# Research Papers — 2025-12 · bundle page 100 of 175 > Full-text markdown of papers #4951–5000 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/100 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/99.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/101.md) ### When Actions Teach You to Think: Reasoning-Action Synergy via Reinforcement Learning in Conversational Agents Authors: Mrinal Rawat, Arkajyoti Chakraborty, Neha Gupta, Roberto Pieraccini Published: 2025-12-12 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.11277v1 Supervised fine-tuning (SFT) has emerged as one of the most effective ways to improve the performance of large language models (LLMs) in downstream tasks. However, SFT can have difficulty generalizing when the underlying data distribution changes, even when the new data does not fall completely outside the training domain. Recent reasoning-focused models such as o1 and R1 have demonstrated consistent gains over their non-reasoning counterparts, highlighting the importance of reasoning for improved generalization and reliability. However, collecting high-quality reasoning traces for SFT remains challenging -- annotations are costly, subjective, and difficult to scale. To address this limitation, we leverage Reinforcement Learning (RL) to enable models to learn reasoning strategies directly from task outcomes. We propose a pipeline in which LLMs generate reasoning steps that guide both the invocation of tools (e.g., function calls) and the final answer generation for conversational agents. Our method employs Group Relative Policy Optimization (GRPO) with rewards designed around tool accuracy and answer correctness, allowing the model to iteratively refine its reasoning and actions. Experimental results demonstrate that our approach improves both the quality of reasoning and the precision of tool invocations, achieving a 1.5% relative improvement over the SFT model (trained without explicit thinking) and a 40% gain compared to the base of the vanilla Qwen3-1.7B model. These findings demonstrate the promise of unifying reasoning and action learning through RL to build more capable and generalizable conversational agents. --- ### Words to Describe What I'm Feeling: Exploring the Potential of AI Agents for High Subjectivity Decisions in Advance Care Planning Authors: Kellie Yu Hui Sim, Pin Sym Foong, Chenyu Zhao, Melanie Yi Ning Quek, Swarangi Subodh Mehta, Kenny Tsu Wei Choo Published: 2025-12-12 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2512.11276v3 Loss of decisional capacity, coupled with the increasing absence of reliable human proxies, raises urgent questions about how individuals' values can be represented in Advance Care Planning (ACP). To probe this fraught design space of high-risk, high-subjectivity decision support, we built an experience prototype (\acpagent{}) and asked 15 participants in 4 workshops to train it to be their personal ACP proxy. We analysed their coping strategies and feature requests and mapped the results onto axes of agent autonomy and human control. Our findings show a surprising 86.7\% agreement with \acpagent{}, arguing for a potential new role of AI in ACP where agents act as personal advocates for individuals, building mutual intelligibility over time. We propose that the key areas of future risk that must be addressed are the moderation of users' expectations and designing accountability and oversight over agent deployment and cutoffs. --- ### FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion Authors: Xiangyang Luo, Qingyu Li, Xiaokun Liu, Wenyu Qin, Miao Yang, Meng Wang, Pengfei Wan, Di Zhang, Kun Gai, Shao-Lun Huang Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11274v1 Current video generation models perform well at single-shot synthesis but struggle with multi-shot videos, facing critical challenges in maintaining character and background consistency across shots and flexibly generating videos of arbitrary length and shot count. To address these limitations, we introduce \textbf{FilmWeaver}, a novel framework designed to generate consistent, multi-shot videos of arbitrary length. First, it employs an autoregressive diffusion paradigm to achieve arbitrary-length video generation. To address the challenge of consistency, our key insight is to decouple the problem into inter-shot consistency and intra-shot coherence. We achieve this through a dual-level cache mechanism: a shot memory caches keyframes from preceding shots to maintain character and scene identity, while a temporal memory retains a history of frames from the current shot to ensure smooth, continuous motion. The proposed framework allows for flexible, multi-round user interaction to create multi-shot videos. Furthermore, due to this decoupled design, our method demonstrates high versatility by supporting downstream tasks such as multi-concept injection and video extension. To facilitate the training of our consistency-aware method, we also developed a comprehensive pipeline to construct a high-quality multi-shot video dataset. Extensive experimental results demonstrate that our method surpasses existing approaches on metrics for both consistency and aesthetic quality, opening up new possibilities for creating more consistent, controllable, and narrative-driven video content. Project Page: https://filmweaver.github.io --- ### Integrated Prediction and Multi-period Portfolio Optimization Authors: Yuxuan Linghu, Zhiyuan Liu, Qi Deng Published: 2025-12-12 Categories: cs.CE, cs.LG arXiv: https://arxiv.org/abs/2512.11273v3 Multi-period portfolio optimization is important for real portfolio management, as it accounts for transaction costs, path-dependent risks, and the intertemporal structure of trading decisions that single-period models cannot capture. Classical methods usually follow a two-stage framework: machine learning algorithms are employed to produce forecasts that closely fit the realized returns, and the predicted values are then used in a downstream portfolio optimization problem to determine the asset weights. This separation leads to a fundamental misalignment between predictions and decision outcomes, while also ignoring the impact of transaction costs. To bridge this gap, recent studies have proposed the idea of end-to-end learning, integrating the two stages into a single pipeline. This paper introduces IPMO (Integrated Prediction and Multi-period Portfolio Optimization), a model for multi-period mean-variance portfolio optimization with turnover penalties. The predictor generates multi-period return forecasts that parameterize a differentiable convex optimization layer, which in turn drives learning via portfolio performance. For scalability, we introduce a mirror-descent fixed-point (MDFP) differentiation scheme that avoids factorizing the Karush-Kuhn-Tucker (KKT) systems, which thus yields stable implicit gradients and nearly scale-insensitive runtime as the decision horizon grows. In experiments with real market data and two representative time-series prediction models, the IPMO method consistently outperforms the two-stage benchmarks in risk-adjusted performance net of transaction costs and achieves more coherent allocation paths. Our results show that integrating machine learning prediction with optimization in the multi-period setting improves financial outcomes and remains computationally tractable. --- ### TriFlow: A Progressive Multi-Agent Framework for Intelligent Trip Planning Authors: Yuxing Chen, Basem Suleiman, Qifan Chen Published: 2025-12-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.11271v1 Real-world trip planning requires transforming open-ended user requests into executable itineraries under strict spatial, temporal, and budgetary constraints while aligning with user preferences. Existing LLM-based agents struggle with constraint satisfaction, tool coordination, and efficiency, often producing infeasible or costly plans. To address these limitations, we present TriFlow, a progressive multi-agent framework that unifies structured reasoning and language-based flexibility through a three-stage pipeline of retrieval, planning, and governance. By this design, TriFlow progressively narrows the search space, assembles constraint-consistent itineraries via rule-LLM collaboration, and performs bounded iterative refinement to ensure global feasibility and personalisation. Evaluations on TravelPlanner and TripTailor benchmarks demonstrated state-of-the-art results, achieving 91.1% and 97% final pass rates, respectively, with over 10x runtime efficiency improvement compared to current SOTA. --- ### A-LAMP: Agentic LLM-Based Framework for Automated MDP Modeling and Policy Generation Authors: Hong Je-Gal, Chan-Bin Yi, Hyun-Suk Lee Published: 2025-12-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.11270v1 Applying reinforcement learning (RL) to real-world tasks requires converting informal descriptions into a formal Markov decision process (MDP), implementing an executable environment, and training a policy agent. Automating this process is challenging due to modeling errors, fragile code, and misaligned objectives, which often impede policy training. We introduce an agentic large language model (LLM)-based framework for automated MDP modeling and policy generation (A-LAMP), that automatically translates free-form natural language task descriptions into an MDP formulation and trained policy. The framework decomposes modeling, coding, and training into verifiable stages, ensuring semantic alignment throughout the pipeline. Across both classic control and custom RL domains, A-LAMP consistently achieves higher policy generation capability than a single state-of-the-art LLM model. Notably, even its lightweight variant, which is built on smaller language models, approaches the performance of much larger models. Failure analysis reveals why these improvements occur. In addition, a case study also demonstrates that A-LAMP generates environments and policies that preserve the task's optimality, confirming its correctness and reliability. --- ### A Scalable Multi-GPU Framework for Encrypted Large-Model Inference Authors: Siddharth Jayashankar, Joshua Kim, Michael B. Sullivan, Wenting Zheng, Dimitrios Skarlatos Published: 2025-12-12 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.11269v1 Encrypted AI using fully homomorphic encryption (FHE) provides strong privacy guarantees; but its slow performance has limited practical deployment. Recent works proposed ASICs to accelerate FHE, but require expensive advanced manufacturing processes that constrain their accessibility. GPUs are a far more accessible platform, but achieving ASIC-level performance using GPUs has remained elusive. Furthermore, state-of-the-art approaches primarily focus on small models that fit comfortably within a single device. Supporting large models such as LLMs in FHE introduces a dramatic increase in computational complexity that requires optimized GPU kernels, along with managing terabyte-scale memory footprints that far exceed the capacity of a single GPU. This paper presents Cerium, a multi-GPU framework for FHE inference on large models. Cerium integrates a domain-specific language, an optimizing compiler, and a runtime system to automatically generate high-performance GPU kernels, manage terabyte-scale memory footprints, and parallelize computation across multiple GPUs. It introduces new IR constructs, compiler passes, sparse polynomial representations, memory-efficient data layouts, and communication-aware parallelization techniques that together enable encrypted inference for models ranging from small CNNs to Llama3-8B. We build Cerium on NVIDIA GPUs and demonstrate significant performance gains. For small models, Cerium outperforms expert-written hand-optimized GPU libraries by up to 2.25 times. Cerium achieves performance competitive with state-of-the-art FHE ASICs, outright matching prior FHE ASIC CraterLake. It is the first GPU system to execute bootstrapping in under 10 milliseconds, achieving 7.5 milliseconds, and is the first to demonstrate encrypted inference for BERT-Base and Llama3-8B in 8 seconds and 134 seconds, respectively. --- ### Evaluating the Efficacy of Sentinel-2 versus Aerial Imagery in Serrated Tussock Classification Authors: Rezwana Sultana, Manzur Murshed, Kathryn Sheffield, Singarayer Florentine, Tsz-Kwan Lee, Shyh Wei Teng Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11267v1 Invasive species pose major global threats to ecosystems and agriculture. Serrated tussock (\textit{Nassella trichotoma}) is a highly competitive invasive grass species that disrupts native grasslands, reduces pasture productivity, and increases land management costs. In Victoria, Australia, it presents a major challenge due to its aggressive spread and ecological impact. While current ground surveys and subsequent management practices are effective at small scales, they are not feasible for landscape-scale monitoring. Although aerial imagery offers high spatial resolution suitable for detailed classification, its high cost limits scalability. Satellite-based remote sensing provides a more cost-effective and scalable alternative, though often with lower spatial resolution. This study evaluates whether multi-temporal Sentinel-2 imagery, despite its lower spatial resolution, can provide a comparable and cost-effective alternative for landscape-scale monitoring of serrated tussock by leveraging its higher spectral resolution and seasonal phenological information. A total of eleven models have been developed using various combinations of spectral bands, texture features, vegetation indices, and seasonal data. Using a random forest classifier, the best-performing Sentinel-2 model (M76*) has achieved an Overall Accuracy (OA) of 68\% and an Overall Kappa (OK) of 0.55, slightly outperforming the best-performing aerial imaging model's OA of 67\% and OK of 0.52 on the same dataset. These findings highlight the potential of multi-seasonal feature-enhanced satellite-based models for scalable invasive species classification. --- ### Features Emerge as Discrete States: The First Application of SAEs to 3D Representations Authors: Albert Miao, Chenliang Zhou, Jiawei Zhou, Cengiz Oztireli Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11263v2 Sparse Autoencoders (SAEs) are a powerful dictionary learning technique for decomposing neural network activations, translating the hidden state into human ideas with high semantic value despite no external intervention or guidance. However, this technique has rarely been applied outside of the textual domain, limiting theoretical explorations of feature decomposition. We present the first application of SAEs to the 3D domain, analyzing the features used by a state-of-the-art 3D reconstruction VAE applied to 53k 3D models from the Objaverse dataset. We observe that the network encodes discrete rather than continuous features, leading to our key finding: such models approximate a discrete state space, driven by phase-like transitions from feature activations. Through this state transition framework, we address three otherwise unintuitive behaviors - the inclination of the reconstruction model towards positional encoding representations, the sigmoidal behavior of reconstruction loss from feature ablation, and the bimodality in the distribution of phase transition points. This final observation suggests the model redistributes the interference caused by superposition to prioritize the saliency of different features. Our work not only compiles and explains unexpected phenomena regarding feature decomposition, but also provides a framework to explain the model's feature learning dynamics. The code and dataset of encoded 3D objects will be available on release. --- ### Leveraging LLMs for Title and Abstract Screening for Systematic Review: A Cost-Effective Dynamic Few-Shot Learning Approach Authors: Yun-Chung Liu, Rui Yang, Jonathan Chong Kai Liew, Ziran Yin, Henry Foote, Christopher J. Lindsell, Chuan Hong Published: 2025-12-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.11261v1 Systematic reviews are a key component of evidence-based medicine, playing a critical role in synthesizing existing research evidence and guiding clinical decisions. However, with the rapid growth of research publications, conducting systematic reviews has become increasingly burdensome, with title and abstract screening being one of the most time-consuming and resource-intensive steps. To mitigate this issue, we designed a two-stage dynamic few-shot learning (DFSL) approach aimed at improving the efficiency and performance of large language models (LLMs) in the title and abstract screening task. Specifically, this approach first uses a low-cost LLM for initial screening, then re-evaluates low-confidence instances using a high-performance LLM, thereby enhancing screening performance while controlling computational costs. We evaluated this approach across 10 systematic reviews, and the results demonstrate its strong generalizability and cost-effectiveness, with potential to reduce manual screening burden and accelerate the systematic review process in practical applications. --- ### Do We Need Reformer for Vision? An Experimental Comparison with Vision Transformers Authors: Ali El Bellaj, Mohammed-Amine Cheddadi, Rhassan Berber Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11260v2 Transformers have recently demonstrated strong performance in computer vision, with Vision Transformers (ViTs) leveraging self-attention to capture both low-level and high-level image features. However, standard ViTs remain computationally expensive, since global self-attention scales quadratically with the number of tokens, which limits their practicality for high-resolution inputs and resource-constrained settings. In this work, we investigate the Reformer architecture as an alternative vision backbone. By combining patch-based tokenization with locality-sensitive hashing (LSH) attention, our model approximates global self-attention while reducing its theoretical time complexity from $\mathcal{O}(n^2)$ to $\mathcal{O}(n \log n)$ in the sequence length $n$. We evaluate the proposed Reformer-based vision model on CIFAR-10 to assess its behavior on small-scale datasets, on ImageNet-100 to study its accuracy--efficiency trade-off in a more realistic setting, and on a high-resolution medical imaging dataset to evaluate the model under longer token sequences. While the Reformer achieves higher accuracy on CIFAR-10 compared to our ViT-style baseline, the ViT model consistently outperforms the Reformer in our experiments in terms of practical efficiency and end-to-end computation time across the larger and higher-resolution settings. These results suggest that, despite the theoretical advantages of LSH-based attention, meaningful computation gains require sequence lengths substantially longer than those produced by typical high-resolution images. --- ### Multi-Intent Spoken Language Understanding: Methods, Trends, and Challenges Authors: Di Wu, Ruiyu Fang, Liting Jiang, Shuangyong Song, Xiaomeng Huang, Shiquan Wang, Zhongqiu Li, Lingling Shi, Mengjiao Bao, Yongxiang Li, Hao Huang Published: 2025-12-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.11258v1 Multi-intent spoken language understanding (SLU) involves two tasks: multiple intent detection and slot filling, which jointly handle utterances containing more than one intent. Owing to this characteristic, which closely reflects real-world applications, the task has attracted increasing research attention, and substantial progress has been achieved. However, there remains a lack of a comprehensive and systematic review of existing studies on multi-intent SLU. To this end, this paper presents a survey of recent advances in multi-intent SLU. We provide an in-depth overview of previous research from two perspectives: decoding paradigms and modeling approaches. On this basis, we further compare the performance of representative models and analyze their strengths and limitations. Finally, we discuss the current challenges and outline promising directions for future research. We hope this survey will offer valuable insights and serve as a useful reference for advancing research in multi-intent SLU. --- ### A Simple Generalisation of the Implicit Dynamics of In-Context Learning Authors: Francesco Innocenti, El Mehdi Achour Published: 2025-12-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.11255v1 In-context learning (ICL) refers to the ability of a model to learn new tasks from examples in its input without any parameter updates. In contrast to previous theories of ICL relying on toy models and data settings, recently it has been shown that an abstraction of a transformer block can be seen as implicitly updating the weights of its feedforward network according to the context (Dherin et al., 2025). Here, we provide a simple generalisation of this result for (i) all sequence positions beyond the last, (ii) any transformer block beyond the first, and (iii) more realistic residual blocks including layer normalisation. We empirically verify our theory on simple in-context linear regression tasks and investigate the relationship between the implicit updates related to different tokens within and between blocks. These results help to bring the theory of Dherin et al. (2025) even closer to practice, with potential for validation on large-scale models. --- ### PersonaLive! Expressive Portrait Image Animation for Live Streaming Authors: Zhiyuan Li, Chi-Man Pun, Chen Fang, Jue Wang, Xiaodong Cun Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11253v1 Current diffusion-based portrait animation models predominantly focus on enhancing visual quality and expression realism, while overlooking generation latency and real-time performance, which restricts their application range in the live streaming scenario. We propose PersonaLive, a novel diffusion-based framework towards streaming real-time portrait animation with multi-stage training recipes. Specifically, we first adopt hybrid implicit signals, namely implicit facial representations and 3D implicit keypoints, to achieve expressive image-level motion control. Then, a fewer-step appearance distillation strategy is proposed to eliminate appearance redundancy in the denoising process, greatly improving inference efficiency. Finally, we introduce an autoregressive micro-chunk streaming generation paradigm equipped with a sliding training strategy and a historical keyframe mechanism to enable low-latency and stable long-term video generation. Extensive experiments demonstrate that PersonaLive achieves state-of-the-art performance with up to 7-22x speedup over prior diffusion-based portrait animation models. --- ### Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language Authors: Yunkai Zhang, Yawen Zhang, Ming Zheng, Kezhen Chen, Chongyang Gao, Ruian Ge, Siyuan Teng, Amine Jelloul, Jinmeng Rao, Xiaoyuan Guo, Chiang-Wei Fang, Zeyu Zheng et al. Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11251v1 Time-series data is critical across many scientific and industrial domains, including environmental analysis, agriculture, transportation, and finance. However, mining insights from this data typically requires deep domain expertise, a process that is both time-consuming and labor-intensive. In this paper, we propose \textbf{Insight Miner}, a large-scale multimodal model (LMM) designed to generate high-quality, comprehensive time-series descriptions enriched with domain-specific knowledge. To facilitate this, we introduce \textbf{TS-Insights}\footnote{Available at \href{https://huggingface.co/datasets/zhykoties/time-series-language-alignment}{https://huggingface.co/datasets/zhykoties/time-series-language-alignment}.}, the first general-domain dataset for time series and language alignment. TS-Insights contains 100k time-series windows sampled from 20 forecasting datasets. We construct this dataset using a novel \textbf{agentic workflow}, where we use statistical tools to extract features from raw time series before synthesizing them into coherent trend descriptions with GPT-4. Following instruction tuning on TS-Insights, Insight Miner outperforms state-of-the-art multimodal models, such as LLaVA \citep{liu2023llava} and GPT-4, in generating time-series descriptions and insights. Our findings suggest a promising direction for leveraging LMMs in time series analysis, and serve as a foundational step toward enabling LLMs to interpret time series as a native input modality. --- ### Multi-Objective Reinforcement Learning for Large-Scale Mixed Traffic Control Authors: Iftekharul Islam, Weizi Li Published: 2025-12-12 Categories: cs.MA, cs.LG arXiv: https://arxiv.org/abs/2512.11247v1 Effective mixed traffic control requires balancing efficiency, fairness, and safety. Existing approaches excel at optimizing efficiency and enforcing safety constraints but lack mechanisms to ensure equitable service, resulting in systematic starvation of vehicles on low-demand approaches. We propose a hierarchical framework combining multi-objective reinforcement learning for local intersection control with strategic routing for network-level coordination. Our approach introduces a Conflict Threat Vector that provides agents with explicit risk signals for proactive conflict avoidance, and a queue parity penalty that ensures equitable service across all traffic streams. Extensive experiments on a real-world network across different robot vehicle (RV) penetration rates demonstrate substantial improvements: up to 53% reductions in average wait time, up to 86% reductions in maximum starvation, and up to 86\% reduction in conflict rate compared to baselines, while maintaining fuel efficiency. Our analysis reveals that strategic routing effectiveness scales with RV penetration, becoming increasingly valuable at higher autonomy levels. The results demonstrate that multi-objective optimization through well-curated reward functions paired with strategic RV routing yields significant benefits in fairness and safety metrics critical for equitable mixed-autonomy deployment. --- ### Task-Aware Multi-Expert Architecture For Lifelong Deep Learning Authors: Jianyu Wang, Jacob Nean-Hua Sheikh, Cat P. Le, Hoda Bidkhori Published: 2025-12-12 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.11243v1 Lifelong deep learning (LDL) trains neural networks to learn sequentially across tasks while preserving prior knowledge. We propose Task-Aware Multi-Expert (TAME), a continual learning algorithm that leverages task similarity to guide expert selection and knowledge transfer. TAME maintains a pool of pretrained neural networks and activates the most relevant expert for each new task. A shared dense layer integrates features from the chosen expert to generate predictions. To reduce catastrophic forgetting, TAME uses a replay buffer that stores representative samples and embeddings from previous tasks and reuses them during training. An attention mechanism further prioritizes the most relevant stored information for each prediction. Together, these components allow TAME to adapt flexibly while retaining important knowledge across evolving task sequences. Experiments on binary classification tasks derived from CIFAR-100 show that TAME improves accuracy on new tasks while sustaining performance on earlier ones, highlighting its effectiveness in balancing adaptation and retention in lifelong learning settings. --- ### Cross-modal Prompting for Balanced Incomplete Multi-modal Emotion Recognition Authors: Wen-Jue He, Xiaofeng Zhu, Zheng Zhang Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11239v2 Incomplete multi-modal emotion recognition (IMER) aims at understanding human intentions and sentiments by comprehensively exploring the partially observed multi-source data. Although the multi-modal data is expected to provide more abundant information, the performance gap and modality under-optimization problem hinder effective multi-modal learning in practice, and are exacerbated in the confrontation of the missing data. To address this issue, we devise a novel Cross-modal Prompting (ComP) method, which emphasizes coherent information by enhancing modality-specific features and improves the overall recognition accuracy by boosting each modality's performance. Specifically, a progressive prompt generation module with a dynamic gradient modulator is proposed to produce concise and consistent modality semantic cues. Meanwhile, cross-modal knowledge propagation selectively amplifies the consistent information in modality features with the delivered prompts to enhance the discrimination of the modality-specific output. Additionally, a coordinator is designed to dynamically re-weight the modality outputs as a complement to the balance strategy to improve the model's efficacy. Extensive experiments on 4 datasets with 7 SOTA methods under different missing rates validate the effectiveness of our proposed method. --- ### WildCap: Facial Albedo Capture in the Wild via Hybrid Inverse Rendering Authors: Yuxuan Han, Xin Ming, Tianxiao Li, Zhuofan Shen, Qixuan Zhang, Lan Xu, Feng Xu Published: 2025-12-12 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2512.11237v2 Existing methods achieve high-quality facial albedo capture under controllable lighting, which increases capture cost and limits usability. We propose WildCap, a novel method for high-quality facial albedo capture from a smartphone video recorded in the wild. To disentangle high-quality albedo from complex lighting effects in in-the-wild captures, we propose a novel hybrid inverse rendering framework. We first apply a data-driven method, i.e., SwitchLight, to convert the captured images into more constrained conditions and then adopt model-based inverse rendering. However, unavoidable local artifacts in network predictions, such as shadow-baking, are non-physical and thus hinder accurate inverse rendering of lighting and material. To address this, we propose a novel texel grid lighting model to explain non-physical effects as clean albedo illuminated by local physical lighting. During optimization, we jointly sample a diffusion prior for the albedo map and optimize the lighting, effectively resolving scale ambiguity between local lights and albedo. Other reflectance maps are then predicted from the albedo. Our method achieves significantly better results than prior arts in the same capture setup, closing the quality gap between in-the-wild and controllable recordings by a large margin. --- ### RoomPilot: Controllable Indoor Scene Synthesis via Multimodal Semantic Parsing Authors: Wentang Chen, Shougao Zhang, Yiman Zhang, Tianhao Zhou, Ruihui Li Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11234v2 Generating controllable indoor scenes is fundamental to applications in game development, architectural visualization, and embodied AI. However, existing approaches either support a limited input modalities or rely on implicit generation processes that hinder precise control over scene structure and semantics. To address these limitations, we introduce RoomPilot, a unified framework for controllable indoor scene synthesis from multi-modal inputs, including textual descriptions and CAD floor plans. RoomPilot maps heterogeneous inputs into an Indoor Domain-Specific Language (IDSL), which serves as a structured and interpretable semantic representation for describing indoor scenes. Built upon IDSL, RoomPilot presents a hierarchical synthesis pipeline that progressively organizes scenes at the building, room, and object levels, promoting structural coherence and functional consistency across multi-room layouts. Moreover, RoomPilot constructs a curated asset dataset with rich semantic annotations to support high-quality scene synthesis, improving visual realism and appearance consistency. Extensive experiments demonstrate effective multi-modal understanding, fine-grained controllability in scene generation, and improved physical consistency and visual fidelity, marking a significant step toward controllable 3D indoor scene synthesis. Code and model will be available. --- ### REST: Diffusion-based Real-time End-to-end Streaming Talking Head Generation via ID-Context Caching and Asynchronous Streaming Distillation Authors: Haotian Wang, Yuzhe Weng, Jun Du, Haoran Xu, Xiaoyan Wu, Shan He, Bing Yin, Cong Liu, Qingfeng Liu Published: 2025-12-12 Categories: cs.CV, cs.SD arXiv: https://arxiv.org/abs/2512.11229v3 Diffusion models have significantly advanced the field of talking head generation (THG). However, slow inference speeds and prevalent non-autoregressive paradigms severely constrain the application of diffusion-based THG models. In this study, we propose REST, a pioneering diffusion-based, real-time, end-to-end streaming audio-driven talking head generation framework. To support real-time end-to-end generation, a compact video latent space is first learned through a spatiotemporal variational autoencoder with a high compression ratio. Additionally, to enable semi-autoregressive streaming within the compact video latent space, we introduce an ID-Context Cache mechanism, which integrates ID-Sink and Context-Cache principles into key-value caching for maintaining identity consistency and temporal coherence during long-term streaming generation. Furthermore, an Asynchronous Streaming Distillation (ASD) strategy is proposed to mitigate error accumulation and enhance temporal consistency in streaming generation, leveraging a non-streaming teacher with an asynchronous noise schedule to supervise the streaming student. REST bridges the gap between autoregressive and diffusion-based approaches, achieving a breakthrough in efficiency for applications requiring real-time THG. Experimental results demonstrate that REST outperforms state-of-the-art methods in both generation speed and overall performance. --- ### FutureX: Enhance End-to-End Autonomous Driving via Latent Chain-of-Thought World Model Authors: Hongbin Lin, Yiming Yang, Yifan Zhang, Chaoda Zheng, Jie Feng, Sheng Wang, Zhennan Wang, Shijia Chen, Boyang Wang, Yu Zhang, Xianming Liu, Shuguang Cui et al. Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11226v1 In autonomous driving, end-to-end planners learn scene representations from raw sensor data and utilize them to generate a motion plan or control actions. However, exclusive reliance on the current scene for motion planning may result in suboptimal responses in highly dynamic traffic environments where ego actions further alter the future scene. To model the evolution of future scenes, we leverage the World Model to represent how the ego vehicle and its environment interact and change over time, which entails complex reasoning. The Chain of Thought (CoT) offers a promising solution by forecasting a sequence of future thoughts that subsequently guide trajectory refinement. In this paper, we propose FutureX, a CoT-driven pipeline that enhances end-to-end planners to perform complex motion planning via future scene latent reasoning and trajectory refinement. Specifically, the Auto-think Switch examines the current scene and decides whether additional reasoning is required to yield a higher-quality motion plan. Once FutureX enters the Thinking mode, the Latent World Model conducts a CoT-guided rollout to predict future scene representation, enabling the Summarizer Module to further refine the motion plan. Otherwise, FutureX operates in an Instant mode to generate motion plans in a forward pass for relatively simple scenes. Extensive experiments demonstrate that FutureX enhances existing methods by producing more rational motion plans and fewer collisions without compromising efficiency, thereby achieving substantial overall performance gains, e.g., 6.2 PDMS improvement for TransFuser on NAVSIM. Code will be released. --- ### VFMF: World Modeling by Forecasting Vision Foundation Model Features Authors: Gabrijel Boduljak, Yushi Lan, Christian Rupprecht, Andrea Vedaldi Published: 2025-12-12 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.11225v1 Forecasting from partial observations is central to world modeling. Many recent methods represent the world through images, and reduce forecasting to stochastic video generation. Although such methods excel at realism and visual fidelity, predicting pixels is computationally intensive and not directly useful in many applications, as it requires translating RGB into signals useful for decision making. An alternative approach uses features from vision foundation models (VFMs) as world representations, performing deterministic regression to predict future world states. These features can be directly translated into actionable signals such as semantic segmentation and depth, while remaining computationally efficient. However, deterministic regression averages over multiple plausible futures, undermining forecast accuracy by failing to capture uncertainty. To address this crucial limitation, we introduce a generative forecaster that performs autoregressive flow matching in VFM feature space. Our key insight is that generative modeling in this space requires encoding VFM features into a compact latent space suitable for diffusion. We show that this latent space preserves information more effectively than previously used PCA-based alternatives, both for forecasting and other applications, such as image generation. Our latent predictions can be easily decoded into multiple useful and interpretable output modalities: semantic segmentation, depth, surface normals, and even RGB. With matched architecture and compute, our method produces sharper and more accurate predictions than regression across all modalities. Our results suggest that stochastic conditional generation of VFM features offers a promising and scalable foundation for future world models. --- ### Adaptive Soft Rolling KV Freeze with Entropy-Guided Recovery: Sublinear Memory Growth for Efficient LLM Inference Authors: Adilet Metinov, Gulida M. Kudakeeva, Bolotbek uulu Nursultan, Gulnara D. Kabaeva Published: 2025-12-12 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.11221v1 We present Adaptive Soft Rolling KV Freeze with Entropy-Guided Recovery (ASR-KF-EGR), a training-free inference-time framework for efficient large language model generation. Our method introduces a reversible soft-freeze mechanism that temporarily suspends key-value (KV) updates for low-importance tokens identified within a sliding attention window. Unlike eviction-based approaches that permanently discard context, ASR-KF-EGR preserves all tokens in off-GPU storage and restores them on demand. We extend the framework with sublinear freeze scheduling, where freeze duration grows sublinearly with repeated low-importance detections, preventing over-aggressive compression. Preliminary experiments on LLaMA-3 8B demonstrate 55-67% reduction in active KV cache size while maintaining generation quality and passing needle-in-haystack retrieval tests. The method is architecture-agnostic, requires no fine-tuning, and provides a practical solution for memory-constrained deployment of long-context LLMs. --- ### Latent Variable Causal Discovery under Selection Bias Authors: Haoyue Dai, Yiwen Qiu, Ignavier Ng, Xinshuai Dong, Peter Spirtes, Kun Zhang Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11219v1 Addressing selection bias in latent variable causal discovery is important yet underexplored, largely due to a lack of suitable statistical tools: While various tools beyond basic conditional independencies have been developed to handle latent variables, none have been adapted for selection bias. We make an attempt by studying rank constraints, which, as a generalization to conditional independence constraints, exploits the ranks of covariance submatrices in linear Gaussian models. We show that although selection can significantly complicate the joint distribution, interestingly, the ranks in the biased covariance matrices still preserve meaningful information about both causal structures and selection mechanisms. We provide a graph-theoretic characterization of such rank constraints. Using this tool, we demonstrate that the one-factor model, a classical latent variable model, can be identified under selection bias. Simulations and real-world experiments confirm the effectiveness of using our rank constraints. --- ### Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policy Authors: Kechun Xu, Zhenjie Zhu, Anzhe Chen, Shuqi Zhao, Qing Huang, Yifei Yang, Haojian Lu, Rong Xiong, Masayoshi Tomizuka, Yue Wang Published: 2025-12-12 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.11218v1 The pursuit of out-of-distribution generalization in Vision-Language-Action (VLA) models is often hindered by catastrophic forgetting of the Vision-Language Model (VLM) backbone during fine-tuning. While co-training with external reasoning data helps, it requires experienced tuning and data-related overhead. Beyond such external dependencies, we identify an intrinsic cause within VLA datasets: modality imbalance, where language diversity is much lower than visual and action diversity. This imbalance biases the model toward visual shortcuts and language forgetting. To address this, we introduce BayesVLA, a Bayesian factorization that decomposes the policy into a visual-action prior, supporting seeing-to-act, and a language-conditioned likelihood, enabling prompt-to-specify. This inherently preserves generalization and promotes instruction following. We further incorporate pre- and post-contact phases to better leverage pre-trained foundation models. Information-theoretic analysis formally validates our effectiveness in mitigating shortcut learning. Extensive experiments show superior generalization to unseen instructions, objects, and environments compared to existing methods. Project page is available at: https://xukechun.github.io/papers/BayesVLA. --- ### SmokeBench: Evaluating Multimodal Large Language Models for Wildfire Smoke Detection Authors: Tianye Qi, Weihao Li, Nick Barnes Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11215v1 Wildfire smoke is transparent, amorphous, and often visually confounded with clouds, making early-stage detection particularly challenging. In this work, we introduce a benchmark, called SmokeBench, to evaluate the ability of multimodal large language models (MLLMs) to recognize and localize wildfire smoke in images. The benchmark consists of four tasks: (1) smoke classification, (2) tile-based smoke localization, (3) grid-based smoke localization, and (4) smoke detection. We evaluate several MLLMs, including Idefics2, Qwen2.5-VL, InternVL3, Unified-IO 2, Grounding DINO, GPT-4o, and Gemini-2.5 Pro. Our results show that while some models can classify the presence of smoke when it covers a large area, all models struggle with accurate localization, especially in the early stages. Further analysis reveals that smoke volume is strongly correlated with model performance, whereas contrast plays a comparatively minor role. These findings highlight critical limitations of current MLLMs for safety-critical wildfire monitoring and underscore the need for methods that improve early-stage smoke localization. --- ### FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaboration Authors: Dongwon Jung, Peng Shi, Muhao Chen, Yi Zhang Published: 2025-12-12 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.11213v2 Scaling test-time computation has been shown to significantly improve large language model (LLM) performance without additional training. However, extending these techniques to multi-agent systems remains challenging: existing approaches lack principled mechanisms for allocating compute to enable effective collaboration, scaling coordination itself, or optimizing compute usage under explicit budget constraints. To address this gap, we propose FutureWeaver, a framework for planning and optimizing test-time compute allocation in multi-agent systems under fixed budgets. It introduces collaboration modules, formalized as modular, callable functions that encapsulate reusable multi-agent workflows and are automatically induced via self-play reflection from recurring interaction patterns. Building on these modules, it employs \emph{a dual-level planning architecture} that jointly performs short-horizon action selection and long-horizon abstract lookahead to optimize inference trajectories under budget constraints. Experiments on complex agent benchmarks demonstrate that FutureWeaver consistently outperforms baselines across diverse budget settings, validating its effectiveness for multi-agent collaboration in inference-time optimization. --- ### AutoRefiner: Improving Autoregressive Video Diffusion Models via Reflective Refinement Over the Stochastic Sampling Path Authors: Zhengyang Yu, Akio Hayakawa, Masato Ishii, Qingtao Yu, Takashi Shibuya, Jing Zhang, Yuki Mitsufuji Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11203v2 Autoregressive video diffusion models (AR-VDMs) show strong promise as scalable alternatives to bidirectional VDMs, enabling real-time and interactive applications. Yet there remains room for improvement in their sample fidelity. A promising solution is inference-time alignment, which optimizes the noise space to improve sample fidelity without updating model parameters. Yet, optimization- or search-based methods are computationally impractical for AR-VDMs. Recent text-to-image (T2I) works address this via feedforward noise refiners that modulate sampled noises in a single forward pass. Can such noise refiners be extended to AR-VDMs? We identify the failure of naively extending T2I noise refiners to AR-VDMs and propose AutoRefiner-a noise refiner tailored for AR-VDMs, with two key designs: pathwise noise refinement and a reflective KV-cache. Experiments demonstrate that AutoRefiner serves as an efficient plug-in for AR-VDMs, effectively enhancing sample fidelity by refining noise along stochastic denoising paths. --- ### amc: The Automated Mission Classifier for Telescope Bibliographies Authors: John F. Wu, Joshua E. G. Peek, Sophie J. Miller, Jenny Novacescu, Achu J. Usha, Christopher A. Wilkinson Published: 2025-12-12 Categories: astro-ph.IM, cs.AI, cs.DL, cs.LG arXiv: https://arxiv.org/abs/2512.11202v1 Telescope bibliographies record the pulse of astronomy research by capturing publication statistics and citation metrics for telescope facilities. Robust and scalable bibliographies ensure that we can measure the scientific impact of our facilities and archives. However, the growing rate of publications threatens to outpace our ability to manually label astronomical literature. We therefore present the Automated Mission Classifier (amc), a tool that uses large language models (LLMs) to identify and categorize telescope references by processing large quantities of paper text. A modified version of amc performs well on the TRACS Kaggle challenge, achieving a macro $F_1$ score of 0.84 on the held-out test set. amc is valuable for other telescopes beyond TRACS; we developed the initial software for identifying papers that featured scientific results by NASA missions. Additionally, we investigate how amc can also be used to interrogate historical datasets and surface potential label errors. Our work demonstrates that LLM-based applications offer powerful and scalable assistance for library sciences. --- ### Fast EXP3 Algorithms Authors: Ryoma Sato, Shinji Ito Published: 2025-12-12 Categories: cs.LG, cs.AI, cs.DS arXiv: https://arxiv.org/abs/2512.11201v1 We point out that EXP3 can be implemented in constant time per round, propose more practical algorithms, and analyze the trade-offs between the regret bounds and time complexities of these algorithms. --- ### Theoretical Foundations of GPU-Native Compilation for Rapid Code Iteration Authors: Adilet Metinov, Gulida M. Kudakeeva, Gulnara D. Kabaeva Published: 2025-12-12 Categories: cs.DC, cs.LG, cs.PL arXiv: https://arxiv.org/abs/2512.11200v1 Current AI code generation systems suffer from significant latency bottlenecks due to CPU-GPU data transfers during compilation, execution, and testing phases. We establish theoretical foundations for three complementary approaches to GPU-native compilation that eliminate these transfers: (1) parallel traditional compilation adapted for GPU execution, (2) neural compilation using learned sequence-to-sequence translation with probabilistic verification, and (3) hybrid architectures combining both strategies. We derive latency and energy bounds demonstrating potential speedups of 10-100x for code iteration cycles. Our analysis shows that traditional GPU compilation provides 2-5x improvements through transfer elimination, neural compilation achieves 10-100x speedups via massive parallelism, and hybrid approaches offer practical deployment paths with guaranteed correctness. We formalize the probabilistic verification framework that enables trading compilation accuracy for parallel exploration, and discuss implications for self-improving AI systems and future analog computing substrates. --- ### CADKnitter: Compositional CAD Generation from Text and Geometry Guidance Authors: Tri Le, Khang Nguyen, Baoru Huang, Tung D. Ta, Anh Nguyen Published: 2025-12-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.11199v2 Computer-aided design (CAD) defines 3D models as compact, precise, and editable representations, making it directly useful for several fields. Recently, CAD generation has been gaining more attention in both the research community and industry. Crafting CAD models has long been a painstaking and time-intensive task, demanding both precision and expertise from designers. Prior works have achieved early success in single-part CAD generation, which is not well-suited for real-world applications, as multiple parts need to be assembled under semantic constraints and geometric compatibility. In this paper, we propose CADKnitter, a compositional CAD generation framework with geometric-guiding cues to steer diffusion sampling. CADKnitter is able to generate a complementary CAD part that follows both the geometric constraints of the given CAD model and the semantic constraints of the desired design text prompt. We also curate a dataset, so-called KnitCAD, containing over 310,000 samples of CAD models, along with textual prompts and assembly metadata that provide semantic and geometric constraints. Intensive experiments demonstrate that our proposed method outperforms other state-of-the-art baselines by a clear margin. Our project page is available at https://cadknitter.github.io/. --- ### Beyond Memorization: Selective Learning for Copyright-Safe Diffusion Model Training Authors: Divya Kothandaraman, Jaclyn Pytlarz Published: 2025-12-12 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.11194v2 Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While conventional dememorization techniques, such as regularization and data filtering, limit overfitting to specific training examples, they fail to systematically prevent the internalization of prohibited concept-level features. Simply discarding all images containing a sensitive feature wastes invaluable training data, necessitating a method for selective learning at the concept level. We introduce a gradient projection method designed to enforce a stringent requirement of concept-level feature exclusion. Our defense operates during backpropagation by systematically identifying and excising training signals aligned with embeddings of prohibited attributes. Specifically, we project each gradient update onto the orthogonal complement of the sensitive feature's embedding space, thereby zeroing out its influence on the model's weights. Our method integrates seamlessly into standard diffusion model training pipelines and complements existing defenses. We analyze our method against an adversary aiming for feature extraction. In extensive experiments, we demonstrate that our framework drastically reduces memorization while rigorously preserving generation quality and semantic fidelity. By reframing memorization control as selective learning, our approach establishes a new paradigm for IP-safe and privacy-preserving generative AI. --- ### SciLaD: A Large-Scale, Transparent, Reproducible Dataset for Natural Scientific Language Processing Authors: Luca Foppiano, Sotaro Takeshita, Pedro Ortiz Suarez, Ekaterina Borisova, Raia Abu Ahmad, Malte Ostendorff, Fabio Barth, Julian Moreno-Schneider, Georg Rehm Published: 2025-12-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.11192v2 SciLaD is a novel, large-scale dataset of scientific language constructed entirely using open-source frameworks and publicly available data sources. It comprises a curated English split containing over 10 million scientific publications and a multilingual, unfiltered TEI XML split including more than 35 million publications. We also publish the extensible pipeline for generating SciLaD. The dataset construction and processing workflow demonstrates how open-source tools can enable large-scale, scientific data curation while maintaining high data quality. Finally, we pre-train a RoBERTa model on our dataset and evaluate it across a comprehensive set of benchmarks, achieving performance comparable to other scientific language models of similar size, validating the quality and utility of SciLaD. We publish the dataset and evaluation pipeline to promote reproducibility, transparency, and further research in natural scientific language processing and understanding, including scholarly document processing. --- ### Multi-task Learning with Extended Temporal Shift Module for Temporal Action Localization Authors: Anh-Kiet Duong, Petra Gomez-Krämer Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11189v1 We present our solution to the BinEgo-360 Challenge at ICCV 2025, which focuses on temporal action localization (TAL) in multi-perspective and multi-modal video settings. The challenge provides a dataset containing panoramic, third-person, and egocentric recordings, annotated with fine-grained action classes. Our approach is built on the Temporal Shift Module (TSM), which we extend to handle TAL by introducing a background class and classifying fixed-length non-overlapping intervals. We employ a multi-task learning framework that jointly optimizes for scene classification and TAL, leveraging contextual cues between actions and environments. Finally, we integrate multiple models through a weighted ensemble strategy, which improves robustness and consistency of predictions. Our method is ranked first in both the initial and extended rounds of the competition, demonstrating the effectiveness of combining multi-task learning, an efficient backbone, and ensemble learning for TAL. --- ### Deep Learning--Accelerated Multi-Start Large Neighborhood Search for Real-time Freight Bundling Authors: Haohui Zhang, Wouter van Heeswijk, Xinyu Hu, Neil Yorke-Smith, Martijn Mes Published: 2025-12-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.11187v1 Online Freight Exchange Systems (OFEX) play a crucial role in modern freight logistics by facilitating real-time matching between shippers and carrier. However, efficient combinatorial bundling of transporation jobs remains a bottleneck. We model the OFEX combinatorial bundling problem as a multi-commodity one-to-one pickup-and-delivery selective traveling salesperson problem (m1-PDSTSP), which optimizes revenue-driven freight bundling under capacity, precedence, and route-length constraints. The key challenge is to couple combinatorial bundle selection with pickup-and-delivery routing under sub-second latency. We propose a learning--accelerated hybrid search pipeline that pairs a Transformer Neural Network-based constructive policy with an innovative Multi-Start Large Neighborhood Search (MSLNS) metaheuristic within a rolling-horizon scheme in which the platform repeatedly freezes the current marketplace into a static snapshot and solves it under a short time budget. This pairing leverages the low-latency, high-quality inference of the learning-based constructor alongside the robustness of improvement search; the multi-start design and plausible seeds help LNS to explore the solution space more efficiently. Across benchmarks, our method outperforms state-of-the-art neural combinatorial optimization and metaheuristic baselines in solution quality with comparable time, achieving an optimality gap of less than 2\% in total revenue relative to the best available exact baseline method. To our knowledge, this is the first work to establish that a Deep Neural Network-based constructor can reliably provide high-quality seeds for (multi-start) improvement heuristics, with applicability beyond the \textit{m1-PDSTSP} to a broad class of selective traveling salesperson problems and pickup and delivery problems. --- ### Lightweight 3D Gaussian Splatting Compression via Video Codec Authors: Qi Yang, Geert Van Der Auwera, Zhu Li Published: 2025-12-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.11186v1 Current video-based GS compression methods rely on using Parallel Linear Assignment Sorting (PLAS) to convert 3D GS into smooth 2D maps, which are computationally expensive and time-consuming, limiting the application of GS on lightweight devices. In this paper, we propose a Lightweight 3D Gaussian Splatting (GS) Compression method based on Video codec (LGSCV). First, a two-stage Morton scan is proposed to generate blockwise 2D maps that are friendly for canonical video codecs in which the coding units (CU) are square blocks. A 3D Morton scan is used to permute GS primitives, followed by a 2D Morton scan to map the ordered GS primitives to 2D maps in a blockwise style. However, although the blockwise 2D maps report close performance to the PLAS map in high-bitrate regions, they show a quality collapse at medium-to-low bitrates. Therefore, a principal component analysis (PCA) is used to reduce the dimensionality of spherical harmonics (SH), and a MiniPLAS, which is flexible and fast, is designed to permute the primitives within certain block sizes. Incorporating SH PCA and MiniPLAS leads to a significant gain in rate-distortion (RD) performance, especially at medium and low bitrates. MiniPLAS can also guide the setting of the codec CU size configuration and significantly reduce encoding time. Experimental results on the MPEG dataset demonstrate that the proposed LGSCV achieves over 20% RD gain compared with state-of-the-art methods, while reducing 2D map generation time to approximately 1 second and cutting encoding time by 50%. The code is available at https://github.com/Qi-Yangsjtu/LGSCV . --- ### On the failure of ReLU activation for physics-informed machine learning Authors: Conor Rowan Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11184v2 Physics-informed machine learning uses governing ordinary and/or partial differential equations to train neural networks to represent the solution field. Like any machine learning problem, the choice of activation function influences the characteristics and performance of the solution obtained from physics-informed training. Several studies have compared common activation functions on benchmark differential equations, and have unanimously found that the rectified linear unit (ReLU) is outperformed by competitors such as the sigmoid, hyperbolic tangent, and swish activation functions. In this work, we diagnose the poor performance of ReLU on physics-informed machine learning problems. While it is well-known that the piecewise linear form of ReLU prevents it from being used on second-order differential equations, we show that ReLU fails even on variational problems involving only first derivatives. We identify the cause of this failure as second derivatives of the activation, which are taken not in the formulation of the loss, but in the process of training. Namely, we show that automatic differentiation in PyTorch fails to characterize derivatives of discontinuous fields, which causes the gradient of the physics-informed loss to be mis-specified, thus explaining the poor performance of ReLU. --- ### Progress over Points: Reframing LM Benchmarks Around Scientific Objectives Authors: Alwin Jin, Sean M. Hendryx, Vaskar Nath Published: 2025-12-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.11183v1 Current benchmarks that test LLMs on static, already-solved problems (e.g., math word problems) effectively demonstrated basic capability acquisition. The natural progression has been toward larger, more comprehensive and challenging collections of static problems, an approach that inadvertently constrains the kinds of advances we can measure and incentivize. To address this limitation, we argue for progress-oriented benchmarks, problem environments whose objectives are themselves the core targets of scientific progress, so that achieving state of the art on the benchmark advances the field. As a introductory step, we instantiate an environment based on the NanoGPT speedrun. The environment standardizes a dataset slice, a reference model and training harness, and rich telemetry, with run-time verification and anti-gaming checks. Evaluation centers on the scientific delta achieved: best-attained loss and the efficiency frontier. Using this environment, we achieve a new state-of-the-art training time, improving upon the previous record by 3 seconds, and qualitatively observe the emergence of novel algorithmic ideas. Moreover, comparisons between models and agents remain possible, but they are a means, not the end; the benchmark's purpose is to catalyze reusable improvements to the language modeling stack. With this release, the overarching goal is to seed a community shift from static problem leaderboards to test-time research on open-ended yet measurable scientific problems. In this new paradigm, progress on the benchmark is progress on the science, thus reframing "benchmarking" as a vehicle for scientific advancement. --- ### Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR Authors: Yufeng Zhong, Lei Chen, Zhixiong Zeng, Xuanle Zhao, Deyang Jiang, Liming Zheng, Jing Huang, Haibo Qiu, Peng Shi, Siqi Yang, Lin Ma Published: 2025-12-11 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.08834v1 Reading text from images or scanned documents via OCR models has been a longstanding focus of researchers. Intuitively, text reading is perceived as a straightforward perceptual task, and existing work primarily focuses on constructing enriched data engineering to enhance SFT capabilities. In this work, we observe that even advanced OCR models exhibit significantly higher entropy in formatted text (\emph{e.g.}, formula, table, etc.) compared to plain text, often by an order of magnitude. These statistical patterns reveal that advanced OCR models struggle with high output uncertainty when dealing with format sensitive document, suggesting that reasoning over diverse reading pathways may improve OCR performance. To address this, we propose format decoupled reinforcement learning (FD-RL), which leverages high-entropy patterns for targeted optimization. Our approach employs entropy-based data filtration strategy to identify format-intensive instances, and adopt format decoupled rewards tailored to different format types, enabling format-level validation rather than token-level memorization. FD-RL achieves an average score of 90.41 on OmniDocBench, setting a new record for end-to-end models on this highly popular benchmark. More importantly, we conduct comprehensive ablation studies over data, training, filtering, and rewarding strategies, thoroughly validating their effectiveness. --- ### HLS4PC: A Parametrizable Framework For Accelerating Point-Based 3D Point Cloud Models on FPGA Authors: Amur Saqib Pal, Muhammad Mohsin Ghaffar, Faisal Shafait, Christian Weis, Norbert Wehn Published: 2025-12-11 Categories: cs.DC, cs.AI, cs.AR, cs.RO arXiv: https://arxiv.org/abs/2512.22139v1 Point-based 3D point cloud models employ computation and memory intensive mapping functions alongside NN layers for classification/segmentation, and are executed on server-grade GPUs. The sparse, and unstructured nature of 3D point cloud data leads to high memory and computational demand, hindering real-time performance in safety critical applications due to GPU under-utilization. To address this challenge, we present HLS4PC, a parameterizable HLS framework for FPGA acceleration. Our approach leverages FPGA parallelization and algorithmic optimizations to enable efficient fixed-point implementations of both mapping and NN functions. We explore several hardware-aware compression techniques on a state-of-the-art PointMLP-Elite model, including replacing FPS with URS, parameter quantization, layer fusion, and input-points pruning, yielding PointMLP-Lite, a 4x less complex variant with only 2% accuracy drop on ModelNet40. Secondly, we demonstrate that the FPGA acceleration of the PointMLP-Lite results in 3.56x higher throughput than previous works. Furthermore, our implementation achieves 2.3x and 22x higher throughput compared to the GPU and CPU implementations, respectively. --- ### SlimEdge: Performance and Device Aware Distributed DNN Deployment on Resource-Constrained Edge Hardware Authors: Mahadev Sunil Kumar, Arnab Raha, Debayan Das, Gopakumar G, Rounak Chatterjee, Amitava Mukherjee Published: 2025-12-11 Categories: cs.DC, cs.CV arXiv: https://arxiv.org/abs/2512.22136v2 Distributed deep neural networks (DNNs) have become central to modern computer vision, yet their deployment on resource-constrained edge devices remains hindered by substantial parameter counts, computational demands, and the probability of device failure. Here, we present an approach to the efficient deployment of distributed DNNs that jointly respect hardware limitations, preserve task performance, and remain robust to partial system failures. Our method integrates structured model pruning with a multi-objective optimization framework to tailor network capacity for heterogeneous device constraints, while explicitly accounting for device availability and failure probability during deployment. We demonstrate this framework using Multi-View Convolutional Neural Networks (MVCNN), a state-of-the-art architecture for 3D object recognition, by quantifying the contribution of individual views to classification accuracy and allocating pruning budgets accordingly. Experimental results show that the resulting models satisfy user-specified bounds on accuracy and memory footprint, even under multiple simultaneous device failures. The inference time is reduced by factors up to 4.7x across diverse simulated device configurations. These findings suggest that performance-aware, view-adaptive, and failure-resilient compression provides a viable pathway for deploying complex vision models in distributed edge environments. --- ### SoDA: An Efficient Interaction Paradigm for the Agentic Web Authors: Zicai Cui, Zhouyuan Jian, Weiwen Liu, Weinan Zhang Published: 2025-12-11 Categories: cs.DC, cs.AI, cs.HC, cs.MA arXiv: https://arxiv.org/abs/2512.22135v1 As the internet evolves from the mobile App-dominated Attention Economy to the Intent-Interconnection of the Agentic Web era, existing interaction modes fail to address the escalating challenges of data lock-in and cognitive overload. Addressing this, we defines a future-oriented user sovereignty interaction paradigm, aiming to realize a fundamental shift from killing time to saving time. Specifically, we argue that decoupling memory from application logic eliminates the structural basis of data lock-in, while shifting from explicit manual instruction to implicit intent alignment resolves cognitive overload by offloading execution complexity. This paradigm is implemented via the Sovereign Digital Avatar (SoDA), which employs an orthogonal decoupling design of storage, computation, and interaction. This establishes the architectural principle of data as a persistent asset, model as a transient tool, fundamentally breaking the platform monopoly on user memory. To support the operation of this new paradigm in zero-trust environments, we design an Intent-Permission Handshake Mechanism based on A2A protocols, utilizing dual-factor (Sensitivity Coefficient and Strictness Parameter) adaptive routing to achieve active risk governance. Empirical evaluation with a high-fidelity simulation environment indicates that this paradigm reduces token consumption by approximately 27-35\% during cross-platform service migration and complex task execution. Furthermore, in the orchestration of multi-modal complex tasks, it reduces user cognitive load by 72\% compared to standard Retrieval-Augmented Generation (RAG) architectures, by 88\% relative to manual workflows, while significantly boosting the Information Signal-to-Noise Ratio (SNR). These results demonstrate that the SoDA is the essential interaction infrastructure for building an efficient, low-friction, and decentralized Agentic Web. --- ### ASK: Adaptive Self-improving Knowledge Framework for Audio Text Retrieval Authors: Siyuan Fu, Xuchen Guo, Mingjun Liu, Hongxiang Li, Boyin Tan, Gongxi Zhu, Xianwei Zhuang, Jinghan Ru, Yuxin Xie, Yuguo Yin Published: 2025-12-11 Categories: eess.AS, cs.IR, cs.LG, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2512.19703v2 The dominant paradigm for Audio-Text Retrieval (ATR) relies on dual-encoder architectures optimized via mini-batch contrastive learning. However, restricting optimization to local in-batch samples creates a fundamental limitation we term the Gradient Locality Bottleneck (GLB), which prevents the resolution of acoustic ambiguities and hinders the learning of rare long-tail concepts. While external knowledge injection can break this bottleneck, it often triggers a problem called Representation-Drift Mismatch (RDM), where a static knowledge base becomes misaligned with evolving encoders, degrading guidance into noise. To address these intertwined challenges, we propose the Adaptive Self-improving Knowledge (ASK) framework. ASK breaks the GLB via multi-grained knowledge injection and mitigates RDM through a dynamic refinement strategy that synchronizes the knowledge base with the model. Additionally, an adaptive reliability weighting scheme is employed to filter retrieval noise based on cross-modal consistency. Extensive experiments across multiple benchmarks demonstrate that ASK consistently achieves new state-of-the-art performance across various backbones. --- ### Risk-Aware Financial Forecasting Enhanced by Machine Learning and Intuitionistic Fuzzy Multi-Criteria Decision-Making Authors: Safiye Turgay, Serkan Erdoğan, Željko Stević, Orhan Emre Elma, Tevfik Eren, Zhiyuan Wang, Mahmut Baydaş Published: 2025-12-11 Categories: q-fin.ST, cs.LG, math.OC arXiv: https://arxiv.org/abs/2512.17936v1 In the face of increasing financial uncertainty and market complexity, this study presents a novel risk-aware financial forecasting framework that integrates advanced machine learning techniques with intuitionistic fuzzy multi-criteria decision-making (MCDM). Tailored to the BIST 100 index and validated through a case study of a major defense company in Türkiye, the framework fuses structured financial data, unstructured text data, and macroeconomic indicators to enhance predictive accuracy and robustness. It incorporates a hybrid suite of models, including extreme gradient boosting (XGBoost), long short-term memory (LSTM) network, graph neural network (GNN), to deliver probabilistic forecasts with quantified uncertainty. The empirical results demonstrate high forecasting accuracy, with a net profit mean absolute percentage error (MAPE) of 3.03% and narrow 95% confidence intervals for key financial indicators. The risk-aware analysis indicates a favorable risk-return profile, with a Sharpe ratio of 1.25 and a higher Sortino ratio of 1.80, suggesting relatively low downside volatility and robust performance under market fluctuations. Sensitivity analysis shows that the key financial indicator predictions are highly sensitive to variations of inflation, interest rates, sentiment, and exchange rates. Additionally, using an intuitionistic fuzzy MCDM approach, combining entropy weighting, evaluation based on distance from the average solution (EDAS), and the measurement of alternatives and ranking according to compromise solution (MARCOS) methods, the tabular data learning network (TabNet) outperforms the other models and is identified as the most suitable candidate for deployment. Overall, the findings of this work highlight the importance of integrating advanced machine learning, risk quantification, and fuzzy MCDM methodologies in financial forecasting, particularly in emerging markets. --- ### chatter: a Python library for applying information theory and AI/ML models to animal communication Authors: Mason Youngblood Published: 2025-12-11 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2512.17935v1 The study of animal communication often involves categorizing units into types (e.g. syllables in songbirds, or notes in humpback whales). While this approach is useful in many cases, it necessarily flattens the complexity and nuance present in real communication systems. chatter is a new Python library for analyzing animal communication in continuous latent space using information theory and modern machine learning techniques. It is taxonomically agnostic, and has been tested with the vocalizations of birds, bats, whales, and primates. By leveraging a variety of different architectures, including variational autoencoders and vision transformers, chatter represents vocal sequences as trajectories in high-dimensional latent space, bypassing the need for manual or automatic categorization of units. The library provides an end-to-end workflow -- from preprocessing and segmentation to model training and feature extraction -- that enables researchers to quantify the complexity, predictability, similarity, and novelty of vocal sequences. --- ### TAO-Net: Two-stage Adaptive OOD Classification Network for Fine-grained Encrypted Traffic Classification Authors: Zihao Wang, Wei Peng, Junming Zhang, Jian Li, Wenxin Fang Published: 2025-12-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.15753v1 Encrypted traffic classification aims to identify applications or services by analyzing network traffic data. One of the critical challenges is the continuous emergence of new applications, which generates Out-of-Distribution (OOD) traffic patterns that deviate from known categories and are not well represented by predefined models. Current approaches rely on predefined categories, which limits their effectiveness in handling unknown traffic types. Although some methods mitigate this limitation by simply classifying unknown traffic into a single "Other" category, they fail to make a fine-grained classification. In this paper, we propose a Two-stage Adaptive OOD classification Network (TAO-Net) that achieves accurate classification for both In-Distribution (ID) and OOD encrypted traffic. The method incorporates an innovative two-stage design: the first stage employs a hybrid OOD detection mechanism that integrates transformer-based inter-layer transformation smoothness and feature analysis to effectively distinguish between ID and OOD traffic, while the second stage leverages large language models with a novel semantic-enhanced prompt strategy to transform OOD traffic classification into a generation task, enabling flexible fine-grained classification without relying on predefined labels. Experiments on three datasets demonstrate that TAO-Net achieves 96.81-97.70% macro-precision and 96.77-97.68% macro-F1, outperforming previous methods that only reach 44.73-86.30% macro-precision, particularly in identifying emerging network applications. --- ### GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Prediction Authors: Wei Guan, Jian Cao, Jinyu Cai, Qiqi Cai, Jianqi Gao, See-Kiong Ng Published: 2025-12-11 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2512.15751v2 Agentic Workflows (AWs) have emerged as a promising paradigm for solving complex tasks. However, automatically generating high-quality AWs remains expensive because AW optimization requires evaluating a large number of candidate AWs via execution, resulting in high computational cost and latency. Recently, AW performance prediction has become a hot research topic to avoid costly execution-based evaluation, but existing methods primarily use Graph Neural Networks (GNNs) to model workflow structures and insufficiently capture the semantic relationships among agents. To address this limitation, we propose GLOW, a unified framework for AW performance prediction that combines the graph-structure modeling ability of GNNs with the topology-aware semantic encoding capability of LLMs. Specifically, a graph-oriented LLM is first built through instruction-tuning on graph understanding tasks to extract topology-aware semantic representations from descriptive text of AWs. Meanwhile, a GNN explicitly models the structural information of AWs and produces corresponding structural representations. The semantic and structural representations are then fused in a shared latent space using a Transformer-based fusion module. A contrastive learning strategy is further introduced to learn more discriminative representations for AWs. Experiments on the FLORA-Bench benchmark demonstrate that GLOW consistently outperforms state-of-the-art baselines in both prediction accuracy and ranking utility. Moreover, when integrated into the AFLOW, an automatic AW generation framework, GLOW reduces optimization time by 98.7% with only a 0.031 average score decrease across three datasets, showing its effectiveness as an efficient surrogate evaluator for AW optimization. --- ### A Special Case of Quadratic Extrapolation Under the Neural Tangent Kernel Authors: Abiel Kim Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.15749v1 It has been demonstrated both theoretically and empirically that the ReLU MLP tends to extrapolate linearly for an out-of-distribution evaluation point. The machine learning literature provides ample analysis with respect to the mechanisms to which linearity is induced. However, the analysis of extrapolation at the origin under the NTK regime remains a more unexplored special case. In particular, the infinite-dimensional feature map induced by the neural tangent kernel is not translationally invariant. This means that the study of an out-of-distribution evaluation point very far from the origin is not equivalent to the evaluation of a point very near the origin. And since the feature map is rotation invariant, these two special cases may represent the most canonically extreme bounds of ReLU NTK extrapolation. Ultimately, it is this loose recognition of the two special cases of extrapolation that motivate the discovery of quadratic extrapolation for an evaluation close to the origin. ---