# Research Papers — 2025-12 · bundle page 79 of 175 > Full-text markdown of papers #3901–3950 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/79 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/78.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/80.md) ### Optimizing Multi-Tier Supply Chain Ordering with a Hybrid Liquid Neural Network and Extreme Gradient Boosting Model Authors: Chunan Tong Published: 2025-12-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.14112v1 Supply chain management (SCM) faces significant challenges like demand fluctuations and the bullwhip effect. Traditional methods and even state-of-the-art LLMs struggle with benchmarks like the Vending Machine Test, failing to handle SCM's complex continuous time-series data. While ML approaches like LSTM and XGBoost offer solutions, they are often limited by computational inefficiency. Liquid Neural Networks (LNN), known for their adaptability and efficiency in robotics, remain untapped in SCM. This study proposes a hybrid LNN+XGBoost model for multi-tier supply chains. By combining LNN's dynamic feature extraction with XGBoost's global optimization, the model aims to minimize the bullwhip effect and increase profitability. This innovative approach addresses the need for efficiency and adaptability, filling a critical gap in intelligent SCM. --- ### HydroGEM: A Self Supervised Zero Shot Hybrid TCN Transformer Foundation Model for Continental Scale Streamflow Quality Control Authors: Ijaz Ul Haq, Byung Suk Lee, Julia N. Perdrial, David Baude Published: 2025-12-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.14106v3 Advances in sensor networks have enabled real-time stream discharge monitoring, yet persistent sensor malfunctions limit data utility. Manual quality control by expert hydrologists cannot scale with networks generating millions of measurements annually. We introduce HydroGEM, a foundation model for continental-scale streamflow quality control designed to support human expertise. HydroGEM uses self-supervised pretraining on 6.03 million clean sequences from 3,724 USGS stations to learn general hydrological representations, followed by fine-tuning with synthetic anomalies for detection and reconstruction. A hybrid TCN-Transformer architecture (14.2M parameters) captures both local and long-range temporal dependencies, while hierarchical normalization handles six orders of magnitude in discharge. On held-out observations from 799 stations with 18 synthetic anomaly types grounded in USGS standards, HydroGEM achieves F1=0.792 for detection and 68.7% reconstruction error reduction, outperforming the strongest baseline by 36.3%. For cross-national validation on 100 Environment and Climate Change Canada stations using tolerant evaluation with a plus or minus 24-hour buffer, HydroGEM achieves Tolerant F1=0.70 with 90.1% segment-level event detection, demonstrating cross-national generalization. The model maintains consistent detection across correction magnitudes and aligns with operational seasonal patterns, with peak flagging during winter ice-affected periods matching hydrologists' correction behavior. Architectural separation between simplified training anomalies and complex test anomalies confirms that performance reflects learned hydrometric principles rather than pattern memorization. --- ### Neurosymbolic Inference On Foundation Models For Remote Sensing Text-to-image Retrieval With Complex Queries Authors: Emanuele Mezzi, Gertjan Burghouts, Maarten Kruithof Published: 2025-12-16 Categories: cs.CV, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2512.14102v1 Text-to-image retrieval in remote sensing (RS) has advanced rapidly with the rise of large vision-language models (LVLMs) tailored for aerial and satellite imagery, culminating in remote sensing large vision-language models (RS-LVLMS). However, limited explainability and poor handling of complex spatial relations remain key challenges for real-world use. To address these issues, we introduce RUNE (Reasoning Using Neurosymbolic Entities), an approach that combines Large Language Models (LLMs) with neurosymbolic AI to retrieve images by reasoning over the compatibility between detected entities and First-Order Logic (FOL) expressions derived from text queries. Unlike RS-LVLMs that rely on implicit joint embeddings, RUNE performs explicit reasoning, enhancing performance and interpretability. For scalability, we propose a logic decomposition strategy that operates on conditioned subsets of detected entities, guaranteeing shorter execution time compared to neural approaches. Rather than using foundation models for end-to-end retrieval, we leverage them only to generate FOL expressions, delegating reasoning to a neurosymbolic inference module. For evaluation we repurpose the DOTA dataset, originally designed for object detection, by augmenting it with more complex queries than in existing benchmarks. We show the LLM's effectiveness in text-to-logic translation and compare RUNE with state-of-the-art RS-LVLMs, demonstrating superior performance. We introduce two metrics, Retrieval Robustness to Query Complexity (RRQC) and Retrieval Robustness to Image Uncertainty (RRIU), which evaluate performance relative to query complexity and image uncertainty. RUNE outperforms joint-embedding models in complex RS retrieval tasks, offering gains in performance, robustness, and explainability. We show RUNE's potential for real-world RS applications through a use case on post-flood satellite image retrieval. --- ### A First-Order Logic-Based Alternative to Reward Models in RLHF Authors: Chunjin Jian, Xinhua Zhu Published: 2025-12-16 Categories: cs.LG, cs.LO arXiv: https://arxiv.org/abs/2512.14100v1 Reinforcement Learning from Human Feedback (RLHF) plays a crucial role in aligning large language models (LLMs) with human values and preferences. However, the quality and stability of the trained reward model largely determine the final alignment performance. Existing approaches such as Proximal Policy Optimization (PPO) rely heavily on reward models to guide LLMs toward human-aligned behaviors. In this work, we propose a logic-similarity-based reward mechanism as an alternative to conventional reward modeling. Instead of relying on heuristic reward estimation, our method leverages formal logical consistency to steer model alignment with human preferences. Since real-world questions can be interpreted from multiple perspectives, to ensure that logic-based reinforcement learning does not cause model collapse, we introduce S-GRPO, a supervised variant of the GRPO framework. S-GRPO incorporates an additional supervised component and jointly optimizes the generation term, KL-divergence regularization, and label-based objective during training. Experimental results demonstrate that S-GRPO consistently outperforms standard supervised fine-tuning (SFT) in both performance and robustness. Furthermore, it extends existing preference-learning frameworks such as GRPO and DPO, offering a more flexible and task-adaptive approach to alignment training. Our code is available at https://github.com/ChunjinJiang/sgrpo. --- ### ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models Authors: Ruishu Zhu, Zhihao Huang, Jiacheng Sun, Ping Luo, Hongyuan Zhang, Xuelong Li Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14099v3 Motivated by discrete diffusion's success in language-vision modeling, we explore its potential for multi-view generation, a task dominated by continuous approaches. We introduce ViewMask-1-to-3, formulating multi-view generation as a discrete sequence modeling problem where each viewpoint is represented as visual tokens from MAGVIT-v2. Through discrete diffusion via masked token prediction, our approach enables progressive multi-view generation via iterative token unmasking, unifying language and vision in a shared token space. Importantly, simple random masking combined with self-attention naturally encourages cross-view consistency without specialized architectures or 3D geometric priors. Our method outperforms the baseline on the GSO and 3D-FUTURE benchmarks, ranking first on average across standard image metrics, and achieving a 10.6% higher IoU than continuous diffusion models on 3D-FUTURE. Furthermore, the proposed framework can be naturally extended to support text-to-image generation and multimodal understanding, highlighting its potential toward a more unified paradigm for multimodal understanding and generation. --- ### Cornfigurator: Automated Planning for Any-to-Any Multimodal Model Serving Authors: Jeff J. Ma, Jae-Won Chung, Jisang Ahn, Yizhuo Liang, Runyu Lu, Akshay Jajoo, Myungjin Lee, Mosharaf Chowdhury Published: 2025-12-16 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2512.14098v3 Any-to-Any models are an emerging class of multimodal models that accept combinations of text and multimodal data as input and generate them as output, introducing heterogeneous computation paths and component scaling characteristics. There are existing mechanisms for deploying Any-to-Any models--or special cases of them--for inference serving, but they either require manual effort and expertise to tune, or do not generalize to generic Any-to-Any models. We present Cornfigurator, the first deployment planner for generic Any-to-Any model inference serving. The goal of Cornfigurator is to maximize the overall goodput of serving the model, defined as the throughput of requests meeting their latency targets. To do so, based on model and workload characteristics, Cornfigurator explores the full spectrum of deployment strategies, from colocation to disaggregation and mixing different strategies. Cornfigurator performs coarse-to-fine statistical evaluation to efficiently navigate the large space of candidate plans. Plans generated by Cornfigurator either match or deliver 1.12$\times$-6.32$\times$ higher goodput compared to existing systems and expert-tuned deployment plans. --- ### RSTR: Reducing SpatioTemporal Redundancy in Diffusion Transformers Authors: Ruitong Sun, Tianze Yang, Wei Niu, Jin Sun Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14096v2 Diffusion Transformers (DiTs) have achieved remarkable success in image generation, yet their deployment is hindered by high computational costs. We identify two sources of redundancy. First, temporal redundancy: Classifier-Free Guidance (CFG) applies costly dual forward passes at every timestep, yet guidance matters only at specific steps, and variable scales at critical steps can compensate for skipping others. Second, spatial redundancy: under variable guidance, different transformer blocks exhibit heterogeneous sensitivity, yet uniform calibration across all blocks wastes computation while failing to address their varying requirements. We present RSTR, the first framework to jointly reduce spatiotemporal redundancy in diffusion transformers. Stage-1 addresses temporal redundancy through evolutionary search, discovering sparse guidance schedules with variable scales. Stage-2 addresses spatial redundancy through adaptive rank allocation, assigning calibration capacities to transformer regions based on their sensitivity. Experiments on DiT-XL/2, PixArt-$α$, FLUX, and state-of-the-art Qwen-Image demonstrate 50%-70% compute savings while maintaining or improving quality. On DiT-XL/2, RSTR achieves 57% savings with 15% FID improvement; on Qwen-Image, 3.43$\times$ speedup with preserved quality. --- ### AnchorHOI: Zero-shot Generation of 4D Human-Object Interaction via Anchor-based Prior Distillation Authors: Sisi Dai, Kai Xu Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14095v1 Despite significant progress in text-driven 4D human-object interaction (HOI) generation with supervised methods, the scalability remains limited by the scarcity of large-scale 4D HOI datasets. To overcome this, recent approaches attempt zero-shot 4D HOI generation with pre-trained image diffusion models. However, interaction cues are minimally distilled during the generation process, restricting their applicability across diverse scenarios. In this paper, we propose AnchorHOI, a novel framework that thoroughly exploits hybrid priors by incorporating video diffusion models beyond image diffusion models, advancing 4D HOI generation. Nevertheless, directly optimizing high-dimensional 4D HOI with such priors remains challenging, particularly for human pose and compositional motion. To address this challenge, AnchorHOI introduces an anchor-based prior distillation strategy, which constructs interaction-aware anchors and then leverages them to guide generation in a tractable two-step process. Specifically, two tailored anchors are designed for 4D HOI generation: anchor Neural Radiance Fields (NeRFs) for expressive interaction composition, and anchor keypoints for realistic motion synthesis. Extensive experiments demonstrate that AnchorHOI outperforms previous methods with superior diversity and generalization. --- ### Quality-Aware Framework for Video-Derived Respiratory Signals Authors: Nhi Nguyen, Constantino Álvarez Casado, Le Nguyen, Manuel Lage Cañellas, Miguel Bordallo López Published: 2025-12-16 Categories: cs.CV, eess.SP arXiv: https://arxiv.org/abs/2512.14093v1 Video-based respiratory rate (RR) estimation is often unreliable due to inconsistent signal quality across extraction methods. We present a predictive, quality-aware framework that integrates heterogeneous signal sources with dynamic assessment of reliability. Ten signals are extracted from facial remote photoplethysmography (rPPG), upper-body motion, and deep learning pipelines, and analyzed using four spectral estimators: Welch's method, Multiple Signal Classification (MUSIC), Fast Fourier Transform (FFT), and peak detection. Segment-level quality indices are then used to train machine learning models that predict accuracy or select the most reliable signal. This enables adaptive signal fusion and quality-based segment filtering. Experiments on three public datasets (OMuSense-23, COHFACE, MAHNOB-HCI) show that the proposed framework achieves lower RR estimation errors than individual methods in most cases, with performance gains depending on dataset characteristics. These findings highlight the potential of quality-driven predictive modeling to deliver scalable and generalizable video-based respiratory monitoring solutions. --- ### ProtoFlow: Interpretable and Robust Surgical Workflow Modeling with Learned Dynamic Scene Graph Prototypes Authors: Felix Holm, Ghazal Ghazaei, Nassir Navab Published: 2025-12-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.14092v1 Purpose: Detailed surgical recognition is critical for advancing AI-assisted surgery, yet progress is hampered by high annotation costs, data scarcity, and a lack of interpretable models. While scene graphs offer a structured abstraction of surgical events, their full potential remains untapped. In this work, we introduce ProtoFlow, a novel framework that learns dynamic scene graph prototypes to model complex surgical workflows in an interpretable and robust manner. Methods: ProtoFlow leverages a graph neural network (GNN) encoder-decoder architecture that combines self-supervised pretraining for rich representation learning with a prototype-based fine-tuning stage. This process discovers and refines core prototypes that encapsulate recurring, clinically meaningful patterns of surgical interaction, forming an explainable foundation for workflow analysis. Results: We evaluate our approach on the fine-grained CAT-SG dataset. ProtoFlow not only outperforms standard GNN baselines in overall accuracy but also demonstrates exceptional robustness in limited-data, few-shot scenarios, maintaining strong performance when trained on as few as one surgical video. Our qualitative analyses further show that the learned prototypes successfully identify distinct surgical sub-techniques and provide clear, interpretable insights into workflow deviations and rare complications. Conclusion: By uniting robust representation learning with inherent explainability, ProtoFlow represents a significant step toward developing more transparent, reliable, and data-efficient AI systems, accelerating their potential for clinical adoption in surgical training, real-time decision support, and workflow optimization. --- ### Arithmetic-Intensity-Aware Quantization Authors: Taig Singh, Shreshth Rajan, Nikhil Jain Published: 2025-12-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.14090v2 As modern neural networks become increasingly memory-bound, inference throughput is limited by DRAM bandwidth rather than compute. We present Arithmetic-Intensity-Aware Quantization (AIQ), a mixed precision quantization framework that chooses per-layer bit-widths to maximize arithmetic intensity (AI) while minimizing accuracy loss. AIQ is a post-training quantization method that uses search algorithms over per-layer quantization schemes to minimize a weighted loss over AI and accuracy. On ResNet-20/CIFAR-10, AIQ increases AI by ~50% over an FP32 baseline while keeping test accuracy within ~1 percentage point, and outperforming global uniform quantization schemes. On a memory-bound MobileNetV2 architecture, AIQ configurations give a 1.66x higher throughput than the FP32 baseline while keeping test accuracy within 1 percentage point. We also find that AIQ naturally quantizes larger layers more aggressively. --- ### GaussianPlant: Structure-aligned Gaussian Splatting for 3D Reconstruction of Plants Authors: Yang Yang, Risa Shinoda, Hiroaki Santo, Fumio Okura Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14087v1 We present a method for jointly recovering the appearance and internal structure of botanical plants from multi-view images based on 3D Gaussian Splatting (3DGS). While 3DGS exhibits robust reconstruction of scene appearance for novel-view synthesis, it lacks structural representations underlying those appearances (e.g., branching patterns of plants), which limits its applicability to tasks such as plant phenotyping. To achieve both high-fidelity appearance and structural reconstruction, we introduce GaussianPlant, a hierarchical 3DGS representation, which disentangles structure and appearance. Specifically, we employ structure primitives (StPs) to explicitly represent branch and leaf geometry, and appearance primitives (ApPs) to the plants' appearance using 3D Gaussians. StPs represent a simplified structure of the plant, i.e., modeling branches as cylinders and leaves as disks. To accurately distinguish the branches and leaves, StP's attributes (i.e., branches or leaves) are optimized in a self-organized manner. ApPs are bound to each StP to represent the appearance of branches or leaves as in conventional 3DGS. StPs and ApPs are jointly optimized using a re-rendering loss on the input multi-view images, as well as the gradient flow from ApP to StP using the binding correspondence information. We conduct experiments to qualitatively evaluate the reconstruction accuracy of both appearance and structure, as well as real-world experiments to qualitatively validate the practical performance. Experiments show that the GaussianPlant achieves both high-fidelity appearance reconstruction via ApPs and accurate structural reconstruction via StPs, enabling the extraction of branch structure and leaf instances. --- ### Derivative-Informed Fourier Neural Operator: Universal Approximation and Applications to PDE-Constrained Optimization Authors: Boyuan Yao, Dingcheng Luo, Lianghao Cao, Nikola Kovachki, Thomas O'Leary-Roseberry, Omar Ghattas Published: 2025-12-16 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2512.14086v2 We present approximation theories and efficient training methods for derivative-informed Fourier neural operators (DIFNOs) with applications to PDE-constrained optimization. A DIFNO is an FNO trained by minimizing its prediction error jointly on output and Fréchet derivative samples of a high-fidelity operator (e.g., a parametric PDE solution operator). As a result, a DIFNO can closely emulate not only the high-fidelity operator's response but also its sensitivities. To motivate the use of DIFNOs instead of conventional FNOs as surrogate models, we show that accurate surrogate-driven PDE-constrained optimization requires accurate surrogate Fréchet derivatives. Then, we establish (i) simultaneous universal approximation of continuously differentiable operators and their Fréchet derivatives by FNOs on compact sets, and (ii) universal approximation of continuously differentiable operators by FNOs in weighted Sobolev spaces with input measures that have unbounded supports. Our theoretical results certify the capability of FNOs for accurate derivative-informed operator learning and for the solution of PDE-constrained optimization problems. Furthermore, we develop efficient training schemes that leverage dimensionality reduction and multi-resolution techniques to significantly reduce memory and computational costs in Fréchet derivative learning. Numerical examples on nonlinear diffusion--reaction, Helmholtz, and Navier--Stokes equations demonstrate that DIFNOs are superior in sample complexity for operator learning and solving infinite-dimensional PDE-constrained inverse problems, achieving high accuracy at low training sample sizes. --- ### Multilingual and Continuous Backchannel Prediction: A Cross-lingual Study Authors: Koji Inoue, Mikey Elmers, Yahui Fu, Zi Haur Pang, Taiga Mori, Divesh Lala, Keiko Ochi, Tatsuya Kawahara Published: 2025-12-16 Categories: cs.CL, cs.HC, cs.SD arXiv: https://arxiv.org/abs/2512.14085v1 We present a multilingual, continuous backchannel prediction model for Japanese, English, and Chinese, and use it to investigate cross-linguistic timing behavior. The model is Transformer-based and operates at the frame level, jointly trained with auxiliary tasks on approximately 300 hours of dyadic conversations. Across all three languages, the multilingual model matches or surpasses monolingual baselines, indicating that it learns both language-universal cues and language-specific timing patterns. Zero-shot transfer with two-language training remains limited, underscoring substantive cross-lingual differences. Perturbation analyses reveal distinct cue usage: Japanese relies more on short-term linguistic information, whereas English and Chinese are more sensitive to silence duration and prosodic variation; multilingual training encourages shared yet adaptable representations and reduces overreliance on pitch in Chinese. A context-length study further shows that Japanese is relatively robust to shorter contexts, while Chinese benefits markedly from longer contexts. Finally, we integrate the trained model into a real-time processing software, demonstrating CPU-only inference. Together, these findings provide a unified model and empirical evidence for how backchannel timing differs across languages, informing the design of more natural, culturally-aware spoken dialogue systems. --- ### Scalable Frameworks for Real-World Audio-Visual Speech Recognition Authors: Sungnyun Kim Published: 2025-12-16 Categories: eess.AS, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.14083v1 The practical deployment of Audio-Visual Speech Recognition (AVSR) systems is fundamentally challenged by significant performance degradation in real-world environments, characterized by unpredictable acoustic noise and visual interference. This dissertation posits that a systematic, hierarchical approach is essential to overcome these challenges, achieving the robust scalability at the representation, architecture, and system levels. At the representation level, we investigate methods for building a unified model that learns audio-visual features inherently robust to diverse real-world corruptions, thereby enabling generalization to new environments without specialized modules. To address architectural scalability, we explore how to efficiently expand model capacity while ensuring the adaptive and reliable use of multimodal inputs, developing a framework that intelligently allocates computational resources based on the input characteristics. Finally, at the system level, we present methods to expand the system's functionality through modular integration with large-scale foundation models, leveraging their powerful cognitive and generative capabilities to maximize final recognition accuracy. By systematically providing solutions at each of these three levels, this dissertation aims to build a next-generation, robust, and scalable AVSR system with high reliability in real-world applications. --- ### A Unified Sparse Attention via Multi-Granularity Compression Authors: Siran Liu, Zane Cao, Yongchao He Published: 2025-12-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.14082v1 Efficient long-context understanding and reasoning are increasingly vital for large language model (LLM) applications such as multi-turn dialogue and program analysis. However, the core self-attention mechanism scales quadratically with sequence length, creating a fundamental computational bottleneck. Existing sparse attention methods alleviate this issue but face trade-offs: training-based methods are costly and cannot be directly applied as acceleration plugins for other models, while inference-time methods often compromise efficiency or cross-modal generality. To address these limitations, we present UniSparse, a unified mechanism that introduces the notion of composite tokens--compact representations that aggregate multi-granularity contextual information. Building on this abstraction, UniSparse dynamically constructs sparse attention through multi-granularity compression and block-level selection, enabling efficient and hardware-friendly execution on GPU. Across multiple modalities and tasks ranging from synthetic benchmarks to real-world applications, UniSparse consistently surpasses state-of-the-art sparse attention methods (e.g., MInference, XAttention, FlexPrefill) in both accuracy and efficiency, achieving $\ge$ 99% of full-attention accuracy and up to 2.61$\times$ faster attention computation than FlashAttention. --- ### SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations Authors: Wentao Guo, Mayank Mishra, Xinle Cheng, Ion Stoica, Tri Dao Published: 2025-12-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.14080v2 Mixture of Experts (MoE) models have emerged as the de facto architecture for scaling up language models without significantly increasing the computational cost. Recent MoE models demonstrate a clear trend towards high expert granularity (smaller expert intermediate dimension) and higher sparsity (constant number of activated experts with a higher number of total experts), which improve model quality per FLOP. However, fine-grained MoEs suffer from increased activation memory footprint and reduced hardware efficiency due to higher IO costs, while sparser MoEs suffer from wasted computations due to padding in Grouped GEMM kernels. In response, we propose a memory-efficient algorithm to compute the forward and backward passes of MoEs with minimal activation caching for the backward pass. We also design GPU kernels that overlap memory IO with computation, benefiting all MoE architectures. Finally, we propose a novel "token rounding" method that minimizes the wasted compute due to padding in Grouped GEMM kernels. As a result, our method SonicMoE reduces activation memory by 45% and achieves a 1.86x compute throughput improvement on Hopper GPUs compared to ScatterMoE's BF16 MoE kernel for a fine-grained 7B MoE. Concretely, SonicMoE on 64 H100s achieves a training throughput of 213 billion tokens per day, comparable to ScatterMoE's 225 billion tokens per day on 96 H100s for a 7B MoE model training with FSDP-2 using the lm-engine codebase. On Blackwell GPUs, SonicMoE also achieves a 25% and 15% relative speedup on the forward and backward pass respectively compared to a highly optimized DeepGEMM baseline on OLMoE-sized 7B MoE models. Under high MoE sparsity settings, our tile-aware token rounding algorithm yields an additional 1.16x speedup on kernel execution time compared to vanilla top-K routing while maintaining similar downstream performance on Hopper GPUs. We open-source all our kernels. --- ### Grammar Search for Multi-Agent Systems Authors: Mayank Singh, Vikas Yadav, Shiva Krishna Reddy Malay, Shravan Nayak, Sai Rajeswar, Sathwik Tejaswi Madhusudhan, Eduardo Blanco Published: 2025-12-16 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2512.14079v1 Automatic search for Multi-Agent Systems has recently emerged as a key focus in agentic AI research. Several prior approaches have relied on LLM-based free-form search over the code space. In this work, we propose a more structured framework that explores the same space through a fixed set of simple, composable components. We show that, despite lacking the generative flexibility of LLMs during the candidate generation stage, our method outperforms prior approaches on four out of five benchmarks across two domains: mathematics and question answering. Furthermore, our method offers additional advantages, including a more cost-efficient search process and the generation of modular, interpretable multi-agent systems with simpler logic. --- ### FusAD: Time-Frequency Fusion with Adaptive Denoising for General Time Series Analysis Authors: Da Zhang, Bingyu Li, Zhiyuan Zhao, Feiping Nie, Junyu Gao, Xuelong Li Published: 2025-12-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.14078v1 Time series analysis plays a vital role in fields such as finance, healthcare, industry, and meteorology, underpinning key tasks including classification, forecasting, and anomaly detection. Although deep learning models have achieved remarkable progress in these areas in recent years, constructing an efficient, multi-task compatible, and generalizable unified framework for time series analysis remains a significant challenge. Existing approaches are often tailored to single tasks or specific data types, making it difficult to simultaneously handle multi-task modeling and effectively integrate information across diverse time series types. Moreover, real-world data are often affected by noise, complex frequency components, and multi-scale dynamic patterns, which further complicate robust feature extraction and analysis. To ameliorate these challenges, we propose FusAD, a unified analysis framework designed for diverse time series tasks. FusAD features an adaptive time-frequency fusion mechanism, integrating both Fourier and Wavelet transforms to efficiently capture global-local and multi-scale dynamic features. With an adaptive denoising mechanism, FusAD automatically senses and filters various types of noise, highlighting crucial sequence variations and enabling robust feature extraction in complex environments. In addition, the framework integrates a general information fusion and decoding structure, combined with masked pre-training, to promote efficient learning and transfer of multi-granularity representations. Extensive experiments demonstrate that FusAD consistently outperforms state-of-the-art models on mainstream time series benchmarks for classification, forecasting, and anomaly detection tasks, while maintaining high efficiency and scalability. Code is available at https://github.com/zhangda1018/FusAD. --- ### RADAR: Accelerate Large Language Model Inference With RL-Based Dynamic Draft Trees Authors: Junjie Ma, Jinlong Li, Jiajun Luo Published: 2025-12-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.14069v2 Inference with modern Large Language Models (LLMs) is expensive and slow, and speculative sampling has emerged as an effective solution to this problem. However, the number of calls to the draft model for generating candidate tokens in speculative sampling is a preset hyperparameter, lacking flexibility. To generate and utilize the candidate tokens more effectively, we propose RADAR, a novel speculative sampling method with RL-based dynamic draft trees. RADAR formulates the draft tree generation process as a Markov Decision Process (MDP) and employs offline reinforcement learning to train a prediction model, which enables real-time decisions on calls to the draft model, reducing redundant computations and further accelerating inference. Evaluations across three LLMs and four tasks show that RADAR achieves a speedup of 3.17x-4.82x over the auto-regressive decoding baseline. The code is available at https://github.com/minaduki-sora/RADAR. --- ### SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding Authors: Shuang Cheng, Yuhua Jiang, Zineng Zhou, Dawei Liu, Wang Tao, Linfeng Zhang, Biqing Qi, Bowen Zhou Published: 2025-12-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.14068v1 Block-wise discrete diffusion offers an attractive balance between parallel generation and causal dependency modeling, making it a promising backbone for vision-language modeling. However, its practical adoption has been limited by high training cost, slow convergence, and instability, which have so far kept it behind strong autoregressive (AR) baselines. We present \textbf{SDAR-VL}, the first systematic application of block-wise discrete diffusion to large-scale vision-language understanding (VLU), together with an \emph{integrated framework for efficient and stable training}. This framework unifies three components: (1) \textbf{Asynchronous Block-wise Noise Scheduling} to diversify supervision within each batch; (2) \textbf{Effective Mask Ratio Scaling} for unbiased loss normalization under stochastic masking; and (3) a \textbf{Progressive Beta Noise Curriculum} that increases effective mask coverage while preserving corruption diversity. Experiments on 21 single-image, multi-image, and video benchmarks show that SDAR-VL consistently improves \emph{training efficiency}, \emph{convergence stability}, and \emph{task performance} over conventional block diffusion. On this evaluation suite, SDAR-VL sets a new state of the art among diffusion-based vision-language models and, under matched settings, matches or surpasses strong AR baselines such as LLaVA-OneVision as well as the global diffusion baseline LLaDA-V, establishing block-wise diffusion as a practical backbone for VLU. --- ### Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed Authors: Yonggan Fu, Lexington Whalen, Zhifan Ye, Xin Dong, Shizhe Diao, Jingyu Liu, Chengyue Wu, Hao Zhang, Enze Xie, Song Han, Maksim Khadkevich, Jan Kautz et al. Published: 2025-12-16 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.14067v2 Diffusion language models (dLMs) have emerged as a promising paradigm that enables parallel, non-autoregressive generation, but their learning efficiency lags behind that of autoregressive (AR) language models when trained from scratch. To this end, we study AR-to-dLM conversion to transform pretrained AR models into efficient dLMs that excel in speed while preserving AR models' task accuracy. We achieve this by identifying limitations in the attention patterns and objectives of existing AR-to-dLM methods and then proposing principles and methodologies for more effective AR-to-dLM conversion. Specifically, we first systematically compare different attention patterns and find that maintaining pretrained AR weight distributions is critical for effective AR-to-dLM conversion. As such, we introduce a continuous pretraining scheme with a block-wise attention pattern, which remains causal across blocks while enabling bidirectional modeling within each block. We find that this approach can better preserve pretrained AR models' weight distributions than fully bidirectional modeling, in addition to its known benefit of enabling KV caching, and leads to a win-win in accuracy and efficiency. Second, to mitigate the training-test gap in mask token distributions (uniform vs. highly left-to-right), we propose a position-dependent token masking strategy that assigns higher masking probabilities to later tokens during training to better mimic test-time behavior. Leveraging this framework, we conduct extensive studies of dLMs' attention patterns, training dynamics, and other design choices, providing actionable insights into scalable AR-to-dLM conversion. These studies lead to the Efficient-DLM family, which outperforms state-of-the-art AR models and dLMs, e.g., our Efficient-DLM 8B achieves +5.4%/+2.7% higher accuracy with 4.5x/2.7x higher throughput compared to Dream 7B and Qwen3 4B, respectively. --- ### What Affects the Effective Depth of Large Language Models? Authors: Yi Hu, Cai Zhou, Muhan Zhang Published: 2025-12-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.14064v1 The scaling of large language models (LLMs) emphasizes increasing depth, yet performance gains diminish with added layers. Prior work introduces the concept of "effective depth", arguing that deeper models fail to fully utilize their layers for meaningful computation. Building on this, we systematically study how effective depth varies with model scale, training type, and task difficulty. First, we analyze the model behavior of Qwen-2.5 family (1.5B-32B) and find that while the number of effective layers grows with model size, the effective depth ratio remains stable. Besides, comparisons between base and corresponding long-CoT models show no increase in effective depth, suggesting that improved reasoning stems from longer context rather than deeper per-token computation. Furthermore, evaluations across tasks of varying difficulty indicate that models do not dynamically use more layers for harder problems. Our results suggest that current LLMs underuse available depth across scales, training paradigms and tasks of varying difficulties, pointing out research opportunities on increasing the layer utilization rate of LLMs, model pruning, and early exiting. Our code is released at https://github.com/AheadOFpotato/what_affects_effective_depth. --- ### Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution Authors: Hao Chen, Junyang Chen, Jinshan Pan, Jiangxin Dong Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14061v1 Recent diffusion-based one-step methods have shown remarkable progress in the field of image super-resolution, yet they remain constrained by three critical limitations: (1) inferior fidelity performance caused by the information loss from compression encoding of low-quality (LQ) inputs; (2) insufficient region-discriminative activation of generative priors; (3) misalignment between text prompts and their corresponding semantic regions. To address these limitations, we propose CODSR, a controllable one-step diffusion network for image super-resolution. First, we propose an LQ-guided feature modulation module that leverages original uncompressed information from LQ inputs to provide high-fidelity conditioning for the diffusion process. We then develop a region-adaptive generative prior activation method to effectively enhance perceptual richness without sacrificing local structural fidelity. Finally, we employ a text-matching guidance strategy to fully harness the conditioning potential of text prompts. Extensive experiments demonstrate that CODSR achieves superior perceptual quality and competitive fidelity compared with state-of-the-art methods with efficient one-step inference. --- ### Real-time prediction of workplane illuminance distribution for daylight-linked controls using non-intrusive multimodal deep learning Authors: Zulin Zhuang, Yu Bian Published: 2025-12-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.14058v1 Daylight-linked controls (DLCs) have significant potential for energy savings in buildings, especially when abundant daylight is available and indoor workplane illuminance can be accurately predicted in real time. Most existing studies on indoor daylight predictions were developed and tested for static scenes. This study proposes a multimodal deep learning framework that predicts indoor workplane illuminance distributions in real time from non-intrusive images with temporal-spatial features. By extracting image features only from the side-lit window areas rather than interior pixels, the approach remains applicable in dynamically occupied indoor spaces. A field experiment was conducted in a test room in Guangzhou (China), where 17,344 samples were collected for model training and validation. The model achieved R2 > 0.98 with RMSE < 0.14 on the same-distribution test set and R2 > 0.82 with RMSE < 0.17 on an unseen-day test set, indicating high accuracy and acceptable temporal generalization. --- ### FacEDiT: Unified Talking Face Editing and Generation via Facial Motion Infilling Authors: Kim Sung-Bin, Joohyun Chang, David Harwath, Tae-Hyun Oh Published: 2025-12-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.14056v1 Talking face editing and face generation have often been studied as distinct problems. In this work, we propose viewing both not as separate tasks but as subtasks of a unifying formulation, speech-conditional facial motion infilling. We explore facial motion infilling as a self-supervised pretext task that also serves as a unifying formulation of dynamic talking face synthesis. To instantiate this idea, we propose FacEDiT, a speech-conditional Diffusion Transformer trained with flow matching. Inspired by masked autoencoders, FacEDiT learns to synthesize masked facial motions conditioned on surrounding motions and speech. This formulation enables both localized generation and edits, such as substitution, insertion, and deletion, while ensuring seamless transitions with unedited regions. In addition, biased attention and temporal smoothness constraints enhance boundary continuity and lip synchronization. To address the lack of a standard editing benchmark, we introduce FacEDiTBench, the first dataset for talking face editing, featuring diverse edit types and lengths, along with new evaluation metrics. Extensive experiments validate that talking face editing and generation emerge as subtasks of speech-conditional motion infilling; FacEDiT produces accurate, speech-aligned facial edits with strong identity preservation and smooth visual continuity while generalizing effectively to talking face generation. --- ### Expert Switching for Robust AAV Landing: A Dual-Detector Framework in Simulation Authors: Humaira Tasnim, Ashik E Rasul, Bruce Jo, Hyung-Jin Yoon Published: 2025-12-16 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.14054v2 Reliable helipad detection is essential for Autonomous Aerial Vehicle (AAV) landing, especially under GPS-denied or visually degraded conditions. While modern detectors such as YOLOv8 offer strong baseline performance, single-model pipelines struggle to remain robust across the extreme scale transitions that occur during descent, where helipads appear small at high altitude and large near touchdown. To address this limitation, we propose a scale-adaptive dual-expert perception framework that decomposes the detection task into far-range and close-range regimes. Two YOLOv8 experts are trained on scale-specialized versions of the HelipadCat dataset, enabling one model to excel at detecting small, low-resolution helipads and the other to provide high-precision localization when the target dominates the field of view. During inference, both experts operate in parallel, and a geometric gating mechanism selects the expert whose prediction is most consistent with the AAV's viewpoint. This adaptive routing prevents the degradation commonly observed in single-detector systems when operating across wide altitude ranges. The dual-expert perception module is evaluated in a closed-loop landing environment that integrates CARLA's photorealistic rendering with NASA's GUAM flight-dynamics engine. Results show substantial improvements in alignment stability, landing accuracy, and overall robustness compared to single-detector baselines. By introducing a scale-aware expert routing strategy tailored to the landing problem, this work advances resilient vision-based perception for autonomous descent and provides a foundation for future multi-expert AAV frameworks. --- ### HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices Authors: HyperAI Team, Yuchen Liu, Kaiyang Han, Zhiqiang Xia, Yuhang Dong, Chen Song, Kangyu Tang, Jiaming Xu, Xiushi Feng, WenXuan Yu, Li Peng, Mingyang Wang et al. Published: 2025-12-16 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2512.14052v1 Current multimodal large lanauge models possess strong perceptual and reasoning capabilities, however high computational and memory requirements make them difficult to deploy directly on on-device environments. While small-parameter models are progressively endowed with strong general capabilities, standard Vision Transformer (ViT) encoders remain a critical bottleneck, suffering from excessive latency and memory consumption when processing high-resolution inputs.To address these challenges, we introduce HyperVL, an efficient multimodal large language model tailored for on-device inference. HyperVL adopts an image-tiling strategy to cap peak memory usage and incorporates two novel techniques: (1) a Visual Resolution Compressor (VRC) that adaptively predicts optimal encoding resolutions to eliminate redundant computation, and (2) Dual Consistency Learning (DCL), which aligns multi-scale ViT encoders within a unified framework, enabling dynamic switching between visual branches under a shared LLM. Extensive experiments demonstrate that HyperVL achieves state-of-the-art performance among models of comparable size across multiple benchmarks. Furthermore, it significantly significantly reduces latency and power consumption on real mobile devices, demonstrating its practicality for on-device multimodal inference. --- ### OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value Authors: Mengzhang Cai, Xin Gao, Yu Li, Honglin Lin, Zheng Liu, Zhuoshi Pan, Qizhi Pei, Xiaoran Shang, Mengyuan Sun, Zinan Tang, Xiaoyang Wang, Zhanping Zhong et al. Published: 2025-12-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.14051v1 The rapid evolution of Large Language Models (LLMs) is predicated on the quality and diversity of post-training datasets. However, a critical dichotomy persists: while models are rigorously benchmarked, the data fueling them remains a black box--characterized by opaque composition, uncertain provenance, and a lack of systematic evaluation. This opacity hinders reproducibility and obscures the causal link between data characteristics and model behaviors. To bridge this gap, we introduce OpenDataArena (ODA), a holistic and open platform designed to benchmark the intrinsic value of post-training data. ODA establishes a comprehensive ecosystem comprising four key pillars: (i) a unified training-evaluation pipeline that ensures fair, open comparisons across diverse models (e.g., Llama, Qwen) and domains; (ii) a multi-dimensional scoring framework that profiles data quality along tens of distinct axes; (iii) an interactive data lineage explorer to visualize dataset genealogy and dissect component sources; and (iv) a fully open-source toolkit for training, evaluation, and scoring to foster data research. Extensive experiments on ODA--covering over 120 training datasets across multiple domains on 22 benchmarks, validated by more than 600 training runs and 40 million processed data points--reveal non-trivial insights. Our analysis uncovers the inherent trade-offs between data complexity and task performance, identifies redundancy in popular benchmarks through lineage tracing, and maps the genealogical relationships across datasets. We release all results, tools, and configurations to democratize access to high-quality data evaluation. Rather than merely expanding a leaderboard, ODA envisions a shift from trial-and-error data curation to a principled science of Data-Centric AI, paving the way for rigorous studies on data mixing laws and the strategic composition of foundation models. --- ### SELECT: Detecting Label Errors in Real-world Scene Text Data Authors: Wenjun Liu, Qian Wu, Yifeng Hu, Yuke Li Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14050v1 We introduce SELECT (Scene tExt Label Errors deteCTion), a novel approach that leverages multi-modal training to detect label errors in real-world scene text datasets. Utilizing an image-text encoder and a character-level tokenizer, SELECT addresses the issues of variable-length sequence labels, label sequence misalignment, and character-level errors, outperforming existing methods in accuracy and practical utility. In addition, we introduce Similarity-based Sequence Label Corruption (SSLC), a process that intentionally introduces errors into the training labels to mimic real-world error scenarios during training. SSLC not only can cause a change in the sequence length but also takes into account the visual similarity between characters during corruption. Our method is the first to detect label errors in real-world scene text datasets successfully accounting for variable-length labels. Experimental results demonstrate the effectiveness of SELECT in detecting label errors and improving STR accuracy on real-world text datasets, showcasing its practical utility. --- ### Intention Chain-of-Thought Prompting with Dynamic Routing for Code Generation Authors: Shen Li, Li Huang, Shaoxiong Zhan, Weifeng Sun, Tao Yin, Zhongxin Liu, Meng Yan Published: 2025-12-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.14048v1 Large language models (LLMs) exhibit strong generative capabilities and have shown great potential in code generation. Existing chain-of-thought (CoT) prompting methods enhance model reasoning by eliciting intermediate steps, but suffer from two major limitations: First, their uniform application tends to induce overthinking on simple tasks. Second, they lack intention abstraction in code generation, such as explicitly modeling core algorithmic design and efficiency, leading models to focus on surface-level structures while neglecting the global problem objective. Inspired by the cognitive economy principle of engaging structured reasoning only when necessary to conserve cognitive resources, we propose RoutingGen, a novel difficulty-aware routing framework that dynamically adapts prompting strategies for code generation. For simple tasks, it adopts few-shot prompting; for more complex ones, it invokes a structured reasoning strategy, termed Intention Chain-of-Thought (ICoT), which we introduce to guide the model in capturing task intention, such as the core algorithmic logic and its time complexity. Experiments across three models and six standard code generation benchmarks show that RoutingGen achieves state-of-the-art performance in most settings, while reducing total token usage by 46.37% on average across settings. Furthermore, ICoT outperforms six existing prompting baselines on challenging benchmarks. --- ### A Deep Dive into Function Inlining and its Security Implications for ML-based Binary Analysis Authors: Omar Abusabha, Jiyong Uhm, Tamer Abuhmed, Hyungjoon Koo Published: 2025-12-16 Categories: cs.CR, cs.LG, cs.PL arXiv: https://arxiv.org/abs/2512.14045v1 A function inlining optimization is a widely used transformation in modern compilers, which replaces a call site with the callee's body in need. While this transformation improves performance, it significantly impacts static features such as machine instructions and control flow graphs, which are crucial to binary analysis. Yet, despite its broad impact, the security impact of function inlining remains underexplored to date. In this paper, we present the first comprehensive study of function inlining through the lens of machine learning-based binary analysis. To this end, we dissect the inlining decision pipeline within the LLVM's cost model and explore the combinations of the compiler options that aggressively promote the function inlining ratio beyond standard optimization levels, which we term extreme inlining. We focus on five ML-assisted binary analysis tasks for security, using 20 unique models to systematically evaluate their robustness under extreme inlining scenarios. Our extensive experiments reveal several significant findings: i) function inlining, though a benign transformation in intent, can (in)directly affect ML model behaviors, being potentially exploited by evading discriminative or generative ML models; ii) ML models relying on static features can be highly sensitive to inlining; iii) subtle compiler settings can be leveraged to deliberately craft evasive binary variants; and iv) inlining ratios vary substantially across applications and build configurations, undermining assumptions of consistency in training and evaluation of ML models. --- ### OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving Authors: Zhenguo Zhang, Haohan Zheng, Yishen Wang, Le Xu, Tianchen Deng, Xuefeng Chen, Qu Chen, Bo Zhang, Wuxiong Huang Published: 2025-12-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.14044v3 The deployment of Vision-Language Models (VLMs) in safety-critical domains like autonomous driving (AD) is critically hindered by reliability failures, most notably object hallucination. This failure stems from their reliance on ungrounded, text-based Chain-of-Thought (CoT) reasoning. While existing multi-modal CoT approaches attempt mitigation, they suffer from two fundamental flaws: (1) decoupled perception and reasoning stages that prevent end-to-end joint optimization, and (2) reliance on expensive, dense localization labels. Thus we introduce OmniDrive-R1, an end-to-end VLM framework designed for autonomous driving, which unifies perception and reasoning through an interleaved Multi-modal Chain-of-Thought (iMCoT) mechanism. Our core innovation is an Reinforcement-driven visual grounding capability, enabling the model to autonomously direct its attention and "zoom in" on critical regions for fine-grained analysis. This capability is enabled by our pure two-stage reinforcement learning training pipeline and Clip-GRPO algorithm. Crucially, Clip-GRPO introduces an annotation-free, process-based grounding reward. This reward not only eliminates the need for dense labels but also circumvents the instability of external tool calls by enforcing real-time cross-modal consistency between the visual focus and the textual reasoning. Extensive experiments on DriveLMM-o1 demonstrate our model's significant improvements. Compared to the baseline Qwen2.5VL-7B, OmniDrive-R1 improves the overall reasoning score from 51.77% to 80.35%, and the final answer accuracy from 37.81% to 73.62%. --- ### Evaluating Small Language Models for Agentic On-Farm Decision Support Systems Authors: Enhong Liu, Haiyu Yang, Miel Hostens Published: 2025-12-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.14043v1 Large Language Models (LLM) hold potential to support dairy scholars and farmers by supporting decision-making and broadening access to knowledge for stakeholders with limited technical expertise. However, the substantial computational demand restricts access to LLM almost exclusively through cloud-based service, which makes LLM-based decision support tools impractical for dairy farming. To address this gap, lightweight alternatives capable of running locally on farm hardware are required. In this work, we benchmarked 20 open-source Small Language Models (SLM) available on HuggingFace under farm-realistic computing constraints. Building on our prior work, we developed an agentic AI system that integrates five task-specific agents: literature search, web search, SQL database interaction, NoSQL database interaction, and graph generation following predictive models. Evaluation was conducted in two phases. In the first phase, five test questions were used for the initial screening to identify models capable of following basic dairy-related instructions and performing reliably in a compute-constrained environment. Models that passed this preliminary stage were then evaluated using 30 questions (five per task category mentioned above, plus one category addressing integrity and misconduct) in phase two. In results, Qwen-4B achieved superior performance across most of task categories, although showed unstable effectiveness in NoSQL database interactions through PySpark. To our knowledge, this is the first work explicitly evaluating the feasibility of SLM as engines for dairy farming decision-making, with central emphases on privacy and computational efficiency. While results highlight the promise of SLM-assisted tools for practical deployment in dairy farming, challenges remain, and fine-tuning is still needed to refine SLM performance in dairy-specific questions. --- ### ChartAgent: A Chart Understanding Framework with Tool Integrated Reasoning Authors: Boran Wang, Xinming Wang, Yi Chen, Xiang Li, Jian Xu, Jing Yuan, Chenglin Liu Published: 2025-12-16 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.14040v1 With their high information density and intuitive readability, charts have become the de facto medium for data analysis and communication across disciplines. Recent multimodal large language models (MLLMs) have made notable progress in automated chart understanding, yet they remain heavily dependent on explicit textual annotations and the performance degrades markedly when key numerals are absent. To address this limitation, we introduce ChartAgent, a chart understanding framework grounded in Tool-Integrated Reasoning (TIR). Inspired by human cognition, ChartAgent decomposes complex chart analysis into a sequence of observable, replayable steps. Supporting this architecture is an extensible, modular tool library comprising more than a dozen core tools, such as keyelement detection, instance segmentation, and optical character recognition (OCR), which the agent dynamically orchestrates to achieve systematic visual parsing across diverse chart types. Leveraging TIRs transparency and verifiability, ChartAgent moves beyond the black box paradigm by standardizing and consolidating intermediate outputs into a structured Evidence Package, providing traceable and reproducible support for final conclusions. Experiments show that ChartAgent substantially improves robustness under sparse annotation settings, offering a practical path toward trustworthy and extensible systems for chart understanding. --- ### ASAP-Textured Gaussians: Enhancing Textured Gaussians with Adaptive Sampling and Anisotropic Parameterization Authors: Meng Wei, Cheng Zhang, Jianmin Zheng, Hamid Rezatofighi, Jianfei Cai Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14039v1 Recent advances have equipped 3D Gaussian Splatting with texture parameterizations to capture spatially varying attributes, improving the performance of both appearance modeling and downstream tasks. However, the added texture parameters introduce significant memory efficiency challenges. Rather than proposing new texture formulations, we take a step back to examine the characteristics of existing textured Gaussian methods and identify two key limitations in common: (1) Textures are typically defined in canonical space, leading to inefficient sampling that wastes textures' capacity on low-contribution regions; and (2) texture parameterization is uniformly assigned across all Gaussians, regardless of their visual complexity, resulting in over-parameterization. In this work, we address these issues through two simple yet effective strategies: adaptive sampling based on the Gaussian density distribution and error-driven anisotropic parameterization that allocates texture resources according to rendering error. Our proposed ASAP Textured Gaussians, short for Adaptive Sampling and Anisotropic Parameterization, significantly improve the quality efficiency tradeoff, achieving high-fidelity rendering with far fewer texture parameters. --- ### ACE-SLAM: Scene Coordinate Regression for Neural Implicit Real-Time SLAM Authors: Ignacio Alzugaray, Marwan Taher, Andrew J. Davison Published: 2025-12-16 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2512.14032v1 We present a novel neural RGB-D Simultaneous Localization And Mapping (SLAM) system that learns an implicit map of the scene in real time. For the first time, we explore the use of Scene Coordinate Regression (SCR) as the core implicit map representation in a neural SLAM pipeline, a paradigm that trains a lightweight network to directly map 2D image features to 3D global coordinates. SCR networks provide efficient, low-memory 3D map representations, enable extremely fast relocalization, and inherently preserve privacy, making them particularly suitable for neural implicit SLAM. Our system is the first one to achieve strict real-time in neural implicit RGB-D SLAM by relying on a SCR-based representation. We introduce a novel SCR architecture specifically tailored for this purpose and detail the critical design choices required to integrate SCR into a live SLAM pipeline. The resulting framework is simple yet flexible, seamlessly supporting both sparse and dense features, and operates reliably in dynamic environments without special adaptation. We evaluate our approach on established synthetic and real-world benchmarks, demonstrating competitive performance against the state of the art. Project Page: https://github.com/ialzugaray/ace-slam --- ### Sample-Efficient Robot Skill Learning for Construction Tasks: Benchmarking Hierarchical Reinforcement Learning and Vision-Language-Action VLA Model Authors: Zhaofeng Hu, Hongrui Yu, Vaidhyanathan Chandramouli, Ci-Jyun Liang Published: 2025-12-16 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.14031v1 This study evaluates two leading approaches for teaching construction robots new skills to understand their applicability for construction automation: a Vision-Language-Action (VLA) model and Reinforcement Learning (RL) methods. The goal is to understand both task performance and the practical effort needed to deploy each approach on real jobs. The authors developed two teleoperation interfaces to control the robots and collect the demonstrations needed, both of which proved effective for training robots for long-horizon and dexterous tasks. In addition, the authors conduct a three-stage evaluation. First, the authors compare a Multi-Layer Perceptron (MLP) policy with a Deep Q-network (DQN) imitation model to identify the stronger RL baseline, focusing on model performance, generalization, and a pick-up experiment. Second, three different VLA models are trained in two different scenarios and compared with each other. Third, the authors benchmark the selected RL baseline against the VLA model using computational and sample-efficiency measures and then a robot experiment on a multi-stage panel installation task that includes transport and installation. The VLA model demonstrates strong generalization and few-shot capability, achieving 60% and 100% success in the pickup phase. In comparison, DQN can be made robust but needs additional noise during tuning, which increases the workload. Overall, the findings indicate that VLA offers practical advantages for changing tasks by reducing programming effort and enabling useful performance with minimal data, while DQN provides a viable baseline when sufficient tuning effort is acceptable. --- ### Robust Single-shot Structured Light 3D Imaging via Neural Feature Decoding Authors: Jiaheng Li, Qiyu Dai, Lihan Li, Praneeth Chakravarthula, He Sun, Baoquan Chen, Wenzheng Chen Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14028v1 We consider the problem of active 3D imaging using single-shot structured light systems, which are widely employed in commercial 3D sensing devices such as Apple Face ID and Intel RealSense. Traditional structured light methods typically decode depth correspondences through pixel-domain matching algorithms, resulting in limited robustness under challenging scenarios like occlusions, fine-structured details, and non-Lambertian surfaces. Inspired by recent advances in neural feature matching, we propose a learning-based structured light decoding framework that performs robust correspondence matching within feature space rather than the fragile pixel domain. Our method extracts neural features from the projected patterns and captured infrared (IR) images, explicitly incorporating their geometric priors by building cost volumes in feature space, achieving substantial performance improvements over pixel-domain decoding approaches. To further enhance depth quality, we introduce a depth refinement module that leverages strong priors from large-scale monocular depth estimation models, improving fine detail recovery and global structural coherence. To facilitate effective learning, we develop a physically-based structured light rendering pipeline, generating nearly one million synthetic pattern-image pairs with diverse objects and materials for indoor settings. Experiments demonstrate that our method, trained exclusively on synthetic data with multiple structured light patterns, generalizes well to real-world indoor environments, effectively processes various pattern types without retraining, and consistently outperforms both commercial structured light systems and passive stereo RGB-based depth estimation methods. Project page: https://namisntimpot.github.io/NSLweb/. --- ### Unleashing the Power of Image-Tabular Self-Supervised Learning via Breaking Cross-Tabular Barriers Authors: Yibing Fu, Yunpeng Zhao, Zhitao Zeng, Cheng Chen, Yueming Jin Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14026v1 Multi-modal learning integrating medical images and tabular data has significantly advanced clinical decision-making in recent years. Self-Supervised Learning (SSL) has emerged as a powerful paradigm for pretraining these models on large-scale unlabeled image-tabular data, aiming to learn discriminative representations. However, existing SSL methods for image-tabular representation learning are often confined to specific data cohorts, mainly due to their rigid tabular modeling mechanisms when modeling heterogeneous tabular data. This inter-tabular barrier hinders the multi-modal SSL methods from effectively learning transferrable medical knowledge shared across diverse cohorts. In this paper, we propose a novel SSL framework, namely CITab, designed to learn powerful multi-modal feature representations in a cross-tabular manner. We design the tabular modeling mechanism from a semantic-awareness perspective by integrating column headers as semantic cues, which facilitates transferrable knowledge learning and the scalability in utilizing multiple data sources for pretraining. Additionally, we propose a prototype-guided mixture-of-linear layer (P-MoLin) module for tabular feature specialization, empowering the model to effectively handle the heterogeneity of tabular data and explore the underlying medical concepts. We conduct comprehensive evaluations on Alzheimer's disease diagnosis task across three publicly available data cohorts containing 4,461 subjects. Experimental results demonstrate that CITab outperforms state-of-the-art approaches, paving the way for effective and scalable cross-tabular multi-modal learning. --- ### Multivariate Time Series Forecasting with Hybrid Euclidean-SPD Manifold Graph Neural Networks Authors: Yong Fang, Na Li, Hangguan Shan, Eryun Liu, Xinyu Li, Wei Ni, Er-Ping Li Published: 2025-12-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.14023v1 Multivariate Time Series (MTS) forecasting plays a vital role in various real-world applications, such as traffic management and predictive maintenance. Existing approaches typically model MTS data in either Euclidean or Riemannian space, limiting their ability to capture the diverse geometric structures and complex spatio-temporal dependencies inherent in real-world data. To overcome this limitation, we propose the Hybrid Symmetric Positive-Definite Manifold Graph Neural Network (HSMGNN), a novel graph neural network-based model that captures data geometry within a hybrid Euclidean-Riemannian framework. To the best of our knowledge, this is the first work to leverage hybrid geometric representations for MTS forecasting, enabling expressive and comprehensive modeling of geometric properties. Specifically, we introduce a Submanifold-Cross-Segment (SCS) embedding to project input MTS into both Euclidean and Riemannian spaces, thereby capturing spatio-temporal variations across distinct geometric domains. To alleviate the high computational cost of Riemannian distance, we further design an Adaptive-Distance-Bank (ADB) layer with a trainable memory mechanism. Finally, a Fusion Graph Convolutional Network (FGCN) is devised to integrate features from the dual spaces via a learnable fusion operator for accurate prediction. Experiments on three benchmark datasets demonstrate that HSMGNN achieves up to a 13.8 percent improvement over state-of-the-art baselines in forecasting accuracy. --- ### Deep Learning Perspective of Scene Understanding in Autonomous Robots Authors: Afia Maham, Dur E Nayab Tashfa Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14020v1 This paper provides a review of deep learning applications in scene understanding in autonomous robots, including innovations in object detection, semantic and instance segmentation, depth estimation, 3D reconstruction, and visual SLAM. It emphasizes how these techniques address limitations of traditional geometric models, improve depth perception in real time despite occlusions and textureless surfaces, and enhance semantic reasoning to understand the environment better. When these perception modules are integrated into dynamic and unstructured environments, they become more effective in decisionmaking, navigation and interaction. Lastly, the review outlines the existing problems and research directions to advance learning-based scene understanding of autonomous robots. --- ### EXAONE Path 2.5: Pathology Foundation Model with Multi-Omics Alignment Authors: Juseung Yun, Sunwoo Yu, Sumin Ha, Jonghyun Kim, Janghyeon Lee, Jongseong Jang, Soonyoung Lee Published: 2025-12-16 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2512.14019v1 Cancer progression arises from interactions across multiple biological layers, especially beyond morphological and across molecular layers that remain invisible to image-only models. To capture this broader biological landscape, we present EXAONE Path 2.5, a pathology foundation model that jointly models histologic, genomic, epigenetic and transcriptomic modalities, producing an integrated patient representation that reflects tumor biology more comprehensively. Our approach incorporates three key components: (1) multimodal SigLIP loss enabling all-pairwise contrastive learning across heterogeneous modalities, (2) a fragment-aware rotary positional encoding (F-RoPE) module that preserves spatial structure and tissue-fragment topology in WSI, and (3) domain-specialized internal foundation models for both WSI and RNA-seq to provide biologically grounded embeddings for robust multimodal alignment. We evaluate EXAONE Path 2.5 against six leading pathology foundation models across two complementary benchmarks: an internal real-world clinical dataset and the Patho-Bench benchmark covering 80 tasks. Our framework demonstrates high data and parameter efficiency, achieving on-par performance with state-of-the-art foundation models on Patho-Bench while exhibiting the highest adaptability in the internal clinical setting. These results highlight the value of biologically informed multimodal design and underscore the potential of integrated genotype-to-phenotype modeling for next-generation precision oncology. --- ### PerfCoder: Large Language Models for Interpretable Code Performance Optimization Authors: Jiuding Yang, Shengyao Lu, Hongxuan Liu, Shayan Shirahmad Gale Bagi, Zahra Fazel, Tomasz Czajkowski, Di Niu Published: 2025-12-16 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.14018v2 Large language models (LLMs) have achieved remarkable progress in automatic code generation, yet their ability to produce high-performance code remains limited--a critical requirement in real-world software systems. We argue that current LLMs struggle not only due to data scarcity but, more importantly, because they lack supervision that guides interpretable and effective performance improvements. In this work, we introduce PerfCoder, a family of LLMs specifically designed to generate performance-enhanced code from source code via interpretable, customized optimizations. PerfCoder is fine-tuned on a curated collection of real-world optimization trajectories with human-readable annotations, and preference-aligned by reinforcement fine-tuning using runtime measurements, enabling it to propose input-specific improvement strategies and apply them directly without relying on iterative refinement. On the PIE code performance benchmark, PerfCoder surpasses all existing models in both runtime speedup and effective optimization rate, demonstrating that performance optimization cannot be achieved by scale alone but requires optimization stratetgy awareness. In addition, PerfCoder can generate interpretable feedback about the source code, which, when provided as input to a larger LLM in a planner-and-optimizer cooperative workflow, can further improve outcomes. Specifically, we elevate the performance of 32B models and GPT-5 to new levels on code optimization, substantially surpassing their original performance. --- ### KFS-Bench: Comprehensive Evaluation of Key Frame Sampling in Long Video Understanding Authors: Zongyao Li, Kengo Ishida, Satoshi Yamazaki, Xiaotong Ji, Jianquan Liu Published: 2025-12-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.14017v1 We propose KFS-Bench, the first benchmark for key frame sampling in long video question answering (QA), featuring multi-scene annotations to enable direct and robust evaluation of sampling strategies. Key frame sampling is crucial for efficient long-form video understanding. In long video QA, selecting informative frames enables multimodal large language models (MLLMs) to improve both accuracy and efficiency. KFS-Bench addresses the limitation of prior works that only indirectly assess frame selection quality via QA accuracy. By providing ground-truth annotations of multiple disjoint scenes required per question, KFS-Bench allows us to directly analyze how different sampling approaches capture essential content across an entire long video. Using KFS-Bench, we conduct a comprehensive study of key frame sampling methods and identify that not only sampling precision but also scene coverage and sampling balance are the key factors influencing QA performance. Regarding all the factors, we design a novel sampling quality metric that correlates with QA accuracy. Furthermore, we develop a novel key frame sampling method that leverages question-video relevance to balance sampling diversity against question-frame similarity, thereby improving coverage of relevant scenes. Our adaptively balanced sampling approach achieves superior performance in both key frame sampling and QA performance. The benchmark is available at https://github.com/NEC-VID/KFS-Bench. --- ### MobileWorldBench: Towards Semantic World Modeling For Mobile Agents Authors: Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Yusuke Kato, Kazuki Kozuka, Aditya Grover Published: 2025-12-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.14014v2 World models have shown great utility in improving the task performance of embodied agents. While prior work largely focuses on pixel-space world models, these approaches face practical limitations in GUI settings, where predicting complex visual elements in future states is often difficult. In this work, we explore an alternative formulation of world modeling for GUI agents, where state transitions are described in natural language rather than predicting raw pixels. First, we introduce MobileWorldBench, a benchmark that evaluates the ability of vision-language models (VLMs) to function as world models for mobile GUI agents. Second, we release MobileWorld, a large-scale dataset consisting of 1.4M samples, that significantly improves the world modeling capabilities of VLMs. Finally, we propose a novel framework that integrates VLM world models into the planning framework of mobile agents, demonstrating that semantic world models can directly benefit mobile agents by improving task success rates. The code and dataset is available at https://github.com/jacklishufan/MobileWorld --- ### Professional Software Developers Don't Vibe, They Control: AI Agent Use for Coding in 2025 Authors: Ruanqianqian Huang, Avery Reyna, Sorin Lerner, Haijun Xia, Brian Hempel Published: 2025-12-16 Categories: cs.SE, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2512.14012v2 The rise of AI agents is transforming how software can be built. The promise of agents is that developers might write code quicker, delegate multiple tasks to different agents, and even write a full piece of software purely out of natural language. In reality, what roles agents play in professional software development remains in question. This paper investigates how experienced developers use agents in building software, including their motivations, strategies, task suitability, and sentiments. Through field observations (N=13) and qualitative surveys (N=99), we find that while experienced developers value agents as a productivity boost, they retain their agency in software design and implementation out of insistence on fundamental software quality attributes, employing strategies for controlling agent behavior leveraging their expertise. In addition, experienced developers enjoy working with agents as source of collaboration rather than complete delegation given their judgment for task suitability. Our results shed light on the value of software development best practices in effective use of agents, suggest the kinds of tasks for which agents may be suitable, and point towards future opportunities for better agentic interfaces and agentic use guidelines. --- ### Accelerating MHC-II Epitope Discovery via Multi-Scale Prediction in Antigen Presentation Authors: Yue Wan, Jiayi Yuan, Zhiwei Feng, Xiaowei Jia Published: 2025-12-16 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2512.14011v1 Antigenic epitope presented by major histocompatibility complex II (MHC-II) proteins plays an essential role in immunotherapy. However, compared to the more widely studied MHC-I in computational immunotherapy, the study of MHC-II antigenic epitope poses significantly more challenges due to its complex binding specificity and ambiguous motif patterns. Consequently, existing datasets for MHC-II interactions are smaller and less standardized than those available for MHC-I. To address these challenges, we present a well-curated dataset derived from the Immune Epitope Database (IEDB) and other public sources. It not only extends and standardizes existing peptide-MHC-II datasets, but also introduces a novel antigen-MHC-II dataset with richer biological context. Leveraging this dataset, we formulate three major machine learning (ML) tasks of peptide binding, peptide presentation, and antigen presentation, which progressively capture the broader biological processes within the MHC-II antigen presentation pathway. We further employ a multi-scale evaluation framework to benchmark existing models, along with a comprehensive analysis over various modeling designs to this problem with a modular framework. Overall, this work serves as a valuable resource for advancing computational immunotherapy, providing a foundation for future research in ML guided epitope discovery and predictive modeling of immune responses. --- ### Physics-Informed Machine Learning for Two-Phase Moving-Interface and Stefan Problems Authors: Che-Chia Chang, Te-Sheng Lin, Ming-Chih Lai Published: 2025-12-16 Categories: physics.comp-ph, cs.LG arXiv: https://arxiv.org/abs/2512.14010v1 The Stefan problem is a classical free-boundary problem that models phase-change processes and poses computational challenges due to its moving interface and nonlinear temperature-phase coupling. In this work, we develop a physics-informed neural network framework for solving two-phase Stefan problems. The proposed method explicitly tracks the interface motion and enforces the discontinuity in the temperature gradient across the interface while maintaining global consistency of the temperature field. Our approach employs two neural networks: one representing the moving interface and the other for the temperature field. The interface network allows rapid categorization of thermal diffusivity in the spatial domain, which is a crucial step for selecting training points for the temperature network. The temperature network's input is augmented with a modified zero-level set function to accurately capture the jump in its normal derivative across the interface. Numerical experiments on two-phase dynamical Stefan problems demonstrate the superior accuracy and effectiveness of our proposed method compared with the ones obtained by other neural network methodology in literature. The results indicate that the proposed framework offers a robust and flexible alternative to traditional numerical methods for solving phase-change problems governed by moving boundaries. In addition, the proposed method can capture an unstable interface evolution associated with the Mullins-Sekerka instability. --- ### Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models Authors: Shufan Li, Jiuxiang Gu, Kangning Liu, Zhe Lin, Zijun Wei, Aditya Grover, Jason Kuen Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14008v2 Masked Discrete Diffusion Models (MDMs) have achieved strong performance across a wide range of multimodal tasks, including image understanding, generation, and editing. However, their inference speed remains suboptimal due to the need to repeatedly process redundant masked tokens at every sampling step. In this work, we propose Sparse-LaViDa, a novel modeling framework that dynamically truncates unnecessary masked tokens at each inference step to accelerate MDM sampling. To preserve generation quality, we introduce specialized register tokens that serve as compact representations for the truncated tokens. Furthermore, to ensure consistency between training and inference, we design a specialized attention mask that faithfully matches the truncated sampling procedure during training. Built upon the state-of-the-art unified MDM LaViDa-O, Sparse-LaViDa achieves up to a 2x speedup across diverse tasks including text-to-image generation, image editing, and mathematical reasoning, while maintaining generation quality. ---