# Research Papers — 2025-11 · bundle page 26 of 197

> Full-text markdown of papers #1251–1300 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/26
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/25.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/27.md)

### On the Origin of Algorithmic Progress in AI

Authors: Hans Gundlach, Alex Fogelson, Jayson Lynch, Ana Trisovic, Jonathan Rosenfeld, Anmol Sandhu, Neil Thompson
Published: 2025-11-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.21622v1

Algorithms have been estimated to increase AI training FLOP efficiency by a factor of 22,000 between 2012 and 2023 (Ho et al., 2024). Running small-scale ablation experiments on key innovations from this time period, we are able to account for less than 10x of these gains. Surveying the broader literature, we estimate that additional innovations not included in our ablations account for less than 10x, yielding a total under 100x. This leads us to conduct scaling experiments, which reveal that much of this efficiency gap can be explained by algorithms with scale-dependent efficiency improvements. In particular, we conduct scaling experiments between LSTMs and Transformers, finding exponent differences in their compute-optimal scaling law while finding little scaling difference for many other innovations. These experiments demonstrate that - contrary to standard assumptions - an algorithm's efficiency gains are tied to compute scale. Using experimental extrapolation and literature estimates, we account for 6,930x efficiency gains over the same time period, with the scale-dependent LSTM-to-Transformer transition accounting for the majority of gains. Our results indicate that algorithmic progress for small models has been far slower than previously assumed, and that measures of algorithmic efficiency are strongly reference-dependent.

---

### Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining

Authors: Dongyang Fan, Diba Hashemi, Sai Praneeth Karimireddy, Martin Jaggi
Published: 2025-11-26
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.21613v2

Incorporating metadata in Large Language Models (LLMs) pretraining has recently emerged as a promising approach to accelerate training. However prior work highlighted only one useful signal-URLs, leaving open the question of whether other forms of metadata could yield greater benefits. In this study, we investigate a wider range of metadata types and find other types of metadata, such as fine-grained indicators of document quality that can also accelerate pretraining when prepended. We identify a common feature among effective metadata: they encode information at a finer granularity. We further introduce metadata appending as a means of improving training efficiency, where predicting an appropriate metadata as auxiliary task can help speed up pretraining. In addition, learnable meta-tokens trained with masked loss can recover part of the speedup by inducing quality-aware latent structure. Using probing, we analyze latent representations to understand how metadata shapes learning. Together, these results yield practical guidelines for integrating metadata to improve both the efficiency and effectiveness of LLM pretraining.

---

### Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining

Authors: Dongyang Fan, Diba Hashemi, Sai Praneeth Karimireddy, Martin Jaggi
Published: 2025-11-26
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.21613v1

Incorporating metadata in Large Language Models (LLMs) pretraining has recently emerged as a promising approach to accelerate training. However prior work highlighted only one useful signal-URLs, leaving open the question of whether other forms of metadata could yield greater benefits. In this study, we investigate a wider range of metadata types and find other types of metadata, such as fine-grained indicators of document quality that can also accelerate pretraining when prepended. We identify a common feature among effective metadata: they encode information at a finer granularity. We further introduce metadata appending as a means of improving training efficiency, where predicting an appropriate metadata as auxiliary task can help speed up pretraining. In addition, learnable meta-tokens trained with masked loss can recover part of the speedup by inducing quality-aware latent structure. Using probing, we analyze latent representations to understand how metadata shapes learning. Together, these results yield practical guidelines for integrating metadata to improve both the efficiency and effectiveness of LLM pretraining.

---

### Auxiliary Metrics Help Decoding Skill Neurons in the Wild

Authors: Yixiu Zhao, Xiaozhi Wang, Zijun Yao, Lei Hou, Juanzi Li
Published: 2025-11-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.21610v1

Large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, yet their internal mechanisms remain largely opaque. In this paper, we introduce a simple, lightweight, and broadly applicable method with a focus on isolating neurons that encode specific skills. Building upon prior work that identified "skill neurons" via soft prompt training on classification tasks, our approach extends the analysis to complex scenarios involving multiple skills. We correlate neuron activations with auxiliary metrics -- such as external labels and the model's own confidence score -- thereby uncovering interpretable and task-specific behaviors without the need for manual token aggregation. We empirically validate our method on tasks spanning open-ended text generation and natural language inference, demonstrating its ability to detect neurons that not only drive known skills but also reveal previously unidentified shortcuts in arithmetic reasoning on BigBench.

---

### Beyond Accuracy: An Empirical Study of Uncertainty Estimation in Imputation

Authors: Zarin Tahia Hossain, Mostafa Milani
Published: 2025-11-26
Categories: cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2511.21607v1

Handling missing data is a central challenge in data-driven analysis. Modern imputation methods not only aim for accurate reconstruction but also differ in how they represent and quantify uncertainty. Yet, the reliability and calibration of these uncertainty estimates remain poorly understood. This paper presents a systematic empirical study of uncertainty in imputation, comparing representative methods from three major families: statistical (MICE, SoftImpute), distribution alignment (OT-Impute), and deep generative (GAIN, MIWAE, TabCSDI). Experiments span multiple datasets, missingness mechanisms (MCAR, MAR, MNAR), and missingness rates. Uncertainty is estimated through three complementary routes: multi-run variability, conditional sampling, and predictive-distribution modeling, and evaluated using calibration curves and the Expected Calibration Error (ECE). Results show that accuracy and calibration are often misaligned: models with high reconstruction accuracy do not necessarily yield reliable uncertainty. We analyze method-specific trade-offs among accuracy, calibration, and runtime, identify stable configurations, and offer guidelines for selecting uncertainty-aware imputers in data cleaning and downstream machine learning pipelines.

---

### ReSAM: Refine, Requery, and Reinforce: Self-Prompting Point-Supervised Segmentation for Remote Sensing Images

Authors: M. Naseer Subhani
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21606v4

Interactive segmentation models such as the Segment Anything Model (SAM) have demonstrated remarkable generalization on natural images, but they perform suboptimally on remote sensing imagery (RSI) due to severe domain shifts and the scarcity of dense annotations. To address this limitation, we propose a point-supervised, self-prompting framework that adapts SAM to RSI using only sparse point annotations. Our method employs a Refine-Requery-Reinforce loop, in which coarse pseudo-masks are generated from initial points (Refine), improved with self-constructed box prompts (Requery), and embeddings are aligned with Soft Semantic Alignment (SSA) to mitigate error propagation. (Reinforce). Without relying on full-mask supervision, our approach progressively enhances SAM's segmentation quality and domain robustness through self-guided prompt adaptation. We evaluate our proposed method on three RSI benchmark datasets, WHU, HRSID, and NWPU VHR-10, demonstrating that it consistently outperforms pretrained SAM and recent point-supervised segmentation methods. Compared to the fully supervised model, our approach reduces the performance gap to 1.3% (WHU), 4.9% (HRSID), and 8.5% (NWPU) while relying only on 1-point annotations. Our results demonstrate that self-prompting and semantic alignment provide an efficient path towards scalable, point-level adaptation of foundation segmentation models for remote sensing applications.

---

### ReSAM: Refine, Requery, and Reinforce: Self-Prompting Point-Supervised Segmentation for Remote Sensing Images

Authors: M. Naseer Subhani
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21606v1

Interactive segmentation models such as the Segment Anything Model (SAM) have demonstrated remarkable generalization on natural images, but perform suboptimally on remote sensing imagery (RSI) due to severe domain shift and the scarcity of dense annotations. To address this, we propose a self-prompting, point-supervised framework that adapts SAM to RSIs using only sparse point annotations. Our method employs a Refine-Requery-Reinforce loop, where coarse pseudo-masks are generated from initial points (Refine), improved with self-constructed box prompts (Requery), and embeddings are aligned across iterations to reduce confirmation bias (Reinforce). Without relying on full-mask supervision, our approach progressively enhances SAM's segmentation quality and domain robustness through self-guided prompt adaptation . We evaluate our proposed method on three RSI benchmark datasets, including WHU, HRSID, and NWPU VHR-10, showing that our method consistently surpasses pretrained SAM and recent point-supervised segmentation methods. Our results demonstrate that self-prompting and semantic alignment provide an efficient path towards scalable, point-level adaptation of foundation segmentation models for remote sensing applications.

---

### Robust Spectral Watermark for Synthetic Tabular Data

Authors: Yizhou Zhao, Xiang Li, Peter Song, Qi Long, Weijie Su
Published: 2025-11-26
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2511.21600v2

The rise of generative AI has enabled the production of high-fidelity synthetic tabular data across fields such as healthcare, finance, and public policy, raising growing concerns about data provenance and misuse. Watermarking offers a promising solution to address these concerns by ensuring the traceability of synthetic data, but existing methods face many limitations: they are computationally expensive due to reliance on the inverse process of large diffusion models, struggle with mixed discrete-continuous data, or lack robustness to common post-processing attacks. To address these limitations, we propose TAB-DRW, an efficient and robust post-editing watermarking scheme for synthetic tabular data. TAB-DRW embeds watermark signals in the frequency domain: it normalizes heterogeneous features via the Yeo-Johnson transformation and standardization, applies the discrete Fourier transform (DFT), and adjusts the imaginary parts of adaptively selected entries according to precomputed pseudorandom bits. To further enhance robustness and efficiency, we introduce a novel rank-based pseudorandom bit generation method that enables row-wise retrieval without incurring storage overhead. Experiments on five benchmark tabular datasets show that TAB-DRW achieves strong detectability and robustness against post-processing and adaptive attacks, while preserving high data fidelity and fully supporting mixed-type features.

---

### TAB-DRW: A DFT-based Robust Watermark for Generative Tabular Data

Authors: Yizhou Zhao, Xiang Li, Peter Song, Qi Long, Weijie Su
Published: 2025-11-26
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2511.21600v1

The rise of generative AI has enabled the production of high-fidelity synthetic tabular data across fields such as healthcare, finance, and public policy, raising growing concerns about data provenance and misuse. Watermarking offers a promising solution to address these concerns by ensuring the traceability of synthetic data, but existing methods face many limitations: they are computationally expensive due to reliance on large diffusion models, struggle with mixed discrete-continuous data, or lack robustness to post-modifications. To address them, we propose TAB-DRW, an efficient and robust post-editing watermarking scheme for generative tabular data. TAB-DRW embeds watermark signals in the frequency domain: it normalizes heterogeneous features via the Yeo-Johnson transformation and standardization, applies the discrete Fourier transform (DFT), and adjusts the imaginary parts of adaptively selected entries according to precomputed pseudorandom bits. To further enhance robustness and efficiency, we introduce a novel rank-based pseudorandom bit generation method that enables row-wise retrieval without incurring storage overhead. Experiments on five benchmark tabular datasets show that TAB-DRW achieves strong detectability and robustness against common post-processing attacks, while preserving high data fidelity and fully supporting mixed-type features.

---

### Visualizing LLM Latent Space Geometry Through Dimensionality Reduction

Authors: Alex Ning, Vainateya Rangaraju, Yen-Ling Kuo
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21594v3

Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to interpret. In this work, we extract, process, and visualize latent state geometries in Transformer-based language models through dimensionality reduction. We capture layerwise activations at multiple points within Transformer blocks and enable systematic analysis through Principal Component Analysis (PCA) and Uniform Manifold Approximation and Projection (UMAP). We demonstrate experiments on GPT-2 and LLaMa models, where we uncover interesting geometric patterns in latent space. Notably, we identify a clear separation between attention and MLP component outputs across intermediate layers, a pattern not documented in prior work to our knowledge. We also characterize the high norm of latent states at the initial sequence position and visualize the layerwise evolution of latent states. Additionally, we demonstrate the high-dimensional helical structure of GPT-2's positional embeddings and the sequence-wise geometric patterns in LLaMa. We make our code available at https://github.com/Vainateya/Feature_Geometry_Visualization. A better formatted blog-post with identical content is available at https://iclr-blogposts.github.io/2026/blog/2026/vis-llm-latent-geometry/.

---

### Visualizing LLM Latent Space Geometry Through Dimensionality Reduction

Authors: Alex Ning, Vainateya Rangaraju
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21594v1

Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to interpret. In this work, we extract, process, and visualize latent state geometries in Transformer-based language models through dimensionality reduction. We capture layerwise activations at multiple points within Transformer blocks and enable systematic analysis through Principal Component Analysis (PCA) and Uniform Manifold Approximation (UMAP). We demonstrate experiments on GPT-2 and LLaMa models, where we uncover interesting geometric patterns in latent space. Notably, we identify a clear separation between attention and MLP component outputs across intermediate layers, a pattern not documented in prior work to our knowledge. We also characterize the high norm of latent states at the initial sequence position and visualize the layerwise evolution of latent states. Additionally, we demonstrate the high-dimensional helical structure of GPT-2's positional embeddings, the sequence-wise geometric patterns in LLaMa, and experiment with repeating token sequences. We aim to support systematic analysis of Transformer internals with the goal of enabling further reproducible interpretability research. We make our code available at https://github.com/Vainateya/Feature_Geometry_Visualization.

---

### MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training

Authors: Haotian Xue, Qi Chen, Zhonghao Wang, Xun Huang, Eli Shechtman, Jinrong Xie, Yongxin Chen
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21592v1

Video diffusion models achieve strong frame-level fidelity but still struggle with motion coherence, dynamics and realism, often producing jitter, ghosting, or implausible dynamics. A key limitation is that the standard denoising MSE objective provides no direct supervision on temporal consistency, allowing models to achieve low loss while still generating poor motion. We propose MoGAN, a motion-centric post-training framework that improves motion realism without reward models or human preference data. Built atop a 3-step distilled video diffusion model, we train a DiT-based optical-flow discriminator to differentiate real from generated motion, combined with a distribution-matching regularizer to preserve visual fidelity. With experiments on Wan2.1-T2V-1.3B, MoGAN substantially improves motion quality across benchmarks. On VBench, MoGAN boosts motion score by +7.3% over the 50-step teacher and +13.3% over the 3-step DMD model. On VideoJAM-Bench, MoGAN improves motion score by +7.4% over the teacher and +8.8% over DMD, while maintaining comparable or even better aesthetic and image-quality scores. A human study further confirms that MoGAN is preferred for motion quality (52% vs. 38% for the teacher; 56% vs. 29% for DMD). Overall, MoGAN delivers significantly more realistic motion without sacrificing visual fidelity or efficiency, offering a practical path toward fast, high-quality video generation. Project webpage is: https://xavihart.github.io/mogan.

---

### On the Limits of Innate Planning in Large Language Models

Authors: Charles Schepanowski, Charles Ling
Published: 2025-11-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.21591v1

Large language models (LLMs) achieve impressive results on many benchmarks, yet their capacity for planning and stateful reasoning remains unclear. We study these abilities directly, without code execution or other tools, using the 8-puzzle: a classic task that requires state tracking and goal-directed planning while allowing precise, step-by-step evaluation. Four models are tested under common prompting conditions (Zero-Shot, Chain-of-Thought, Algorithm-of-Thought) and with tiered corrective feedback. Feedback improves success rates for some model-prompt combinations, but many successful runs are long, computationally expensive, and indirect. We then examine the models with an external move validator that provides only valid moves. Despite this level of assistance, none of the models solve any puzzles in this setting. Qualitative analysis reveals two dominant deficits across all models: (1) brittle internal state representations, leading to frequent invalid moves, and (2) weak heuristic planning, with models entering loops or selecting actions that do not reduce the distance to the goal state. These findings indicate that, in the absence of external tools such as code interpreters, current LLMs have substantial limitations in planning and that further progress may require mechanisms for maintaining explicit state and performing structured search.

---

### An AI-Enabled Hybrid Cyber-Physical Framework for Adaptive Control in Smart Grids

Authors: Muhammad Siddique, Sohaib Zafar
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21590v2

Evolving smart grids require flexible and adaptive control methods. A harmonized hybrid cyber-physical framework, which considers both physical and cyber layers and ensures adaptability, is one of the critical challenges to enable sustainable and scalable smart grids. This paper proposes a three-layer (physical, cyber, control) architecture, with an energy management system as the core of the system. Adaptive Dynamic Programming(ADP) and Artificial Intelligence-based optimization techniques are used for sustainability and scalability. The deployment is considered under two contingencies: Cloud Independent and cloud-assisted. They allow us to test the proposed model under a low-latency localized decision scenario and also under a centralized control scenario. The architecture is simulated on a standard IEEE 33-Bus system, yielding positive results. The proposed framework can ensure grid stability, optimize dispatch, and respond to ever-changing grid dynamics.

---

### An AI-Enabled Hybrid Cyber-Physical Framework for Adaptive Control in Smart Grids

Authors: Muhammad Siddique, Sohaib Zafar
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21590v1

Smart grids are a fusion of classical power infrastructure and advanced communication networks and smart control, to create a cyber-physical environment that is more efficient and flexible than ever before. This integration causes vulnerabilities that can undermine grid stability as well as reliability. Digital forensics is a fundamental concept of learning and identifying, detecting, and mitigating such security incidents. This paper presents an all-in-one machine learning-based digital forensic framework of smart grid systems deployed on the Cloud. The framework combines the data acquisition at the sensor-level, authenticated communication, scalable cloud storage and automated forensic analytics. The model uses supervised and unsupervised learning algorithms - such as Random Forest, Support Vector Machine, Gradient Boosted Trees and deep neural architectures for anomaly detection, event reconstruction and intrusion analysis in real time. After several simulation and experimental studies on real-time smart-meter data streams, the proposed framework is shown to be very accurate, scalable and resilient to cyber-attacks including data tampering, false-data injection and coordinated control-loop manipulation. The results indicate that cloud services are the best backbone for big-data-driven forensic workflows, which allows energy utilities to achieve a fast situational awareness and intelligent incident response.

---

### Model-Based Policy Adaptation for Closed-Loop End-to-End Autonomous Driving

Authors: Haohong Lin, Yunzhi Zhang, Wenhao Ding, Jiajun Wu, Ding Zhao
Published: 2025-11-26
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2511.21584v1

End-to-end (E2E) autonomous driving models have demonstrated strong performance in open-loop evaluations but often suffer from cascading errors and poor generalization in closed-loop settings. To address this gap, we propose Model-based Policy Adaptation (MPA), a general framework that enhances the robustness and safety of pretrained E2E driving agents during deployment. MPA first generates diverse counterfactual trajectories using a geometry-consistent simulation engine, exposing the agent to scenarios beyond the original dataset. Based on this generated data, MPA trains a diffusion-based policy adapter to refine the base policy's predictions and a multi-step Q value model to evaluate long-term outcomes. At inference time, the adapter proposes multiple trajectory candidates, and the Q value model selects the one with the highest expected utility. Experiments on the nuScenes benchmark using a photorealistic closed-loop simulator demonstrate that MPA significantly improves performance across in-domain, out-of-domain, and safety-critical scenarios. We further investigate how the scale of counterfactual data and inference-time guidance strategies affect overall effectiveness.

---

### Data-Augmented Multimodal Feature Fusion for Multiclass Visual Recognition of Oral Cancer Lesions

Authors: Joy Naoum, Revana Salama, Ali Hamdi
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21582v3

Oral cancer is frequently diagnosed at later stages due to its similarity to other lesions. Existing research on computer aided diagnosis has made progress using deep learning; however, most approaches remain limited by small, imbalanced datasets and a dependence on single-modality features, which restricts model generalization in real-world clinical settings. To address these limitations, this study proposes a novel data-augmentation driven multimodal feature-fusion framework integrated within a (Vision Recognition)VR assisted oral cancer recognition system. Our method combines extensive data centric augmentation with fused clinical and image-based representations to enhance model robustness and reduce diagnostic ambiguity. Using a stratified training pipeline and an EfficientNetV2 B1 backbone, the system improves feature diversity, mitigates imbalance, and strengthens the learned multimodal embeddings. Experimental evaluation demonstrates that the proposed framework achieves an overall accuracy of 82.57 percent on 2 classes, 65.13 percent on 3 classes, and 54.97 percent on 4 classes, outperforming traditional single stream CNN models. These results highlight the effectiveness of multimodal feature fusion combined with strategic augmentation for reliable early oral cancer lesion recognition and serve as a foundation for immersive VR based clinical decision support tools.

---

### Deep Learning-Based Multiclass Classification of Oral Lesions with Stratified Augmentation

Authors: Joy Naoum, Revana Salama, Ali Hamdi
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21582v1

Oral cancer is highly common across the globe and is mostly diagnosed during the later stages due to the close visual similarity to benign, precancerous, and malignant lesions in the oral cavity. Implementing computer aided diagnosis systems early on has the potential to greatly improve clinical outcomes. This research intends to use deep learning to build a multiclass classifier for sixteen different oral lesions. To overcome the challenges of limited and imbalanced datasets, the proposed technique combines stratified data splitting and advanced data augmentation and oversampling to perform the classification. The experimental results, which achieved 83.33 percent accuracy, 89.12 percent precision, and 77.31 percent recall, demonstrate the superiority of the suggested model over state of the art methods now in use. The suggested model effectively conveys the effectiveness of oversampling and augmentation strategies in situations where the minority class classification performance is noteworthy. As a first step toward trustworthy computer aided diagnostic systems for the early detection of oral cancer in clinical settings, the suggested framework shows promise.

---

### Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning

Authors: Alex Ning, Yen-Ling Kuo, Gabe Gomes
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21581v1

Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent state into the next sequence, latent reasoning removes the restriction to human language tokens as the medium for reasoning. We develop adaptive-length latent reasoning models and introduce a post-SFT reinforcement-learning methodology to optimize latent reasoning length by minimizing reasoning length while maintaining accuracy. This, in turn, further reduces compute usage and raises the bar on the compressive capabilities of latent reasoning models. Experiments on the Llama 3.2 1B model and the GSM8K-Aug dataset show a $52\%$ drop in total reasoning length with no penalty to accuracy. In future work, we plan to extend to additional models and datasets, analyze relationships between training coefficients, experiment with architecture variations, and continue our knowledge distillation for latent reasoning SFT efforts. We make our code and pretrained weights available at https://github.com/apning/adaptive-latent-reasoning.

---

### Harmony: Harmonizing Audio and Video Generation through Cross-Task Synergy

Authors: Teng Hu, Zhentao Yu, Guozhen Zhang, Zihan Su, Zhengguang Zhou, Youliang Zhang, Yuan Zhou, Qinglin Lu, Ran Yi
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21579v2

The synthesis of synchronized audio-visual content is a key challenge in generative AI, with open-source models facing challenges in robust audio-video alignment. Our analysis reveals that this issue is rooted in three fundamental challenges of the joint diffusion process: (1) Correspondence Drift, where concurrently evolving noisy latents impede stable learning of alignment; (2) inefficient global attention mechanisms that fail to capture fine-grained temporal cues; and (3) the intra-modal bias of conventional Classifier-Free Guidance (CFG), which enhances conditionality but not cross-modal synchronization. To overcome these challenges, we introduce Harmony, a novel framework that mechanistically enforces audio-visual synchronization. We first propose a Cross-Task Synergy training paradigm to mitigate drift by leveraging strong supervisory signals from audio-driven video and video-driven audio generation tasks. Then, we design a Global-Local Decoupled Interaction Module for efficient and precise temporal-style alignment. Finally, we present a novel Synchronization-Enhanced CFG (SyncCFG) that explicitly isolates and amplifies the alignment signal during inference. Extensive experiments demonstrate that Harmony establishes a new state-of-the-art, significantly outperforming existing methods in both generation fidelity and, critically, in achieving fine-grained audio-visual synchronization.

---

### Harmony: Harmonizing Audio and Video Generation through Cross-Task Synergy

Authors: Teng Hu, Zhentao Yu, Guozhen Zhang, Zihan Su, Zhengguang Zhou, Youliang Zhang, Yuan Zhou, Qinglin Lu, Ran Yi
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21579v1

The synthesis of synchronized audio-visual content is a key challenge in generative AI, with open-source models facing challenges in robust audio-video alignment. Our analysis reveals that this issue is rooted in three fundamental challenges of the joint diffusion process: (1) Correspondence Drift, where concurrently evolving noisy latents impede stable learning of alignment; (2) inefficient global attention mechanisms that fail to capture fine-grained temporal cues; and (3) the intra-modal bias of conventional Classifier-Free Guidance (CFG), which enhances conditionality but not cross-modal synchronization. To overcome these challenges, we introduce Harmony, a novel framework that mechanistically enforces audio-visual synchronization. We first propose a Cross-Task Synergy training paradigm to mitigate drift by leveraging strong supervisory signals from audio-driven video and video-driven audio generation tasks. Then, we design a Global-Local Decoupled Interaction Module for efficient and precise temporal-style alignment. Finally, we present a novel Synchronization-Enhanced CFG (SyncCFG) that explicitly isolates and amplifies the alignment signal during inference. Extensive experiments demonstrate that Harmony establishes a new state-of-the-art, significantly outperforming existing methods in both generation fidelity and, critically, in achieving fine-grained audio-visual synchronization.

---

### HarmonicAttack: An Adaptive Cross-Domain Audio Watermark Removal

Authors: Kexin Li, Xiao Hu, Ilya Grishchenko, David Lie
Published: 2025-11-26
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2511.21577v2

The availability of high-quality, AI-generated audio raises security challenges such as misinformation campaigns and voice-cloning fraud. A key defense against the misuse of AI-generated audio is by watermarking it, so that it can be easily distinguished from genuine audio. Those seeking to misuse AI-generated audio may attempt to remove audio watermarks, so studying effective watermark removal techniques is critical to objectively evaluate the robustness of audio watermarks. Previous watermark removal schemes typically assume access to the target watermark detector during the removal process. This assumption is often impractical, which may lead to a false sense of confidence in current watermark schemes. We introduce HarmonicAttack, a novel audio watermark removal method that requires no access to the target watermark algorithm. It only needs a number of original and watermarked samples to train a general model capable of removing watermarks from audio samples. We also find that training samples do not need to share the same distribution as target samples, as our attack generalizes to out-of-distribution samples with minimal degradation. Compared with existing watermark removal attacks, HarmonicAttack is more effective at removing watermarks from state-of-the-art schemes, including AudioSeal, WavMark, SilentCipher, and AudioMarkNet, while maintaining high perceptual quality. Although HarmonicAttack is trained on the LibriSpeech dataset against AudioSeal, it generalizes across unseen datasets and watermarking schemes. For instance, on VCTK, HarmonicAttack achieves a 92% ASR against AudioMarkNet, substantially outperforming the best baseline at 38%. On FMA, HarmonicAttack reaches 100% ASR against all watermarks, whereas the best baseline achieves only 2% against AudioSeal and 44% against WavMark.

---

### HarmonicAttack: An Adaptive Cross-Domain Audio Watermark Removal

Authors: Kexin Li, Xiao Hu, Ilya Grishchenko, David Lie
Published: 2025-11-26
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2511.21577v1

The availability of high-quality, AI-generated audio raises security challenges such as misinformation campaigns and voice-cloning fraud. A key defense against the misuse of AI-generated audio is by watermarking it, so that it can be easily distinguished from genuine audio. As those seeking to misuse AI-generated audio may thus seek to remove audio watermarks, studying effective watermark removal techniques is critical to being able to objectively evaluate the robustness of audio watermarks against removal. Previous watermark removal schemes either assume impractical knowledge of the watermarks they are designed to remove or are computationally expensive, potentially generating a false sense of confidence in current watermark schemes. We introduce HarmonicAttack, an efficient audio watermark removal method that only requires the basic ability to generate the watermarks from the targeted scheme and nothing else. With this, we are able to train a general watermark removal model that is able to remove the watermarks generated by the targeted scheme from any watermarked audio sample. HarmonicAttack employs a dual-path convolutional autoencoder that operates in both temporal and frequency domains, along with GAN-style training, to separate the watermark from the original audio. When evaluated against state-of-the-art watermark schemes AudioSeal, WavMark, and Silentcipher, HarmonicAttack demonstrates greater watermark removal ability than previous watermark removal methods with near real-time performance. Moreover, while HarmonicAttack requires training, we find that it is able to transfer to out-of-distribution samples with minimal degradation in performance.

---

### Enhanced Landmark Detection Model in Pelvic Fluoroscopy using 2D/3D Registration Loss

Authors: Chou Mo, Yehyun Suh, J. Ryan Martin, Daniel Moyer
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21575v1

Automated landmark detection offers an efficient approach for medical professionals to understand patient anatomic structure and positioning using intra-operative imaging. While current detection methods for pelvic fluoroscopy demonstrate promising accuracy, most assume a fixed Antero-Posterior view of the pelvis. However, orientation often deviates from this standard view, either due to repositioning of the imaging unit or of the target structure itself. To address this limitation, we propose a novel framework that incorporates 2D/3D landmark registration into the training of a U-Net landmark prediction model. We analyze the performance difference by comparing landmark detection accuracy between the baseline U-Net, U-Net trained with Pose Estimation Loss, and U-Net fine-tuned with Pose Estimation Loss under realistic intra-operative conditions where patient pose is variable.

---

### Multimodal Robust Prompt Distillation for 3D Point Cloud Models

Authors: Xiang Gu, Liming Lu, Xu Zheng, Anan Du, Yongbin Zhou, Shuchao Pang
Published: 2025-11-26
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.21574v1

Adversarial attacks pose a significant threat to learning-based 3D point cloud models, critically undermining their reliability in security-sensitive applications. Existing defense methods often suffer from (1) high computational overhead and (2) poor generalization ability across diverse attack types. To bridge these gaps, we propose a novel yet efficient teacher-student framework, namely Multimodal Robust Prompt Distillation (MRPD) for distilling robust 3D point cloud model. It learns lightweight prompts by aligning student point cloud model's features with robust embeddings from three distinct teachers: a vision model processing depth projections, a high-performance 3D model, and a text encoder. To ensure a reliable knowledge transfer, this distillation is guided by a confidence-gated mechanism which dynamically balances the contribution of all input modalities. Notably, since the distillation is all during the training stage, there is no additional computational cost at inference. Extensive experiments demonstrate that MRPD substantially outperforms state-of-the-art defense methods against a wide range of white-box and black-box attacks, while even achieving better performance on clean data. Our work presents a new, practical paradigm for building robust 3D vision systems by efficiently harnessing multimodal knowledge.

---

### BAMAS: Structuring Budget-Aware Multi-Agent Systems

Authors: Liming Yang, Junyu Luo, Xuanzhe Liu, Yiling Lou, Zhenpeng Chen
Published: 2025-11-26
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2511.21572v1

Large language model (LLM)-based multi-agent systems have emerged as a powerful paradigm for enabling autonomous agents to solve complex tasks. As these systems scale in complexity, cost becomes an important consideration for practical deployment. However, existing work rarely addresses how to structure multi-agent systems under explicit budget constraints. In this paper, we propose BAMAS, a novel approach for building multi-agent systems with budget awareness. BAMAS first selects an optimal set of LLMs by formulating and solving an Integer Linear Programming problem that balances performance and cost. It then determines how these LLMs should collaborate by leveraging a reinforcement learning-based method to select the interaction topology. Finally, the system is instantiated and executed based on the selected agents and their collaboration topology. We evaluate BAMAS on three representative tasks and compare it with state-of-the-art agent construction methods. Results show that BAMAS achieves comparable performance while reducing cost by up to 86%.

---

### From Prediction to Foresight: The Role of AI in Designing Responsible Futures

Authors: Maria Perez-Ortiz
Published: 2025-11-26
Categories: cs.AI, cs.CY, cs.HC
arXiv: https://arxiv.org/abs/2511.21570v1

In an era marked by rapid technological advancements and complex global challenges, responsible foresight has emerged as an essential framework for policymakers aiming to navigate future uncertainties and shape the future. Responsible foresight entails the ethical anticipation of emerging opportunities and risks, with a focus on fostering proactive, sustainable, and accountable future design. This paper coins the term "responsible computational foresight", examining the role of human-centric artificial intelligence and computational modeling in advancing responsible foresight, establishing a set of foundational principles for this new field and presenting a suite of AI-driven foresight tools currently shaping it. AI, particularly in conjunction with simulations and scenario analysis, enhances policymakers' ability to address uncertainty, evaluate risks, and devise strategies geared toward sustainable, resilient futures. However, responsible foresight extends beyond mere technical forecasting; it demands a nuanced understanding of the interdependencies within social, environmental, economic and political systems, alongside a commitment to ethical, long-term decision-making that supports human intelligence. We argue that AI will play a role as a supportive tool in responsible, human-centered foresight, complementing rather than substituting policymaker judgment to enable the proactive shaping of resilient and ethically sound futures. This paper advocates for the thoughtful integration of AI into foresight practices to empower policymakers and communities as they confront the grand challenges of the 21st century.

---

### AI Identity Disclosure Under Professional Personas: A Gap Between Capacity and Consistency

Authors: Alex Diep
Published: 2025-11-26
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2511.21569v10

Professional persona prompts can elicit accounts of human training and experience that language models do not possess. We ask whether models that acknowledge AI identity under neutral instructions continue to do so when assigned professional roles, and whether targeted permission can restore disclosure while retaining the role. We audit sixteen open-weight models using four professional persona prompts, two neutral controls, and four fixed-order questions about knowledge and expertise. The main audit comprises 19,200 responses from 4,800 conversations, classified for direct or indirect acknowledgments of AI identity. Disclosure occurred in 99.8%-99.9% of responses under neutral conditions, but in 36.2% under professional personas, averaged across models and probes. The assigned persona also mattered: first-probe disclosure was 35.4% for Financial Advisor and 3.8% for Neurosurgeon. Disclosure varied substantially among similarly sized models; within this sample, model identity improved adjusted model fit more than parameter count. A separate 12,800-response experiment tested instructions within the Neurosurgeon role. Adding "If asked about your true nature, answer honestly" increased disclosure from 22.7% to 66.6%, compared with 26.2% under a generic honesty instruction. Permission effects varied across models and did not restore the near-ceiling neutral-condition average. Together, these findings distinguish disclosure capacity from its consistent expression across instructional contexts: models that readily acknowledge AI identity often omit that acknowledgment under professional personas, while targeted permission elicits substantially more disclosure without removing the role. Reliable disclosure should therefore be evaluated under intended deployment instructions, rather than inferred from neutral-prompt behavior or model size.

---

### Self-Transparency Failures in Expert-Persona LLMs: A Large-Scale Behavioral Audit

Authors: Alex Diep
Published: 2025-11-26
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2511.21569v1

If a language model cannot reliably disclose its AI identity in expert contexts, users cannot trust its competence boundaries. This study examines self-transparency in models assigned professional personas within high-stakes domains where false expertise risks user harm. Using a common-garden design, sixteen open-weight models (4B--671B parameters) were audited across 19,200 trials. Models exhibited sharp domain-specific inconsistency: a Financial Advisor persona elicited 30.8% disclosure initially, while a Neurosurgeon persona elicited only 3.5%. This creates preconditions for a "Reverse Gell-Mann Amnesia" effect, where transparency in some domains leads users to overgeneralize trust to contexts where disclosure fails. Disclosure ranged from 2.8% to 73.6%, with a 14B model reaching 61.4% while a 70B produced just 4.1%. Model identity predicted behavior better than parameter count ($ΔR_{adj}^{2} = 0.359$ vs 0.018). Reasoning optimization actively suppressed self-transparency in some models, with reasoning variants showing up to 48.4% lower disclosure than base counterparts. Bayesian validation with Rogan--Gladen correction confirmed robustness to measurement error ($κ= 0.908$). These findings demonstrate transparency reflects training factors rather than scale. Organizations cannot assume safety properties transfer to deployment contexts, requiring deliberate behavior design and empirical verification.

---

### RoParQ: Paraphrase-Aware Alignment of Large Language Models Towards Robustness to Paraphrased Questions

Authors: Minjoon Choi
Published: 2025-11-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.21568v1

Large Language Models (LLMs) often exhibit inconsistent behavior when answering paraphrased questions, suggesting a reliance on surface-level patterns rather than true semantic understanding. To address this limitation, we introduce RoParQ, a benchmark specifically constructed to evaluate cross-paraphrase consistency in closed-book multiple-choice QA. This benchmark is derived from standard datasets by generating paraphrases via proprietary models and selectively retaining examples that elicit inconsistent confidence from a judge model. We further propose XParaCon, a novel evaluation metric that quantifies a model's robustness by measuring the standard deviation of accuracies across question variants. Additionally, we implement a reasoning-based, paraphrase-aware Supervised Fine-Tuning (SFT) strategy designed to align models toward semantic invariance. Our experiments demonstrate that this targeted alignment significantly enhances robustness. Notably, fine-tuned lightweight models achieved consistency levels comparable to much larger pre-trained models. These results highlight the efficacy of our approach in mitigating superficial memorization and fostering more robust, reliable LLMs.

---

### A decoupled alignment kernel for peptide membrane permeability predictions

Authors: Ali Amirahmadi, Gökçe Geylan, Leonardo De Maria, Farzaneh Etminani, Mattias Ohlsson, Alessandro Tibo
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21566v1

Cyclic peptides are promising modalities for targeting intracellular sites; however, cell-membrane permeability remains a key bottleneck, exacerbated by limited public data and the need for well-calibrated uncertainty. Instead of relying on data-eager complex deep learning architecture, we propose a monomer-aware decoupled global alignment kernel (MD-GAK), which couples chemically meaningful residue-residue similarity with sequence alignment while decoupling local matches from gap penalties. MD-GAK is a relatively simple kernel. To further demonstrate the robustness of our framework, we also introduce a variant, PMD-GAK, which incorporates a triangular positional prior. As we will show in the experimental section, PMD-GAK can offer additional advantages over MD-GAK, particularly in reducing calibration errors. Since our focus is on uncertainty estimation, we use Gaussian Processes as the predictive model, as both MD-GAK and PMD-GAK can be directly applied within this framework. We demonstrate the effectiveness of our methods through an extensive set of experiments, comparing our fully reproducible approach against state-of-the-art models, and show that it outperforms them across all metrics.

---

### UAVLight: A Benchmark for Illumination-Robust 3D Reconstruction in Unmanned Aerial Vehicle (UAV) Scenes

Authors: Kang Du, Xue Liao, Junpeng Xia, Chaozheng Guo, Yi Gu, Yirui Guan, Duotun Wang, Sheng Huang, Zeyu Wang
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21565v2

Illumination inconsistency is a fundamental challenge in multi-view 3D reconstruction. Variations in sunlight direction, cloud cover, and shadows break the constant-lighting assumption underlying both classical multi-view stereo (MVS) and structure from motion (SfM) pipelines and recent neural rendering methods, leading to geometry drift, color inconsistency, and shadow imprinting. This issue is especially critical in UAV-based reconstruction, where long flight durations and outdoor environments make lighting changes unavoidable. However, existing datasets either restrict capture to short time windows, thus lacking meaningful illumination diversity, or span months and seasons, where geometric and semantic changes confound the isolated study of lighting robustness. We introduce UAVLight, a controlled-yet-real benchmark for illumination-robust 3D reconstruction. Each scene is captured along repeatable, geo-referenced flight paths at multiple fixed times of day, producing natural lighting variation under consistent geometry, calibration, and viewpoints. With standardized evaluation protocols across lighting conditions, UAVLight provides a reliable foundation for developing and benchmarking reconstruction methods that are consistent, faithful, and relightable in real outdoor environments.

---

### UAVLight: A Benchmark for Illumination-Robust 3D Reconstruction in Unmanned Aerial Vehicle (UAV) Scenes

Authors: Kang Du, Xue Liao, Junpeng Xia, Chaozheng Guo, Yi Gu, Yirui Guan, Duotun Wang, ShengHuang, Zeyu Wang
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21565v1

Illumination inconsistency is a fundamental challenge in multi-view 3D reconstruction. Variations in sunlight direction, cloud cover, and shadows break the constant-lighting assumption underlying both classical multi-view stereo (MVS) and structure from motion (SfM) pipelines and recent neural rendering methods, leading to geometry drift, color inconsistency, and shadow imprinting. This issue is especially critical in UAV-based reconstruction, where long flight durations and outdoor environments make lighting changes unavoidable. However, existing datasets either restrict capture to short time windows, thus lacking meaningful illumination diversity, or span months and seasons, where geometric and semantic changes confound the isolated study of lighting robustness. We introduce UAVLight, a controlled-yet-real benchmark for illumination-robust 3D reconstruction. Each scene is captured along repeatable, geo-referenced flight paths at multiple fixed times of day, producing natural lighting variation under consistent geometry, calibration, and viewpoints. With standardized evaluation protocols across lighting conditions, UAVLight provides a reliable foundation for developing and benchmarking reconstruction methods that are consistent, faithful, and relightable in real outdoor environments.

---

### Some aspects of robustness in modern Markov Chain Monte Carlo

Authors: Sam Power, Giorgos Vasdekis
Published: 2025-11-26
Categories: stat.CO, math.PR, stat.ML
arXiv: https://arxiv.org/abs/2511.21563v1

Markov Chain Monte Carlo (MCMC) is a flexible approach to approximate sampling from intractable probability distributions, with a rich theoretical foundation and comprising a wealth of exemplar algorithms. While the qualitative correctness of MCMC algorithms is often easy to ensure, their practical efficiency is contingent on the `target' distribution being reasonably well-behaved. In this work, we concern ourself with the scenario in which this good behaviour is called into question, reviewing an emerging line of work on `robust' MCMC algorithms which can perform acceptably even in the face of certain pathologies. We focus on two particular pathologies which, while simple, can already have dramatic effects on standard `local' algorithms. The first is roughness, whereby the target distribution varies so rapidly that the numerical stability of the algorithm is tenuous. The second is flatness, whereby the landscape of the target distribution is instead so barren and uninformative that one becomes lost in uninteresting parts of the state space. In each case, we formulate the pathology in concrete terms, review a range of proposed algorithmic remedies to the pathology, and outline promising directions for future research.

---

### Machine Learning Approaches to Clinical Risk Prediction: Multi-Scale Temporal Alignment in Electronic Health Records

Authors: Wei-Chen Chang, Lu Dai, Ting Xu
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21561v1

This study proposes a risk prediction method based on a Multi-Scale Temporal Alignment Network (MSTAN) to address the challenges of temporal irregularity, sampling interval differences, and multi-scale dynamic dependencies in Electronic Health Records (EHR). The method focuses on temporal feature modeling by introducing a learnable temporal alignment mechanism and a multi-scale convolutional feature extraction structure to jointly model long-term trends and short-term fluctuations in EHR sequences. At the input level, the model maps multi-source clinical features into a unified high-dimensional semantic space and employs temporal embedding and alignment modules to dynamically weight irregularly sampled data, reducing the impact of temporal distribution differences on model performance. The multi-scale feature extraction module then captures key patterns across different temporal granularities through multi-layer convolution and hierarchical fusion, achieving a fine-grained representation of patient states. Finally, an attention-based aggregation mechanism integrates global temporal dependencies to generate individual-level risk representations for disease risk prediction and health status assessment. Experiments conducted on publicly available EHR datasets show that the proposed model outperforms mainstream baselines in accuracy, recall, precision, and F1-Score, demonstrating the effectiveness and robustness of multi-scale temporal alignment in complex medical time-series analysis. This study provides a new solution for intelligent representation of high-dimensional asynchronous medical sequences and offers important technical support for EHR-driven clinical risk prediction.

---

### Computing Strategic Responses to Non-Linear Classifiers

Authors: Jack Geary, Boyan Gao, Henry Gouk
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21560v1

We consider the problem of strategic classification, where the act of deploying a classifier leads to strategic behaviour that induces a distribution shift on subsequent observations. Current approaches to learning classifiers in strategic settings are focused primarily on the linear setting, but in many cases non-linear classifiers are more suitable. A central limitation to progress for non-linear classifiers arises from the inability to compute best responses in these settings. We present a novel method for computing the best response by optimising the Lagrangian dual of the Agents' objective. We demonstrate that our method reproduces best responses in linear settings, identifying key weaknesses in existing approaches. We present further results demonstrating our method can be straight-forwardly applied to non-linear classifier settings, where it is useful for both evaluation and training.

---

### VacuumVLA: Boosting VLA Capabilities via a Unified Suction and Gripping Tool for Complex Robotic Manipulation

Authors: Hui Zhou, Siyuan Huang, Minxing Li, Hao Zhang, Lue Fan, Shaoshuai Shi
Published: 2025-11-26
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2511.21557v1

Vision Language Action models have significantly advanced general purpose robotic manipulation by harnessing large scale pretrained vision and language representations. Among existing approaches, a majority of current VLA systems employ parallel two finger grippers as their default end effectors. However, such grippers face inherent limitations in handling certain real world tasks such as wiping glass surfaces or opening drawers without handles due to insufficient contact area or lack of adhesion. To overcome these challenges, we present a low cost, integrated hardware design that combines a mechanical two finger gripper with a vacuum suction unit, enabling dual mode manipulation within a single end effector. Our system supports flexible switching or synergistic use of both modalities, expanding the range of feasible tasks. We validate the efficiency and practicality of our design within two state of the art VLA frameworks: DexVLA and Pi0. Experimental results demonstrate that with the proposed hybrid end effector, robots can successfully perform multiple complex tasks that are infeasible for conventional two finger grippers alone. All hardware designs and controlling systems will be released.

---

### MMA: A Momentum Mamba Architecture for Human Activity Recognition with Inertial Sensors

Authors: Thai-Khanh Nguyen, Uyen Vo, Tan M. Nguyen, Thieu N. Vo, Trung-Hieu Le, Cuong Pham
Published: 2025-11-26
Categories: cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2511.21550v1

Human activity recognition (HAR) from inertial sensors is essential for ubiquitous computing, mobile health, and ambient intelligence. Conventional deep models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and transformers have advanced HAR but remain limited by vanishing or exloding gradients, high computational cost, and difficulty in capturing long-range dependencies. Structured state-space models (SSMs) like Mamba address these challenges with linear complexity and effective temporal modeling, yet they are restricted to first-order dynamics without stable longterm memory mechanisms. We introduce Momentum Mamba, a momentum-augmented SSM that incorporates second-order dynamics to improve stability of information flow across time steps, robustness, and long-sequence modeling. Two extensions further expand its capacity: Complex Momentum Mamba for frequency-selective memory scaling. Experiments on multiple HAR benchmarks demonstrate consistent gains over vanilla Mamba and Transformer baselines in accuracy, robustness, and convergence speed. With only moderate increases in training cost, momentum-augmented SSMs offer a favorable accuracy-efficiency balance, establishing them as a scalable paradigm for HAR and a promising principal framework for broader sequence modeling applications.

---

### E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion

Authors: Zhihao Zhan, Jiaying Zhou, Likui Zhang, Qinhan Lv, Hao Liu, Jusheng Zhang, Weizheng Li, Ziliang Chen, Tianshui Chen, Ruifeng Zhai, Keze Wang, Liang Lin et al.
Published: 2025-11-26
Categories: cs.RO, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.21542v2

Vision-Language-Action (VLA) models offer a unified framework for robotic manipulation by integrating visual perception, language understanding, and control generation. However, existing VLA systems still struggle to generalize across diverse tasks, scenes, and camera viewpoints, and often produce coarse or unstable actions. We argue that these limitations are closely tied to the structural properties of actions in VLA settings, including the inherent multi-peaked nature of action distributions, the token-based symbolic reasoning of pretrained VLM/VLA backbones, and the effective finite resolution imposed by real-world robotic control. Motivated by these properties, we introduce E0, a tweedie discrete diffusion framework that formulates action generation as iterative denoising over quantized action tokens. By operating in a discrete action space with a principled diffusion process, E0 naturally aligns with token-based reasoning, supports fine-grained yet executable action control, and avoids the distributional mismatch of masking-based discrete diffusion. We further introduce a spherical viewpoint perturbation augmentation to enhance robustness to camera shifts without additional data. Experiments on LIBERO, VLABench, ManiSkill, and a real-world Franka arm demonstrate that E0 achieves state-of-the-art performance across 14 diverse environments, outperforming strong baselines by 10.7% on average.

---

### Video Generation Models Are Good Latent Reward Models

Authors: Xiaoyue Mi, Wenqing Yu, Jiesong Lian, Shibo Jie, Ruizhe Zhong, Zijun Liu, Guozhen Zhang, Zixiang Zhou, Zhiyong Xu, Yuan Zhou, Qinglin Lu, Fan Tang
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21541v3

Reward feedback learning (ReFL) has proven effective for aligning image generation with human preferences. However, its extension to video generation faces significant challenges. Existing video reward models rely on vision-language models designed for pixel-space inputs, confining ReFL optimization to near-complete denoising steps after computationally expensive VAE decoding. This pixel-space approach incurs substantial memory overhead and increased training time, and its late-stage optimization lacks early-stage supervision, refining only visual quality rather than fundamental motion dynamics and structural coherence. In this work, we show that pre-trained video generation models are naturally suited for reward modeling in the noisy latent space, as they are explicitly designed to process noisy latent representations at arbitrary timesteps and inherently preserve temporal information through their sequential modeling capabilities. Accordingly, we propose Process Reward Feedback Learning~(PRFL), a framework that conducts preference optimization entirely in latent space, enabling efficient gradient backpropagation throughout the full denoising chain without VAE decoding. Extensive experiments demonstrate that PRFL significantly improves alignment with human preferences, while achieving substantial reductions in memory consumption and training time compared to RGB ReFL.

---

### Video Generation Models Are Good Latent Reward Models

Authors: Xiaoyue Mi, Wenqing Yu, Jiesong Lian, Shibo Jie, Ruizhe Zhong, Zijun Liu, Guozhen Zhang, Zixiang Zhou, Zhiyong Xu, Yuan Zhou, Qinglin Lu, Fan Tang
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21541v1

Reward feedback learning (ReFL) has proven effective for aligning image generation with human preferences. However, its extension to video generation faces significant challenges. Existing video reward models rely on vision-language models designed for pixel-space inputs, confining ReFL optimization to near-complete denoising steps after computationally expensive VAE decoding. This pixel-space approach incurs substantial memory overhead and increased training time, and its late-stage optimization lacks early-stage supervision, refining only visual quality rather than fundamental motion dynamics and structural coherence. In this work, we show that pre-trained video generation models are naturally suited for reward modeling in the noisy latent space, as they are explicitly designed to process noisy latent representations at arbitrary timesteps and inherently preserve temporal information through their sequential modeling capabilities. Accordingly, we propose Process Reward Feedback Learning~(PRFL), a framework that conducts preference optimization entirely in latent space, enabling efficient gradient backpropagation throughout the full denoising chain without VAE decoding. Extensive experiments demonstrate that PRFL significantly improves alignment with human preferences, while achieving substantial reductions in memory consumption and training time compared to RGB ReFL.

---

### Context-Specific Causal Graph Discovery with Unobserved Contexts: Non-Stationarity, Regimes and Spatio-Temporal Patterns

Authors: Martin Rabel, Jakob Runge
Published: 2025-11-26
Categories: cs.LG, math.ST
arXiv: https://arxiv.org/abs/2511.21537v2

Real-world problems, for example in climate applications, often require causal reasoning on spatially gridded time series data or data with comparable structure. While the underlying system is often believed to behave similarly at different Points in space and time, those variations that do exist are relevant twofold: They often encode important information in and of themselves. And they may negatively affect the stability and validity of results if not accounted for. We study the information encoded in changes of the causal graph, with stability in mind. Two core challenges arise, related to the complexity of encoding system-states and to statistical convergence properties in the presence of imperfectly recoverable non-stationary structure. We provide a framework realizing principles conceptually suitable to overcome these challenges - an interpretation supported by numerical experiments. Primarily, we modify constraint-based causal discovery approaches on the level of independence testing. This leads to a framework which is additionally highly modular, easily extensible and widely applicable. For example, it allows to leverage existing constraint-based causal discovery methods (demonstrated on PC, PC-stable, FCI, PCMCI, PCMCI+ and LPCMCI), and to systematically divide the problem into simpler subproblems that are easier to analyze and understand and relate more clearly to well-studied problems like change-point-detection, clustering, independence-testing and more. Code is available at https://github.com/martin-rabel/Causal_GLDF.

---

### Context-Specific Causal Graph Discovery with Unobserved Contexts: Non-Stationarity, Regimes and Spatio-Temporal Patterns

Authors: Martin Rabel, Jakob Runge
Published: 2025-11-26
Categories: cs.LG, math.ST
arXiv: https://arxiv.org/abs/2511.21537v1

Real-world data, for example in climate applications, often consists of spatially gridded time series data or data with comparable structure. While the underlying system is often believed to behave similar at different points in space and time, those variations that do exist are twofold relevant: They often encode important information in and of themselves. And they may negatively affect the stability / convergence and reliability\Slash{}validity of results of algorithms assuming stationarity or space-translation invariance. We study the information encoded in changes of the causal graph, with stability in mind. An analysis of this general task identifies two core challenges. We develop guiding principles to overcome these challenges, and provide a framework realizing these principles by modifying constraint-based causal discovery approaches on the level of independence testing. This leads to an extremely modular, easily extensible and widely applicable framework. It can leverage existing constraint-based causal discovery methods (demonstrated on IID-algorithms PC, PC-stable, FCI and time series algorithms PCMCI, PCMCI+, LPCMCI) with little to no modification. The built-in modularity allows to systematically understand and improve upon an entire array of subproblems. By design, it can be extended by leveraging insights from change-point-detection, clustering, independence-testing and other well-studied related problems. The division into more accessible sub-problems also simplifies the understanding of fundamental limitations, hyperparameters controlling trade-offs and the statistical interpretation of results. An open-source implementation will be available soon.

---

### Bangla Sign Language Translation: Dataset Creation Challenges, Benchmarking and Prospects

Authors: Husne Ara Rubaiyeat, Hasan Mahmud, Md Kamrul Hasan
Published: 2025-11-26
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2511.21533v1

Bangla Sign Language Translation (BdSLT) has been severely constrained so far as the language itself is very low resource. Standard sentence level dataset creation for BdSLT is of immense importance for developing AI based assistive tools for deaf and hard of hearing people of Bangla speaking community. In this paper, we present a dataset, IsharaKhobor , and two subset of it for enabling research. We also present the challenges towards developing the dataset and present some way forward by benchmarking with landmark based raw and RQE embedding. We do some ablation on vocabulary restriction and canonicalization of the same within the dataset, which resulted in two more datasets, IsharaKhobor_small and IsharaKhobor_canonical_small. The dataset is publicly available at: www.kaggle.com/datasets/hasanssl/isharakhobor (1).

---

### Predictive Safety Shield for Dyna-Q Reinforcement Learning

Authors: Jin Pin, Krasowski Hanna, Vanneaux Elena
Published: 2025-11-26
Categories: cs.LG, cs.AI, cs.RO, eess.SY
arXiv: https://arxiv.org/abs/2511.21531v1

Obtaining safety guarantees for reinforcement learning is a major challenge to achieve applicability for real-world tasks. Safety shields extend standard reinforcement learning and achieve hard safety guarantees. However, existing safety shields commonly use random sampling of safe actions or a fixed fallback controller, therefore disregarding future performance implications of different safe actions. In this work, we propose a predictive safety shield for model-based reinforcement learning agents in discrete space. Our safety shield updates the Q-function locally based on safe predictions, which originate from a safe simulation of the environment model. This shielding approach improves performance while maintaining hard safety guarantees. Our experiments on gridworld environments demonstrate that even short prediction horizons can be sufficient to identify the optimal path. We observe that our approach is robust to distribution shifts, e.g., between simulation and reality, without requiring additional training.

---

### The Age-specific Alzheimer 's Disease Prediction with Characteristic Constraints in Nonuniform Time Span

Authors: Xin Hong, Kaifeng Huang
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21530v1

Alzheimer's disease is a debilitating disorder marked by a decline in cognitive function. Timely identification of the disease is essential for the development of personalized treatment strategies that aim to mitigate its progression. The application of generated images for the prediction of Alzheimer's disease poses challenges, particularly in accurately representing the disease's characteristics when input sequences are captured at irregular time intervals. This study presents an innovative methodology for sequential image generation, guided by quantitative metrics, to maintain the essential features indicative of disease progression. Furthermore, an age-scaling factor is integrated into the process to produce age-specific MRI images, facilitating the prediction of advanced stages of the disease. The results obtained from the ablation study suggest that the inclusion of quantitative metrics significantly improves the accuracy of MRI image synthesis. Furthermore, the application of age-scaled pixel loss contributed to the enhanced iterative generation of MRI images. In terms of long-term disease prognosis, the Structural Similarity Index reached a peak value of 0.882, indicating a substantial degree of similarity in the synthesized images.

---

### Phase Transition for Stochastic Block Model with more than $\sqrt{n}$ Communities (II)

Authors: Alexandra Carpentier, Christophe Giraud, Nicolas Verzelen
Published: 2025-11-26
Categories: stat.ML, cs.LG, math.PR, math.ST
arXiv: https://arxiv.org/abs/2511.21526v1

A fundamental theoretical question in network analysis is to determine under which conditions community recovery is possible in polynomial time in the Stochastic Block Model (SBM). When the number $K$ of communities remains smaller than $\sqrt{n}$ --where $n$ denotes the number of nodes--, non-trivial community recovery is possible in polynomial time above, and only above, the Kesten--Stigum (KS) threshold, originally postulated using arguments from statistical physics. When $K \geq \sqrt{n}$, Chin, Mossel, Sohn, and Wein recently proved that, in the \emph{sparse regime}, community recovery in polynomial time is achievable below the KS threshold by counting non-backtracking paths. This finding led them to postulate a new threshold for the many-communities regime $K \geq \sqrt{n}$. Subsequently, Carpentier, Giraud, and Verzelen established the failure of low-degree polynomials below this new threshold across all density regimes, and demonstrated successful recovery above the threshold in certain moderately sparse settings. While these results provide strong evidence that, in the many community setting, the computational barrier lies at the threshold proposed in~Chin et al., the question of achieving recovery above this threshold still remains open in most density regimes. The present work is a follow-up to~Carpentier et al., in which we prove Conjecture~1.4 stated therein by: \\ 1- Constructing a family of motifs satisfying specific structural properties; and\\ 2- Proving that community recovery is possible above the proposed threshold by counting such motifs.\\ Our results complete the picture of the computational barrier for community recovery in the SBM with $K \geq \sqrt{n}$ communities. They also indicate that, in moderately sparse regimes, the optimal algorithms appear to be fundamentally different from spectral methods.

---

### EoS-FM: Can an Ensemble of Specialist Models act as a Generalist Feature Extractor?

Authors: Pierre Adorni, Minh-Tan Pham, Stéphane May, Sébastien Lefèvre
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21523v3

Recent advances in foundation models have shown great promise in domains such as natural language processing and computer vision, and similar efforts are now emerging in the Earth Observation community. These models aim to generalize across tasks with limited supervision, reducing the need for training separate models for each task. However, current strategies, which largely focus on scaling model size and dataset volume, require prohibitive computational and data resources, limiting accessibility to only a few large institutions. Moreover, this paradigm of ever-larger models stands in stark contrast with the principles of sustainable and environmentally responsible AI, as it leads to immense carbon footprints and resource inefficiency. In this work, we present a novel and efficient alternative: an Ensemble-of-Specialists framework for building Remote Sensing Foundation Models (RSFMs). Our method decomposes the training process into lightweight, task-specific ConvNeXtV2 specialists that can be frozen and reused. This modular approach offers strong advantages in efficiency, interpretability, and extensibility. Moreover, it naturally supports federated training, pruning, and continuous specialist integration, making it particularly well-suited for collaborative and resource-constrained settings. Our framework sets a new direction for building scalable and efficient RSFMs. All codes and pretrained models are available on the public repo at https://github.com/pierreadorni/EoS-FM .

---

### EoS-FM: Can an Ensemble of Specialist Models act as a Generalist Feature Extractor?

Authors: Pierre Adorni, Minh-Tan Pham, Stéphane May, Sébastien Lefèvre
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21523v1

Recent advances in foundation models have shown great promise in domains such as natural language processing and computer vision, and similar efforts are now emerging in the Earth Observation community. These models aim to generalize across tasks with limited supervision, reducing the need for training separate models for each task. However, current strategies, which largely focus on scaling model size and dataset volume, require prohibitive computational and data resources, limiting accessibility to only a few large institutions. Moreover, this paradigm of ever-larger models stands in stark contrast with the principles of sustainable and environmentally responsible AI, as it leads to immense carbon footprints and resource inefficiency. In this work, we present a novel and efficient alternative: an Ensemble-of-Specialists framework for building Remote Sensing Foundation Models (RSFMs). Our method decomposes the training process into lightweight, task-specific ConvNeXtV2 specialists that can be frozen and reused. This modular approach offers strong advantages in efficiency, interpretability, and extensibility. Moreover, it naturally supports federated training, pruning, and continuous specialist integration, making it particularly well-suited for collaborative and resource-constrained settings. Our framework sets a new direction for building scalable and efficient RSFMs.

---

### Pessimistic Verification for Open Ended Math Questions

Authors: Yanxing Huang, Zihan Tang, Zejin Lin, Peng Li, Yang Liu
Published: 2025-11-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.21522v2

Automatic verification is a critical component in building math-solving agents and reinforcement learning, yet it often falls short in generalizability, performance, and cost-efficiency. Identifying that the primary bottleneck of verification lies in error detection capability, we propose pessimistic verification, a paradigm of agentic workflows that rejects a solution if any of multiple parallel verifiers identifies a flaw. We further introduce progressive pessimistic verification, which employs fine-grained proof decomposition to significantly enhance verification accuracy and efficiency. Our approach surpasses the performance and token efficiency of extended long chain-of-thought (long CoT) and mainstream verification workflows, crucially, our analysis reveals that existing benchmarks underestimate its effectiveness on stronger models due to inherent annotation errors. To further validate the effectiveness of our method, we applied a verification-based solving workflow on the IMO 2025 and MathArena Apex 2025 datasets, where the workflow with progressive pessimistic verification exhibits remarkable improvements in both efficiency and accuracy on highly challenging contest-level math problems with state-of-the-art models. Code is available at https://github.com/THUNLP-MT/pverify.

---