# Research Papers — 2025-11 · bundle page 4 of 197 > Full-text markdown of papers #151–200 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-11/page/4 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/3.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/5.md) ### Accelerating Streaming Video Large Language Models via Hierarchical Token Compression Authors: Yiyu Wang, Xuyang Liu, Xiyan Gui, Xinying Lin, Boxue Yang, Chenfei Liao, Tailai Chen, Linfeng Zhang Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00891v2 Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-time deployment due to the high computational cost of processing dense visual tokens from continuous video streams. In streaming video scenarios, the primary bottleneck lies in the Vision Transformer (ViT) encoding stage, where redundant processing of temporally similar frames leads to inefficiency. Additionally, inflated token sequences during LLM pre-filling further exacerbate latency and memory overhead. To address these challenges, we propose \textbf{S}treaming \textbf{T}oken \textbf{C}ompression (\textbf{STC}), a plug-and-play hierarchical framework that seamlessly integrates into existing streaming VideoLLMs, optimizing both ViT encoding and LLM pre-filling stages to accelerate processing. STC introduces two token-level accelerators: \textbf{STC-Cacher}, which reduces ViT encoding overhead by caching and reusing features from temporally similar frames, and \textbf{STC-Pruner}, which compresses the visual token sequence before it enters the LLM, preserving only the most salient tokens based on both spatial and temporal relevance. Extensive experiments on four baseline streaming VideoLLMs across five benchmarks demonstrate that STC outperforms other compression methods. Notably, STC retains up to \textbf{99\%} of accuracy on the ReKV framework while reducing ViT encoding latency and LLM pre-filling latency by \textbf{24.5\%} and \textbf{45.3\%}. --- ### Accelerating Streaming Video Large Language Models via Hierarchical Token Compression Authors: Yiyu Wang, Xuyang Liu, Xiyan Gui, Xinying Lin, Boxue Yang, Chenfei Liao, Tailai Chen, Linfeng Zhang Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00891v1 Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-time deployment due to the high computational cost of processing dense visual tokens from continuous video streams. In streaming video scenarios, the primary bottleneck lies in the Vision Transformer (ViT) encoding stage, where redundant processing of temporally similar frames leads to inefficiency. Additionally, inflated token sequences during LLM pre-filling further exacerbate latency and memory overhead. To address these challenges, we propose \textbf{S}treaming \textbf{T}oken \textbf{C}ompression (\textbf{STC}), a plug-and-play hierarchical framework that seamlessly integrates into existing streaming VideoLLMs, optimizing both ViT encoding and LLM pre-filling stages to accelerate processing. STC introduces two token-level accelerators: \textbf{STC-Cacher}, which reduces ViT encoding overhead by caching and reusing features from temporally similar frames, and \textbf{STC-Pruner}, which compresses the visual token sequence before it enters the LLM, preserving only the most salient tokens based on both spatial and temporal relevance. Extensive experiments on four baseline streaming VideoLLMs across five benchmarks demonstrate that STC outperforms other compression methods. Notably, STC retains up to \textbf{99\%} of accuracy on the ReKV framework while reducing ViT encoding latency and LLM pre-filling latency by \textbf{24.5\%} and \textbf{45.3\%}. --- ### Light-Weight Benchmarks Reveal the Hidden Hardware Cost of Zero-Shot Tabular Foundation Models Authors: Ishaan Gangwani, Aayam Bansal Published: 2025-11-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.00888v2 Zero-shot foundation models (FMs) promise training-free prediction on tabular data, yet their hardware footprint remains poorly characterized. We present a fully reproducible benchmark that reports test accuracy together with wall-clock latency, peak CPU RAM, and peak GPU VRAM on four public datasets: Adult-Income, Higgs-100k, Wine-Quality, and California-Housing. Two open FMs (TabPFN-1.0 and TabICL-base) are compared against tuned XGBoost, LightGBM, and Random Forest baselines on a single NVIDIA T4 GPU. The tree ensembles equal or surpass FM accuracy on three datasets while completing full-test batches in <= 0.40 s and <= 150 MB RAM, using zero VRAM. TabICL achieves a 0.8 percentage-point gain on Higgs but requires roughly 40,000 times more latency (960 s) and 9 GB VRAM. TabPFN matches tree-model accuracy on Wine and Housing but peaks at 4 GB VRAM and cannot process the full 100k-row Higgs table. These results quantify the substantial hardware-versus-accuracy trade-offs in current tabular FMs and provide an open baseline for future efficiency-oriented research. --- ### Light-Weight Benchmarks Reveal the Hidden Hardware Cost of Zero-Shot Tabular Foundation Models Authors: Aayam Bansal, Ishaan Gangwani Published: 2025-11-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.00888v1 Zero-shot foundation models (FMs) promise training-free prediction on tabular data, yet their hardware footprint remains poorly characterized. We present a fully reproducible benchmark that reports test accuracy together with wall-clock latency, peak CPU RAM, and peak GPU VRAM on four public datasets: Adult-Income, Higgs-100k, Wine-Quality, and California-Housing. Two open FMs (TabPFN-1.0 and TabICL-base) are compared against tuned XGBoost, LightGBM, and Random Forest baselines on a single NVIDIA T4 GPU. The tree ensembles equal or surpass FM accuracy on three datasets while completing full-test batches in <= 0.40 s and <= 150 MB RAM, using zero VRAM. TabICL achieves a 0.8 percentage-point gain on Higgs but requires roughly 40,000 times more latency (960 s) and 9 GB VRAM. TabPFN matches tree-model accuracy on Wine and Housing but peaks at 4 GB VRAM and cannot process the full 100k-row Higgs table. These results quantify the substantial hardware-versus-accuracy trade-offs in current tabular FMs and provide an open baseline for future efficiency-oriented research. --- ### Multilingual Training-Free Remote Sensing Image Captioning Authors: Carlos Rebelo, Gil Rocha, João Daniel Silva, Bruno Martins Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00887v2 Remote sensing image captioning has advanced rapidly through encoder--decoder models, although the reliance on large annotated datasets and the focus on English restricts global applicability. To address these limitations, we propose the first training-free multilingual approach, based on retrieval-augmented prompting. For a given aerial image, we employ a domain-adapted SigLIP2 encoder to retrieve related captions and few-shot examples from a datastore, which are then provided to a language model. We explore two variants: an image-blind setup, where a multilingual Large Language Model (LLM) generates the caption from textual prompts alone, and an image-aware setup, where a Vision--Language Model (VLM) jointly processes the prompt and the input image. To improve the coherence of the retrieved content, we introduce a graph-based re-ranking strategy using PageRank on a graph of images and captions. Experiments on four benchmark datasets across ten languages demonstrate that our approach is competitive with fully supervised English-only systems and generalizes to other languages. Results also highlight the importance of re-ranking with PageRank, yielding up to 35% improvements in performance metrics. Additionally, it was observed that while VLMs tend to generate visually grounded but lexically diverse captions, LLMs can achieve stronger BLEU and CIDEr scores. Lastly, directly generating captions in the target language consistently outperforms other translation-based strategies. Overall, our work delivers one of the first systematic evaluations of multilingual, training-free captioning for remote sensing imagery, advancing toward more inclusive and scalable multimodal Earth observation systems. --- ### Multilingual Training-Free Remote Sensing Image Captioning Authors: Carlos Rebelo, Gil Rocha, João Daniel Silva, Bruno Martins Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00887v1 Remote sensing image captioning has advanced rapidly through encoder--decoder models, although the reliance on large annotated datasets and the focus on English restricts global applicability. To address these limitations, we propose the first training-free multilingual approach, based on retrieval-augmented prompting. For a given aerial image, we employ a domain-adapted SigLIP2 encoder to retrieve related captions and few-shot examples from a datastore, which are then provided to a language model. We explore two variants: an image-blind setup, where a multilingual Large Language Model (LLM) generates the caption from textual prompts alone, and an image-aware setup, where a Vision--Language Model (VLM) jointly processes the prompt and the input image. To improve the coherence of the retrieved content, we introduce a graph-based re-ranking strategy using PageRank on a graph of images and captions. Experiments on four benchmark datasets across ten languages demonstrate that our approach is competitive with fully supervised English-only systems and generalizes to other languages. Results also highlight the importance of re-ranking with PageRank, yielding up to 35% improvements in performance metrics. Additionally, it was observed that while VLMs tend to generate visually grounded but lexically diverse captions, LLMs can achieve stronger BLEU and CIDEr scores. Lastly, directly generating captions in the target language consistently outperforms other translation-based strategies. Overall, our work delivers one of the first systematic evaluations of multilingual, training-free captioning for remote sensing imagery, advancing toward more inclusive and scalable multimodal Earth observation systems. --- ### HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics Authors: Masatoshi Tateno, Gido Kato, Hirokatsu Kataoka, Yoichi Sato, Takuma Yagi Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00885v2 Hand-object interaction (HOI) inherently involves dynamics where human manipulations produce distinct spatio-temporal effects on objects. However, existing semantic HOI benchmarks focused either on manipulation or on the resulting effects at a coarse level, lacking fine-grained spatio-temporal reasoning to capture the underlying dynamics in HOI. We introduce HanDyVQA, a fine-grained video question-answering benchmark that comprehensively covers both the manipulation and effect aspects of HOI. HanDyVQA comprises six complementary question types (Action, Process, Objects, Location, State Change, and Object Parts), totalling 11.1K multiple-choice QA pairs. Collected QA pairs recognizing manipulation styles, hand/object motions, and part-level state changes. HanDyVQA also includes 10.3K segmentation masks for Objects and Object Parts questions, enabling the evaluation of object/part-level reasoning in video object segmentation. We evaluated recent video foundation models on our benchmark and found that even the best-performing model, Gemini-2.5-Pro, reached only 73% average accuracy, which is far from human performance (97%). Further analysis shows the remaining challenges in spatial relationship, motion, and part-level geometric understanding. We also found that integrating explicit HOI-related cues into visual features improves performance, offering insights for developing future models with a deeper understanding of HOI dynamics. --- ### HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics Authors: Masatoshi Tateno, Gido Kato, Hirokatsu Kataoka, Yoichi Sato, Takuma Yagi Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00885v1 Hand-object interaction (HOI) inherently involves dynamics where human manipulations produce distinct spatio-temporal effects on objects. However, existing semantic HOI benchmarks focused either on manipulation or on the resulting effects at a coarse level, lacking fine-grained spatio-temporal reasoning to capture the underlying dynamics in HOI. We introduce HanDyVQA, a fine-grained video question-answering benchmark that comprehensively covers both the manipulation and effect aspects of HOI. HanDyVQA comprises six complementary question types (Action, Process, Objects, Location, State Change, and Object Parts), totalling 11.1K multiple-choice QA pairs. Collected QA pairs recognizing manipulation styles, hand/object motions, and part-level state changes. HanDyVQA also includes 10.3K segmentation masks for Objects and Object Parts questions, enabling the evaluation of object/part-level reasoning in video object segmentation. We evaluated recent video foundation models on our benchmark and found that even the best-performing model, Gemini-2.5-Pro, reached only 73% average accuracy, which is far from human performance (97%). Further analysis shows the remaining challenges in spatial relationship, motion, and part-level geometric understanding. We also found that integrating explicit HOI-related cues into visual features improves performance, offering insights for developing future models with a deeper understanding of HOI dynamics. --- ### Towards Active Synthetic Data Generation for Finetuning Language Models Authors: Samuel Kessler, Menglin Xia, Daniel Madrigal Diaz, Dongge Han, Helia Heshemi, Saravan Rajmohan, Victor Ruehle, Jordan T. Ash Published: 2025-11-30 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2512.00884v2 A common and effective means for improving language model capabilities involves finetuning a ``student'' language model's parameters on generations from a more proficient ``teacher'' model. Termed ``synthetic data'', these generations are often produced before any student finetuning, but some work has considered generating new synthetic samples as training progresses. This paper studies and advocates for the latter case, where data are generated in an iterative, closed-loop fashion that is guided by the current state of the student model. For a fixed budget of generated samples, or a budget in terms of compute spent querying a teacher, we show that this curation of finetuning data affords improved student performance over static generation. Further, while there have been several LLM-specific methods proposed that operate in this regime, we find that simple, inexpensive selection criteria from the active learning literature tend to be most performant. We validate these claims across four mathematical and logical reasoning datasets using four different small language models. --- ### Towards Active Synthetic Data Generation for Finetuning Language Models Authors: Samuel Kessler, Menglin Xia, Daniel Madrigal Diaz, Dongge Han, Helia Heshemi, Saravan Rajmohan, Victor Ruehle, Jordan T. Ash Published: 2025-11-30 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2512.00884v1 A common and effective means for improving language model capabilities involves finetuning a ``student'' language model's parameters on generations from a more proficient ``teacher'' model. Termed ``synthetic data'', these generations are often produced before any student finetuning, but some work has considered generating new synthetic samples as training progresses. This paper studies and advocates for the latter case, where data are generated in an iterative, closed-loop fashion that is guided by the current state of the student model. For a fixed budget of generated samples, or a budget in terms of compute spent querying a teacher, we show that this curation of finetuning data affords improved student performance over static generation. Further, while there have been several LLM-specific methods proposed that operate in this regime, we find that simple, inexpensive selection criteria from the active learning literature tend to be most performant. We validate these claims across four mathematical and logical reasoning datasets using four different small language models. --- ### Audio-Visual World Models: Learning Physically Grounded Multisensory Dynamics Authors: Jiahua Wang, Leqi Zheng, Jialong Wu, Yaoxin Mao, Shijie Cheng Published: 2025-11-30 Categories: cs.MM, cs.CV, cs.SD arXiv: https://arxiv.org/abs/2512.00883v4 World models simulate environmental dynamics to enable embodied agents to plan and reason about future states. While real-world perception is inherently multimodal, existing approaches focus primarily on visual observations, leaving crucial spatial and temporal acoustic cues underexplored. In this work, we present a unified formulation of Audio-Visual World Models (AVWM), casting multimodal environment simulation under action control as a partially observable Markov decision process with synchronized audio-visual observations. As a foundational benchmark, we construct AVW-4k, comprising 30 hours of action-annotated binaural audio-visual trajectories across 76 indoor environments. To capture these physically grounded multisensory dynamics, we propose AV-CDiT (Audio-Visual Conditional Diffusion Transformer), featuring a novel modality expert architecture that balances visual and auditory learning, optimized via a three-stage training strategy. Extensive experiments demonstrate that AV-CDiT achieves high-fidelity prediction across both visual and auditory modalities. Furthermore, we validate its practical utility in embodied navigation, showing that AVWM significantly enhances a pretrained agent in continuous audio-visual navigation tasks. --- ### Audio-Visual World Models: Towards Multisensory Imagination in Sight and Sound Authors: Jiahua Wang, Shannan Yan, Leqi Zheng, Jialong Wu, Yaoxin Mao Published: 2025-11-30 Categories: cs.MM, cs.CV, cs.SD arXiv: https://arxiv.org/abs/2512.00883v1 World models simulate environmental dynamics to enable agents to plan and reason about future states. While existing approaches have primarily focused on visual observations, real-world perception inherently involves multiple sensory modalities. Audio provides crucial spatial and temporal cues such as sound source localization and acoustic scene properties, yet its integration into world models remains largely unexplored. No prior work has formally defined what constitutes an audio-visual world model or how to jointly capture binaural spatial audio and visual dynamics under precise action control with task reward prediction. This work presents the first formal framework for Audio-Visual World Models (AVWM), formulating multimodal environment simulation as a partially observable Markov decision process with synchronized audio-visual observations, fine-grained actions, and task rewards. To address the lack of suitable training data, we construct AVW-4k, a dataset comprising 30 hours of binaural audio-visual trajectories with action annotations and reward signals across 76 indoor environments. We propose AV-CDiT, an Audio-Visual Conditional Diffusion Transformer with a novel modality expert architecture that balances visual and auditory learning, optimized through a three-stage training strategy for effective multimodal integration. Extensive experiments demonstrate that AV-CDiT achieves high-fidelity multimodal prediction across visual and auditory modalities with reward. Furthermore, we validate its practical utility in continuous audio-visual navigation tasks, where AVWM significantly enhances the agent's performance. --- ### Look, Recite, Then Answer: Enhancing VLM Performance via Self-Generated Knowledge Hints Authors: Xisheng Feng Published: 2025-11-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.00882v3 Vision-Language Models (VLMs) exhibit significant performance plateaus in specialized domains like precision agriculture, primarily due to "Reasoning-Driven Hallucination" where linguistic priors override visual perception. A key bottleneck is the "Modality Gap": visual embeddings fail to reliably activate the fine-grained expert knowledge already encoded in model parameters. We propose "Look, Recite, Then Answer," a parameter-efficient framework that enhances VLMs via self-generated knowledge hints while keeping backbone models frozen. The framework decouples inference into three stages: (1) Look generates objective visual descriptions and candidate sets; (2) Recite employs a lightweight 1.7B router to transform visual cues into targeted queries that trigger candidate-specific parametric knowledge; (3) Answer performs parallel evidence alignment between descriptions and recited knowledge to select the most consistent label. On AgroBench, our method achieves state-of-the-art results, improving Weed Identification accuracy by 23.52% over Qwen2-VL-72B and surpassing GPT-4o without external search overhead. This modular design mitigates hallucinations by transforming passive perception into active, controllable knowledge retrieval --- ### Look, Recite, Then Answer: Enhancing VLM Performance via Self-Generated Knowledge Hints Authors: Xisheng Feng Published: 2025-11-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.00882v1 Vision-Language Models (VLMs) exhibit significant performance plateaus in specialized domains like precision agriculture, primarily due to "Reasoning-Driven Hallucination" where linguistic priors override visual perception. A key bottleneck is the "Modality Gap": visual embeddings fail to reliably activate the fine-grained expert knowledge already encoded in model parameters. We propose "Look, Recite, Then Answer," a parameter-efficient framework that enhances VLMs via self-generated knowledge hints while keeping backbone models frozen. The framework decouples inference into three stages: (1) Look generates objective visual descriptions and candidate sets; (2) Recite employs a lightweight 1.7B router to transform visual cues into targeted queries that trigger candidate-specific parametric knowledge; (3) Answer performs parallel evidence alignment between descriptions and recited knowledge to select the most consistent label. On AgroBench, our method achieves state-of-the-art results, improving Weed Identification accuracy by 23.6% over Qwen-VL and surpassing GPT-4o without external search overhead. This modular design mitigates hallucinations by transforming passive perception into active, controllable knowledge retrieval --- ### Hybrid-DMKG: A Hybrid Reasoning Framework over Dynamic Multimodal Knowledge Graphs for Multimodal Multihop QA with Knowledge Editing Authors: Li Yuan, Qingfei Huang, Bingshan Zhu, Yi Cai, Qingbao Huang, Changmeng Zheng, Zikun Deng, Tao Wang Published: 2025-11-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.00881v1 Multimodal Knowledge Editing (MKE) extends traditional knowledge editing to settings involving both textual and visual modalities. However, existing MKE benchmarks primarily assess final answer correctness while neglecting the quality of intermediate reasoning and robustness to visually rephrased inputs. To address this limitation, we introduce MMQAKE, the first benchmark for multimodal multihop question answering with knowledge editing. MMQAKE evaluates (1) a model's ability to reason over 2-5-hop factual chains that span both text and images, including performance at each intermediate step, and (2) robustness to visually rephrased inputs in multihop questions. Our evaluation shows that current MKE methods often struggle to consistently update and reason over multimodal reasoning chains after knowledge edits. To overcome these challenges, we propose Hybrid-DMKG, a hybrid reasoning framework built on a dynamic multimodal knowledge graph (DMKG) to enable accurate multihop reasoning over updated multimodal knowledge. Hybrid-DMKG first uses a large language model to decompose multimodal multihop questions into sequential sub-questions, then applies a multimodal retrieval model to locate updated facts by jointly encoding each sub-question with candidate entities and their associated images. For answer inference, a hybrid reasoning module operates over the DMKG via two parallel paths: (1) relation linking prediction, and (2) RAG reasoning with large vision-language models. A decision module aggregates evidence from both paths to select the most credible answer. Experimental results on MMQAKE show that Hybrid-DMKG significantly outperforms existing MKE approaches, achieving higher accuracy and improved robustness to knowledge updates. --- ### Quantum-Inspired Spectral Geometry for Neural Operator Equivalence and Structured Pruning Authors: Haijian Shao, Wei Liu, Xing Deng Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00880v1 The rapid growth of multimodal intelligence on resource-constrained and heterogeneous domestic hardware exposes critical bottlenecks: multimodal feature heterogeneity, real-time requirements in dynamic scenarios, and hardware-specific operator redundancy. This work introduces a quantum-inspired geometric framework for neural operators that represents each operator by its normalized singular value spectrum on the Bloch hypersphere. We prove a tight spectral-to-functional equivalence theorem showing that vanishing Fubini--Study/Wasserstein-2 distance implies provable functional closeness, establishing the first rigorous foundation for cross-modal and cross-architecture operator substitutability. Based on this metric, we propose Quantum Metric-Driven Functional Redundancy Graphs (QM-FRG) and one-shot structured pruning. Controlled simulation validates the superiority of the proposed metric over magnitude and random baselines. An extensive experimental validation on large-scale multimodal transformers and domestic heterogeneous hardware (Huawei Ascend, Cambricon MLU, Kunlunxin) hardware is deferred to an extended journal version currently in preparation. --- ### Less is More: Resource-Efficient Low-Rank Adaptation Authors: Chunlin Tian, Xuyang Wei, Huanrong Liu, Zhijiang Guo, Li Li Published: 2025-11-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.00878v1 Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning (PEFT) method for Large Language Models (LLMs), but it still incurs notable overhead and suffers from parameter interference in complex datasets. While recent works decouple LoRA update matrices to exploit matrix-wise asymmetry, training costs remain high. We revisit LoRA from the perspective of inter-matrix and intra-layer parameter redundancy and propose Resource-Efficient Low-Rank Adaptation, EffiLoRA, a lightweight and generalizable approach for language, multimodal, and diffusion models. EffiLoRA employs a unified A matrix across all transformer layers and introduces a runtime selective B matrices update to dynamically trade-off the system resource budget and model performance. EffiLoRA consistently outperforms LoRA across diverse modalities, including commonsense reasoning, visual instruction tuning, and image generation, demonstrating improved efficiency and robustness. --- ### Feed-Forward 3D Gaussian Splatting Compression with Long-Context Modeling Authors: Zhening Liu, Rui Song, Yushi Huang, Yingdong Hu, Xinjie Zhang, Jiawei Shao, Zehong Lin, Jun Zhang Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00877v1 3D Gaussian Splatting (3DGS) has emerged as a revolutionary 3D representation. However, its substantial data size poses a major barrier to widespread adoption. While feed-forward 3DGS compression offers a practical alternative to costly per-scene per-train compressors, existing methods struggle to model long-range spatial dependencies, due to the limited receptive field of transform coding networks and the inadequate context capacity in entropy models. In this work, we propose a novel feed-forward 3DGS compression framework that effectively models long-range correlations to enable highly compact and generalizable 3D representations. Central to our approach is a large-scale context structure that comprises thousands of Gaussians based on Morton serialization. We then design a fine-grained space-channel auto-regressive entropy model to fully leverage this expansive context. Furthermore, we develop an attention-based transform coding model to extract informative latent priors by aggregating features from a wide range of neighboring Gaussians. Our method yields a $20\times$ compression ratio for 3DGS in a feed-forward inference and achieves state-of-the-art performance among generalizable codecs. --- ### Neural Discrete Representation Learning for Sparse-View CBCT Reconstruction: From Algorithm Design to Prospective Multicenter Clinical Evaluation Authors: Haoshen Wang, Lei Chen, Wei-Hua Zhang, Linxia Wu, Yong Luo, Zengmao Wang, Yuan Xiong, Chengcheng Zhu, Wenjuan Tang, Xueyi Zhang, Wei Zhou, Xuhua Duan et al. Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00873v1 Cone beam computed tomography (CBCT)-guided puncture has become an established approach for diagnosing and treating early- to mid-stage thoracic tumours, yet the associated radiation exposure substantially elevates the risk of secondary malignancies. Although multiple low-dose CBCT strategies have been introduced, none have undergone validation using large-scale multicenter retrospective datasets, and prospective clinical evaluation remains lacking. Here, we propose DeepPriorCBCT - a three-stage deep learning framework that achieves diagnostic-grade reconstruction using only one-sixth of the conventional radiation dose. 4102 patients with 8675 CBCT scans from 12 centers were included to develop and validate DeepPriorCBCT. Additionally, a prospective cross-over trial (Registry number: NCT07035977) which recruited 138 patients scheduled for percutaneous thoracic puncture was conducted to assess the model's clinical applicability. Assessment by 11 physicians confirmed that reconstructed images were indistinguishable from original scans. Moreover, diagnostic performance and overall image quality were comparable to those generated by standard reconstruction algorithms. In the prospective trial, five radiologists reported no significant differences in image quality or lesion assessment between DeepPriorCBCT and the clinical standard (all P>0.05). Likewise, 25 interventionalists expressed no preference between model-based and full-sampling images for surgical guidance (Kappa<0.2). Radiation exposure with DeepPriorCBCT was reduced to approximately one-sixth of that with the conventional approach, and collectively, the findings confirm that it enables high-quality CBCT reconstruction under sparse sampling conditions while markedly decreasing intraoperative radiation risk. --- ### TAP-CT: 3D Task-Agnostic Pretraining of Computed Tomography Foundation Models Authors: Tim Veenboer, George Yiasemis, Eric Marcus, Vivien Van Veldhuizen, Cees G. M. Snoek, Jonas Teuwen, Kevin B. W. Groot Lipman Published: 2025-11-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.00872v1 Existing foundation models (FMs) in the medical domain often require extensive fine-tuning or rely on training resource-intensive decoders, while many existing encoders are pretrained with objectives biased toward specific tasks. This illustrates a need for a strong, task-agnostic foundation model that requires minimal fine-tuning beyond feature extraction. In this work, we introduce a suite of task-agnostic pretraining of CT foundation models (TAP-CT): a simple yet effective adaptation of Vision Transformers (ViTs) and DINOv2 for volumetric data, enabling scalable self-supervised pretraining directly on 3D CT volumes. Our approach incorporates targeted modifications to patch embeddings, positional encodings, and volumetric augmentations, making the architecture depth-aware while preserving the simplicity of the underlying architectures. We show that large-scale 3D pretraining on an extensive in-house CT dataset (105K volumes) yields stable, robust frozen representations that generalize strongly across downstream tasks. To promote transparency and reproducibility, and to establish a powerful, low-resource baseline for future research in medical imaging, we will release all pretrained models, experimental configurations, and downstream benchmark code at https://huggingface.co/fomofo/tap-ct-b-3d. --- ### HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs Authors: Ningning Chen, Weicai Ye, Ying Jiang Published: 2025-11-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.00862v3 We introduce HBLLM, a wavelet-enhanced high-fidelity $1$-bit post-training quantization method for Large Language Models (LLMs). By leveraging Haar wavelet transforms to enhance expressive capacity through frequency decomposition, HBLLM significantly improves quantization fidelity while maintaining minimal overhead. This approach features two innovative structure-aware grouping strategies: (1) frequency-aware multi-parameter intra-row grouping and (2) $\ell_2$-norm-based saliency-driven column selection. For non-salient weights, a shared mean is employed across quantization groups within each frequency band to optimize storage efficiency. Experiments conducted on the OPT and LLaMA models demonstrate that HBLLM achieves state-of-the-art performance in $1$-bit quantization, attaining a perplexity of $6.71$ on LLaMA$2$-$13$B with an average weight storage of only $1.08$ bits. Code available at: https://github.com/Yeyke/HBLLM. --- ### HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs Authors: Ningning Chen, Weicai Ye, Ying Jiang Published: 2025-11-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.00862v1 We introduce HBLLM, a wavelet-enhanced high-fidelity $1$-bit post-training quantization method for Large Language Models (LLMs). By leveraging Haar wavelet transforms to enhance expressive capacity through frequency decomposition, HBLLM significantly improves quantization fidelity while maintaining minimal overhead. This approach features two innovative structure-aware grouping strategies: (1) frequency-aware multi-parameter intra-row grouping and (2) $\ell_2$-norm-based saliency-driven column selection. For non-salient weights, a shared mean is employed across quantization groups within each frequency band to optimize storage efficiency. Experiments conducted on the OPT and LLaMA models demonstrate that HBLLM achieves state-of-the-art performance in $1$-bit quantization, attaining a perplexity of $6.71$ on LLaMA$2$-$13$B with an average weight storage of only $1.08$ bits. Code available at: https://github.com/Yeyke/HBLLM. --- ### The Spectral Dimension of NTKs is Constant: A Theory of Implicit Regularization, Finite-Width Stability, and Scalable Estimation Authors: Praveen Anilkumar Shukla Published: 2025-11-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.00860v1 Modern deep networks are heavily overparameterized yet often generalize well, suggesting a form of low intrinsic complexity not reflected by parameter counts. We study this complexity at initialization through the effective rank of the Neural Tangent Kernel (NTK) Gram matrix, $r_{\text{eff}}(K) = (\text{tr}(K))^2/\|K\|_F^2$. For i.i.d. data and the infinite-width NTK $k$, we prove a constant-limit law $\lim_{n\to\infty} \mathbb{E}(r_{\text{eff}}(K_n)) = \mathbb{E}(k(x, x))^2 / \mathbb{E}(k(x, x')^2) =: r_\infty$, with sub-Gaussian concentration. We further establish finite-width stability: if the finite-width NTK deviates in operator norm by $O_p(m^{-1/2})$ (width $m$), then $r_{\text{eff}}$ changes by $O_p(m^{-1/2})$. We design a scalable estimator using random output probes and a CountSketch of parameter Jacobians and prove conditional unbiasedness and consistency with explicit variance bounds. On CIFAR-10 with ResNet-20/56 (widths 16/32) across $n \in \{10^3, 5\times10^3, 10^4, 2.5\times10^4, 5\times10^4\}$, we observe $r_{\text{eff}} \approx 1.0\text{--}1.3$ and slopes $\approx 0$ in $n$, consistent with the theory, and the kernel-moment prediction closely matches fitted constants. --- ### Robust Probabilistic Load Forecasting for a Single Household: A Comparative Study from SARIMA to Transformers on the REFIT Dataset Authors: Midhun Manoj Published: 2025-11-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.00856v1 Probabilistic forecasting is essential for modern risk management, allowing decision-makers to quantify uncertainty in critical systems. This paper tackles this challenge using the volatile REFIT household dataset, which is complicated by a large structural data gap. We first address this by conducting a rigorous comparative experiment to select a Seasonal Imputation method, demonstrating its superiority over linear interpolation in preserving the data's underlying distribution. We then systematically evaluate a hierarchy of models, progressing from classical baselines (SARIMA, Prophet) to machine learning (XGBoost) and advanced deep learning architectures (LSTM). Our findings reveal that classical models fail to capture the data's non-linear, regime-switching behavior. While the LSTM provided the most well-calibrated probabilistic forecast, the Temporal Fusion Transformer (TFT) emerged as the superior all-round model, achieving the best point forecast accuracy (RMSE 481.94) and producing safer, more cautious prediction intervals that effectively capture extreme volatility. --- ### One Swallow Does Not Make a Summer: Understanding Semantic Structures in Embedding Spaces Authors: Yandong Sun, Qiang Huang, Ziwei Xu, Yiqun Sun, Yixuan Tang, Anthony K. H. Tung Published: 2025-11-30 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.00852v1 Embedding spaces are fundamental to modern AI, translating raw data into high-dimensional vectors that encode rich semantic relationships. Yet, their internal structures remain opaque, with existing approaches often sacrificing semantic coherence for structural regularity or incurring high computational overhead to improve interpretability. To address these challenges, we introduce the Semantic Field Subspace (SFS), a geometry-preserving, context-aware representation that captures local semantic neighborhoods within the embedding space. We also propose SAFARI (SemAntic Field subspAce deteRmInation), an unsupervised, modality-agnostic algorithm that uncovers hierarchical semantic structures using a novel metric called Semantic Shift, which quantifies how semantics evolve as SFSes evolve. To ensure scalability, we develop an efficient approximation of Semantic Shift that replaces costly SVD computations, achieving a 15~30x speedup with average errors below 0.01. Extensive evaluations across six real-world text and image datasets show that SFSes outperform standard classifiers not only in classification but also in nuanced tasks such as political bias detection, while SAFARI consistently reveals interpretable and generalizable semantic hierarchies. This work presents a unified framework for structuring, analyzing, and scaling semantic understanding in embedding spaces. --- ### City-Conditioned Memory for Multi-City Traffic and Mobility Forecasting Authors: Wenzhang Du Published: 2025-11-30 Categories: cs.LG, cs.CY arXiv: https://arxiv.org/abs/2512.00851v1 Deploying spatio-temporal forecasting models across many cities is difficult: traffic networks differ in size and topology, data availability can vary by orders of magnitude, and new cities may provide only a short history of logs. Existing deep traffic models are typically trained per city and backbone, creating high maintenance cost and poor transfer to data-scarce cities. We ask whether a single, backbone-agnostic layer can condition on "which city this sequence comes from", improve accuracy in full- and low-data regimes, and support better cross-city adaptation with minimal code changes. We propose CityCond, a light-weight city-conditioned memory layer that augments existing spatio-temporal backbones. CityCond combines a city-ID encoder with an optional shared memory bank (CityMem). Given a city index and backbone hidden states, it produces city-conditioned features fused through gated residual connections. We attach CityCond to five representative backbones (GRU, TCN, Transformer, GNN, STGCN) and evaluate three regimes: full-data, low-data, and cross-city few-shot transfer on METR-LA and PEMS-BAY. We also run auxiliary experiments on SIND, a drone-based multi-agent trajectory dataset from a signalized intersection in Tianjin (we focus on pedestrian tracks). Across more than fourteen model variants and three random seeds, CityCond yields consistent improvements, with the largest gains for high-capacity backbones such as Transformers and STGCNs. CityMem reduces Transformer error by roughly one third in full-data settings and brings substantial gains in low-data and cross-city transfer. On SIND, simple city-ID conditioning modestly improves low-data LSTM performance. CityCond can therefore serve as a reusable design pattern for scalable, multi-city forecasting under realistic data constraints. --- ### Smol-GS: Compact Representations for Abstract 3D Gaussian Splatting Authors: Haishan Wang, Mohammad Hassan Vali, Arno Solin Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00850v3 We present Smol-GS, a novel method for learning compact representations for 3D Gaussian Splatting (3DGS). Our approach learns highly efficient splat-wise features to model 3D space, which capture abstracted cues, including color, opacity, transformation, and material properties. We propose octree-derived positional encoding, which explicitly models spatial locality and enhances representation efficiency. We further apply entropy-based compression to exploit feature redundancy and compress splat coordinates using a recursive voxel hierarchy. This design enables orders-of-magnitude reduction in storage while preserving representation flexibility. Smol-GS achieves state-of-the-art compression performance on standard benchmarks with high-level rendering quality. --- ### Smol-GS: Compact Representations for Abstract 3D Gaussian Splatting Authors: Haishan Wang, Mohammad Hassan Vali, Arno Solin Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00850v1 We present Smol-GS, a novel method for learning compact representations for 3D Gaussian Splatting (3DGS). Our approach learns highly efficient encodings in 3D space that integrate both spatial and semantic information. The model captures the coordinates of the splats through a recursive voxel hierarchy, while splat-wise features store abstracted cues, including color, opacity, transformation, and material properties. This design allows the model to compress 3D scenes by orders of magnitude without loss of flexibility. Smol-GS achieves state-of-the-art compression on standard benchmarks while maintaining high rendering quality. Beyond visual fidelity, the discrete representations could potentially serve as a foundation for downstream tasks such as navigation, planning, and broader 3D scene understanding. --- ### Topological Federated Clustering via Gravitational Potential Fields under Local Differential Privacy Authors: Yunbo Long, Jiaquan Zhang, Xi Chen, Alexandra Brintrup Published: 2025-11-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.00849v1 Clustering non-independent and identically distributed (non-IID) data under local differential privacy (LDP) in federated settings presents a critical challenge: preserving privacy while maintaining accuracy without iterative communication. Existing one-shot methods rely on unstable pairwise centroid distances or neighborhood rankings, degrading severely under strong LDP noise and data heterogeneity. We present Gravitational Federated Clustering (GFC), a novel approach to privacy-preserving federated clustering that overcomes the limitations of distance-based methods under varying LDP. Addressing the critical challenge of clustering non-IID data with diverse privacy guarantees, GFC transforms privatized client centroids into a global gravitational potential field where true cluster centers emerge as topologically persistent singularities. Our framework introduces two key innovations: (1) a client-side compactness-aware perturbation mechanism that encodes local cluster geometry as "mass" values, and (2) a server-side topological aggregation phase that extracts stable centroids through persistent homology analysis of the potential field's superlevel sets. Theoretically, we establish a closed-form bound between the privacy budget $ε$ and centroid estimation error, proving the potential field's Lipschitz smoothing properties exponentially suppress noise in high-density regions. Empirically, GFC outperforms state-of-the-art methods on ten benchmarks, especially under strong LDP constraints ($ε< 1$), while maintaining comparable performance at lower privacy budgets. By reformulating federated clustering as a topological persistence problem in a synthetic physics-inspired space, GFC achieves unprecedented privacy-accuracy trade-offs without iterative communication, providing a new perspective for privacy-preserving distributed learning. --- ### AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent Authors: Neeraj Anand, Rishabh Jain, Sohan Patnaik, Balaji Krishnamurthy, Mausoom Sarkar Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00846v2 There is a growing demand for mobile user interface (UI) automation, driven by its broad applications across industries. With the advent of visual language models (VLMs), GUI automation has progressed from generating text-based instructions for humans to autonomously executing tasks, thus optimizing automation workflows. Recent approaches leverage VLMs for this problem due to their ability to 1) process on-screen content directly, 2) remain independent of device-specific APIs by utilizing human actions (e.g., clicks, typing), and 3) apply real-world contextual knowledge for task understanding. However, these models often have trouble accurately identifying widgets and determining actions due to limited spatial information in vision encoder features. Additionally, top-performing models are often large, requiring extensive training and resulting in inference delays. In this work, we introduce AFRAgent, an instruct-BLIP-based multimodal architecture that achieves superior performance in GUI automation while being less than one-fourth the size of its nearest competitor. To enhance image embeddings in the large language model (LLM) pipeline, we propose an adaptive feature renormalization-based (a token-level affine transformation) technique that effectively enriches low-resolution image embeddings and fuses high-resolution details. We evaluate AFRAgent on Meta-GUI and AITW benchmarks, establishing a new state-of-the-art baseline for smartphone automation. --- ### FC-ADL: Efficient Microservice Anomaly Detection and Localisation Through Functional Connectivity Authors: Giles Winchester, George Parisis, Luc Berthouze Published: 2025-11-30 Categories: cs.SE, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2512.00844v1 Microservices have transformed software architecture through the creation of modular and independent services. However, they introduce operational complexities in service integration and system management that makes swift and accurate anomaly detection and localisation challenging. Despite the complex, dynamic, and interconnected nature of microservice architectures, prior works that investigate metrics for anomaly detection rarely include explicit information about time-varying interdependencies. And whilst prior works on fault localisation typically do incorporate information about dependencies between microservices, they scale poorly to real world large-scale deployments due to their reliance on computationally expensive causal inference. To address these challenges we propose FC-ADL, an end-to-end scalable approach for detecting and localising anomalous changes from microservice metrics based on the neuroscientific concept of functional connectivity. We show that by efficiently characterising time-varying changes in dependencies between microservice metrics we can both detect anomalies and provide root cause candidates without incurring the significant overheads of causal and multivariate approaches. We demonstrate that our approach can achieve top detection and localisation performance across a wide degree of different fault scenarios when compared to state-of-the-art approaches. Furthermore, we illustrate the scalability of our approach by applying it to Alibaba's extremely large real-world microservice deployment. --- ### Prediction-space knowledge markets for communication-efficient federated learning on multimedia tasks Authors: Wenzhang Du Published: 2025-11-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.00841v1 Federated learning (FL) enables collaborative training over distributed multimedia data but suffers acutely from statistical heterogeneity and communication constraints, especially when clients deploy large models. Classic parameter-averaging methods such as FedAvg transmit full model weights and can diverge under nonindependent and identically distributed (non-IID) data. We propose KTA v2, a prediction-space knowledge trading market for FL. Each round, clients locally train on their private data, then share only logits on a small public reference set. The server constructs a client-client similarity graph in prediction space, combines it with reference-set accuracy to form per-client teacher ensembles, and sends back personalized soft targets for a second-stage distillation update. This two-stage procedure can be interpreted as approximate block-coordinate descent on a unified objective with prediction-space regularization. Experiments on FEMNIST, CIFAR-10 and AG News show that, under comparable or much lower communication budgets, KTA v2 consistently outperforms a local-only baseline and strong parameter-based methods (FedAvg, FedProx), and substantially improves over a FedMD-style global teacher. On CIFAR-10 with ResNet-18, KTA v2 reaches 57.7% test accuracy using approximately 1/1100 of FedAvg's communication, while on AG News it attains 89.3% accuracy with approximately 1/300 of FedAvg's traffic. --- ### ARCADIA: Scalable Causal Discovery for Corporate Bankruptcy Analysis Using Agentic AI Authors: Fabrizio Maturo, Donato Riccio, Andrea Mazzitelli, Giuseppe Bifulco, Francesco Paolone, Iulia Brezeanu Published: 2025-11-30 Categories: cs.AI, stat.CO, stat.ME arXiv: https://arxiv.org/abs/2512.00839v1 This paper introduces ARCADIA, an agentic AI framework for causal discovery that integrates large-language-model reasoning with statistical diagnostics to construct valid, temporally coherent causal structures. Unlike traditional algorithms, ARCADIA iteratively refines candidate DAGs through constraint-guided prompting and causal-validity feedback, leading to stable and interpretable models for real-world high-stakes domains. Experiments on corporate bankruptcy data show that ARCADIA produces more reliable causal graphs than NOTEARS, GOLEM, and DirectLiNGAM while offering a fully explainable, intervention-ready pipeline. The framework advances AI by demonstrating how agentic LLMs can participate in autonomous scientific modeling and structured causal inference. --- ### WaterSearch: Exploring Seed Pooling for Improving the Quality-Detectability Trade-off in LLM Watermarking Authors: Yukang Lin, Jiahao Shao, Shuoran Jiang, Wentao Zhu, Bingjie Lu, Xiangping Wu, Joanna Siebert, Qingcai Chen Published: 2025-11-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.00837v3 Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated content. Existing approaches typically embed signals by manipulating token generation probabilities. Despite their effectiveness, these methods inherently face a trade-off between detectability and text quality: the signal strength and randomness required for robust watermarking tend to degrade the performance of downstream tasks. In this paper, we design a novel embedding scheme that controls seed pools to facilitate diverse parallel generation of watermarked text. Based on that scheme, we propose WaterSearch, a sentence-level, search-based watermarking framework adaptable to a wide range of existing methods. WaterSearch enhances text quality by jointly optimizing two key aspects: 1) distribution fidelity and 2) watermark signal characteristics. Furthermore, WaterSearch is complemented by a sentence-level detection method with strong attack robustness. We evaluate our method on three popular LLMs across ten diverse tasks. Extensive experiments demonstrate that our method achieves an average performance improvement of 51.01\% over state-of-the-art baselines at a watermark detectability strength of 95\%. In challenging scenarios such as short text generation and low-entropy output generation, our method yields performance gains of 47.78\% and 36.47\%, respectively. Moreover, under different attack senarios including insertion, synonym substitution and paraphrase attasks, WaterSearch maintains high detectability, further validating its robust anti-attack capabilities. Our code is available at \href{https://github.com/Yukang-Lin/WaterSearch}{https://github.com/Yukang-Lin/WaterSearch}. --- ### Assessing model error in counterfactual worlds Authors: Emily Howerton, Justin Lessler Published: 2025-11-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.00836v1 Counterfactual scenario modeling exercises that ask "what would happen if?" are one of the most common ways we plan for the future. Despite their ubiquity in planning and decision making, scenario projections are rarely evaluated retrospectively. Differences between projections and observations come from two sources: scenario deviation and model miscalibration. We argue the latter is most important for assessing the value of models in decision making, but requires estimating model error in counterfactual worlds. Here we present and contrast three approaches for estimating this error, and demonstrate the benefits and limitations of each in a simulation experiment. We provide recommendations for the estimation of counterfactual error and discuss the components of scenario design that are required to make scenario projections evaluable. --- ### Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows Authors: Adriel Sosa Marco, John Daniel Kirwan, Alexia Toumpa, Simos Gerasimou Published: 2025-11-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.00835v1 Quantifying uncertainty in deep regression models is important both for understanding the confidence of the model and for safe decision-making in high-risk domains. Existing approaches that yield prediction intervals overlook distributional information, neglecting the effect of multimodal or asymmetric distributions on decision-making. Similarly, full or approximated Bayesian methods, while yielding the predictive posterior density, demand major modifications to the model architecture and retraining. We introduce MCNF, a novel post hoc uncertainty quantification method that produces both prediction intervals and the full conditioned predictive distribution. MCNF operates on top of the underlying trained predictive model; thus, no predictive model retraining is needed. We provide experimental evidence that the MCNF-based uncertainty estimate is well calibrated, is competitive with state-of-the-art uncertainty quantification methods, and provides richer information for downstream decision-making tasks. --- ### SemAgent: Semantic-Driven Agentic AI Empowered Trajectory Prediction in Vehicular Networks Authors: Lin Zhu, Kezhi Wang, Luping Xiang, Kun Yang Published: 2025-11-30 Categories: cs.AI, cs.NI arXiv: https://arxiv.org/abs/2512.00834v1 Efficient information exchange and reliable contextual reasoning are essential for vehicle-to-everything (V2X) networks. Conventional communication schemes often incur significant transmission overhead and latency, while existing trajectory prediction models generally lack environmental perception and logical inference capabilities. This paper presents a trajectory prediction framework that integrates semantic communication with Agentic AI to enhance predictive performance in vehicular environments. In vehicle-to-infrastructure (V2I) communication, a feature-extraction agent at the Roadside Unit (RSU) derives compact representations from historical vehicle trajectories, followed by semantic reasoning performed by a semantic-analysis agent. The RSU then transmits both feature representations and semantic insights to the target vehicle via semantic communication, enabling the vehicle to predict future trajectories by combining received semantics with its own historical data. In vehicle-to-vehicle (V2V) communication, each vehicle performs local feature extraction and semantic analysis while receiving predicted trajectories from neighboring vehicles, and jointly utilizes this information for its own trajectory prediction. Extensive experiments across diverse communication conditions demonstrate that the proposed method significantly outperforms baseline schemes, achieving up to a 47.5% improvement in prediction accuracy under low signal-to-noise ratio (SNR) conditions. --- ### PanFlow: Decoupled Motion Control for Panoramic Video Generation Authors: Cheng Zhang, Hanwen Liang, Donny Y. Chen, Qianyi Wu, Konstantinos N. Plataniotis, Camilo Cruz Gambardella, Jianfei Cai Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00832v1 Panoramic video generation has attracted growing attention due to its applications in virtual reality and immersive media. However, existing methods lack explicit motion control and struggle to generate scenes with large and complex motions. We propose PanFlow, a novel approach that exploits the spherical nature of panoramas to decouple the highly dynamic camera rotation from the input optical flow condition, enabling more precise control over large and dynamic motions. We further introduce a spherical noise warping strategy to promote loop consistency in motion across panorama boundaries. To support effective training, we curate a large-scale, motion-rich panoramic video dataset with frame-level pose and flow annotations. We also showcase the effectiveness of our method in various applications, including motion transfer and video editing. Extensive experiments demonstrate that PanFlow significantly outperforms prior methods in motion fidelity, visual quality, and temporal coherence. Our code, dataset, and models are available at https://github.com/chengzhag/PanFlow. --- ### ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning Authors: Yuchen Zeng, Shuibai Zhang, Wonjun Kang, Shutong Wu, Lynnix Zou, Ying Fan, Heeju Kim, Ziqian Lin, Jungtaek Kim, Hyung Il Koo, Dimitris Papailiopoulos, Kangwook Lee Published: 2025-11-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.00831v2 Large Reasoning Models (LRMs) are Large Language Models (LLMs) explicitly trained to generate long-form Chain-of-Thoughts (CoTs), achieving impressive success on challenging tasks like math and programming. However, their underlying reasoning "algorithms" remain poorly understood. To investigate this, we propose ReJump, which represents a reasoning trace as a visitation order over nodes in a tree of intermediate problem-solving steps. Transitions between nodes, which we term jumps, include adjacent moves that capture behaviors such as calculation, and non-adjacent moves that capture behaviors such as backtracking and verification. ReJump enables analyzing LLM reasoning with diverse metrics that quantify exploration, exploitation, overthinking, forgetting, and verification. Using our proposed LLM agent to extract reasoning traces into ReJump format, we evaluate state-of-the-art LRMs on two tasks and find that models with similar accuracy can exhibit distinct reasoning behaviors, while different tasks favor different reasoning styles (e.g., varying balance between exploration and exploitation). To further understand how learning strategies shape reasoning, we use ReJump to compare distilled LRMs with their teachers, CoT-prompted LLMs with LRMs, and to examine how the number of reasoning examples and reinforcement learning affect reasoning behavior. Finally, we show that ReJump can improve reasoning quality at test time through strategies such as ReJump-guided Best-of-N selection and prompt selection. Our code is publicly available at https://github.com/UW-Madison-Lee-Lab/ReJump. --- ### Accelerating Bangla NLP Tasks with Automatic Mixed Precision: Resource-Efficient Training Preserving Model Efficacy Authors: Md Mehrab Hossain Opi, Sumaiya Khan, Moshammad Farzana Rahman Published: 2025-11-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.00829v1 Training models for Natural Language Processing (NLP) requires substantial computational resources and time, posing significant challenges, especially for NLP development in Bangla, where access to high-end hardware is often limited. In this work, we explore automatic mixed precision (AMP) training as a means to improve computational efficiency without sacrificing model performance. By leveraging a dynamic mix of 16-bit and 32-bit floating-point computations, AMP lowers GPU memory requirements and speeds up training without degrading model performance. We evaluate AMP across four standard Bangla NLP tasks, namely sentiment analysis, named entity recognition, error classification, and question answering, using four transformer-based models: BanglaBERT, BanglishBERT, XLM-R, and mBERT. Our results demonstrate that AMP accelerates training by 44.5% and reduces memory consumption by 17.6%, while maintaining F-1 score within 99.7% of the full-precision baselines. This empirical study highlights AMP's potential to democratize access to state-of-the-art NLP capabilities in hardware-constrained settings by lowering computational barriers. --- ### Med-CMR: A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic for Medical Complex Multimodal Reasoning Authors: Haozhen Gong, Xiaozhong Ji, Yuansen Liu, Wenbin Wu, Xiaoxiao Yan, Jingjing Liu, Kai Wu, Jiazhen Pan, Bailiang Jian, Jiangning Zhang, Xiaobin Hu, Hongwei Bran Li Published: 2025-11-30 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.00818v2 MLLMs MLLMs are beginning to appear in clinical workflows, but their ability to perform complex medical reasoning remains unclear. We present Med-CMR, a fine-grained Medical Complex Multimodal Reasoning benchmark. Med-CMR distinguishes from existing counterparts by three core features: 1) Systematic capability decomposition, splitting medical multimodal reasoning into fine-grained visual understanding and multi-step reasoning to enable targeted evaluation; 2) Challenging task design, with visual understanding across three key dimensions (small-object detection, fine-detail discrimination, spatial understanding) and reasoning covering four clinically relevant scenarios (temporal prediction, causal reasoning, long-tail generalization, multi-source integration); 3) Broad, high-quality data coverage, comprising 20,653 Visual Question Answering (VQA) pairs spanning 11 organ systems and 12 imaging modalities, validated via a rigorous two-stage (human expert + model-assisted) review to ensure clinical authenticity. We evaluate 18 state-of-the-art MLLMs with Med-CMR, revealing GPT-5 as the top-performing commercial model: 57.81 accuracy on multiple-choice questions (MCQs) and a 48.70 open-ended score, outperforming Gemini 2.5 Pro (49.87 MCQ accuracy, 45.98 open-ended score) and leading open-source model Qwen3-VL-235B-A22B (49.34 MCQ accuracy, 42.62 open-ended score). However, specialized medical MLLMs do not reliably outperform strong general models, and long-tail generalization emerges as the dominant failure mode. Med-CMR thus provides a stress test for visual-reasoning integration and rare-case robustness in medical MLLMs, and a rigorous yardstick for future clinical systems. --- ### IRPO: Boosting Image Restoration via Post-training GRPO Authors: Haoxuan Xu, Yi Liu, Tianfu Li, Ruolin Shen, Boyuan Jiang, Jinlong Peng, Donghao Luo, Xiaobin Hu, Shuicheng Yan, Haoang Li Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00814v3 Post-training has become effective for high-level generation, but its role in low-level vision remains underexplored. Existing image restoration methods often rely on fixed pixel-wise fitting to ground-truth images, which can lead to over-smoothing and weak generalization. We propose IRPO, a GRPO-based post-training framework for deterministic restoration models. IRPO is built around two axes: data formulation and reward modeling. For data formulation, we select the 30% underperforming samples from the pre-training stage, which improves both accuracy and training efficiency. For reward modeling, we combine fidelity-oriented and quality-aware feedback with three components: a General Reward for structural fidelity, an Expert Reward that uses a Vision-Language Model as a coarse visual-quality judge, and a Restoration Reward for task-specific low-level cues. Experiments on six in-domain and five out-of-domain (OOD) benchmarks show that IRPO improves the AdaIR baseline by 0.93 dB on in-domain tasks and 3.43 dB on OOD settings. Our code can be shown in https://github.com/HaoxuanXU1024/IRPO. --- ### Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classification Authors: Yijia Fan, Jusheng Zhang, Kaitong Cai, Jing Yang, Keze Wang Published: 2025-11-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.00812v1 Multi-label classification (MLC) remains vulnerable to label imbalance, spurious correlations, and distribution shifts, challenges that are particularly detrimental to rare label prediction. To address these limitations, we introduce the Causal Cooperative Game (CCG) framework, which conceptualizes MLC as a cooperative multi-player interaction. CCG unifies explicit causal discovery via Neural Structural Equation Models with a counterfactual curiosity reward to drive robust feature learning. Furthermore, it incorporates a causal invariance loss to ensure generalization across diverse environments, complemented by a specialized enhancement strategy for rare labels. Extensive benchmarking demonstrates that CCG substantially outperforms strong baselines in both rare label prediction and overall robustness. Through rigorous ablation studies and qualitative analysis, we validate the efficacy and interpretability of our components, underscoring the potential of synergizing causal inference with cooperative game theory for advancing multi-label learning. --- ### Soft Quality-Diversity Optimization Authors: Saeed Hedayatian, Stefanos Nikolaidis Published: 2025-11-30 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2512.00810v2 Quality-Diversity (QD) algorithms constitute a branch of optimization that is concerned with discovering a diverse and high-quality set of solutions to an optimization problem. Current QD methods commonly maintain diversity by dividing the behavior space into discrete regions, ensuring that solutions are distributed across different parts of the space. The QD problem is then solved by searching for the best solution in each region. This approach to QD optimization poses challenges in large solution spaces, where storing many solutions is impractical, and in high-dimensional behavior spaces, where discretization becomes ineffective due to the curse of dimensionality. We present an alternative framing of the QD problem, called \emph{Soft QD}, that sidesteps the need for discretizations. We validate this formulation by demonstrating its desirable properties, such as monotonicity, and by relating its limiting behavior to the widely used QD Score metric. Furthermore, we leverage it to derive a novel differentiable QD algorithm, \emph{Soft QD Using Approximated Diversity (SQUAD)}, and demonstrate empirically that it is competitive with current state of the art methods on standard benchmarks while offering better scalability to higher dimensional problems. Source code is available at https://github.com/conflictednerd/soft-qd. --- ### BioPro: Towards Difference-Aware Gender Fairness for Vision-Language Models Authors: Yujie Lin, Jiayao Ma, Qingguo Hu, Wenbo Li, Genji Li, Derek Wong, Jinsong Su Published: 2025-11-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.00807v2 Vision-Language Models (VLMs) inherit significant social biases from their training data, notably in gender representation. Current fairness interventions often adopt a difference-unaware perspective that enforces uniform treatment across demographic groups. These approaches, however, fail to distinguish between contexts where neutrality is required and those where group-specific attributes are legitimate and must be preserved. Building upon recent advances in difference-aware fairness for text-only models, we extend this concept to the multimodal domain and formalize the problem of difference-aware gender fairness for image captioning and text-to-image generation. We advocate for selective debiasing, which aims to mitigate unwanted bias in neutral contexts while preserving valid distinctions in explicit ones. To achieve this, we propose BioPro (Bias Orthogonal Projection), an entirely training-free framework. BioPro identifies a low-dimensional gender-variation subspace through counterfactual embeddings and applies projection to selectively neutralize gender-related information. Experiments show that BioPro effectively reduces gender bias in neutral cases while maintaining gender faithfulness in explicit ones, thus providing a promising direction toward achieving selective fairness in VLMs. Beyond gender bias, we further demonstrate that BioPro can effectively generalize to continuous bias variables, such as scene brightness, highlighting its broader applicability. --- ### Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding Authors: Pengfei Hu, Meng Cao, Yingyao Wang, Yi Wang, Jiahua Dong, Jun Song, Yu Cheng, Bo Zheng, Xiaodan Liang Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00805v2 Long video understanding is essential for human-like intelligence, enabling coherent perception and reasoning over extended temporal contexts. While the emerging thinking-with-frames paradigm, which alternates between global temporal reasoning and local frame examination, has advanced the reasoning capabilities of video multi-modal large language models (MLLMs), it suffers from a significant efficiency bottleneck due to the progressively growing and redundant multi-modal context. To address this, we propose SpecTemp, a reinforcement learning-based Speculative Temporal reasoning framework that decouples temporal perception from reasoning via a cooperative dual-model design. In SpecTemp, a lightweight draft MLLM rapidly explores and proposes salient frames from densely sampled temporal regions, while a powerful target MLLM focuses on temporal reasoning and verifies the draft's proposals, iteratively refining its attention until convergence. This design mirrors the collaborative pathways of the human brain, balancing efficiency with accuracy. To support training, we construct the SpecTemp-80K dataset, featuring synchronized dual-level annotations for coarse evidence spans and fine-grained frame-level evidence. Experiments across multiple video understanding benchmarks demonstrate that SpecTemp not only maintains competitive accuracy but also significantly accelerates inference compared with existing thinking-with-frames methods. --- ### Epistemic Bias Injection: Manipulating LLM Opinion via Selective Context Retrieval Authors: Hao Wu, Prateek Saxena Published: 2025-11-30 Categories: cs.CR, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2512.00804v3 When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases. These are often populated from unvetted sources, e.g. the open web, and can contain maliciously crafted data. This paper studies attacks that can manipulate the context retrieved by LLMs from such RAG databases. Prior work on such context manipulation primarily injects false or toxic content, which can often be detected by fact-checking or linguistic analysis. A more subtle threat, which we call epistemic bias injection (EBI), is where adversaries inject factually correct yet epistemically biased passages that systematically favor one side of an open-ended issue. Although linguistically coherent and truthful, such adversarial passages effectively crowd out alternative viewpoints during retrieval from the RAG and push LLM outputs towards an attack-desired stance. As a core contribution, we propose a novel characterization of the problem: We give a geometric metric that quantifies stance polarity and epistemic bias. This metric can be computed directly on embeddings of text passages. Leveraging it, we construct EBI attacks and develop a lightweight prototype defense called BiasDef for them. We evaluate them both on a comprehensive benchmark constructed from public question answering datasets. Our results show that: (1) the proposed attack induces significant stance polarity shifts, effectively evading existing retrieval-based sanitization defenses, and (2) BiasDef substantially reduces adversarial retrieval and epistemic bias in LLM's answers. Overall, this demonstrates the new threat as well as the ease of employing epistemic bias metrics for filtering in RAG-enabled LLMs. --- ### CircleFlow: Flow-Guided Camera Blur Estimation using a Circle Grid Target Authors: Jiajian He, Enjie Hu, Shiqi Chen, Tianchen Qiu, Huajun Feng, Zhihai Xu, Yueting Chen Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00796v1 The point spread function (PSF) serves as a fundamental descriptor linking the real-world scene to the captured signal, manifesting as camera blur. Accurate PSF estimation is crucial for both optical characterization and computational vision, yet remains challenging due to the inherent ambiguity and the ill-posed nature of intensity-based deconvolution. We introduce CircleFlow, a high-fidelity PSF estimation framework that employs flow-guided edge localization for precise blur characterization. CircleFlow begins with a structured capture that encodes locally anisotropic and spatially varying PSFs by imaging a circle grid target, while leveraging the target's binary luminance prior to decouple image and kernel estimation. The latent sharp image is then reconstructed through subpixel alignment of an initialized binary structure guided by optical flow, whereas the PSF is modeled as an energy-constrained implicit neural representation. Both components are jointly optimized within a demosaicing-aware differentiable framework, ensuring physically consistent and robust PSF estimation enabled by accurate edge localization. Extensive experiments on simulated and real-world data demonstrate that CircleFlow achieves state-of-the-art accuracy and reliability, validating its effectiveness for practical PSF calibration. --- ### PolarGS: Polarimetric Cues for Ambiguity-Free Gaussian Splatting with Accurate Geometry Recovery Authors: Bo Guo, Sijia Wen, Yifan Zhao, Jia Li, Zhiming Zheng Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00794v1 Recent advances in surface reconstruction for 3D Gaussian Splatting (3DGS) have enabled remarkable geometric accuracy. However, their performance degrades in photometrically ambiguous regions such as reflective and textureless surfaces, where unreliable cues disrupt photometric consistency and hinder accurate geometry estimation. Reflected light is often partially polarized in a manner that reveals surface orientation, making polarization an optic complement to photometric cues in resolving such ambiguities. Therefore, we propose PolarGS, an optics-aware extension of RGB-based 3DGS that leverages polarization as an optical prior to resolve photometric ambiguities and enhance reconstruction accuracy. Specifically, we introduce two complementary modules: a polarization-guided photometric correction strategy, which ensures photometric consistency by identifying reflective regions via the Degree of Linear Polarization (DoLP) and refining reflective Gaussians with Color Refinement Maps; and a polarization-enhanced Gaussian densification mechanism for textureless area geometry recovery, which integrates both Angle and Degree of Linear Polarization (A/DoLP) into a PatchMatch-based depth completion process. This enables the back-projection and fusion of new Gaussians, leading to more complete reconstruction. PolarGS is framework-agnostic and achieves superior geometric accuracy compared to state-of-the-art methods. --- ### Estimating the Effective Rank of Vision Transformers via Low-Rank Factorization Authors: Liyu Zerihun Published: 2025-11-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.00792v1 Deep networks are heavily over-parameterized, yet their learned representations often admit low-rank structure. We introduce a framework for estimating a model's intrinsic dimensionality by treating learned representations as projections onto a low-rank subspace of the model's full capacity. Our approach: train a full-rank teacher, factorize its weights at multiple ranks, and train each factorized student via distillation to measure performance as a function of rank. We define effective rank as a region, not a point: the smallest contiguous set of ranks for which the student reaches 85-95% of teacher accuracy. To stabilize estimates, we fit accuracy vs. rank with a monotone PCHIP interpolant and identify crossings of the normalized curve. We also define the effective knee as the rank maximizing perpendicular distance between the smoothed accuracy curve and its endpoint secant; an intrinsic indicator of where marginal gains concentrate. On ViT-B/32 fine-tuned on CIFAR-100 (one seed, due to compute constraints), factorizing linear blocks and training with distillation yields an effective-rank region of approximately (16, 34) and an effective knee at r* ~ 31. At rank 32, the student attains 69.46% top-1 accuracy vs. 73.35% for the teacher (~94.7% of baseline) while achieving substantial parameter compression. We provide a framework to estimate effective-rank regions and knees across architectures and datasets, offering a practical tool for characterizing the intrinsic dimensionality of deep models. ---