# Research Papers — 2026-01 · bundle page 37 of 189 > Full-text markdown of papers #1801–1850 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-01/page/37 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/36.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/38.md) ### Let's Roll a BiFTA: Bi-refinement for Fine-grained Text-visual Alignment in Vision-Language Models Authors: Yuhao Sun, Chengyi Cai, Jiacheng Zhang, Zesheng Ye, Xingliang Yuan, Feng Liu Published: 2026-01-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.20419v1 Recent research has shown that aligning fine-grained text descriptions with localized image patches can significantly improve the zero-shot performance of pre-trained vision-language models (e.g., CLIP). However, we find that both fine-grained text descriptions and localized image patches often contain redundant information, making text-visual alignment less effective. In this paper, we tackle this issue from two perspectives: \emph{View Refinement} and \emph{Description refinement}, termed as \textit{\textbf{Bi}-refinement for \textbf{F}ine-grained \textbf{T}ext-visual \textbf{A}lignment} (BiFTA). \emph{View refinement} removes redundant image patches with high \emph{Intersection over Union} (IoU) ratios, resulting in more distinctive visual samples. \emph{Description refinement} removes redundant text descriptions with high pairwise cosine similarity, ensuring greater diversity in the remaining descriptions. BiFTA achieves superior zero-shot performance on 6 benchmark datasets for both ViT-based and ResNet-based CLIP, justifying the necessity to remove redundant information in visual-text alignment. --- ### SpeechMapper: Speech-to-text Embedding Projector for LLMs Authors: Biswesh Mohapatra, Marcely Zanon Boito, Ioan Calapodescu Published: 2026-01-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.20417v2 Current speech LLMs bridge speech foundation models to LLMs using projection layers, training all of these components on speech instruction data. This strategy is computationally intensive and susceptible to task and prompt overfitting. We present SpeechMapper, a cost-efficient speech-to-LLM-embedding training approach that mitigates overfitting, enabling more robust and generalizable models. Our model is first pretrained without the LLM on inexpensive hardware, and then efficiently attached to the target LLM via a brief 1K-step instruction tuning (IT) stage. Through experiments on speech translation and spoken question answering, we demonstrate the versatility of SpeechMapper's pretrained block, presenting results for both task-agnostic IT, an ASR-based adaptation strategy that does not train in the target task, and task-specific IT. In task-agnostic settings, Speechmapper rivals the best instruction-following speech LLM from IWSLT25, despite never being trained on these tasks, while in task-specific settings, it outperforms this model across many datasets, despite requiring less data and compute. Overall, SpeechMapper offers a practical and scalable approach for efficient, generalizable speech-LLM integration without large-scale IT. --- ### Beyond Accuracy: A Cognitive Load Framework for Mapping the Capability Boundaries of Tool-use Agents Authors: Qihao Wang, Yue Hu, Mingzhe Lu, Jiayue Wu, Yanbing Liu, Yuanmin Tang Published: 2026-01-28 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2601.20412v1 The ability of Large Language Models (LLMs) to use external tools unlocks powerful real-world interactions, making rigorous evaluation essential. However, current benchmarks primarily report final accuracy, revealing what models can do but obscuring the cognitive bottlenecks that define their true capability boundaries. To move from simple performance scoring to a diagnostic tool, we introduce a framework grounded in Cognitive Load Theory. Our framework deconstructs task complexity into two quantifiable components: Intrinsic Load, the inherent structural complexity of the solution path, formalized with a novel Tool Interaction Graph; and Extraneous Load, the difficulty arising from ambiguous task presentation. To enable controlled experiments, we construct ToolLoad-Bench, the first benchmark with parametrically adjustable cognitive load. Our evaluation reveals distinct performance cliffs as cognitive load increases, allowing us to precisely map each model's capability boundary. We validate that our framework's predictions are highly calibrated with empirical results, establishing a principled methodology for understanding an agent's limits and a practical foundation for building more efficient systems. --- ### AWGformer: Adaptive Wavelet-Guided Transformer for Multi-Resolution Time Series Forecasting Authors: Wei Li Published: 2026-01-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.20409v1 Time series forecasting requires capturing patterns across multiple temporal scales while maintaining computational efficiency. This paper introduces AWGformer, a novel architecture that integrates adaptive wavelet decomposition with cross-scale attention mechanisms for enhanced multi-variate time series prediction. Our approach comprises: (1) an Adaptive Wavelet Decomposition Module (AWDM) that dynamically selects optimal wavelet bases and decomposition levels based on signal characteristics; (2) a Cross-Scale Feature Fusion (CSFF) mechanism that captures interactions between different frequency bands through learnable coupling matrices; (3) a Frequency-Aware Multi-Head Attention (FAMA) module that weights attention heads according to their frequency selectivity; (4) a Hierarchical Prediction Network (HPN) that generates forecasts at multiple resolutions before reconstruction. Extensive experiments on benchmark datasets demonstrate that AWGformer achieves significant average improvements over state-of-the-art methods, with particular effectiveness on multi-scale and non-stationary time series. Theoretical analysis provides convergence guarantees and establishes the connection between our wavelet-guided attention and classical signal processing principles. --- ### Meeting SLOs, Slashing Hours: Automated Enterprise LLM Optimization with OptiKIT Authors: Nicholas Santavas, Kareem Eissa, Patrycja Cieplicka, Piotr Florek, Matteo Nulli, Stefan Vasilev, Seyyed Hadi Hashemi, Antonios Gasteratos, Shahram Khadivi Published: 2026-01-28 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2601.20408v2 Enterprise LLM deployment faces a critical scalability challenge: organizations must optimize models systematically to scale AI initiatives within constrained compute budgets, yet the specialized expertise required for manual optimization remains a niche and scarce skillset. This challenge is particularly evident in managing GPU utilization across heterogeneous infrastructure while enabling teams with diverse workloads and limited LLM optimization experience to deploy models efficiently. We present OPTIKIT, a distributed LLM optimization framework that democratizes model compression and tuning by automating complex optimization workflows for non-expert teams. OPTIKIT provides dynamic resource allocation, staged pipeline execution with automatic cleanup, and seamless enterprise integration. In production, it delivers more than 2x GPU throughput improvement while empowering application teams to achieve consistent performance improvements without deep LLM optimization expertise. We share both the platform design and key engineering insights into resource management, pipeline orchestration, and integration patterns that enable large-scale, production-grade democratization of model optimization. Finally, we open-source the system to enable external contributions and broader reproducibility. --- ### On the Impact of AGENTS.md Files on the Efficiency of AI Coding Agents Authors: Jai Lal Lulla, Seyedmoein Mohsenimofidi, Matthias Galster, Jie M. Zhang, Sebastian Baltes, Christoph Treude Published: 2026-01-28 Categories: cs.SE, cs.AI, cs.ET, cs.HC arXiv: https://arxiv.org/abs/2601.20404v2 AI coding agents such as Codex and Claude Code are increasingly used to autonomously contribute to software repositories. However, little is known about how repository-level configuration artifacts affect operational efficiency of the agents. In this paper, we study the impact of AGENTS$.$md files on the runtime and token consumption of AI coding agents operating on GitHub pull requests. We analyze 10 repositories and 124 pull requests, executing agents under two conditions: with and without an AGENTS$.$md file. We measure wall-clock execution time and token usage during agent execution. Our results show that the presence of AGENTS$.$md is associated with a lower median runtime ($Δ28.64$%) and reduced output token consumption ($Δ16.58$%), while maintaining a comparable task completion behavior. Based on these results, we discuss immediate implications for the configuration and deployment of AI coding agents in practice, and outline a broader research agenda on the role of repository-level instructions in shaping the behavior, efficiency, and integration of AI coding agents in software development workflows. --- ### GuideAI: A Real-time Personalized Learning Solution with Adaptive Interventions Authors: Ananya Shukla, Chaitanya Modi, Satvik Bajpai, Siddharth Siddharth Published: 2026-01-28 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.20402v1 Large Language Models (LLMs) have emerged as powerful learning tools, but they lack awareness of learners' cognitive and physiological states, limiting their adaptability to the user's learning style. Contemporary learning techniques primarily focus on structured learning paths, knowledge tracing, and generic adaptive testing but fail to address real-time learning challenges driven by cognitive load, attention fluctuations, and engagement levels. Building on findings from a formative user study (N=66), we introduce GuideAI, a multi-modal framework that enhances LLM-driven learning by integrating real-time biosensory feedback including eye gaze tracking, heart rate variability, posture detection, and digital note-taking behavior. GuideAI dynamically adapts learning content and pacing through cognitive optimizations (adjusting complexity based on learning progress markers), physiological interventions (breathing guidance and posture correction), and attention-aware strategies (redirecting focus using gaze analysis). Additionally, GuideAI supports diverse learning modalities, including text-based, image-based, audio-based, and video-based instruction, across varied knowledge domains. A preliminary study (N = 25) assessed GuideAI's impact on knowledge retention and cognitive load through standardized assessments. The results show statistically significant improvements in both problem-solving capability and recall-based knowledge assessments. Participants also experienced notable reductions in key NASA-TLX measures including mental demand, frustration levels, and effort, while simultaneously reporting enhanced perceived performance. These findings demonstrate GuideAI's potential to bridge the gap between current LLM-based learning systems and individualized learner needs, paving the way for adaptive, cognition-aware education at scale. --- ### ScatterFusion: A Hierarchical Scattering Transform Framework for Enhanced Time Series Forecasting Authors: Wei Li Published: 2026-01-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.20401v1 Time series forecasting presents significant challenges due to the complex temporal dependencies at multiple time scales. This paper introduces ScatterFusion, a novel framework that synergistically integrates scattering transforms with hierarchical attention mechanisms for robust time series forecasting. Our approach comprises four key components: (1) a Hierarchical Scattering Transform Module (HSTM) that extracts multi-scale invariant features capturing both local and global patterns; (2) a Scale-Adaptive Feature Enhancement (SAFE) module that dynamically adjusts feature importance across different scales; (3) a Multi-Resolution Temporal Attention (MRTA) mechanism that learns dependencies at varying time horizons; and (4) a Trend-Seasonal-Residual (TSR) decomposition-guided structure-aware loss function. Extensive experiments on seven benchmark datasets demonstrate that ScatterFusion outperforms other common methods, achieving significant reductions in error metrics across various prediction horizons. --- ### Convergence Analysis of Randomized Subspace Normalized SGD under Heavy-Tailed Noise Authors: Gaku Omiya, Pierre-Louis Poirion, Akiko Takeda Published: 2026-01-28 Categories: math.OC, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2601.20399v2 Randomized subspace methods reduce per-iteration cost; however, in nonconvex optimization, most analyses are expectation-based, and high-probability bounds remain scarce even under sub-Gaussian noise. We first prove that randomized subspace SGD (RS-SGD) admits a high-probability convergence bound under sub-Gaussian noise, achieving the same order of oracle complexity as prior in-expectation results. Motivated by the prevalence of heavy-tailed gradients in modern machine learning, we then propose randomized subspace normalized SGD (RS-NSGD), which integrates direction normalization into subspace updates. Assuming the noise has bounded $p$-th moments, we establish both in-expectation and high-probability convergence guarantees, and show that RS-NSGD can achieve better oracle complexity than full-dimensional normalized SGD. --- ### FedRD: Reducing Divergences for Generalized Federated Learning via Heterogeneity-aware Parameter Guidance Authors: Kaile Wang, Jiannong Cao, Yu Yang, Xiaoyin Li, Mingjin Zhang Published: 2026-01-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.20397v1 Heterogeneous federated learning (HFL) aims to ensure effective and privacy-preserving collaboration among different entities. As newly joined clients require significant adjustments and additional training to align with the existing system, the problem of generalizing federated learning models to unseen clients under heterogeneous data has become progressively crucial. Consequently, we highlight two unsolved challenging issues in federated domain generalization: Optimization Divergence and Performance Divergence. To tackle the above challenges, we propose FedRD, a novel heterogeneity-aware federated learning algorithm that collaboratively utilizes parameter-guided global generalization aggregation and local debiased classification to reduce divergences, aiming to obtain an optimal global model for participating and unseen clients. Extensive experiments on public multi-domain datasets demonstrate that our approach exhibits a substantial performance advantage over competing baselines in addressing this specific problem. --- ### Graph-Structured Deep Learning Framework for Multi-task Contention Identification with High-dimensional Metrics Authors: Xiao Yang, Yinan Ni, Yuqi Tang, Zhimin Qiu, Chen Wang, Tingzhou Yuan Published: 2026-01-28 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2601.20389v1 This study addresses the challenge of accurately identifying multi-task contention types in high-dimensional system environments and proposes a unified contention classification framework that integrates representation transformation, structural modeling, and a task decoupling mechanism. The method first constructs system state representations from high-dimensional metric sequences, applies nonlinear transformations to extract cross-dimensional dynamic features, and integrates multiple source information such as resource utilization, scheduling behavior, and task load variations within a shared representation space. It then introduces a graph-based modeling mechanism to capture latent dependencies among metrics, allowing the model to learn competitive propagation patterns and structural interference across resource links. On this basis, task-specific mapping structures are designed to model the differences among contention types and enhance the classifier's ability to distinguish multiple contention patterns. To achieve stable performance, the method employs an adaptive multi-task loss weighting strategy that balances shared feature learning with task-specific feature extraction and generates final contention predictions through a standardized inference process. Experiments conducted on a public system trace dataset demonstrate advantages in accuracy, recall, precision, and F1, and sensitivity analyses on batch size, training sample scale, and metric dimensionality further confirm the model's stability and applicability. The study shows that structured representations and multi-task classification based on high-dimensional metrics can significantly improve contention pattern recognition and offer a reliable technical approach for performance management in complex computing environments. --- ### HINT: Hierarchical Interaction Modeling for Autoregressive Multi-Human Motion Generation Authors: Mengge Liu, Yan Di, Gu Wang, Yun Qu, Dekai Zhu, Yanyan Li, Xiangyang Ji Published: 2026-01-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.20383v1 Text-driven multi-human motion generation with complex interactions remains a challenging problem. Despite progress in performance, existing offline methods that generate fixed-length motions with a fixed number of agents, are inherently limited in handling long or variable text, and varying agent counts. These limitations naturally encourage autoregressive formulations, which predict future motions step by step conditioned on all past trajectories and current text guidance. In this work, we introduce HINT, the first autoregressive framework for multi-human motion generation with Hierarchical INTeraction modeling in diffusion. First, HINT leverages a disentangled motion representation within a canonicalized latent space, decoupling local motion semantics from inter-person interactions. This design facilitates direct adaptation to varying numbers of human participants without requiring additional refinement. Second, HINT adopts a sliding-window strategy for efficient online generation, and aggregates local within-window and global cross-window conditions to capture past human history, inter-person dependencies, and align with text guidance. This strategy not only enables fine-grained interaction modeling within each window but also preserves long-horizon coherence across all the long sequence. Extensive experiments on public benchmarks demonstrate that HINT matches the performance of strong offline models and surpasses autoregressive baselines. Notably, on InterHuman, HINT achieves an FID of 3.100, significantly improving over the previous state-of-the-art score of 5.154. --- ### OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution Authors: Le Zhang, Yixiong Xiao, Xinjiang Lu, Jingjia Cao, Yusai Zhao, Jingbo Zhou, Lang An, Zikan Feng, Wanxiang Sha, Yu Shi, Congxi Xiao, Jian Xiong et al. Published: 2026-01-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.20380v1 Graphical User Interface (GUI) agents show great potential for enabling foundation models to complete real-world tasks, revolutionizing human-computer interaction and improving human productivity. In this report, we present OmegaUse, a general-purpose GUI agent model for autonomous task execution on both mobile and desktop platforms, supporting computer-use and phone-use scenarios. Building an effective GUI agent model relies on two factors: (1) high-quality data and (2) effective training methods. To address these, we introduce a carefully engineered data-construction pipeline and a decoupled training paradigm. For data construction, we leverage rigorously curated open-source datasets and introduce a novel automated synthesis framework that integrates bottom-up autonomous exploration with top-down taxonomy-guided generation to create high-fidelity synthetic data. For training, to better leverage these data, we adopt a two-stage strategy: Supervised Fine-Tuning (SFT) to establish fundamental interaction syntax, followed by Group Relative Policy Optimization (GRPO) to improve spatial grounding and sequential planning. To balance computational efficiency with agentic reasoning capacity, OmegaUse is built on a Mixture-of-Experts (MoE) backbone. To evaluate cross-terminal capabilities in an offline setting, we introduce OS-Nav, a benchmark suite spanning multiple operating systems: ChiM-Nav, targeting Chinese Android mobile environments, and Ubu-Nav, focusing on routine desktop interactions on Ubuntu. Extensive experiments show that OmegaUse is highly competitive across established GUI benchmarks, achieving a state-of-the-art (SOTA) score of 96.3% on ScreenSpot-V2 and a leading 79.1% step success rate on AndroidControl. OmegaUse also performs strongly on OS-Nav, reaching 74.24% step success on ChiM-Nav and 55.9% average success on Ubu-Nav. --- ### Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution Authors: Zhengbo Jiao, Hongyu Xian, Qinglong Wang, Yunpu Ma, Zhebo Wang, Zifan Zhang, Dezhang Kong, Meng Han Published: 2026-01-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.20379v2 Large language models (LLMs) struggle with complex, long-horizon reasoning due to instability caused by their frozen policy assumption. Current test-time scaling methods treat execution feedback merely as an external signal for filtering or rewriting trajectories, without internalizing it to improve the underlying reasoning strategy. Inspired by Popper's epistemology of "conjectures and refutations," we argue that intelligence requires real-time evolution of the model's policy through learning from failed attempts. We introduce Policy of Thoughts (PoT), a framework that recasts reasoning as a within-instance online optimization process. PoT first generates diverse candidate solutions via an efficient exploration mechanism, then uses Group Relative Policy Optimization (GRPO) to update a transient LoRA adapter based on execution feedback. This closed-loop design enables dynamic, instance-specific refinement of the model's reasoning priors. Experiments show that PoT dramatically boosts performance: a 4B model achieves 49.71% accuracy on LiveCodeBench, outperforming GPT-4o and DeepSeek-V3 despite being over 50 smaller. --- ### LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning Authors: Wei Huang, Anda Cheng, Yinggui Wang, Lei Wang, Tao Wei Published: 2026-01-28 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.20375v2 Large Language Models (LLMs) can be fine-tuned on domain-specific data to enhance their performance in specialized fields. However, such data often contains numerous low-quality samples, necessitating effective data processing (DP). In practice, DP strategies are typically developed through iterative manual analysis and trial-and-error adjustment. These processes inevitably incur high labor costs and may lead to privacy issues in high-privacy domains like healthcare due to direct human access to sensitive data. Thus, achieving automated data processing without exposing the raw data has become a critical challenge. To address this challenge, we propose LLM-AutoDP, a novel framework that leverages LLMs as agents to automatically generate and optimize data processing strategies. Our method generates multiple candidate strategies and iteratively refines them using feedback signals and comparative evaluations. This iterative in-context learning mechanism enables the agent to converge toward high-quality processing pipelines without requiring direct human intervention or access to the underlying data. To further accelerate strategy search, we introduce three key techniques: Distribution Preserving Sampling, which reduces data volume while maintaining distributional integrity; Processing Target Selection, which uses a binary classifier to identify low-quality samples for focused processing; Cache-and-Reuse Mechanism}, which minimizes redundant computations by reusing prior processing results. Results show that models trained on data processed by our framework achieve over 80% win rates against models trained on unprocessed data. Compared to AutoML baselines based on LLM agents, LLM-AutoDP achieves approximately a 65% win rate. Moreover, our acceleration techniques reduce the total searching time by up to 10 times, demonstrating both effectiveness and efficiency. --- ### RepSFNet : A Single Fusion Network with Structural Reparameterization for Crowd Counting Authors: Mas Nurul Achmadiah, Chi-Chia Sun, Wen-Kai Kuo, Jun-Wei Hsieh Published: 2026-01-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.20369v1 Crowd counting remains challenging in variable-density scenes due to scale variations, occlusions, and the high computational cost of existing models. To address these issues, we propose RepSFNet (Reparameterized Single Fusion Network), a lightweight architecture designed for accurate and real-time crowd estimation. RepSFNet leverages a RepLK-ViT backbone with large reparameterized kernels for efficient multi-scale feature extraction. It further integrates a Feature Fusion module combining Atrous Spatial Pyramid Pooling (ASPP) and Context-Aware Network (CAN) to achieve robust, density-adaptive context modeling. A Concatenate Fusion module is employed to preserve spatial resolution and generate high-quality density maps. By avoiding attention mechanisms and multi-branch designs, RepSFNet significantly reduces parameters and computational complexity. The training objective combines Mean Squared Error and Optimal Transport loss to improve both count accuracy and spatial distribution alignment. Experiments conducted on ShanghaiTech, NWPU, and UCF-QNRF datasets demonstrate that RepSFNet achieves competitive accuracy while reducing inference latency by up to 34 percent compared to recent state-of-the-art methods, making it suitable for real-time and low-power edge computing applications. --- ### Unsupervised Anomaly Detection in Multi-Agent Trajectory Prediction via Transformer-Based Models Authors: Qing Lyu, Zhe Fu, Alexandre Bayen Published: 2026-01-28 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2601.20367v1 Identifying safety-critical scenarios is essential for autonomous driving, but the rarity of such events makes supervised labeling impractical. Traditional rule-based metrics like Time-to-Collision are too simplistic to capture complex interaction risks, and existing methods lack a systematic way to verify whether statistical anomalies truly reflect physical danger. To address this gap, we propose an unsupervised anomaly detection framework based on a multi-agent Transformer that models normal driving and measures deviations through prediction residuals. A dual evaluation scheme has been proposed to assess both detection stability and physical alignment: Stability is measured using standard ranking metrics in which Kendall Rank Correlation Coefficient captures rank agreement and Jaccard index captures the consistency of the top-K selected items; Physical alignment is assessed through correlations with established Surrogate Safety Measures (SSM). Experiments on the NGSIM dataset demonstrate our framework's effectiveness: We show that the maximum residual aggregator achieves the highest physical alignment while maintaining stability. Furthermore, our framework identifies 388 unique anomalies missed by Time-to-Collision and statistical baselines, capturing subtle multi-agent risks like reactive braking under lateral drift. The detected anomalies are further clustered into four interpretable risk types, offering actionable insights for simulation and testing. --- ### Dual-Modality IoT Framework for Integrated Access Control and Environmental Safety Monitoring with Real-Time Cloud Analytics Authors: Abdul Hasib, A. S. M. Ahsanul Sarkar Akib, Nihal Das Ankur, Anish Giri Published: 2026-01-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.20366v1 The integration of physical security systems with environmental safety monitoring represents a critical advancement in smart infrastructure management. Traditional approaches maintain these systems as independent silos, creating operational inefficiencies, delayed emergency responses, and increased management complexity. This paper presents a comprehensive dual-modality Internet of Things framework that seamlessly integrates RFID-based access control with multi-sensor environmental safety monitoring through a unified cloud architecture. The system comprises two coordinated subsystems: Subsystem 1 implements RFID authentication with servo-actuated gate control and real-time Google Sheets logging, while Subsystem 2 provides comprehensive safety monitoring incorporating flame detection, water flow measurement, LCD status display, and personnel identification. Both subsystems utilize ESP32 microcontrollers for edge processing and wireless connectivity. Experimental evaluation over 45 days demonstrates exceptional performance metrics: 99.2\% RFID authentication accuracy with 0.82-second average response time, 98.5\% flame detection reliability within 5-meter range, and 99.8\% cloud data logging success rate. The system maintains operational integrity during network disruptions through intelligent local caching mechanisms and achieves total implementation cost of 5,400 BDT (approximately \$48), representing an 82\% reduction compared to commercial integrated solutions. This research establishes a practical framework for synergistic security-safety integration, demonstrating that professional-grade performance can be achieved through careful architectural design and component optimization while maintaining exceptional cost-effectiveness and accessibility for diverse application scenarios. --- ### RAW-Flow: Advancing RGB-to-RAW Image Reconstruction with Deterministic Latent Flow Matching Authors: Zhen Liu, Diedong Feng, Hai Jiang, Liaoyuan Zeng, Hao Wang, Chaoyu Feng, Lei Lei, Bing Zeng, Shuaicheng Liu Published: 2026-01-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.20364v1 RGB-to-RAW reconstruction, or the reverse modeling of a camera Image Signal Processing (ISP) pipeline, aims to recover high-fidelity RAW data from RGB images. Despite notable progress, existing learning-based methods typically treat this task as a direct regression objective and struggle with detail inconsistency and color deviation, due to the ill-posed nature of inverse ISP and the inherent information loss in quantized RGB images. To address these limitations, we pioneer a generative perspective by reformulating RGB-to-RAW reconstruction as a deterministic latent transport problem and introduce a novel framework named RAW-Flow, which leverages flow matching to learn a deterministic vector field in latent space, to effectively bridge the gap between RGB and RAW representations and enable accurate reconstruction of structural details and color information. To further enhance latent transport, we introduce a cross-scale context guidance module that injects hierarchical RGB features into the flow estimation process. Moreover, we design a dual-domain latent autoencoder with a feature alignment constraint to support the proposed latent transport framework, which jointly encodes RGB and RAW inputs while promoting stable training and high-fidelity reconstruction. Extensive experiments demonstrate that RAW-Flow outperforms state-of-the-art approaches both quantitatively and visually. --- ### Can Continuous-Time Diffusion Models Generate and Solve Globally Constrained Discrete Problems? A Study on Sudoku Authors: Mariia Drozdova Published: 2026-01-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.20363v1 Can standard continuous-time generative models represent distributions whose support is an extremely sparse, globally constrained discrete set? We study this question using completed Sudoku grids as a controlled testbed, treating them as a subset of a continuous relaxation space. We train flow-matching and score-based models along a Gaussian probability path and compare deterministic (ODE) sampling, stochastic (SDE) sampling, and DDPM-style discretizations derived from the same continuous-time training. Unconditionally, stochastic sampling substantially outperforms deterministic flows; score-based samplers are the most reliable among continuous-time methods, and DDPM-style ancestral sampling achieves the highest validity overall. We further show that the same models can be repurposed for guided generation: by repeatedly sampling completions under clamped clues and stopping when constraints are satisfied, the model acts as a probabilistic Sudoku solver. Although far less sample-efficient than classical solvers and discrete-geometry-aware diffusion methods, these experiments demonstrate that classic diffusion/flow formulations can assign non-zero probability mass to globally constrained combinatorial structures and can be used for constraint satisfaction via stochastic search. --- ### Switchcodec: Adaptive residual-expert sparse quantization for high-fidelity neural audio coding Authors: Xiangbo Wang, Wenbin Jiang, Jin Wang, Yubo You, Sheng Fang, Fei Wen Published: 2026-01-28 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2601.20362v2 Recent neural audio compression models often rely on residual vector quantization for high-fidelity coding, but using a fixed number of per-frame codebooks is suboptimal for the wide variability of audio content-especially for signals that are either very simple or highly complex. To address this limitation, we propose SwitchCodec, a neural audio codec based on Residual Experts Vector Quantization (REVQ). REVQ combines a shared quantizer with dynamically routed expert quantizers that are activated according to the input audio, decoupling bitrate from codebook capacity and improving compression efficiency. This design ensures full training and utilization of each quantizer. In addition, a variable-bitrate mechanism adjusts the number of active expert quantizers at inference, enabling multi-bitrate operation without retraining. Experiments demonstrate that SwitchCodec surpasses existing baselines on both objective metrics and subjective listening tests. --- ### TINNs: Time-Induced Neural Networks for Solving Time-Dependent PDEs Authors: Chen-Yang Dai, Che-Chia Chang, Te-Sheng Lin, Ming-Chih Lai, Chieh-Hsin Lai Published: 2026-01-28 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2601.20361v2 Physics-informed neural networks (PINNs) solve time-dependent partial differential equations (PDEs) by learning a mesh-free, differentiable solution that can be evaluated anywhere in space and time. However, standard space-time PINNs take time as an input but reuse a single network with shared weights across all times, forcing the same features to represent markedly different dynamics. This coupling degrades error performance and can destabilize training when enforcing PDE, boundary, and initial constraints jointly. We propose Time-Induced Neural Networks (TINNs), a novel architecture that parameterizes the network weights as a learned function of time, allowing the effective spatial representation to evolve over time while maintaining shared structure. The resulting formulation naturally yields a nonlinear least-squares problem, which we optimize efficiently using a Levenberg-Marquardt method. Experiments on various time-dependent PDEs show up to 4 times improved relative error and 10 times faster convergence compared to PINNs and strong baselines. --- ### TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs Authors: Minjae Lee, Wonjun Kang, Byeongkeun Ahn, Christian Classen, Kevin Galim, Seunghyuk Oh, Minghao Yan, Hyung Il Koo, Kangwook Lee Published: 2026-01-28 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2601.20357v1 Speculative decoding (SD) has proven effective for accelerating LLM inference by quickly generating draft tokens and verifying them in parallel. However, SD remains largely unexplored for Large Vision-Language Models (LVLMs), which extend LLMs to process both image and text prompts. To address this gap, we benchmark existing inference methods with small draft models on 11 datasets across diverse input scenarios and observe scenario-specific performance fluctuations. Motivated by these findings, we propose Test-time Adaptive Batched Ensemble Drafting (TABED), which dynamically ensembles multiple drafts obtained via batch inference by leveraging deviations from past ground truths available in the SD setting. The dynamic ensemble method achieves an average robust walltime speedup of 1.74x over autoregressive decoding and a 5% improvement over single drafting methods, while remaining training-free and keeping ensembling costs negligible through parameter sharing. With its plug-and-play compatibility, we further enhance TABED by integrating advanced verification and alternative drafting methods. Code and custom-trained models are available at https://github.com/furiosa-ai/TABED. --- ### CURVE: Learning Causality-Inspired Invariant Representations for Robust Scene Understanding via Uncertainty-Guided Regularization Authors: Yue Liang, Jiatong Du, Ziyi Yang, Yanjun Huang, Hong Chen Published: 2026-01-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.20355v1 Scene graphs provide structured abstractions for scene understanding, yet they often overfit to spurious correlations, severely hindering out-of-distribution generalization. To address this limitation, we propose CURVE, a causality-inspired framework that integrates variational uncertainty modeling with uncertainty-guided structural regularization to suppress high-variance, environment-specific relations. Specifically, we apply prototype-conditioned debiasing to disentangle invariant interaction dynamics from environment-dependent variations, promoting a sparse and domain-stable topology. Empirically, we evaluate CURVE in zero-shot transfer and low-data sim-to-real adaptation, verifying its ability to learn domain-stable sparse topologies and provide reliable uncertainty estimates to support risk prediction under distribution shifts. --- ### Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models Authors: Zengbin Wang, Xuecai Hu, Yong Wang, Feng Xiong, Man Zhang, Xiangxiang Chu Published: 2026-01-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.20354v2 Text-to-image (T2I) models have achieved remarkable success in generating high-fidelity images, but they often fail in handling complex spatial relationships, e.g., spatial perception, reasoning, or interaction. These critical aspects are largely overlooked by current benchmarks due to their short or information-sparse prompt design. In this paper, we introduce SpatialGenEval, a new benchmark designed to systematically evaluate the spatial intelligence of T2I models, covering two key aspects: (1) SpatialGenEval involves 1,230 long, information-dense prompts across 25 real-world scenes. Each prompt integrates 10 spatial sub-domains and corresponding 10 multi-choice question-answer pairs, ranging from object position and layout to occlusion and causality. Our extensive evaluation of 21 state-of-the-art models reveals that higher-order spatial reasoning remains a primary bottleneck. (2) To demonstrate that the utility of our information-dense design goes beyond simple evaluation, we also construct the SpatialT2I dataset. It contains 15,400 text-image pairs with rewritten prompts to ensure image consistency while preserving information density. Fine-tuned results on current foundation models (i.e., Stable Diffusion-XL, Uniworld-V1, OmniGen2) yield consistent performance gains (+4.2%, +5.7%, +4.4%) and more realistic effects in spatial relations, highlighting a data-centric paradigm to achieve spatial intelligence in T2I models. --- ### AMA: Adaptive Memory via Multi-Agent Collaboration Authors: Weiquan Huang, Zixuan Wang, Hehai Lin, Sudong Wang, Bo Xu, Qian Li, Beier Zhu, Linyi Yang, Chengwei Qin Published: 2026-01-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.20352v4 The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and complex reasoning. Benefiting from the strong capabilities of LLMs, recent research focus has shifted from simple context extension to the development of dedicated agentic memory systems. However, existing approaches typically rely on rigid retrieval granularity, accumulation-heavy maintenance strategies, and coarse-grained update mechanisms. These design choices create a persistent mismatch between stored information and task-specific reasoning demands, while leading to the unchecked accumulation of logical inconsistencies over time. To address these challenges, we propose Adaptive Memory via Multi-Agent Collaboration (AMA), a novel framework that leverages coordinated agents to manage memory across multiple granularities. AMA employs a hierarchical memory design that dynamically aligns retrieval granularity with task complexity. Specifically, the Constructor and Retriever jointly enable multi-granularity memory construction and adaptive query routing. The Judge verifies the relevance and consistency of retrieved content, triggering iterative retrieval when evidence is insufficient or invoking the Refresher upon detecting logical conflicts. The Refresher then enforces memory consistency by performing targeted updates or removing outdated entries. Extensive experiments on challenging long-context benchmarks show that AMA significantly outperforms state-of-the-art baselines while reducing token consumption by approximately 80% compared to full-context methods, demonstrating its effectiveness in maintaining retrieval precision and long-term memory consistency. --- ### PalmBridge: A Plug-and-Play Feature Alignment Framework for Open-Set Palmprint Verification Authors: Chenke Zhang, Ziyuan Yang, Licheng Yan, Shuyi Li, Andrew Beng Jin Teoh, Bob Zhang, Yi Zhang Published: 2026-01-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.20351v1 Palmprint recognition is widely used in biometric systems, yet real-world performance often degrades due to feature distribution shifts caused by heterogeneous deployment conditions. Most deep palmprint models assume a closed and stationary distribution, leading to overfitting to dataset-specific textures rather than learning domain-invariant representations. Although data augmentation is commonly used to mitigate this issue, it assumes augmented samples can approximate the target deployment distribution, an assumption that often fails under significant domain mismatch. To address this limitation, we propose PalmBridge, a plug-and-play feature-space alignment framework for open-set palmprint verification based on vector quantization. Rather than relying solely on data-level augmentation, PalmBridge learns a compact set of representative vectors directly from training features. During enrollment and verification, each feature vector is mapped to its nearest representative vector under a minimum-distance criterion, and the mapped vector is then blended with the original vector. This design suppresses nuisance variation induced by domain shifts while retaining discriminative identity cues. The representative vectors are jointly optimized with the backbone network using task supervision, a feature-consistency objective, and an orthogonality regularization term to form a stable and well-structured shared embedding space. Furthermore, we analyze feature-to-representative mappings via assignment consistency and collision rate to assess model's sensitivity to blending weights. Experiments on multiple palmprint datasets and backbone architectures show that PalmBridge consistently reduces EER in intra-dataset open-set evaluation and improves cross-dataset generalization with negligible to modest runtime overhead. --- ### MMSF: Multitask and Multimodal Supervised Framework for WSI Classification and Survival Analysis Authors: Chengying She, Chengwei Chen, Xinran Zhang, Ben Wang, Lizhuang Liu, Chengwei Shao, Yun Bian Published: 2026-01-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.20347v2 Multimodal evidence is critical in computational pathology: gigapixel whole slide images capture tumor morphology, while patient-level clinical descriptors preserve complementary context for prognosis. Integrating such heterogeneous signals remains challenging because feature spaces exhibit distinct statistics and scales. We introduce MMSF, a multitask and multimodal supervised framework built on a linear-complexity MIL backbone that explicitly decomposes and fuses cross-modal information. MMSF comprises a graph feature extraction module embedding tissue topology at the patch level, a clinical data embedding module standardizing patient attributes, a feature fusion module aligning modality-shared and modality-specific representations, and a Mamba-based MIL encoder with multitask prediction heads. Experiments on CAMELYON16 and TCGA-NSCLC demonstrate 2.1--6.6\% accuracy and 2.2--6.9\% AUC improvements over competitive baselines, while evaluations on five TCGA survival cohorts yield 7.1--9.8\% C-index improvements compared with unimodal methods and 5.6--7.1\% over multimodal alternatives. --- ### Multimodal Multi-Agent Ransomware Analysis Using AutoGen Authors: Asifullah Khan, Aimen Wadood, Mubashar Iqbal, Umme Zahoora Published: 2026-01-28 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.20346v2 Ransomware has become one of the most serious cybersecurity threats causing major financial losses and operational disruptions worldwide.Traditional detection methods such as static analysis, heuristic scanning and behavioral analysis often fall short when used alone. To address these limitations, this paper presents multimodal multi agent ransomware analysis framework designed for ransomware classification. Proposed multimodal multiagent architecture combines information from static, dynamic and network sources. Each data type is handled by specialized agent that uses auto encoder based feature extraction. These representations are then integrated through a fusion agent. After that fused representation are used by transformer based classifier. It identifies the specific ransomware family. The agents interact through an interagent feedback mechanism that iteratively refines feature representations by suppressing low confidence information. The framework was evaluated on large scale datasets containing thousands of ransomware and benign samples. Multiple experiments were conducted on ransomware dataset. It outperforms single modality and nonadaptive fusion baseline achieving improvement of up to 0.936 in Macro-F1 for family classification and reducing calibration error. Over 100 epochs, the agentic feedback loop displays a stable monotonic convergence leading to over +0.75 absolute improvement in terms of agent quality and a final composite score of around 0.88 without fine tuning of the language models. Zeroday ransomware detection remains family dependent on polymorphism and modality disruptions. Confidence aware abstention enables reliable real world deployment by favoring conservativeand trustworthy decisions over forced classification. The findings indicate that proposed approach provides a practical andeffective path toward improving real world ransomware defense systems. --- ### Improving Diffusion Language Model Decoding through Joint Search in Generation Order and Token Space Authors: Yangyi Shen, Tianjian Feng, Jiaqi Han, Wen Wang, Tianlang Chen, Chunhua Shen, Jure Leskovec, Stefano Ermon Published: 2026-01-28 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.20339v2 Diffusion Language Models (DLMs) offer order-agnostic generation that can explore many possible decoding trajectories. However, current decoding methods commit to a single trajectory, limiting exploration in trajectory space. We introduce Order-Token Search to explore this space through jointly searching over generation order and token values. Its core is a likelihood estimator that scores denoising actions, enabling stable pruning and efficient exploration of diverse trajectories. Across mathematical reasoning and coding benchmarks, Order-Token Search consistently outperforms baselines on GSM8K, MATH500, Countdown, and HumanEval (3.1%, 3.8%, 7.9%, and 6.8% absolute over backbone), matching or surpassing diffu-GRPO post-trained d1-LLaDA. Our work establishes joint search as a key component for advancing decoding in DLMs. --- ### Are Whitepaper Claims Reflected in Market Structure? A Contamination-Aware Pipeline and a Power-Limited Null Authors: Murad Farzulla Published: 2026-01-28 Categories: q-fin.CP, cs.LG arXiv: https://arxiv.org/abs/2601.20336v7 Do the functional narratives in cryptocurrency whitepapers correspond to their tokens' market behaviour? We compare ten-category topical-emphasis profiles for 43 screened documents with seven market statistics calculated from 2023--2024 exchange data. The primary specification reconstructs USD notional turnover from hourly bars. Dimension-matched Procrustes congruence is $φ=0.280$ (permutation $p=0.507$), slightly below its permutation-null mean of $0.284$; the zero-padded statistic gives the same non-detection. A four-leg comparison separates document replacement from changes in the assets included. Replacing documents on the 34 common assets changes padded congruence by $-0.014$ under USD turnover and $-0.009$ under base-token volume. Entity rankings and threshold crossings depend on both composition and specification, so an earlier contamination-only attribution is withdrawn. The documents are not a verified historical corpus: at least two postdate the market window. Excluding these documents, or excluding all seven assets with shorter histories, does not produce a significant alignment. Fresh numerical simulations distinguish injected signal from fitted congruence and compare noise restricted to the market subspace with noise throughout the text space. At the lowest classifier-agreement scenario, detection remains below $43\%$ even at the largest injected signal. These are conditional checks of the alignment stage, not validation of the text instrument or exclusion bounds on economic effects. The contribution is an auditable non-detection and a specification-sensitive corpus diagnosis, with the inferential limits made explicit. --- ### MobileBench-OL: A Comprehensive Chinese Benchmark for Evaluating Mobile GUI Agents in Real-World Environment Authors: Qinzhuo Wu, Zhizhuo Yang, Hanhao Li, Pengzhi Gao, Wei Liu, Jian Luan Published: 2026-01-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.20335v2 Recent advances in mobile Graphical User Interface (GUI) agents highlight the growing need for comprehensive evaluation benchmarks. While new online benchmarks offer more realistic testing than offline ones, they tend to focus on the agents' task instruction-following ability while neglecting their reasoning and exploration ability. Moreover, these benchmarks do not consider the random noise in real-world mobile environments. This leads to a gap between benchmarks and real-world environments. To addressing these limitations, we propose MobileBench-OL, an online benchmark with 1080 tasks from 80 Chinese apps. It measures task execution, complex reasoning, and noise robustness of agents by including 5 subsets, which set multiple evaluation dimensions. We also provide an auto-eval framework with a reset mechanism, enabling stable and repeatable real-world benchmarking. Evaluating 12 leading GUI agents on MobileBench-OL shows significant room for improvement to meet real-world requirements. Human evaluation further confirms that MobileBench-OL can reliably measure the performance of leading GUI agents in real environments. Our data and code will be released upon acceptance. --- ### Demonstration-Free Robotic Control via LLM Agents Authors: Brian Y. Tsui, Alan Y. Fang, Tiffany J. Hwu Published: 2026-01-28 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.20334v2 Robotic manipulation has increasingly adopted vision-language-action (VLA) models, which achieve strong performance but typically require task-specific demonstrations and fine-tuning, and often generalize poorly under domain shift. We investigate whether general-purpose large language model (LLM) agent frameworks, originally developed for software engineering, can serve as an alternative control paradigm for embodied manipulation. We introduce FAEA (Frontier Agent as Embodied Agent), which applies an LLM agent framework directly to embodied manipulation without modification. Using the same iterative reasoning that enables software agents to debug code, FAEA enables embodied agents to reason through manipulation strategies. We evaluate an unmodified frontier agent, Claude Agent SDK, across the LIBERO, ManiSkill3, and MetaWorld benchmarks. With privileged environment state access, FAEA achieves success rates of 84.9%, 85.7%, and 96%, respectively. This level of task success approaches that of VLA models trained with less than 100 demonstrations per task, without requiring demonstrations or fine-tuning. With one round of human feedback as an optional optimization, performance increases to 88.2% on LIBERO. This demonstration-free capability has immediate practical value: FAEA can autonomously explore novel scenarios in simulation and generate successful trajectories for training data augmentation in embodied learning. Our results indicate that general-purpose agents are sufficient for a class of manipulation tasks dominated by deliberative, task-level planning. This opens a path for robotics systems to leverage actively maintained agent infrastructure and benefit directly from ongoing advances in frontier models. Code is available at https://github.com/robiemusketeer/faea-sim --- ### Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chaining Authors: Ali Zia, Usman Ali, Umer Ramzan, Abdul Rehman, Abdelwahed Khamis, Wei Xiang Published: 2026-01-28 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.20333v1 Deep topological data analysis (TDA) offers a principled framework for capturing structural invariants such as connectivity and cycles that persist across scales, making it a natural fit for anomaly segmentation (AS). Unlike thresholdbased binarisation, which produces brittle masks under distribution shift, TDA allows anomalies to be characterised as disruptions to global structure rather than local fluctuations. We introduce TopoOT, a topology-aware optimal transport (OT) framework that integrates multi-filtration persistence diagrams (PDs) with test-time adaptation (TTA). Our key innovation is Optimal Transport Chaining, which sequentially aligns PDs across thresholds and filtrations, yielding geodesic stability scores that identify features consistently preserved across scales. These stabilityaware pseudo-labels supervise a lightweight head trained online with OT-consistency and contrastive objectives, ensuring robust adaptation under domain shift. Across standard 2D and 3D anomaly detection benchmarks, TopoOT achieves state-of-the-art performance, outperforming the most competitive methods by up to +24.1% mean F1 on 2D datasets and +10.2% on 3D AS benchmarks. --- ### Window-Diffusion: Accelerating Diffusion Language Model Inference with Windowed Token Pruning and Caching Authors: Fengrui Zuo, Zhiwei Ke, Yiming Liu, Wenqi Lou, Chao Wang, Xuehai Zhou Published: 2026-01-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.20332v3 Diffusion language models (DLMs) generate text through iterative denoising, but inference requires full-sequence attention at every iteration, resulting in substantial redundant computation on masked tokens. Block-wise diffusion can reduce this cost, yet it typically relies on retraining and constrained update orders, limiting its direct applicability to pretrained DLMs. Our token-level analysis reveals pronounced structural locality in DLM inference. Decoding is driven by a small set of prefix-localized active tokens; the influence of distant undecoded context diminishes rapidly, and decoded tokens exhibit stage-wise temporal stability, enabling reuse of intermediate representations except for a brief post-decode transient. Motivated by these observations, we propose \textbf{\placeholder}\footnote{The source code is available at https://github.com/vhicrgit/Window-Diffusion.}, a window-based token pruning and caching method for inference. We maintain a local computation window that slides rightward as denoising progresses, and partition undecoded tokens into: (i) \textit{active tokens} that are computed online, (ii) \textit{buffer tokens} whose KV states are cached and periodically refreshed, and (iii) \textit{far-field tokens} that are pruned outside the window. Computation is restricted to active and buffer tokens within the window, while far-field tokens are omitted at each stage. Experiments on LLaDA and Dream show that, under matched compute budgets, our method achieves up to $99\times$ inference speedup while largely preserving generation performance. --- ### GVGS: Gaussian Visibility-Aware Multi-View Geometry for Accurate Surface Reconstruction Authors: Mai Su, Qihan Yu, Zhongtao Wang, Yilong Li, Chengwei Pan, Yisong Chen, Guoping Wang, Fei Zhu Published: 2026-01-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.20331v3 3D Gaussian Splatting (3DGS) enables efficient rendering, yet accurate surface reconstruction remains challenging due to unreliable geometric supervision. Existing approaches predominantly rely on depth-based reprojection to infer visibility and enforce multi-view consistency, leading to a fundamental circular dependency: visibility estimation requires accurate depth, while depth supervision itself is conditioned on visibility. In this work, we revisit multi-view geometric supervision from the perspective of visibility modeling. Instead of inferring visibility from pixel-wise depth consistency, we explicitly model visibility at the level of Gaussian primitives. We introduce a Gaussian visibility-aware multi-view geometric consistency (GVMV) formulation, which aggregates cross-view visibility of shared Gaussians to construct reliable supervision over co-visible regions. To further incorporate monocular priors, we propose a progressive quadtree-calibrated depth alignment (QDC) strategy that performs block-wise affine calibration under visibility-aware guidance, effectively mitigating scale ambiguity while preserving local geometric structures. Extensive experiments on DTU and Tanks and Temples demonstrate that our method consistently improves reconstruction accuracy over prior Gaussian-based approaches. Our code is fully open-sourced and available at an anonymous repository: https://github.com/GVGScode/GVGS. --- ### PsychePass: Calibrating LLM Therapeutic Competence via Trajectory-Anchored Tournaments Authors: Zhuang Chen, Dazhen Wan, Zhangkai Zheng, Guanqun Bi, Xiyao Xiao, Binghang Li, Minlie Huang Published: 2026-01-28 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.20330v1 While large language models show promise in mental healthcare, evaluating their therapeutic competence remains challenging due to the unstructured and longitudinal nature of counseling. We argue that current evaluation paradigms suffer from an unanchored defect, leading to two forms of instability: process drift, where unsteered client simulation wanders away from specific counseling goals, and standard drift, where static pointwise scoring lacks the stability for reliable judgment. To address this, we introduce Ps, a unified framework that calibrates the therapeutic competence of LLMs via trajectory-anchored tournaments. We first anchor the interaction trajectory in simulation, where clients precisely control the fluid consultation process to probe multifaceted capabilities. We then anchor the battle trajectory in judgments through an efficient Swiss-system tournament, utilizing dynamic pairwise battles to yield robust Elo ratings. Beyond ranking, we demonstrate that tournament trajectories can be transformed into credible reward signals, enabling on-policy reinforcement learning to enhance LLMs' performance. Extensive experiments validate the effectiveness of PsychePass and its strong consistency with human expert judgments. --- ### CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria Authors: Xinyu Hu, Yancheng He, Weixun Wang, Tao Feng, Li Lin, Jiashun Liu, Wenbo Su, Bo Zheng, Xiaojun Wan Published: 2026-01-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.20327v2 Automatic evaluation is crucial yet challenging for open-ended natural language generation, especially when rule-based metrics are infeasible. Compared with traditional methods, the recent LLM-as-a-Judge paradigms enable better and more flexible evaluation, and show promise as generative reward models for reinforcement learning. However, prior work has revealed a notable gap between their seemingly impressive benchmark performance and actual effectiveness in RL practice. We attribute this issue to some limitations in existing studies, including the dominance of pairwise evaluation and inadequate optimization of evaluation criteria. Therefore, we propose CE-RM-4B, a pointwise generative reward model trained with a dedicated two-stage rollout method, and adopting unified query-based criteria. Using only about 5.7K high-quality data curated from the open-source preference dataset, our CE-RM-4B achieves superior performance on diverse reward model benchmarks, especially in Best-of-N scenarios, and delivers more effective improvements in downstream RL practice. --- ### Beyond Speedup -- Utilizing KV Cache for Sampling and Reasoning Authors: Zeyu Xing, Xing Li, Hui-Ling Zhen, Mingxuan Yuan, Sinno Jialin Pan Published: 2026-01-28 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.20326v1 KV caches, typically used only to speed up autoregressive decoding, encode contextual information that can be reused for downstream tasks at no extra cost. We propose treating the KV cache as a lightweight representation, eliminating the need to recompute or store full hidden states. Despite being weaker than dedicated embeddings, KV-derived representations are shown to be sufficient for two key applications: \textbf{(i) Chain-of-Embedding}, where they achieve competitive or superior performance on Llama-3.1-8B-Instruct and Qwen2-7B-Instruct; and \textbf{(ii) Fast/Slow Thinking Switching}, where they enable adaptive reasoning on Qwen3-8B and DeepSeek-R1-Distil-Qwen-14B, reducing token generation by up to $5.7\times$ with minimal accuracy loss. Our findings establish KV caches as a free, effective substrate for sampling and reasoning, opening new directions for representation reuse in LLM inference. Code: https://github.com/cmd2001/ICLR2026_KV-Embedding. --- ### UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion Authors: Lulu Xue, Shengshan Hu, Wei Lu, Ziqi Zhou, Yufei Song, Jianhong Cheng, Minghui Li, Yanjun Zhang, Leo Yu Zhang Published: 2026-01-28 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2601.20325v1 Machine unlearning is an emerging technique that aims to remove the influence of specific data from trained models, thereby enhancing privacy protection. However, recent research has uncovered critical privacy vulnerabilities, showing that adversaries can exploit unlearning inversion to reconstruct data that was intended to be erased. Despite the severity of this threat, dedicated defenses remain lacking. To address this gap, we propose UnlearnShield, the first defense specifically tailored to counter unlearning inversion. UnlearnShield introduces directional perturbations in the cosine representation space and regulates them through a constraint module to jointly preserve model accuracy and forgetting efficacy, thereby reducing inversion risk while maintaining utility. Experiments demonstrate that it achieves a good trade-off among privacy protection, accuracy, and forgetting. --- ### ECG-Agent: On-Device Tool-Calling Agent for ECG Multi-Turn Dialogue Authors: Hyunseung Chung, Jungwoo Oh, Daeun Kyung, Jiho Kim, Yeonsu Kwon, Min-Gyu Kim, Edward Choi Published: 2026-01-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.20323v1 Recent advances in Multimodal Large Language Models have rapidly expanded to electrocardiograms, focusing on classification, report generation, and single-turn QA tasks. However, these models fall short in real-world scenarios, lacking multi-turn conversational ability, on-device efficiency, and precise understanding of ECG measurements such as the PQRST intervals. To address these limitations, we introduce ECG-Agent, the first LLM-based tool-calling agent for multi-turn ECG dialogue. To facilitate its development and evaluation, we also present ECG-Multi-Turn-Dialogue (ECG-MTD) dataset, a collection of realistic user-assistant multi-turn dialogues for diverse ECG lead configurations. We develop ECG-Agents in various sizes, from on-device capable to larger agents. Experimental results show that ECG-Agents outperform baseline ECG-LLMs in response accuracy. Furthermore, on-device agents achieve comparable performance to larger agents in various evaluations that assess response accuracy, tool-calling ability, and hallucinations, demonstrating their viability for real-world applications. --- ### CPiRi: Channel Permutation-Invariant Relational Interaction for Multivariate Time Series Forecasting Authors: Jiyuan Xu, Wenyu Zhang, Xin Jing, Shuai Chen, Shuai Zhang, Jiahao Nie Published: 2026-01-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.20318v2 Current methods for multivariate time series forecasting can be classified into channel-dependent and channel-independent models. Channel-dependent models learn cross-channel features but often overfit the channel ordering, which hampers adaptation when channels are added or reordered. Channel-independent models treat each channel in isolation to increase flexibility, yet this neglects inter-channel dependencies and limits performance. To address these limitations, we propose \textbf{CPiRi}, a \textbf{channel permutation invariant (CPI)} framework that infers cross-channel structure from data rather than memorizing a fixed ordering, enabling deployment in settings with structural and distributional co-drift without retraining. CPiRi couples \textbf{spatio-temporal decoupling architecture} with \textbf{permutation-invariant regularization training strategy}: a frozen pretrained temporal encoder extracts high-quality temporal features, a lightweight spatial module learns content-driven inter-channel relations, while a channel shuffling strategy enforces CPI during training. We further \textbf{ground CPiRi in theory} by analyzing permutation equivariance in multivariate time series forecasting. Experiments on multiple benchmarks show state-of-the-art results. CPiRi remains stable when channel orders are shuffled and exhibits strong \textbf{inductive generalization} to unseen channels even when trained on \textbf{only half} of the channels, while maintaining \textbf{practical efficiency} on large-scale datasets. The source code is released at https://github.com/JasonStraka/CPiRi. --- ### Less is More: Benchmarking LLM Based Recommendation Agents Authors: Kargi Chauhan, Mahalakshmi Venkateswarlu Published: 2026-01-28 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2601.20316v1 Large Language Models (LLMs) are increasingly deployed for personalized product recommendations, with practitioners commonly assuming that longer user purchase histories lead to better predictions. We challenge this assumption through a systematic benchmark of four state of the art LLMs GPT-4o-mini, DeepSeek-V3, Qwen2.5-72B, and Gemini 2.5 Flash across context lengths ranging from 5 to 50 items using the REGEN dataset. Surprisingly, our experiments with 50 users in a within subject design reveal no significant quality improvement with increased context length. Quality scores remain flat across all conditions (0.17--0.23). Our findings have significant practical implications: practitioners can reduce inference costs by approximately 88\% by using context (5--10 items) instead of longer histories (50 items), without sacrificing recommendation quality. We also analyze latency patterns across providers and find model specific behaviors that inform deployment decisions. This work challenges the existing ``more context is better'' paradigm and provides actionable guidelines for cost effective LLM based recommendation systems. --- ### SAPO: Self-Adaptive Process Optimization Makes Small Reasoners Stronger Authors: Kaiyuan Chen, Guangmin Zheng, Jin Wang, Xiaobing Zhou, Xuejie Zhang Published: 2026-01-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.20312v2 Existing self-evolution methods overlook the influence of fine-grained reasoning steps, which leads to the reasoner-verifier gap. The computational inefficiency of Monte Carlo (MC) process supervision further exacerbates the difficulty in mitigating the gap. Motivated by the Error-Related Negativity (ERN), which the reasoner can localize error following incorrect decisions, guiding rapid adjustments, we propose a Self-Adaptive Process Optimization (SAPO) method for self-improvement in Small Language Models (SLMs). SAPO adaptively and efficiently introduces process supervision signals by actively minimizing the reasoner-verifier gap rather than relying on inefficient MC estimations. Extensive experiments demonstrate that the proposed method outperforms most existing self-evolution methods on two challenging task types: mathematics and code. Additionally, to further investigate SAPO's impact on verifier performance, this work introduces two new benchmarks for process reward models in both mathematical and coding tasks. --- ### DiagLink: A Dual-User Diagnostic Assistance System by Synergizing Experts with LLMs and Knowledge Graphs Authors: Zihan Zhou, Yinan Liu, Yuyang Xie, Bin Wang, Xiaochun Yang, Zezheng Feng Published: 2026-01-28 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.20311v1 The global shortage and uneven distribution of medical expertise continue to hinder equitable access to accurate diagnostic care. While existing intelligent diagnostic system have shown promise, most struggle with dual-user interaction, and dynamic knowledge integration -- limiting their real-world applicability. In this study, we present DiagLink, a dual-user diagnostic assistance system that synergizes large language models (LLMs), knowledge graphs (KGs), and medical experts to support both patients and physicians. DiagLink uses guided dialogues to elicit patient histories, leverages LLMs and KGs for collaborative reasoning, and incorporates physician oversight for continuous knowledge validation and evolution. The system provides a role-adaptive interface, dynamically visualized history, and unified multi-source evidence to improve both trust and usability. We evaluate DiagLink through user study, use cases and expert interviews, demonstrating its effectiveness in improving user satisfaction and diagnostic efficiency, while offering insights for the design of future AI-assisted diagnostic systems. --- ### SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks Authors: Xin Zhang, Zijin Yang, Kejiang Chen, Linfeng Ma, Weiming Zhang, Nenghai Yu Published: 2026-01-28 Categories: cs.CR, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.20310v1 Latent-based watermarks, integrated into the generation process of latent diffusion models (LDMs), simplify detection and attribution of generated images. However, recent black-box forgery attacks, where an attacker needs at least one watermarked image and black-box access to the provider's model, can embed the provider's watermark into images not produced by the provider, posing outsized risk to provenance and trust. We propose SemBind, the first defense framework for latent-based watermarks that resists black-box forgery by binding latent signals to image semantics via a learned semantic masker. Trained with contrastive learning, the masker yields near-invariant codes for the same prompt and near-orthogonal codes across prompts; these codes are reshaped and permuted to modulate the target latent before any standard latent-based watermark. SemBind is generally compatible with existing latent-based watermarking schemes and keeps image quality essentially unchanged, while a simple mask-ratio parameter offers a tunable trade-off between anti-forgery strength and robustness. Across four mainstream latent-based watermark methods, our SemBind-enabled anti-forgery variants markedly reduce false acceptance under black-box forgery while providing a controllable robustness-security balance. --- ### SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips Authors: Jiahuan Yu, Mingtao Hu, Zichao Lin, Minjia Zhang Published: 2026-01-28 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.20309v2 Large Language Model (LLM) serving faces a fundamental tension between stringent latency Service Level Objectives (SLOs) and limited GPU memory capacity. When high request rates exhaust the KV cache budget, existing LLM inference systems often suffer severe head-of-line (HOL) blocking. While prior work explored PCIe-based offloading, these approaches cannot sustain responsiveness under high request rates, often failing to meet tight Time-To-First-Token (TTFT) and Time-Between-Tokens (TBT) SLOs. We present SuperInfer, a high-performance LLM inference system designed for emerging Superchips (e.g., NVIDIA GH200) with tightly coupled GPU-CPU architecture via NVLink-C2C. SuperInfer introduces RotaSched, the first proactive, SLO-aware rotary scheduler that rotates requests to maintain responsiveness on Superchips, and DuplexKV, an optimized rotation engine that enables full-duplex transfer over NVLink-C2C. Evaluations on GH200 using various models and datasets show that SuperInfer improves TTFT SLO attainment rates by up to 74.7% while maintaining comparable TBT and throughput compared to state-of-the-art systems, demonstrating that SLO-aware scheduling and memory co-design unlocks the full potential of Superchips for responsive LLM serving. Code is available in https://github.com/Supercomputing-System-AI-Lab/SuperInfer. --- ### Taming Real-World Space-Time Video Super-Resolution with One-Step Diffusion Authors: Shuoyan Wei, Feng Li, Chen Zhou, Runmin Cong, Yao Zhao, Huihui Bai Published: 2026-01-28 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2601.20308v2 Diffusion models have demonstrated exceptional success in video super-resolution (VSR), exhibiting powerful capabilities for generating fine-grained details. However, their potential for space-time video super-resolution (STVSR), which necessitates not only recovering realistic high-resolution visual content but also improving the frame rate with coherent temporal dynamics, remains largely underexplored. Moreover, existing STVSR methods predominantly address spatiotemporal upsampling under simple degradation assumptions, thus failing in real-world scenarios with complex unknown degradations. To address these challenges, we propose OSDEnhancer, the first framework that achieves robust STVSR in one-step diffusion. OSDEnhancer begins with a linear initialization to establish essential spatiotemporal structures and adapt the model for one-step reconstruction. It then applies a divide-and-conquer strategy, introducing the temporal coherence (TC) and texture enrichment (TE) LoRAs that progressively specialize in inter-frame dynamics modeling and fine-grained texture recovery, respectively, while collaborating during inference for enhanced overall performance. A bidirectional VAE decoder employs deformable recurrent blocks to leverage the multi-scale structure of the vanilla VAE, enhancing latent-to-pixel reconstruction through joint multi-scale deformable aggregation and inter-frame feature propagation. Experimental results demonstrate that the proposed method attains state-of-the-art performance with superior generalization in real-world scenarios. The code is available at https://github.com/W-Shuoyan/OSDEnhancer. --- ### Delayed Feedback Modeling for Post-Click Gross Merchandise Volume Prediction: Benchmark, Insights and Approaches Authors: Xinyu Li, Sishuo Chen, Guipeng Xv, Li Zhang, Mingxuan Luo, Zhangming Chan, Xiang-Rong Sheng, Han Zhu, Jian Xu, Chen Lin Published: 2026-01-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.20307v1 The prediction objectives of online advertisement ranking models are evolving from probabilistic metrics like conversion rate (CVR) to numerical business metrics like post-click gross merchandise volume (GMV). Unlike the well-studied delayed feedback problem in CVR prediction, delayed feedback modeling for GMV prediction remains unexplored and poses greater challenges, as GMV is a continuous target, and a single click can lead to multiple purchases that cumulatively form the label. To bridge the research gap, we establish TRACE, a GMV prediction benchmark containing complete transaction sequences rising from each user click, which supports delayed feedback modeling in an online streaming manner. Our analysis and exploratory experiments on TRACE reveal two key insights: (1) the rapid evolution of the GMV label distribution necessitates modeling delayed feedback under online streaming training; (2) the label distribution of repurchase samples substantially differs from that of single-purchase samples, highlighting the need for separate modeling. Motivated by these findings, we propose RepurchasE-Aware Dual-branch prEdictoR (READER), a novel GMV modeling paradigm that selectively activates expert parameters according to repurchase predictions produced by a router. Moreover, READER dynamically calibrates the regression target to mitigate under-estimation caused by incomplete labels. Experimental results show that READER yields superior performance on TRACE over baselines, achieving a 2.19% improvement in terms of accuracy. We believe that our study will open up a new avenue for studying online delayed feedback modeling for GMV prediction, and our TRACE benchmark with the gathered insights will facilitate future research and application in this promising direction. Our code and dataset are available at https://github.com/alimama-tech/OnlineGMV . --- ### TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration Authors: Yanjie Tu, Qingsen Yan, Axi Niu, Jiacong Tang Published: 2026-01-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.20306v2 All-in-one image restoration aims to address diverse degradation types using a single unified model. Existing methods typically rely on degradation priors to guide restoration, yet often struggle to reconstruct content in severely degraded regions. Although recent works leverage semantic information to facilitate content generation, integrating it into the shallow layers of diffusion models often disrupts spatial structures (\emph{e.g.}, blurring artifacts). To address this issue, we propose a Triple-Prior Guided Diffusion (TPGDiff) network for unified image restoration. TPGDiff incorporates degradation priors throughout the diffusion trajectory, while introducing structural priors into shallow layers and semantic priors into deep layers, enabling hierarchical and complementary prior guidance for image reconstruction. Specifically, we leverage multi-source structural cues as structural priors to capture fine-grained details and guide shallow layers representations. To complement this design, we further develop a distillation-driven semantic extractor that yields robust semantic priors, ensuring reliable high-level guidance at deep layers even under severe degradations. Furthermore, a degradation extractor is employed to learn degradation-aware priors, enabling stage-adaptive control of the diffusion process across all timesteps. Extensive experiments on both single- and multi-degradation benchmarks demonstrate that TPGDiff achieves superior performance and generalization across diverse restoration scenarios. Our project page is: https://leoyjtu.github.io/tpgdiff-project. ---