Model (LLM), where the text is split into a sequence of tokens as per the model's fixed vocabulary. This tokenization in LLMs is different from the traditional tokenization in NLP where the text is split into a sequence of "natural" words. In LLMs, a natural word may also be broken into multiple tokens due to limited vocabulary size of the LLMs (e.g., Mistral's tokenizer splits "martial" into "mart" and "ial"). In this paper, we hypothesize that such breaking of natural words negatively impacts LLM performance on various NLP tasks. To quantify this effect, we propose a set of penalty functions that compute a tokenization penalty for a given text for a specific LLM, indicating how "bad" the tokenization is. We establish statistical significance of our hypothesis on multiple NLP tasks for a set of different LLMs. --- ### Hybrid Combinatorial Multi-armed Bandits with Probabilistically Triggered Arms Authors: Kongchang Zhou, Tingyu Zhang, Wei Chen, Fang Kong Published: 2025-12-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21925v1 The problem of combinatorial multi-armed bandits with probabilistically triggered arms (CMAB-T) has been extensively studied. Prior work primarily focuses on either the online setting where an agent learns about the unknown environment through iterative interactions, or the offline setting where a policy is learned solely from logged data. However, each of these paradigms has inherent limitations: online algorithms suffer from high interaction costs and slow adaptation, while offline methods are constrained by dataset quality and lack of exploration capabilities. To address these complementary weaknesses, we propose hybrid CMAB-T, a new framework that integrates offline data with online interaction in a principled manner. Our proposed hybrid CUCB algorithm leverages offline data to guide exploration and accelerate convergence, while strategically incorporating online interactions to mitigate the insufficient coverage or distributional bias of the offline dataset. We provide theoretical guarantees on the algorithm's regret, demonstrating that hybrid CUCB significantly outperforms purely online approaches when high-quality offline data is available, and effectively corrects the bias inherent in offline-only methods when the data is limited or misaligned. Empirical results further demonstrate the consistent advantage of our algorithm. --- ### Unsupervised Anomaly Detection in Brain MRI via Disentangled Anatomy Learning Authors: Tao Yang, Xiuying Wang, Hao Liu, Guanzhong Gong, Lian-Ming Wu, Yu-Ping Wang, Lisheng Wang Published: 2025-12-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.21924v1 Detection of various lesions in brain MRI is clinically critical, but challenging due to the diversity of lesions and variability in imaging conditions. Current unsupervised learning methods detect anomalies mainly through reconstructing abnormal images into pseudo-healthy images (PHIs) by normal samples learning and then analyzing differences between images. However, these unsupervised models face two significant limitations: restricted generalizability to multi-modality and multi-center MRIs due to their reliance on the specific imaging information in normal training data, and constrained performance due to abnormal residuals propagated from input images to reconstructed PHIs. To address these limitations, two novel modules are proposed, forming a new PHI reconstruction framework. Firstly, the disentangled representation module is proposed to improve generalizability by decoupling brain MRI into imaging information and essential imaging-invariant anatomical images, ensuring that the reconstruction focuses on the anatomy. Specifically, brain anatomical priors and a differentiable one-hot encoding operator are introduced to constrain the disentanglement results and enhance the disentanglement stability. Secondly, the edge-to-image restoration module is designed to reconstruct high-quality PHIs by restoring the anatomical representation from the high-frequency edge information of anatomical images, and then recoupling the disentangled imaging information. This module not only suppresses abnormal residuals in PHI by reducing abnormal pixels input through edge-only input, but also effectively reconstructs normal regions using the preserved structural details in the edges. Evaluated on nine public datasets (4,443 patients' MRIs from multiple centers), our method outperforms 17 SOTA methods, achieving absolute improvements of +18.32% in AP and +13.64% in DSC. --- ### AutoPP: Towards Automated Product Poster Generation and Optimization Authors: Jiahao Fan, Yuxin Qin, Wei Feng, Yanyin Chen, Yaoyu Li, Ao Ma, Yixiu Li, Li Zhuang, Haoyi Bian, Zheng Zhang, Jingjing Lv, Junjie Shen et al. Published: 2025-12-26 Categories: cs.CV, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2512.21921v1 Product posters blend striking visuals with informative text to highlight the product and capture customer attention. However, crafting appealing posters and manually optimizing them based on online performance is laborious and resource-consuming. To address this, we introduce AutoPP, an automated pipeline for product poster generation and optimization that eliminates the need for human intervention. Specifically, the generator, relying solely on basic product information, first uses a unified design module to integrate the three key elements of a poster (background, text, and layout) into a cohesive output. Then, an element rendering module encodes these elements into condition tokens, efficiently and controllably generating the product poster. Based on the generated poster, the optimizer enhances its Click-Through Rate (CTR) by leveraging online feedback. It systematically replaces elements to gather fine-grained CTR comparisons and utilizes Isolated Direct Preference Optimization (IDPO) to attribute CTR gains to isolated elements. Our work is supported by AutoPP1M, the largest dataset specifically designed for product poster generation and optimization, which contains one million high-quality posters and feedback collected from over one million users. Experiments demonstrate that AutoPP achieves state-of-the-art results in both offline and online settings. Our code and dataset are publicly available at: https://github.com/JD-GenX/AutoPP --- ### SWE-RM: Execution-free Feedback For Software Engineering Agents Authors: KaShun Shum, Binyuan Hui, Jiawei Chen, Lei Zhang, X. W., Jiaxi Yang, Yuzhen Huang, Junyang Lin, Junxian He Published: 2025-12-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21919v1 Execution-based feedback like unit testing is widely used in the development of coding agents through test-time scaling (TTS) and reinforcement learning (RL). This paradigm requires scalable and reliable collection of unit test cases to provide accurate feedback, and the resulting feedback is often sparse and cannot effectively distinguish between trajectories that are both successful or both unsuccessful. In contrast, execution-free feedback from reward models can provide more fine-grained signals without depending on unit test cases. Despite this potential, execution-free feedback for realistic software engineering (SWE) agents remains underexplored. Aiming to develop versatile reward models that are effective across TTS and RL, however, we observe that two verifiers with nearly identical TTS performance can nevertheless yield very different results in RL. Intuitively, TTS primarily reflects the model's ability to select the best trajectory, but this ability does not necessarily generalize to RL. To address this limitation, we identify two additional aspects that are crucial for RL training: classification accuracy and calibration. We then conduct comprehensive controlled experiments to investigate how to train a robust reward model that performs well across these metrics. In particular, we analyze the impact of various factors such as training data scale, policy mixtures, and data source composition. Guided by these investigations, we introduce SWE-RM, an accurate and robust reward model adopting a mixture-of-experts architecture with 30B total parameters and 3B activated during inference. SWE-RM substantially improves SWE agents on both TTS and RL performance. For example, it increases the accuracy of Qwen3-Coder-Flash from 51.6% to 62.0%, and Qwen3-Coder-Max from 67.0% to 74.6% on SWE-Bench Verified using TTS, achieving new state-of-the-art performance among open-source models. --- ### Semiparametric Preference Optimization: Your Language Model is Secretly a Single-Index Model Authors: Nathan Kallus Published: 2025-12-26 Categories: cs.LG, cs.AI, econ.EM, stat.ML arXiv: https://arxiv.org/abs/2512.21917v3 Policy alignment to preference data typically assumes a known link function between observed preferences and latent rewards (e.g., Bradley-Terry model / logistic link). Misspecification of this link can bias inferred rewards and misalign learned policies. We study policy alignment under an unknown and unrestricted link function. We formulate an $f$-divergence-constrained reward maximization problem and show that realizability in a policy class induces a semiparametric single-index binary choice model, where a scalar policy-induced index captures all dependence on demonstrations and the remaining preference distribution is unrestricted. Rather than impose identifiability of structural parameters of such a model and estimate them, as in econometrics, we develop methods that directly learn policies, with the reward function implicit, analyzing error to the optimal policy and allowing for unidentifiable and nonparametric indices. We prove link-agnostic convergence guarantees in terms of generic function complexity measures and validate the methods and theory empirically. Code is available at https://github.com/causalml/spo/. --- ### Patch as Node: Human-Centric Graph Representation Learning for Multimodal Action Recognition Authors: Zeyu Liang, Hailun Xia, Naichuan Zheng Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21916v1 While human action recognition has witnessed notable achievements, multimodal methods fusing RGB and skeleton modalities still suffer from their inherent heterogeneity and fail to fully exploit the complementary potential between them. In this paper, we propose PAN, the first human-centric graph representation learning framework for multimodal action recognition, in which token embeddings of RGB patches containing human joints are represented as spatiotemporal graphs. The human-centric graph modeling paradigm suppresses the redundancy in RGB frames and aligns well with skeleton-based methods, thus enabling a more effective and semantically coherent fusion of multimodal features. Since the sampling of token embeddings heavily relies on 2D skeletal data, we further propose attention-based post calibration to reduce the dependency on high-quality skeletal data at a minimal cost interms of model performance. To explore the potential of PAN in integrating with skeleton-based methods, we present two variants: PAN-Ensemble, which employs dual-path graph convolution networks followed by late fusion, and PAN-Unified, which performs unified graph representation learning within a single network. On three widely used multimodal action recognition datasets, both PAN-Ensemble and PAN-Unified achieve state-of-the-art (SOTA) performance in their respective settings of multimodal fusion: separate and unified modeling, respectively. --- ### Exploring the Heterogeneity of Tabular Data: A Diversity-aware Data Generator via LLMs Authors: Yafeng Tang, Xiaoou Ding, Jianzhuo Du, Zishuo Yan, Zhuang Ma, Zheng Liang, Zekai Qian, Hongzhi Wang Published: 2025-12-26 Categories: cs.LG, cs.DB arXiv: https://arxiv.org/abs/2512.21915v1 Tabular data generation has become increasingly essential for enabling robust machine learning applications, which require large-scale, high-quality data. Existing solutions leverage generative models to learn original data distributions. However, real-world data are naturally heterogeneous with diverse distributions, making it challenging to obtain a universally good model for diverse data generation. To address this limitation, we introduce Diversity-Aware Tabular data gEnerator (DATE), a framework that (i) prepares high-quality and distributionally distinct examples for in-context learning by effectively partitioning the original heterogeneous data into multiple diverse subsets; (ii) harnesses Large Language Models (LLMs) to explore the diversity of the partitioned distribution with decision tree reasoning as feedback, generating high-quality labeled data for each subset. However, the massive generated data inherently involves a trade-off between diversity and quality. To integrate this issue, existing solutions greedily select the validation-best data. However, we prove that the selection in heterogeneous settings does not possess the greedy-choice property, and design a Multi-Arm Bandit-based sampling algorithm that balances the diversity and quality of generated data. Extensive experiments on tabular classification and regression benchmarks demonstrate that DATE consistently outperforms state-of-the-art GAN-based and LLM-based methods. On average, DATE achieves a 23.75% reduction in error rate with just 100 generated data. Empirically, we demonstrate that data generated by DATE can improve the accuracy of Direct Preference Optimization (DPO) and enhance the reasoning capability of LLMs on the target data. Code is available at https://github.com/windblow32/DATE. --- ### GQ-VAE: A gated quantized VAE for learning variable length tokens Authors: Theo Datta, Kayla Huang, Sham Kakade, David Brandfonbrener Published: 2025-12-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.21913v1 While most frontier models still use deterministic frequency-based tokenization algorithms such as byte-pair encoding (BPE), there has been significant recent work to design learned neural tokenizers. However, these schemes generally add to underlying language model complexity and force large changes to architecture, making them hard to implement at large scales. To overcome these challenges, we propose the gated quantized variational autoencoder (GQ-VAE), a novel architecture that can be independently pre-trained to serve as a drop-in replacement for existing tokenizers. The key innovation of the architecture is to learn to encode variable-length discrete tokens. GQ-VAE improves compression and language modeling performance over a standard VQ-VAE tokenizer, and approaches the compression rate and language modeling performance of BPE. Interestingly, if we use BPE with a smaller vocabulary, such that the compression is equivalent between GQ-VAE and BPE, we find that GQ-VAE improves downstream language model learning. We conclude with a discussion of several exciting avenues for future work. Code can be found at https://github.com/Theo-Datta-115/gq-vae. --- ### Accelerate Speculative Decoding with Sparse Computation in Verification Authors: Jikai Wang, Jianchao Tan, Yuxuan Hu, Jiayu Qin, Yerui Sun, Yuchen Xie, Xunliang Cai, Juntao Li, Min Zhang Published: 2025-12-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21911v1 Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel. However, the verification stage often becomes the dominant computational bottleneck, especially for long-context inputs and mixture-of-experts (MoE) models. Existing sparsification methods are designed primarily for standard token-by-token autoregressive decoding to remove substantial computational redundancy in LLMs. This work systematically adopts different sparse methods on the verification stage of the speculative decoding and identifies structured redundancy across multiple dimensions. Based on these observations, we propose a sparse verification framework that jointly sparsifies attention, FFN, and MoE components during the verification stage to reduce the dominant computation cost. The framework further incorporates an inter-draft token and inter-layer retrieval reuse strategy to further reduce redundant computation without introducing additional training. Extensive experiments across summarization, question answering, and mathematical reasoning datasets demonstrate that the proposed methods achieve favorable efficiency-accuracy trade-offs, while maintaining stable acceptance length. --- ### SpatialBench: Can Agents Analyze Real-World Spatial Biology Data? Authors: Kenny Workman, Zhen Yang, Harihara Muralidharan, Hannah Le Published: 2025-12-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.21907v2 Spatial transcriptomics assays are rapidly increasing in scale and complexity, making computational analysis a major bottleneck in biological discovery. Although frontier AI agents have improved dramatically at software engineering and general data analysis, it remains unclear whether they can extract biological insight from messy, real-world spatial datasets. We introduce SpatialBench, a benchmark of 146 verifiable problems derived from practical spatial analysis workflows spanning five spatial technologies and seven task categories. Each problem provides a snapshot of experimental data immediately prior to an analysis step and a deterministic grader that evaluates recovery of a key biological result. Benchmark data on frontier models shows that base model accuracy remains low (20-38% across model families), with strong model-task and model-platform interactions. Harness design has a large empirical effect on performance, indicating that tools, prompts, control flow, and execution environment should be evaluated and improved as first-class objects. SpatialBench serves both as a measurement tool and a diagnostic lens for developing agents that can interact with real spatial datasets faithfully, transparently, and reproducibly. --- ### High-Fidelity and Long-Duration Human Image Animation with Diffusion Transformer Authors: Shen Zheng, Jiaran Cai, Yuansheng Guan, Shenneng Huang, Xingpei Ma, Junjie Cao, Hanfeng Zhao, Qiang Zhang, Shunsi Zhang, Xiao-Ping Zhang Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21905v1 Recent progress in diffusion models has significantly advanced the field of human image animation. While existing methods can generate temporally consistent results for short or regular motions, significant challenges remain, particularly in generating long-duration videos. Furthermore, the synthesis of fine-grained facial and hand details remains under-explored, limiting the applicability of current approaches in real-world, high-quality applications. To address these limitations, we propose a diffusion transformer (DiT)-based framework which focuses on generating high-fidelity and long-duration human animation videos. First, we design a set of hybrid implicit guidance signals and a sharpness guidance factor, enabling our framework to additionally incorporate detailed facial and hand features as guidance. Next, we incorporate the time-aware position shift fusion module, modify the input format within the DiT backbone, and refer to this mechanism as the Position Shift Adaptive Module, which enables video generation of arbitrary length. Finally, we introduce a novel data augmentation strategy and a skeleton alignment model to reduce the impact of human shape variations across different identities. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches, achieving superior performance in both high-fidelity and long-duration human image animation. --- ### Explainable Statute Prediction via Attention-based Model and LLM Prompting Authors: Sachin Pawar, Girish Keshav Palshikar, Anindita Sinha Banerjee, Nitin Ramrakhiyani, Basit Ali Published: 2025-12-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21902v1 In this paper, we explore the problem of automatic statute prediction where for a given case description, a subset of relevant statutes are to be predicted. Here, the term "statute" refers to a section, a sub-section, or an article of any specific Act. Addressing this problem would be useful in several applications such as AI-assistant for lawyers and legal question answering system. For better user acceptance of such Legal AI systems, we believe the predictions should also be accompanied by human understandable explanations. We propose two techniques for addressing this problem of statute prediction with explanations -- (i) AoS (Attention-over-Sentences) which uses attention over sentences in a case description to predict statutes relevant for it and (ii) LLMPrompt which prompts an LLM to predict as well as explain relevance of a certain statute. AoS uses smaller language models, specifically sentence transformers and is trained in a supervised manner whereas LLMPrompt uses larger language models in a zero-shot manner and explores both standard as well as Chain-of-Thought (CoT) prompting techniques. Both these models produce explanations for their predictions in human understandable forms. We compare statute prediction performance of both the proposed techniques with each other as well as with a set of competent baselines, across two popular datasets. Also, we evaluate the quality of the generated explanations through an automated counter-factual manner as well as through human evaluation. --- ### Flexible Multitask Learning with Factorized Diffusion Policy Authors: Chaoqi Liu, Haonan Chen, Sigmund H. Høeg, Shaoxiong Yao, Yunzhu Li, Kris Hauser, Yilun Du Published: 2025-12-26 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.21898v2 Multitask learning poses significant challenges due to the highly multimodal and diverse nature of robot action distributions. However, effectively fitting policies to these complex task distributions is often difficult, and existing monolithic models often underfit the action distribution and lack the flexibility required for efficient adaptation. We introduce a novel modular diffusion policy framework that factorizes complex action distributions into a composition of specialized diffusion models, each capturing a distinct sub-mode of the behavior space for a more effective overall policy. In addition, this modular structure enables flexible policy adaptation to new tasks by adding or fine-tuning components, which inherently mitigates catastrophic forgetting. Empirically, across both simulation and real-world robotic manipulation settings, we illustrate how our method consistently outperforms strong modular and monolithic baselines. ---