# Research Papers — 2025-11 · bundle page 69 of 197

> Full-text markdown of papers #3401–3450 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/69
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/68.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/70.md)

### Cognitive Foundations for Reasoning and Their Manifestation in LLMs

Authors: Priyanka Kargupta, Shuyue Stella Li, Haocheng Wang, Jinu Lee, Shan Chen, Orevaoghene Ahia, Dean Light, Thomas L. Griffiths, Max Kleiman-Weiner, Jiawei Han, Asli Celikyilmaz, Yulia Tsvetkov
Published: 2025-11-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.16660v2

Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning. To understand this gap, we synthesize cognitive science research into a taxonomy of 28 cognitive elements spanning reasoning invariants, meta-cognitive controls, representations for organizing reasoning & knowledge, and transformation operations. We introduce a fine-grained evaluation framework and conduct the first large-scale empirical analysis of 192K traces from 18 models across text, vision, and audio, complemented by 54 human think-aloud traces, which we make publicly available. We find that models under-utilize cognitive elements correlated with success, narrowing to rigid sequential processing on ill-structured problems where diverse representations and meta-cognitive monitoring are critical. Human traces show more abstraction and conceptual processing, while models default to surface-level enumeration. Meta-analysis of 1.6K LLM reasoning papers reveals the research community concentrates on easily quantifiable elements (sequential organization: 55%, decomposition: 60%) but neglecting meta-cognitive controls (self-awareness: 16%) that correlate with success. Models possess behavioral repertoires associated with success but fail to deploy them spontaneously. Leveraging these patterns, we develop test-time reasoning guidance that automatically scaffold successful structures, improving performance by up to 66.7% on complex problems. By establishing a shared vocabulary between cognitive science and LLM research, our framework enables systematic diagnosis of reasoning failures and principled development of models that reason through robust cognitive mechanisms rather than spurious shortcuts, while providing tools to test theories of human cognition at scale.

---

### Cognitive Foundations for Reasoning and Their Manifestation in LLMs

Authors: Priyanka Kargupta, Shuyue Stella Li, Haocheng Wang, Jinu Lee, Shan Chen, Orevaoghene Ahia, Dean Light, Thomas L. Griffiths, Max Kleiman-Weiner, Jiawei Han, Asli Celikyilmaz, Yulia Tsvetkov
Published: 2025-11-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.16660v1

Large language models solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning. We synthesize cognitive science research into a taxonomy of 28 cognitive elements spanning computational constraints, meta-cognitive controls, knowledge representations, and transformation operations, then analyze their behavioral manifestations in reasoning traces. We propose a fine-grained cognitive evaluation framework and conduct the first large-scale analysis of 170K traces from 17 models across text, vision, and audio modalities, alongside 54 human think-aloud traces, which we make publicly available. Our analysis reveals systematic structural differences: humans employ hierarchical nesting and meta-cognitive monitoring while models rely on shallow forward chaining, with divergence most pronounced on ill-structured problems. Meta-analysis of 1,598 LLM reasoning papers reveals the research community concentrates on easily quantifiable behaviors (sequential organization: 55%, decomposition: 60%) while neglecting meta-cognitive controls (self-awareness: 16%, evaluation: 8%) that correlate with success. Models possess behavioral repertoires associated with success but fail to deploy them spontaneously. Leveraging these patterns, we develop test-time reasoning guidance that automatically scaffold successful structures, improving performance by up to 60% on complex problems. By bridging cognitive science and LLM research, we establish a foundation for developing models that reason through principled cognitive mechanisms rather than brittle spurious reasoning shortcuts or memorization, opening new directions for both improving model capabilities and testing theories of human cognition at scale.

---

### PartUV: Part-Based UV Unwrapping of 3D Meshes

Authors: Zhaoning Wang, Xinyue Wei, Ruoxi Shi, Xiaoshuai Zhang, Hao Su, Minghua Liu
Published: 2025-11-20
Categories: cs.CV, cs.CG, cs.GR
arXiv: https://arxiv.org/abs/2511.16659v2

UV unwrapping flattens 3D surfaces to 2D with minimal distortion, often requiring the complex surface to be decomposed into multiple charts. Although extensively studied, existing UV unwrapping methods frequently struggle with AI-generated meshes, which are typically noisy, bumpy, and poorly conditioned. These methods often produce highly fragmented charts and suboptimal boundaries, introducing artifacts and hindering downstream tasks. We introduce PartUV, a part-based UV unwrapping pipeline that generates significantly fewer, part-aligned charts while maintaining low distortion. Built on top of a recent learning-based part decomposition method PartField, PartUV combines high-level semantic part decomposition with novel geometric heuristics in a top-down recursive framework. It ensures each chart's distortion remains below a user-specified threshold while minimizing the total number of charts. The pipeline integrates and extends parameterization and packing algorithms, incorporates dedicated handling of non-manifold and degenerate meshes, and is extensively parallelized for efficiency. Evaluated across four diverse datasets, including man-made, CAD, AI-generated, and Common Shapes, PartUV outperforms existing tools and recent neural methods in chart count and seam length, achieves comparable distortion, exhibits high success rates on challenging meshes, and enables new applications like part-specific multi-tiles packing. Our project page is at https://www.zhaoningwang.com/PartUV.

---

### PartUV: Part-Based UV Unwrapping of 3D Meshes

Authors: Zhaoning Wang, Xinyue Wei, Ruoxi Shi, Xiaoshuai Zhang, Hao Su, Minghua Liu
Published: 2025-11-20
Categories: cs.CV, cs.CG, cs.GR
arXiv: https://arxiv.org/abs/2511.16659v1

UV unwrapping flattens 3D surfaces to 2D with minimal distortion, often requiring the complex surface to be decomposed into multiple charts. Although extensively studied, existing UV unwrapping methods frequently struggle with AI-generated meshes, which are typically noisy, bumpy, and poorly conditioned. These methods often produce highly fragmented charts and suboptimal boundaries, introducing artifacts and hindering downstream tasks. We introduce PartUV, a part-based UV unwrapping pipeline that generates significantly fewer, part-aligned charts while maintaining low distortion. Built on top of a recent learning-based part decomposition method PartField, PartUV combines high-level semantic part decomposition with novel geometric heuristics in a top-down recursive framework. It ensures each chart's distortion remains below a user-specified threshold while minimizing the total number of charts. The pipeline integrates and extends parameterization and packing algorithms, incorporates dedicated handling of non-manifold and degenerate meshes, and is extensively parallelized for efficiency. Evaluated across four diverse datasets, including man-made, CAD, AI-generated, and Common Shapes, PartUV outperforms existing tools and recent neural methods in chart count and seam length, achieves comparable distortion, exhibits high success rates on challenging meshes, and enables new applications like part-specific multi-tiles packing. Our project page is at https://www.zhaoningwang.com/PartUV.

---

### Enhancing Forex Forecasting Accuracy: The Impact of Hybrid Variable Sets in Cognitive Algorithmic Trading Systems

Authors: Juan C. King, Jose M. Amigo
Published: 2025-11-20
Categories: cs.AI, math.NA
arXiv: https://arxiv.org/abs/2511.16657v1

This paper presents the implementation of an advanced artificial intelligence-based algorithmic trading system specifically designed for the EUR-USD pair within the high-frequency environment of the Forex market. The methodological approach centers on integrating a holistic set of input features: key fundamental macroeconomic variables (for example, Gross Domestic Product and Unemployment Rate) collected from both the Euro Zone and the United States, alongside a comprehensive suite of technical variables (including indicators, oscillators, Fibonacci levels, and price divergences). The performance of the resulting algorithm is evaluated using standard machine learning metrics to quantify predictive accuracy and backtesting simulations across historical data to assess trading profitability and risk. The study concludes with a comparative analysis to determine which class of input features, fundamental or technical, provides greater and more reliable predictive capacity for generating profitable trading signals.

---

### Solving Spatial Supersensing Without Spatial Supersensing

Authors: Vishaal Udandarao, Shyamgopal Karthik, Surabhi S. Nath, Andreas Hochlehnert, Matthias Bethge, Ameya Prabhu
Published: 2025-11-20
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.16655v1

Cambrian-S aims to take the first steps towards improving video world models with spatial supersensing by introducing (i) two benchmarks, VSI-Super-Recall (VSR) and VSI-Super-Counting (VSC), and (ii) bespoke predictive sensing inference strategies tailored to each benchmark. In this work, we conduct a critical analysis of Cambrian-S across both these fronts. First, we introduce a simple baseline, NoSense, which discards almost all temporal structure and uses only a bag-of-words SigLIP model, yet near-perfectly solves VSR, achieving 95% accuracy even on 4-hour videos. This shows benchmarks like VSR can be nearly solved without spatial cognition, world modeling or spatial supersensing. Second, we hypothesize that the tailored inference methods proposed by Cambrian-S likely exploit shortcut heuristics in the benchmark. We illustrate this with a simple sanity check on the VSC benchmark, called VSC-Repeat: We concatenate each video with itself 1-5 times, which does not change the number of unique objects. However, this simple perturbation entirely collapses the mean relative accuracy of Cambrian-S from 42% to 0%. A system that performs spatial supersensing and integrates information across experiences should recognize views of the same scene and keep object-count predictions unchanged; instead, Cambrian-S inference algorithm relies largely on a shortcut in the VSC benchmark that rooms are never revisited. Taken together, our findings suggest that (i) current VSI-Super benchmarks do not yet reliably measure spatial supersensing, and (ii) predictive-sensing inference recipes used by Cambrian-S improve performance by inadvertently exploiting shortcuts rather than from robust spatial supersensing. We include the response from the Cambrian-S authors (in Appendix A) to provide a balanced perspective alongside our claims. We release our code at: https://github.com/bethgelab/supersanity

---

### Comparison of Text-Based and Image-Based Retrieval in Multimodal Retrieval Augmented Generation Large Language Model Systems

Authors: Elias Lumer, Alex Cardenas, Matt Melich, Myles Mason, Sara Dieter, Vamse Kumar Subbiah, Pradeep Honaganahalli Basavaraju, Roberto Hernandez
Published: 2025-11-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.16654v2

Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models (LLMs) to access multimodal knowledge bases containing both text and visual information such as charts, diagrams, and tables in financial documents. However, existing multimodal RAG systems rely on LLM-based summarization to convert images into text during preprocessing, storing only text representations in vector databases, which causes loss of contextual information and visual details critical for downstream retrieval and question answering. To address this limitation, we present a comprehensive comparative analysis of two retrieval approaches for multimodal RAG systems, including text-based chunk retrieval (where images are summarized into text before embedding) and direct multimodal embedding retrieval (where images are stored natively in the vector space). We evaluate all three approaches across 6 LLM models and a two multi-modal embedding models on a newly created financial earnings call benchmark comprising 40 question-answer pairs, each paired with 2 documents (1 image and 1 text chunk). Experimental results demonstrate that direct multimodal embedding retrieval significantly outperforms LLM-summary-based approaches, achieving absolute improvements of 13% in mean average precision (mAP@5) and 11% in normalized discounted cumulative gain. These gains correspond to relative improvements of 32% in mAP@5 and 20% in nDCG@5, providing stronger evidence of their practical impact. We additionally find that direct multimodal retrieval produces more accurate and factually consistent answers as measured by LLM-as-a-judge pairwise comparisons. We demonstrate that LLM summarization introduces information loss during preprocessing, whereas direct multimodal embeddings preserve visual context for retrieval and inference.

---

### Comparison of Text-Based and Image-Based Retrieval in Multimodal Retrieval Augmented Generation Large Language Model Systems

Authors: Elias Lumer, Alex Cardenas, Matt Melich, Myles Mason, Sara Dieter, Vamse Kumar Subbiah, Pradeep Honaganahalli Basavaraju, Roberto Hernandez
Published: 2025-11-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.16654v1

Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models (LLMs) to access multimodal knowledge bases containing both text and visual information such as charts, diagrams, and tables in financial documents. However, existing multimodal RAG systems rely on LLM-based summarization to convert images into text during preprocessing, storing only text representations in vector databases, which causes loss of contextual information and visual details critical for downstream retrieval and question answering. To address this limitation, we present a comprehensive comparative analysis of two retrieval approaches for multimodal RAG systems, including text-based chunk retrieval (where images are summarized into text before embedding) and direct multimodal embedding retrieval (where images are stored natively in the vector space). We evaluate all three approaches across 6 LLM models and a two multi-modal embedding models on a newly created financial earnings call benchmark comprising 40 question-answer pairs, each paired with 2 documents (1 image and 1 text chunk). Experimental results demonstrate that direct multimodal embedding retrieval significantly outperforms LLM-summary-based approaches, achieving absolute improvements of 13% in mean average precision (mAP@5) and 11% in normalized discounted cumulative gain. These gains correspond to relative improvements of 32% in mAP@5 and 20% in nDCG@5, providing stronger evidence of their practical impact. We additionally find that direct multimodal retrieval produces more accurate and factually consistent answers as measured by LLM-as-a-judge pairwise comparisons. We demonstrate that LLM summarization introduces information loss during preprocessing, whereas direct multimodal embeddings preserve visual context for retrieval and inference.

---

### Teacher-Guided One-Shot Pruning via Context-Aware Knowledge Distillation

Authors: Md. Samiul Alim, Sharjil Khan, Amrijit Biswas, Fuad Rahman, Shafin Rahman, Nabeel Mohammed
Published: 2025-11-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.16653v1

Unstructured pruning remains a powerful strategy for compressing deep neural networks, yet it often demands iterative train-prune-retrain cycles, resulting in significant computational overhead. To address this challenge, we introduce a novel teacher-guided pruning framework that tightly integrates Knowledge Distillation (KD) with importance score estimation. Unlike prior approaches that apply KD as a post-pruning recovery step, our method leverages gradient signals informed by the teacher during importance score calculation to identify and retain parameters most critical for both task performance and knowledge transfer. Our method facilitates a one-shot global pruning strategy that efficiently eliminates redundant weights while preserving essential representations. After pruning, we employ sparsity-aware retraining with and without KD to recover accuracy without reactivating pruned connections. Comprehensive experiments across multiple image classification benchmarks, including CIFAR-10, CIFAR-100, and TinyImageNet, demonstrate that our method consistently achieves high sparsity levels with minimal performance degradation. Notably, our approach outperforms state-of-the-art baselines such as EPG and EPSD at high sparsity levels, while offering a more computationally efficient alternative to iterative pruning schemes like COLT. The proposed framework offers a computation-efficient, performance-preserving solution well suited for deployment in resource-constrained environments.

---

### Evolution Strategies at the Hyperscale

Authors: Bidipta Sarkar, Mattie Fellows, Juan Agustin Duque, Alistair Letcher, Antonio León Villares, Anya Sims, Clarisse Wibault, Dmitry Samsonov, Dylan Cope, Jarek Liesen, Kang Li, Lukas Seier et al.
Published: 2025-11-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.16652v2

Evolution Strategies (ES) is a class of powerful black-box optimisation methods that are highly parallelisable and can handle non-differentiable and noisy objectives. However, naïve ES becomes prohibitively expensive at scale on GPUs due to the low arithmetic intensity of batched matrix multiplications with unstructured random perturbations. We introduce Evolution Guided GeneRal Optimisation via Low-rank Learning (EGGROLL), which improves arithmetic intensity by structuring individual perturbations as rank-$r$ matrices, resulting in a hundredfold increase in training speed for billion-parameter models at large population sizes, achieving up to 91% of the throughput of pure batch inference. We provide a rigorous theoretical analysis of Gaussian ES for high-dimensional parameter objectives, investigating conditions needed for ES updates to converge in high dimensions. Our results reveal a linearising effect, and proving consistency between EGGROLL and ES as parameter dimension increases. Our experiments show that EGGROLL: (1) enables the stable pretraining of nonlinear recurrent language models that operate purely in integer datatypes, (2) is competitive with GRPO for post-training LLMs on reasoning tasks, and (3) does not compromise performance compared to ES in tabula rasa RL settings, despite being faster.

---

### Evolution Strategies at the Hyperscale

Authors: Bidipta Sarkar, Mattie Fellows, Juan Agustin Duque, Alistair Letcher, Antonio León Villares, Anya Sims, Dylan Cope, Jarek Liesen, Lukas Seier, Theo Wolf, Uljad Berdica, Alexander David Goldie et al.
Published: 2025-11-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.16652v1

We introduce Evolution Guided General Optimization via Low-rank Learning (EGGROLL), an evolution strategies (ES) algorithm designed to scale backprop-free optimization to large population sizes for modern large neural network architectures with billions of parameters. ES is a set of powerful blackbox optimisation methods that can handle non-differentiable or noisy objectives with excellent scaling potential through parallelisation. Na{ï}ve ES becomes prohibitively expensive at scale due to the computational and memory costs associated with generating matrix perturbations $E\in\mathbb{R}^{m\times n}$ and the batched matrix multiplications needed to compute per-member forward passes. EGGROLL overcomes these bottlenecks by generating random matrices $A\in \mathbb{R}^{m\times r},\ B\in \mathbb{R}^{n\times r}$ with $r\ll \min(m,n)$ to form a low-rank matrix perturbation $A B^\top$ that are used in place of the full-rank perturbation $E$. As the overall update is an average across a population of $N$ workers, this still results in a high-rank update but with significant memory and computation savings, reducing the auxiliary storage from $mn$ to $r(m+n)$ per layer and the cost of a forward pass from $\mathcal{O}(mn)$ to $\mathcal{O}(r(m+n))$ when compared to full-rank ES. A theoretical analysis reveals our low-rank update converges to the full-rank update at a fast $\mathcal{O}\left(\frac{1}{r}\right)$ rate. Our experiments show that (1) EGGROLL does not compromise the performance of ES in tabula-rasa RL settings, despite being faster, (2) it is competitive with GRPO as a technique for improving LLM reasoning, and (3) EGGROLL enables stable pre-training of nonlinear recurrent language models that operate purely in integer datatypes.

---

### Late-decoupled 3D Hierarchical Semantic Segmentation with Semantic Prototype Discrimination based Bi-branch Supervision

Authors: Shuyu Cao, Chongshou Li, Jie Xu, Tianrui Li, Na Zhao
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16650v1

3D hierarchical semantic segmentation (3DHS) is crucial for embodied intelligence applications that demand a multi-grained and multi-hierarchy understanding of 3D scenes. Despite the progress, previous 3DHS methods have overlooked following two challenges: I) multi-label learning with a parameter-sharing model can lead to multi-hierarchy conflicts in cross-hierarchy optimization, and II) the class imbalance issue is inevitable across multiple hierarchies of 3D scenes, which makes the model performance become dominated by major classes. To address these issues, we propose a novel framework with a primary 3DHS branch and an auxiliary discrimination branch. Specifically, to alleviate the multi-hierarchy conflicts, we propose a late-decoupled 3DHS framework which employs multiple decoders with the coarse-to-fine hierarchical guidance and consistency. The late-decoupled architecture can mitigate the underfitting and overfitting conflicts among multiple hierarchies and can also constrain the class imbalance problem in each individual hierarchy. Moreover, we introduce a 3DHS-oriented semantic prototype based bi-branch supervision mechanism, which additionally learns class-wise discriminative point cloud features and performs mutual supervision between the auxiliary and 3DHS branches, to enhance the class-imbalance segmentation. Extensive experiments on multiple datasets and backbones demonstrate that our approach achieves state-of-the-art 3DHS performance, and its core components can also be used as a plug-and-play enhancement to improve previous methods.

---

### TRIM: Scalable 3D Gaussian Diffusion Inference with Temporal and Spatial Trimming

Authors: Zeyuan Yin, Xiaoming Liu
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16642v1

Recent advances in 3D Gaussian diffusion models suffer from time-intensive denoising and post-denoising processing due to the massive number of Gaussian primitives, resulting in slow generation and limited scalability along sampling trajectories. To improve the efficiency of 3D diffusion models, we propose $\textbf{TRIM}$ ($\textbf{T}$rajectory $\textbf{R}$eduction and $\textbf{I}$nstance $\textbf{M}$ask denoising), a post-training approach that incorporates both temporal and spatial trimming strategies, to accelerate inference without compromising output quality while supporting the inference-time scaling for Gaussian diffusion models. Instead of scaling denoising trajectories in a costly end-to-end manner, we develop a lightweight selector model to evaluate latent Gaussian primitives derived from multiple sampled noises, enabling early trajectory reduction by selecting candidates with high-quality potential. Furthermore, we introduce instance mask denoising to prune learnable Gaussian primitives by filtering out redundant background regions, reducing inference computation at each denoising step. Extensive experiments and analysis demonstrate that TRIM significantly improves both the efficiency and quality of 3D generation. Source code is available at $\href{https://github.com/zeyuanyin/TRIM}{link}$.

---

### Codec2Vec: Self-Supervised Speech Representation Learning Using Neural Speech Codecs

Authors: Wei-Cheng Tseng, David Harwath
Published: 2025-11-20
Categories: eess.AS, cs.CL
arXiv: https://arxiv.org/abs/2511.16639v1

Recent advancements in neural audio codecs have not only enabled superior audio compression but also enhanced speech synthesis techniques. Researchers are now exploring their potential as universal acoustic feature extractors for a broader range of speech processing tasks. Building on this trend, we introduce Codec2Vec, the first speech representation learning framework that relies exclusively on discrete audio codec units. This approach offers several advantages, including improved data storage and transmission efficiency, faster training, and enhanced data privacy. We explore masked prediction with various training target derivation strategies to thoroughly understand the effectiveness of this framework. Evaluated on the SUPERB benchmark, Codec2Vec achieves competitive performance compared to continuous-input models while reducing storage requirements by up to 16.5x and training time by 2.3x, showcasing its scalability and efficiency.

---

### Faster Certified Symmetry Breaking Using Orders With Auxiliary Variables

Authors: Markus Anders, Bart Bogaerts, Benjamin Bogø, Arthur Gontier, Wietze Koops, Ciaran McCreesh, Magnus O. Myreen, Jakob Nordström, Andy Oertel, Adrian Rebola-Pardo, Yong Kiam Tan
Published: 2025-11-20
Categories: cs.LO, cs.AI
arXiv: https://arxiv.org/abs/2511.16637v1

Symmetry breaking is a crucial technique in modern combinatorial solving, but it is difficult to be sure it is implemented correctly. The most successful approach to deal with bugs is to make solvers certifying, so that they output not just a solution, but also a mathematical proof of correctness in a standard format, which can then be checked by a formally verified checker. This requires justifying symmetry reasoning within the proof, but developing efficient methods for this has remained a long-standing open challenge. A fully general approach was recently proposed by Bogaerts et al. (2023), but it relies on encoding lexicographic orders with big integers, which quickly becomes infeasible for large symmetries. In this work, we develop a method for instead encoding orders with auxiliary variables. We show that this leads to orders-of-magnitude speed-ups in both theory and practice by running experiments on proof logging and checking for SAT symmetry breaking using the state-of-the-art satsuma symmetry breaker and the VeriPB proof checking toolchain.

---

### SurvAgent: Hierarchical CoT-Enhanced Case Banking and Dichotomy-Based Multi-Agent System for Multimodal Survival Prediction

Authors: Guolin Huang, Wenting Chen, Jiaqi Yang, Xinheng Lyu, Xiaoling Luo, Sen Yang, Xiaohan Xing, Linlin Shen
Published: 2025-11-20
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2511.16635v1

Survival analysis is critical for cancer prognosis and treatment planning, yet existing methods lack the transparency essential for clinical adoption. While recent pathology agents have demonstrated explainability in diagnostic tasks, they face three limitations for survival prediction: inability to integrate multimodal data, ineffective region-of-interest exploration, and failure to leverage experiential learning from historical cases. We introduce SurvAgent, the first hierarchical chain-of-thought (CoT)-enhanced multi-agent system for multimodal survival prediction. SurvAgent consists of two stages: (1) WSI-Gene CoT-Enhanced Case Bank Construction employs hierarchical analysis through Low-Magnification Screening, Cross-Modal Similarity-Aware Patch Mining, and Confidence-Aware Patch Mining for pathology images, while Gene-Stratified analysis processes six functional gene categories. Both generate structured reports with CoT reasoning, storing complete analytical processes for experiential learning. (2) Dichotomy-Based Multi-Expert Agent Inference retrieves similar cases via RAG and integrates multimodal reports with expert predictions through progressive interval refinement. Extensive experiments on five TCGA cohorts demonstrate SurvAgent's superority over conventional methods, proprietary MLLMs, and medical agents, establishing a new paradigm for explainable AI-driven survival prediction in precision oncology.

---

### Stabilizing Policy Gradient Methods via Reward Profiling

Authors: Shihab Ahmed, El Houcine Bergou, Aritra Dutta, Yue Wang
Published: 2025-11-20
Categories: cs.LG, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2511.16629v2

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from unreliable reward improvements and slow convergence, due to high variance in gradient estimations. In this paper, we propose a universal reward profiling framework that can be seamlessly integrated with any policy gradient algorithm, where we selectively update the policy based on high-confidence performance estimations. We theoretically justify that our technique will not slow down the convergence of the baseline policy gradient methods, but with high probability, will result in stable and monotonic improvements of their performance. Empirically, on eight continuous-control benchmarks (Box2D and MuJoCo/PyBullet), our profiling yields up to 1.5x faster convergence to near-optimal returns, up to 1.75x reduction in return variance on some setups. Our profiling approach offers a general, theoretically grounded path to more reliable and efficient policy learning in complex environments.

---

### Stabilizing Policy Gradient Methods via Reward Profiling

Authors: Shihab Ahmed, El Houcine Bergou, Aritra Dutta, Yue Wang
Published: 2025-11-20
Categories: cs.LG, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2511.16629v1

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from unreliable reward improvements and slow convergence, due to high variance in gradient estimations. In this paper, we propose a universal reward profiling framework that can be seamlessly integrated with any policy gradient algorithm, where we selectively update the policy based on high-confidence performance estimations. We theoretically justify that our technique will not slow down the convergence of the baseline policy gradient methods, but with high probability, will result in stable and monotonic improvements of their performance. Empirically, on eight continuous-control benchmarks (Box2D and MuJoCo/PyBullet), our profiling yields up to 1.5x faster convergence to near-optimal returns, up to 1.75x reduction in return variance on some setups. Our profiling approach offers a general, theoretically grounded path to more reliable and efficient policy learning in complex environments.

---

### MedBayes-Lite: A Clinical Uncertainty Governance Layer for Risk-Aware Medical Decision Support

Authors: Elias Hossain, Md Mehedi Hasan Nipu, Maleeha Sheikh, Tasfia Nuzhat, Rajib Rana, Subash Neupane, Björn W. Schuller, Niloofar Yousefi
Published: 2025-11-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.16625v3

Clinical language models often assign high confidence to incorrect predictions, particularly in high-severity and out-of-distribution cases. We present MedBayes-Lite, a retraining-free uncertainty governance layer for transformer-based clinical predictors. It combines Monte Carlo dropout, predictive calibration, and confidence-guided abstention to defer low-confidence predictions for human review, adding no trainable parameters. Evaluated on MedMCQA and MedQA-USMLE, MedBayes-Lite reduces expected calibration error by 0.23 to 0.33 and drives harmful overconfident errors (confident, incorrect, high-severity predictions) toward zero. Under domain shift from MedMCQA to MedQA-USMLE, it reduces confident high-severity errors from about 21% to near zero while roughly halving calibration drift. We also introduce the Clinical Uncertainty Score (CUS), which strongly correlates with harmful overconfidence (r approximately 0.88). Although the framework does not improve risk-coverage ranking, and temperature scaling or deep ensembles may provide advantages in calibration cost or risk ranking, MedBayes-Lite offers a practical calibration-and-abstention layer that reduces confident high-severity errors in clinical question-answering benchmarks.

---

### MedBayes-Lite: Bayesian Uncertainty Quantification for Safe Clinical Decision Support

Authors: Elias Hossain, Md Mehedi Hasan Nipu, Maleeha Sheikh, Rajib Rana, Subash Neupane, Niloofar Yousefi
Published: 2025-11-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.16625v1

We propose MedBayes-Lite, a lightweight Bayesian enhancement for transformer-based clinical language models designed to produce reliable, uncertainty-aware predictions. Although transformers show strong potential for clinical decision support, they remain prone to overconfidence, especially in ambiguous medical cases where calibrated uncertainty is critical. MedBayes-Lite embeds uncertainty quantification directly into existing transformer pipelines without any retraining or architectural rewiring, adding no new trainable layers and keeping parameter overhead under 3 percent. The framework integrates three components: (i) Bayesian Embedding Calibration using Monte Carlo dropout for epistemic uncertainty, (ii) Uncertainty-Weighted Attention that marginalizes over token reliability, and (iii) Confidence-Guided Decision Shaping inspired by clinical risk minimization. Across biomedical QA and clinical prediction benchmarks (MedQA, PubMedQA, MIMIC-III), MedBayes-Lite consistently improves calibration and trustworthiness, reducing overconfidence by 32 to 48 percent. In simulated clinical settings, it can prevent up to 41 percent of diagnostic errors by flagging uncertain predictions for human review. These results demonstrate its effectiveness in enabling reliable uncertainty propagation and improving interpretability in medical AI systems.

---

### SAM 3D: 3Dfy Anything in Images

Authors: SAM 3D Team, Xingyu Chen, Fu-Jen Chu, Pierre Gleize, Kevin J Liang, Alexander Sax, Hao Tang, Weiyao Wang, Michelle Guo, Thibaut Hardin, Xiang Li, Aohan Lin et al.
Published: 2025-11-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.16624v2

We present SAM 3D, a generative model for visually grounded 3D object reconstruction, predicting geometry, texture, and layout from a single image. SAM 3D excels in natural images, where occlusion and scene clutter are common and visual recognition cues from context play a larger role. We achieve this with a human- and model-in-the-loop pipeline for annotating object shape, texture, and pose, providing visually grounded 3D reconstruction data at unprecedented scale. We learn from this data in a modern, multi-stage training framework that combines synthetic pretraining with real-world alignment, breaking the 3D "data barrier". We obtain significant gains over recent work, with at least a 5:1 win rate in human preference tests on real-world objects and scenes. We will release our code and model weights, an online demo, and a new challenging benchmark for in-the-wild 3D object reconstruction.

---

### SAM 3D: 3Dfy Anything in Images

Authors: SAM 3D Team, Xingyu Chen, Fu-Jen Chu, Pierre Gleize, Kevin J Liang, Alexander Sax, Hao Tang, Weiyao Wang, Michelle Guo, Thibaut Hardin, Xiang Li, Aohan Lin et al.
Published: 2025-11-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.16624v1

We present SAM 3D, a generative model for visually grounded 3D object reconstruction, predicting geometry, texture, and layout from a single image. SAM 3D excels in natural images, where occlusion and scene clutter are common and visual recognition cues from context play a larger role. We achieve this with a human- and model-in-the-loop pipeline for annotating object shape, texture, and pose, providing visually grounded 3D reconstruction data at unprecedented scale. We learn from this data in a modern, multi-stage training framework that combines synthetic pretraining with real-world alignment, breaking the 3D "data barrier". We obtain significant gains over recent work, with at least a 5:1 win rate in human preference tests on real-world objects and scenes. We will release our code and model weights, an online demo, and a new challenging benchmark for in-the-wild 3D object reconstruction.

---

### From Polynomials to Databases: Arithmetic Structures in Galois Theory

Authors: Jurgen Mezinaj
Published: 2025-11-20
Categories: math.AC, cs.LG
arXiv: https://arxiv.org/abs/2511.16622v1

We develop a computational framework for classifying Galois groups of irreducible degree-7 polynomials over~$\mathbb{Q}$, combining explicit resolvent methods with machine learning techniques. A database of over one million normalized projective septics is constructed, each annotated with algebraic invariants~$J_0, \dots, J_4$ derived from binary transvections. For each polynomial, we compute resolvent factorizations to determine its Galois group among the seven transitive subgroups of~$S_7$ identified by Foulkes. Using this dataset, we train a neurosymbolic classifier that integrates invariant-theoretic features with supervised learning, yielding improved accuracy in detecting rare solvable groups compared to coefficient-based models. The resulting database provides a reproducible resource for constructive Galois theory and supports empirical investigations into group distribution under height constraints. The methodology extends to higher-degree cases and illustrates the utility of hybrid symbolic-numeric techniques in computational algebra.

---

### SurgSLOT: Segment Anything in Surgical Videos via Semantic Long-term Tracking

Authors: Haofeng Liu, Ziyue Wang, Sudhanshu Mishra, Mingqi Gao, Guanyi Qin, Chang Han Low, Alex Y. W. Kong, Zhu Zhuo, Huazhu Fu, Joseph S. Ng, Yueming Jin
Published: 2025-11-20
Categories: cs.CV, eess.IV, q-bio.TO
arXiv: https://arxiv.org/abs/2511.16618v2

Surgical scene understanding demands temporally consistent tracking of instruments and tissues. For clinical use, such tracking should generalize to new centers and procedure types, yet retraining for each of them is costly and not scalable. Interactive video object segmentation offers a way toward this generalization: the target is specified at inference by a first-frame visual prompt, so a model can generalize to unseen categories and new scenarios without retraining. However, training such a generalizable model demands spatio-temporal masklet annotations at a scale and procedural diversity that existing surgical benchmarks lack. We fill this gap with iSurg, the largest surgical segmentation benchmark to our knowledge, spanning six procedure types with over 170k frames, 410k object masks, and 2.4k masklets, including an in-house clinical dataset of four 30-minute videos. Yet tracking over such long videos remains challenging: the target needs to be re-identified among visually similar objects after long absences, while long-term memory has to judge whether each stored frame genuinely depicts the target, both demanding a stable object-level semantic identity. To this end, we propose SurgSLOT, a surgical segmentation generalist that segments any prompted target through two coupled modules built on this semantic identity: Temporal Semantic Learning learns it for re-identification, and Semantic-driven Long-term Memory reuses it to select reliable memory frames, suppressing identity drift over long procedures. On the SAM2 and SAM3 backbones, SurgSLOT reaches 81.0 and 82.8 Macro Average J&F under cross-dataset evaluation, surpassing their fine-tuned counterparts by 5.1 and 5.3 points and transferring zero-shot to an unseen procedure type and unseen object categories, with the SAM2 version running in real time at 68 FPS.

---

### SAM2S: Segment Anything in Surgical Videos via Semantic Long-term Tracking

Authors: Haofeng Liu, Ziyue Wang, Sudhanshu Mishra, Mingqi Gao, Guanyi Qin, Chang Han Low, Alex Y. W. Kong, Yueming Jin
Published: 2025-11-20
Categories: cs.CV, eess.IV, q-bio.TO
arXiv: https://arxiv.org/abs/2511.16618v1

Surgical video segmentation is crucial for computer-assisted surgery, enabling precise localization and tracking of instruments and tissues. Interactive Video Object Segmentation (iVOS) models such as Segment Anything Model 2 (SAM2) provide prompt-based flexibility beyond methods with predefined categories, but face challenges in surgical scenarios due to the domain gap and limited long-term tracking. To address these limitations, we construct SA-SV, the largest surgical iVOS benchmark with instance-level spatio-temporal annotations (masklets) spanning eight procedure types (61k frames, 1.6k masklets), enabling comprehensive development and evaluation for long-term tracking and zero-shot generalization. Building on SA-SV, we propose SAM2S, a foundation model enhancing \textbf{SAM2} for \textbf{S}urgical iVOS through: (1) DiveMem, a trainable diverse memory mechanism for robust long-term tracking; (2) temporal semantic learning for instrument understanding; and (3) ambiguity-resilient learning to mitigate annotation inconsistencies across multi-source datasets. Extensive experiments demonstrate that fine-tuning on SA-SV enables substantial performance gains, with SAM2 improving by 12.99 average $\mathcal{J}$\&$\mathcal{F}$ over vanilla SAM2. SAM2S further advances performance to 80.42 average $\mathcal{J}$\&$\mathcal{F}$, surpassing vanilla and fine-tuned SAM2 by 17.10 and 4.11 points respectively, while maintaining 68 FPS real-time inference and strong zero-shot generalization. Code and dataset will be released at https://jinlab-imvr.github.io/SAM2S.

---

### Rate-optimal community detection near the KS threshold via node-robust algorithms

Authors: Jingqiu Ding, Yiding Hua, Kasper Lindberg, David Steurer, Aleksandr Storozhenko
Published: 2025-11-20
Categories: stat.ML, cs.CC, cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2511.16613v1

We study community detection in the \emph{symmetric $k$-stochastic block model}, where $n$ nodes are evenly partitioned into $k$ clusters with intra- and inter-cluster connection probabilities $p$ and $q$, respectively. Our main result is a polynomial-time algorithm that achieves the minimax-optimal misclassification rate \begin{equation*} \exp \Bigl(-\bigl(1 \pm o(1)\bigr) \tfrac{C}{k}\Bigr), \quad \text{where } C = (\sqrt{pn} - \sqrt{qn})^2, \end{equation*} whenever $C \ge K\,k^2\,\log k$ for some universal constant $K$, matching the Kesten--Stigum (KS) threshold up to a $\log k$ factor. Notably, this rate holds even when an adversary corrupts an $η\le \exp\bigl(- (1 \pm o(1)) \tfrac{C}{k}\bigr)$ fraction of the nodes. To the best of our knowledge, the minimax rate was previously only attainable either via computationally inefficient procedures (ZZ15) or via polynomial-time algorithms that require strictly stronger assumptions such as $C \ge K k^3$ (GMZZ17). In the node-robust setting, the best known algorithm requires the substantially stronger condition $C \ge K k^{102}$ (LM22). Our results close this gap by providing the first polynomial-time algorithm that achieves the minimax rate near the KS threshold in both settings. Our work has two key technical contributions: (1) we robustify majority voting via the Sum-of-Squares framework, (2) we develop a novel graph bisection algorithm via robust majority voting, which allows us to significantly improve the misclassification rate to $1/\mathrm{poly}(k)$ for the initial estimation near the KS threshold.

---

### Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization

Authors: Yi Zhang, Che Liu, Xiancong Ren, Hanchu Ni, Yingji Zhang, Shuai Zhang, Zeyuan Ding, Jiayu Hu, Haozhe Shan, Junbo Qi, Yan Bai, Dengjie Li et al.
Published: 2025-11-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.16602v1

Developing a universal and versatile embodied intelligence system presents two primary challenges: the critical embodied data bottleneck, where real-world data is scarce and expensive, and the algorithmic inefficiency of existing methods, which are resource-prohibitive. To address these limitations, we introduce Deliberate Practice Policy Optimization (DPPO), a metacognitive ``Metaloop'' training framework that dynamically alternates between supervised fine-tuning (competence expansion) and reinforcement learning (skill refinement). This enables automatic weakness identification and targeted resource allocation, specifically designed to maximize learning efficiency from sparse, finite data. Theoretically, DPPO can be formalised as a unified preference-learning framework. Empirically, training a vision-language embodied model with DPPO, referred to as Pelican-VL 1.0, yields a 20.3% performance improvement over the base model and surpasses open-source models at the 100B-parameter scale by 10.6%. We are open-sourcing both the models and code, providing the first systematic framework that alleviates the data and resource bottleneck and enables the community to build versatile embodied agents efficiently.

---

### You Only Forward Once: An Efficient Compositional Judging Paradigm

Authors: Tianlong Zhang, Hongwei Xue, Shilin Yan, Di Wu, Chen Xu, Guannan Zhang, Yunyun Yang
Published: 2025-11-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.16600v3

Multimodal large language models (MLLMs) show strong potential as judges. However, existing approaches face a fundamental trade-off: adapting MLLMs to output a single score misaligns with the generative nature of MLLMs and limits fine-grained requirement understanding, whereas autoregressively generating judging analyses is prohibitively slow in high-throughput settings. Observing that judgment reduces to verifying whether inputs satisfy a set of structured requirements, we propose YOFO, a template-conditioned method that judges all requirements in a single forward pass. Built on an autoregressive model, YOFO accepts a structured requirement template and, in one inference step, produces a binary yes/no decision for each requirement by reading the logits of the final token associated with that requirement. This design yields orders-of-magnitude speedups while preserving interpretability. Extensive experiments show that YOFO not only achieves state-of-the-art results on standard recommendation datasets, but also supports dependency-aware analysis -- where subsequent judgments are conditioned on previous ones -- and further benefits from post-hoc CoT.

---

### You Only Forward Once: An Efficient Compositional Judging Paradigm

Authors: Tianlong Zhang, Hongwei Xue, Shilin Yan, Di Wu, Chen Xu, Yunyun Yang
Published: 2025-11-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.16600v1

Multimodal large language models (MLLMs) show strong potential as judges. However, existing approaches face a fundamental trade-off: adapting MLLMs to output a single score misaligns with the generative nature of MLLMs and limits fine-grained requirement understanding, whereas autoregressively generating judging analyses is prohibitively slow in high-throughput settings. Observing that judgment reduces to verifying whether inputs satisfy a set of structured requirements, we propose YOFO, a template-conditioned method that judges all requirements in a single forward pass. Built on an autoregressive model, YOFO accepts a structured requirement template and, in one inference step, produces a binary yes/no decision for each requirement by reading the logits of the final token associated with that requirement. This design yields orders-of-magnitude speedups while preserving interpretability. Extensive experiments show that YOFO not only achieves state-of-the-art results on standard recommendation datasets, but also supports dependency-aware analysis-where subsequent judgments are conditioned on previous ones-and further benefits from post-hoc CoT.

---

### Time dependent loss reweighting for flow matching and diffusion models is theoretically justified

Authors: Lukas Billera, Hedwig Nora Nordlinder, Ben Murrell
Published: 2025-11-20
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.16599v1

This brief note clarifies that, in Generator Matching (which subsumes a large family of flow matching and diffusion models over continuous, manifold, and discrete spaces), both the Bregman divergence loss and the linear parameterization of the generator can depend on both the current state $X_t$ and the time $t$, and we show that the expectation over time in the loss can be taken with respect to a broad class of time distributions. We also show this for Edit Flows, which falls outside of Generator Matching. That the loss can depend on $t$ clarifies that time-dependent loss weighting schemes, often used in practice to stabilize training, are theoretically justified when the specific flow or diffusion scheme is a special case of Generator Matching (or Edit Flows). It also often simplifies the construction of $X_1$-predictor schemes, which are sometimes preferred for model-related reasons. We show examples that rely upon the dependence of linear parameterizations, and of the Bregman divergence loss, on $t$ and $X_t$.

---

### Variational Quantum Integrated Sensing and Communication

Authors: Ivana Nikoloska, Osvaldo Simeone
Published: 2025-11-20
Categories: quant-ph, cs.IT, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2511.16597v1

The integration of sensing and communication functionalities within a common system is one of the main innovation drivers for next-generation networks. In this paper, we introduce a quantum integrated sensing and communication (QISAC) protocol that leverages entanglement in quantum carriers of information to enable both superdense coding and quantum sensing. The proposed approach adaptively optimizes encoding and quantum measurement via variational circuit learning, while employing classical machine learning-based decoders and estimators to process the measurement outcomes. Numerical results for qudit systems demonstrate that the proposed QISAC protocol can achieve a flexible trade-off between classical communication rate and accuracy of parameter estimation.

---

### Toward Artificial Palpation: Representation Learning of Touch on Soft Bodies

Authors: Zohar Rimon, Elisei Shafer, Tal Tepper, Efrat Shimron, Aviv Tamar
Published: 2025-11-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.16596v1

Palpation, the use of touch in medical examination, is almost exclusively performed by humans. We investigate a proof of concept for an artificial palpation method based on self-supervised learning. Our key idea is that an encoder-decoder framework can learn a $\textit{representation}$ from a sequence of tactile measurements that contains all the relevant information about the palpated object. We conjecture that such a representation can be used for downstream tasks such as tactile imaging and change detection. With enough training data, it should capture intricate patterns in the tactile measurements that go beyond a simple map of forces -- the current state of the art. To validate our approach, we both develop a simulation environment and collect a real-world dataset of soft objects and corresponding ground truth images obtained by magnetic resonance imaging (MRI). We collect palpation sequences using a robot equipped with a tactile sensor, and train a model that predicts sensory readings at different positions on the object. We investigate the representation learned in this process, and demonstrate its use in imaging and change detection.

---

### TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding

Authors: Boshen Xu, Zihan Xiao, Jiaze Li, Jianzhong Ju, Zhenbo Luo, Jian Luan, Qin Jin
Published: 2025-11-20
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.16595v2

We introduce TimeViper, a hybrid vision-language model designed to tackle challenges of long video understanding. Processing long videos demands both an efficient model architecture and an effective mechanism for handling extended temporal contexts. To this end, TimeViper adopts a hybrid Mamba-Transformer backbone that combines the efficiency of state-space models with the expressivity of attention mechanisms. Through this hybrid design, we reveal the vision-to-text information aggregation phenomenon, where information progressively flows from vision tokens to text tokens across increasing LLM depth, resulting in severe vision token redundancy. Motivated by this observation, we propose TransV, a token information transfer module that transfers and compresses vision tokens into instruction tokens while maintaining multimodal understanding capabilities. This design enables TimeViper to process hour-long videos exceeding 10,000 frames. Extensive experiments across multiple benchmarks demonstrate that TimeViper competes with state-of-the-art models while extending frame numbers. We further analyze attention behaviors of both Mamba and Transformer layers, offering new insights into hybrid model interpretability. This work represents an initial step towards developing, interpreting, and compressing hybrid Mamba-Transformer architectures.

---

### TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding

Authors: Boshen Xu, Zihan Xiao, Jiaze Li, Jianzhong Ju, Zhenbo Luo, Jian Luan, Qin Jin
Published: 2025-11-20
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.16595v1

We introduce TimeViper, a hybrid vision-language model designed to tackle challenges of long video understanding. Processing long videos demands both an efficient model architecture and an effective mechanism for handling extended temporal contexts. To this end, TimeViper adopts a hybrid Mamba-Transformer backbone that combines the efficiency of state-space models with the expressivity of attention mechanisms. Through this hybrid design, we reveal the vision-to-text information aggregation phenomenon, where information progressively flows from vision tokens to text tokens across increasing LLM depth, resulting in severe vision token redundancy. Motivated by this observation, we propose TransV, a token information transfer module that transfers and compresses vision tokens into instruction tokens while maintaining multimodal understanding capabilities. This design enables TimeViper to process hour-long videos exceeding 10,000 frames. Extensive experiments across multiple benchmarks demonstrate that TimeViper competes with state-of-the-art models while extending frame numbers. We further analyze attention behaviors of both Mamba and Transformer layers, offering new insights into hybrid model interpretability. This work represents an initial step towards developing, interpreting, and compressing hybrid Mamba-Transformer architectures.

---

### Green Resilience of Cyber-Physical Systems: Doctoral Dissertation

Authors: Diaeddin Rimawi
Published: 2025-11-20
Categories: cs.SE, cs.AI, cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2511.16593v1

Cyber-physical systems (CPS) combine computational and physical components. Online Collaborative AI System (OL-CAIS) is a type of CPS that learn online in collaboration with humans to achieve a common goal, which makes it vulnerable to disruptive events that degrade performance. Decision-makers must therefore restore performance while limiting energy impact, creating a trade-off between resilience and greenness. This research addresses how to balance these two properties in OL-CAIS. It aims to model resilience for automatic state detection, develop agent-based policies that optimize the greenness-resilience trade-off, and understand catastrophic forgetting to maintain performance consistency. We model OL-CAIS behavior through three operational states: steady, disruptive, and final. To support recovery during disruptions, we introduce the GResilience framework, which provides recovery strategies through multi-objective optimization (one-agent), game-theoretic decision-making (two-agent), and reinforcement learning (RL-agent). We also design a measurement framework to quantify resilience and greenness. Empirical evaluation uses real and simulated experiments with a collaborative robot learning object classification from human demonstrations. Results show that the resilience model captures performance transitions during disruptions, and that GResilience policies improve green recovery by shortening recovery time, stabilizing performance, and reducing human dependency. RL-agent policies achieve the strongest results, although with a marginal increase in CO2 emissions. We also observe catastrophic forgetting after repeated disruptions, while our policies help maintain steadiness. A comparison with containerized execution shows that containerization cuts CO2 emissions by half. Overall, this research provides models, metrics, and policies that ensure the green recovery of OL-CAIS.

---

### gfnx: Fast and Scalable Library for Generative Flow Networks in JAX

Authors: Daniil Tiapkin, Artem Agarkov, Nikita Morozov, Ian Maksimov, Askar Tsyganov, Timofei Gritsaev, Sergey Samsonov
Published: 2025-11-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.16592v1

In this paper, we present gfnx, a fast and scalable package for training and evaluating Generative Flow Networks (GFlowNets) written in JAX. gfnx provides an extensive set of environments and metrics for benchmarking, accompanied with single-file implementations of core objectives for training GFlowNets. We include synthetic hypergrids, multiple sequence generation environments with various editing regimes and particular reward designs for molecular generation, phylogenetic tree construction, Bayesian structure learning, and sampling from the Ising model energy. Across different tasks, gfnx achieves significant wall-clock speedups compared to Pytorch-based benchmarks (such as torchgfn library) and author implementations. For example, gfnx achieves up to 55 times speedup on CPU-based sequence generation environments, and up to 80 times speedup with the GPU-based Bayesian network structure learning setup. Our package provides a diverse set of benchmarks and aims to standardize empirical evaluation and accelerate research and applications of GFlowNets. The library is available on GitHub (https://github.com/d-tiapkin/gfnx) and on pypi (https://pypi.org/project/gfnx/). Documentation is available on https://gfnx.readthedocs.io.

---

### D-GARA: A Dynamic Benchmarking Framework for GUI Agent Robustness in Real-World Anomalies

Authors: Sen Chen, Tong Zhao, Yi Bin, Fei Ma, Wenqi Shao, Zheng Wang
Published: 2025-11-20
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.16590v1

Developing intelligent agents capable of operating a wide range of Graphical User Interfaces (GUIs) with human-level proficiency is a key milestone on the path toward Artificial General Intelligence. While most existing datasets and benchmarks for training and evaluating GUI agents are static and idealized, failing to reflect the complexity and unpredictability of real-world environments, particularly the presence of anomalies. To bridge this research gap, we propose D-GARA, a dynamic benchmarking framework, to evaluate Android GUI agent robustness in real-world anomalies. D-GARA introduces a diverse set of real-world anomalies that GUI agents commonly face in practice, including interruptions such as permission dialogs, battery warnings, and update prompts. Based on D-GARA framework, we construct and annotate a benchmark featuring commonly used Android applications with embedded anomalies to support broader community research. Comprehensive experiments and results demonstrate substantial performance degradation in state-of-the-art GUI agents when exposed to anomaly-rich environments, highlighting the need for robustness-aware learning. D-GARA is modular and extensible, supporting the seamless integration of new tasks, anomaly types, and interaction scenarios to meet specific evaluation goals.

---

### Formal Abductive Latent Explanations for Prototype-Based Networks

Authors: Jules Soria, Zakaria Chihani, Julien Girard-Satabin, Alban Grastien, Romain Xu-Darme, Daniela Cancila
Published: 2025-11-20
Categories: cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2511.16588v1

Case-based reasoning networks are machine-learning models that make predictions based on similarity between the input and prototypical parts of training samples, called prototypes. Such models are able to explain each decision by pointing to the prototypes that contributed the most to the final outcome. As the explanation is a core part of the prediction, they are often qualified as ``interpretable by design". While promising, we show that such explanations are sometimes misleading, which hampers their usefulness in safety-critical contexts. In particular, several instances may lead to different predictions and yet have the same explanation. Drawing inspiration from the field of formal eXplainable AI (FXAI), we propose Abductive Latent Explanations (ALEs), a formalism to express sufficient conditions on the intermediate (latent) representation of the instance that imply the prediction. Our approach combines the inherent interpretability of case-based reasoning models and the guarantees provided by formal XAI. We propose a solver-free and scalable algorithm for generating ALEs based on three distinct paradigms, compare them, and present the feasibility of our approach on diverse datasets for both standard and fine-grained image classification. The associated code can be found at https://github.com/julsoria/ale

---

### Almost Sure Convergence Analysis of Differentially Private Stochastic Gradient Methods

Authors: Amartya Mukherjee, Jun Liu
Published: 2025-11-20
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2511.16587v1

Differentially private stochastic gradient descent (DP-SGD) has become the standard algorithm for training machine learning models with rigorous privacy guarantees. Despite its widespread use, the theoretical understanding of its long-run behavior remains limited: existing analyses typically establish convergence in expectation or with high probability, but do not address the almost sure convergence of single trajectories. In this work, we prove that DP-SGD converges almost surely under standard smoothness assumptions, both in nonconvex and strongly convex settings, provided the step sizes satisfy some standard decaying conditions. Our analysis extends to momentum variants such as the stochastic heavy ball (DP-SHB) and Nesterov's accelerated gradient (DP-NAG), where we show that careful energy constructions yield similar guarantees. These results provide stronger theoretical foundations for differentially private optimization and suggest that, despite privacy-induced distortions, the algorithm remains pathwise stable in both convex and nonconvex regimes.

---

### Consciousness in Artificial Intelligence? A Framework for Classifying Objections and Constraints

Authors: Andres Campero, Derek Shiller, Jaan Aru, Jonathan Simon
Published: 2025-11-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.16582v1

We develop a taxonomical framework for classifying challenges to the possibility of consciousness in digital artificial intelligence systems. This framework allows us to identify the level of granularity at which a given challenge is intended (the levels we propose correspond to Marr's levels) and to disambiguate its degree of force: is it a challenge to computational functionalism that leaves the possibility of digital consciousness open (degree 1), a practical challenge to digital consciousness that suggests improbability without claiming impossibility (degree 2), or an argument claiming that digital consciousness is strictly impossible (degree 3)? We apply this framework to 14 prominent examples from the scientific and philosophical literature. Our aim is not to take a side in the debate, but to provide structure and a tool for disambiguating between challenges to computational functionalism and challenges to digital consciousness, as well as between different ways of parsing such challenges.

---

### Synthesis of Safety Specifications for Probabilistic Systems

Authors: Gaspard Ohlmann, Edwin Hamel-De le Court, Francesco Belardinelli
Published: 2025-11-20
Categories: cs.LO, cs.AI, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2511.16579v1

Ensuring that agents satisfy safety specifications can be crucial in safety-critical environments. While methods exist for controller synthesis with safe temporal specifications, most existing methods restrict safe temporal specifications to probabilistic-avoidance constraints. Formal methods typically offer more expressive ways to express safety in probabilistic systems, such as Probabilistic Computation Tree Logic (PCTL) formulas. Thus, in this paper, we develop a new approach that supports more general temporal properties expressed in PCTL. Our contribution is twofold. First, we develop a theoretical framework for the Synthesis of safe-PCTL specifications. We show how the reducing global specification satisfaction to local constraints, and define CPCTL, a fragment of safe-PCTL. We demonstrate how the expressiveness of CPCTL makes it a relevant fragment for the Synthesis Problem. Second, we leverage these results and propose a new Value Iteration-based algorithm to solve the synthesis problem for these more general temporal properties, and we prove the soundness and completeness of our method.

---

### Integrating Symbolic Natural Language Understanding and Language Models for Word Sense Disambiguation

Authors: Kexin Zhao, Ken Forbus
Published: 2025-11-20
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.16577v1

Word sense disambiguation is a fundamental challenge in natural language understanding. Current methods are primarily aimed at coarse-grained representations (e.g. WordNet synsets or FrameNet frames) and require hand-annotated training data to construct. This makes it difficult to automatically disambiguate richer representations (e.g. built on OpenCyc) that are needed for sophisticated inference. We propose a method that uses statistical language models as oracles for disambiguation that does not require any hand-annotation of training data. Instead, the multiple candidate meanings generated by a symbolic NLU system are converted into distinguishable natural language alternatives, which are used to query an LLM to select appropriate interpretations given the linguistic context. The selected meanings are propagated back to the symbolic NLU system. We evaluate our method against human-annotated gold answers to demonstrate its effectiveness.

---

### ECPv2: Fast, Efficient, and Scalable Global Optimization of Lipschitz Functions

Authors: Fares Fourati, Mohamed-Slim Alouini, Vaneet Aggarwal
Published: 2025-11-20
Categories: cs.LG, cs.AI, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2511.16575v1

We propose ECPv2, a scalable and theoretically grounded algorithm for global optimization of Lipschitz-continuous functions with unknown Lipschitz constants. Building on the Every Call is Precious (ECP) framework, which ensures that each accepted function evaluation is potentially informative, ECPv2 addresses key limitations of ECP, including high computational cost and overly conservative early behavior. ECPv2 introduces three innovations: (i) an adaptive lower bound to avoid vacuous acceptance regions, (ii) a Worst-m memory mechanism that restricts comparisons to a fixed-size subset of past evaluations, and (iii) a fixed random projection to accelerate distance computations in high dimensions. We theoretically show that ECPv2 retains ECP's no-regret guarantees with optimal finite-time bounds and expands the acceptance region with high probability. We further empirically validate these findings through extensive experiments and ablation studies. Using principled hyperparameter settings, we evaluate ECPv2 across a wide range of high-dimensional, non-convex optimization problems. Across benchmarks, ECPv2 consistently matches or outperforms state-of-the-art optimizers, while significantly reducing wall-clock time.

---

### Erase to Retain: Low Rank Adaptation Guided Selective Unlearning in Medical Segmentation Networks

Authors: Nirjhor Datta, Md. Golam Rabiul Alam
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16574v1

The ability to selectively remove knowledge from medical segmentation networks is increasingly important for privacy compliance, ethical deployment, and continual dataset revision. We introduce Erase to Retain, a controllable unlearning framework for medical image segmentation that achieves targeted forgetting without full retraining. Our method uses a teacher-student distillation paradigm with Low-Rank Adaptation (LoRA) constrained subspace updates, enabling the student network to erase lesion-specific or class-specific representations in low-rank decoder spaces while preserving global anatomical understanding. During the strong unlearning phase, LoRA modules are adversarially optimized to contradict the teacher's confident predictions on a designated forget subset, enforcing semantic removal. This is followed by a gentle restoration phase that recovers generalization on retained data through head-only supervised refinement. For ISIC segmentation, the student reduces forget-set IoU from 0.875 to 0.509 while maintaining competitive performance on the retain and validation splits (0.647 to 0.677 IoU). On the cross-domain CHASE dataset, Erase to Retain consistently lowers forget-set IoU while preserving utility on retain and validation sets. For ISIC classification, our method decreases accuracy on the forget subset from 87.0 percent to 64.1 percent while improving retain accuracy from 83.9 percent to 90.6 percent. These results demonstrate that LoRA-based subspace unlearning provides a practical pathway toward responsible, controllable, and reversible unlearning in medical image analysis, enabling models to forget sensitive samples or structures while preserving performance where it matters most.

---

### An Exterior-Embedding Neural Operator Framework for Preserving Conservation Laws

Authors: Huanshuo Dong, Hong Wang, Hao Wu, Zhiwei Zhuang, Xuanze Yang, Ruiqi Shu, Yuan Gao, Xiaomeng Huang
Published: 2025-11-20
Categories: cs.OH, cs.LG
arXiv: https://arxiv.org/abs/2511.16573v1

Neural operators have demonstrated considerable effectiveness in accelerating the solution of time-dependent partial differential equations (PDEs) by directly learning governing physical laws from data. However, for PDEs governed by conservation laws(e.g., conservation of mass, energy, or matter), existing neural operators fail to satisfy conservation properties, which leads to degraded model performance and limited generalizability. Moreover, we observe that distinct PDE problems generally require different optimal neural network architectures. This finding underscores the inherent limitations of specialized models in generalizing across diverse problem domains. To address these limitations, we propose Exterior-Embedded Conservation Framework (ECF), a universal conserving framework that can be integrated with various data-driven neural operators to enforce conservation laws strictly in predictions. The framework consists of two key components: a conservation quantity encoder that extracts conserved quantities from input data, and a conservation quantity decoder that adjusts the neural operator's predictions using these quantities to ensure strict conservation compliance in the final output. Since our architecture enforces conservation laws, we theoretically prove that it enhances model performance. To validate the performance of our method, we conduct experiments on multiple conservation-law-constrained PDE scenarios, including adiabatic systems, shallow water equations, and the Allen-Cahn problem. These baselines demonstrate that our method effectively improves model accuracy while strictly enforcing conservation laws in the predictions.

---

### Boosting Predictive Performance on Tabular Data through Data Augmentation with Latent-Space Flow-Based Diffusion

Authors: Md. Tawfique Ihsan, Md. Rakibul Hasan Rafi, Ahmed Shoyeb Raihan, Imtiaz Ahmed, Abdullahil Azeem
Published: 2025-11-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.16571v1

Severe class imbalance is common in real-world tabular learning, where rare but important minority classes are essential for reliable prediction. Existing generative oversampling methods such as GANs, VAEs, and diffusion models can improve minority-class performance, but they often struggle with tabular heterogeneity, training stability, and privacy concerns. We propose a family of latent-space, tree-driven diffusion methods for minority oversampling that use conditional flow matching with gradient-boosted trees as the vector-field learner. The models operate in compact latent spaces to preserve tabular structure and reduce computation. We introduce three variants: PCAForest, which uses linear PCA embedding; EmbedForest, which uses a learned nonlinear embedding; and AttentionForest, which uses an attention-augmented embedding. Each method couples a GBT-based flow with a decoder back to the original feature space. Across 11 datasets from healthcare, finance, and manufacturing, AttentionForest achieves the best average minority recall while maintaining competitive precision, calibration, and distributional similarity. PCAForest and EmbedForest reach similar utility with much faster generation, offering favorable accuracy-efficiency trade-offs. Privacy evaluated with nearest-neighbor distance ratio and distance-to-closest-record is comparable to or better than the ForestDiffusion baseline. Ablation studies show that smaller embeddings tend to improve minority recall, while aggressive learning rates harm stability. Overall, latent-space, tree-driven diffusion provides an efficient and privacy-aware approach to high-fidelity tabular data augmentation under severe class imbalance.

---

### Failure of uniform laws of large numbers for subdifferentials and beyond

Authors: Lai Tian, Johannes O. Royset
Published: 2025-11-20
Categories: math.OC, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2511.16568v2

We provide counterexamples showing that uniform laws of large numbers do not hold for subdifferentials under natural assumptions. Our constructions are univariate random Lipschitz functions and bivariate random convex functions with two smooth pieces. Consequently, they resolve the questions posed by Shapiro and Xu (J. Math. Anal. Appl., 325 (2007), 1390-1399) in the negative. They also demonstrate the failure of certain graphical and pointwise laws for subdifferentials, revealing fundamental barriers to the consistency of sample-average approximation and subdifferential approximation.

---

### Failure of uniform laws of large numbers for subdifferentials and beyond

Authors: Lai Tian, Johannes O. Royset
Published: 2025-11-20
Categories: math.OC, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2511.16568v1

We provide counterexamples showing that uniform laws of large numbers do not hold for subdifferentials under natural assumptions. Our results apply to random Lipschitz functions and random convex functions with a finite number of smooth pieces. Consequently, they resolve the questions posed by Shapiro and Xu (J. Math. Anal. Appl., 325(2), 2007) in the negative and highlight the obstacles nonsmoothness poses to uniform results.

---

### POMA-3D: The Point Map Way to 3D Scene Understanding

Authors: Ye Mao, Weixun Luo, Ranran Huang, Junpeng Jing, Krystian Mikolajczyk
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16567v3

In this paper, we introduce POMA-3D, the first self-supervised 3D representation model learned from point maps. Point maps encode explicit 3D coordinates on a structured 2D grid, preserving global 3D geometry while remaining compatible with the input format of 2D foundation models. To transfer rich 2D priors into POMA-3D, a view-to-scene alignment strategy is designed. Moreover, as point maps are view-dependent with respect to a canonical space, we introduce POMA-JEPA, a joint embedding-predictive architecture that enforces geometrically consistent point map features across multiple views. Additionally, we introduce ScenePoint, a point map dataset constructed from 6.5K room-level RGB-D scenes and 1M 2D image scenes to facilitate large-scale POMA-3D pretraining. Experiments show that POMA-3D serves as a strong backbone for both specialist and generalist 3D understanding. It benefits diverse tasks, including 3D question answering, embodied navigation, scene retrieval, and embodied localization, all achieved using only geometric inputs (i.e., 3D coordinates). Overall, our POMA-3D explores a point map way to 3D scene understanding, addressing the scarcity of pretrained priors and limited data in 3D representation learning. Project Page: https://matchlab-imperial.github.io/poma3d/

---

### POMA-3D: The Point Map Way to 3D Scene Understanding

Authors: Ye Mao, Weixun Luo, Ranran Huang, Junpeng Jing, Krystian Mikolajczyk
Published: 2025-11-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.16567v1

In this paper, we introduce POMA-3D, the first self-supervised 3D representation model learned from point maps. Point maps encode explicit 3D coordinates on a structured 2D grid, preserving global 3D geometry while remaining compatible with the input format of 2D foundation models. To transfer rich 2D priors into POMA-3D, a view-to-scene alignment strategy is designed. Moreover, as point maps are view-dependent with respect to a canonical space, we introduce POMA-JEPA, a joint embedding-predictive architecture that enforces geometrically consistent point map features across multiple views. Additionally, we introduce ScenePoint, a point map dataset constructed from 6.5K room-level RGB-D scenes and 1M 2D image scenes to facilitate large-scale POMA-3D pretraining. Experiments show that POMA-3D serves as a strong backbone for both specialist and generalist 3D understanding. It benefits diverse tasks, including 3D question answering, embodied navigation, scene retrieval, and embodied localization, all achieved using only geometric inputs (i.e., 3D coordinates). Overall, our POMA-3D explores a point map way to 3D scene understanding, addressing the scarcity of pretrained priors and limited data in 3D representation learning. Project Page: https://matchlab-imperial.github.io/poma3d/

---