# Research Papers — 2025-11 · bundle page 60 of 197

> Full-text markdown of papers #2951–3000 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/60
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/59.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/61.md)

### RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language Models

Authors: Dayan Pan, Jingyuan Wang, Yilong Zhou, Jiawei Cheng, Pengyue Jia, Xiangyu Zhao
Published: 2025-11-21
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.21733v1

Fine-tuning large language models is essential for task-specific adaptation, yet it remains computationally prohibitive. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a solution, but current approaches typically ignore the distinct roles of model components and the heterogeneous importance across layers, thereby limiting adaptation efficiency. Motivated by the observation that Rotary Position Embeddings (RoPE) induce critical activations in the low-frequency dimensions of attention states, we propose RoPE-aware Selective Adaptation (RoSA), a novel PEFT framework that allocates trainable parameters in a more targeted and effective manner. RoSA comprises a RoPE-aware Attention Enhancement (RoAE) module, which selectively enhances the low-frequency components of RoPE-influenced attention states, and a Dynamic Layer Selection (DLS) strategy that adaptively identifies and updates the most critical layers based on LayerNorm gradient norms. By combining dimension-wise enhancement with layer-wise adaptation, RoSA achieves more targeted and efficient fine-tuning. Extensive experiments on fifteen commonsense and arithmetic benchmarks demonstrate that RoSA outperforms existing mainstream PEFT methods under comparable trainable parameters. The code is available to ease reproducibility at https://github.com/Applied-Machine-Learning-Lab/RoSA.

---

### HUMORCHAIN: Theory-Guided Multi-Stage Reasoning for Interpretable Multimodal Humor Generation

Authors: Jiajun Zhang, Shijia Luo, Ruikang Zhang, Qi Su
Published: 2025-11-21
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.21732v2

Humor, as both a creative human activity and a social binding mechanism, has long posed a major challenge for AI generation. Although producing humor requires complex cognitive reasoning and social understanding, theories of humor suggest that it follows learnable patterns and structures, making it theoretically possible for generative models to acquire them implicitly. In recent years, multimodal humor has become a prevalent form of online communication, especially among Gen Z, highlighting the need for AI systems capable of integrating visual understanding with humorous language generation. However, existing data-driven approaches lack explicit modeling or theoretical grounding of humor, often producing literal descriptions that fail to capture its underlying cognitive mechanisms, resulting in the generated image descriptions that are fluent but lack genuine humor or cognitive depth. To address this limitation, we propose HUMORCHAIN (HUmor-guided Multi-step Orchestrated Reasoning Chain for Image Captioning), a theory-guided multi-stage reasoning framework. It integrates visual semantic parsing, humor- and psychology-based reasoning, and a fine-tuned discriminator for humor evaluation, forming an interpretable and controllable cognitive reasoning chain. To the best of our knowledge, this is the first work to explicitly embed cognitive structures from humor theories into multimodal humor generation, enabling a structured reasoning process from visual understanding to humor creation. Experiments on Meme-Image-No-Text, Oogiri-GO, and OxfordTVG-HIC datasets show that HUMORCHAIN outperforms state-of-the-art baselines in human humor preference, Elo/BT scores, and semantic diversity, demonstrating that theory-driven structured reasoning enables large language models to generate humor aligned with human perception.

---

### Identifying Quantum Structure in AI Language: Evidence for Evolutionary Convergence of Human and Artificial Cognition

Authors: Diederik Aerts, Jonito Aerts Arguëlles, Lester Beltran, Suzette Geriente, Roberto Leporini, Massimiliano Sassoli de Bianchi, Sandro Sozzo
Published: 2025-11-21
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.21731v2

We present the results of cognitive tests on conceptual combinations, performed using specific Large Language Models (LLMs) as test subjects. In the first test, performed with ChatGPT and Gemini, we show that Bell's inequalities are significantly violated, which indicates the presence of a 'non-classical probability model' with probabilities that do not satisfy Kolmogorov's axioms. In the second test, also performed using ChatGPT and Gemini, we identify the presence of 'Bose-Einstein statistics', rather than the intuitively expected 'Maxwell-Boltzmann statistics', in the distribution of the words contained in large-size texts. Interestingly, these findings mirror the results previously obtained in both cognitive tests with human participants and information retrieval tests on large corpora. Taken together, they point to the 'systematic emergence of non-classical quantum-like structures in conceptual-linguistic domains', regardless of whether the cognitive agent is human or artificial. Although LLMs are classified as neural networks for historical reasons, we believe that a more essential form of knowledge organization takes place in the distributive semantic structure of vector spaces built on top of the neural network. It is this meaning-bearing structure that lends itself to a phenomenon of evolutionary convergence between human cognition and language, slowly established through biological evolution, and LLM cognition and language, emerging much more rapidly as a result of self-learning and training. We analyze various aspects and examples that contain evidence supporting the above hypothesis. We also advance a unifying framework that explains the pervasive quantum organization of meaning that we identify.

---

### A Benchmark for Procedural Memory Retrieval in Language Agents

Authors: Ishant Kohar, Aswanth Krishnan
Published: 2025-11-21
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.21730v1

Current AI agents excel in familiar settings, but fail sharply when faced with novel tasks with unseen vocabularies -- a core limitation of procedural memory systems. We present the first benchmark that isolates procedural memory retrieval from task execution, evaluating whether agents can recognize functionally equivalent procedures that span different object instantiations. Using ALFWorld, we construct dual corpora of expert and LLM-generated trajectories and evaluate six retrieval methods using systematically stratified queries. Our results expose a clear generalization cliff: embedding-based methods perform strongly on familiar contexts, yet degrade considerably on novel ones, while LLM-generated procedural abstractions demonstrate reliable cross-context transfer. Controlled ablations show that although embeddings capture some lexical-level abstraction, they fundamentally treat procedures as unordered bags of words, discarding temporal structure necessary for cross-context transfer. Corpus scale delivers far larger gains than representation enrichment, revealing an architectural ceiling in current encoders. Our benchmark offers the first diagnostic framework separating genuine procedural understanding from surface-level memorization and gives tools for developing retrieval systems capable of dependable generalization. Resources available at our GitHub repository (https://github.com/qpiai/Proced_mem_bench).

---

### Beyond Component Strength: Synergistic Integration and Adaptive Calibration in Multi-Agent RAG Systems

Authors: Jithin Krishnan
Published: 2025-11-21
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.21729v1

Building reliable retrieval-augmented generation (RAG) systems requires more than adding powerful components; it requires understanding how they interact. Using ablation studies on 50 queries (15 answerable, 10 edge cases, and 25 adversarial), we show that enhancements such as hybrid retrieval, ensemble verification, and adaptive thresholding provide almost no benefit when used in isolation, yet together achieve a 95% reduction in abstention (from 40% to 2%) without increasing hallucinations. We also identify a measurement challenge: different verification strategies can behave safely but assign inconsistent labels (for example, "abstained" versus "unsupported"), creating apparent hallucination rates that are actually artifacts of labeling. Our results show that synergistic integration matters more than the strength of any single component, that standardized metrics and labels are essential for correctly interpreting performance, and that adaptive calibration is needed to prevent overconfident over-answering even when retrieval quality is high.

---

### Affective Multimodal Agents with Proactive Knowledge Grounding for Emotionally Aligned Marketing Dialogue

Authors: Lin Yu, Xiaofei Han, Yifei Kang, Chiung-Yi Tseng, Danyang Zhang, Ziqian Bi, Zhimo Han
Published: 2025-11-21
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.21728v2

Recent advances in large language models (LLMs) have enabled fluent dialogue systems, but most remain reactive and struggle in emotionally rich, goal-oriented settings such as marketing conversations. To address this limitation, we propose AffectMind, a multimodal affective dialogue agent that performs proactive reasoning and dynamic knowledge grounding to sustain emotionally aligned and persuasive interactions. AffectMind combines three components: a Proactive Knowledge Grounding Network (PKGN) that continuously updates factual and affective context from text, vision, and prosody; an Emotion--Intent Alignment Model (EIAM) that jointly models user emotion and purchase intent to adapt persuasion strategies; and a Reinforced Discourse Loop (RDL) that optimizes emotional coherence and engagement via reinforcement signals from user responses. Experiments on two newly curated marketing dialogue datasets, MM-ConvMarket and AffectPromo, show that AffectMind outperforms strong LLM-based baselines in emotional consistency (+26\%), persuasive success rate (+19\%), and long-term user engagement (+23\%), highlighting emotion-grounded proactivity as a key capability for commercial multimodal agents.

---

### Morality in AI. A plea to embed morality in LLM architectures and frameworks

Authors: Gunter Bombaerts, Bram Delisse, Uzay Kaymak
Published: 2025-11-21
Categories: q-bio.NC, cs.AI
arXiv: https://arxiv.org/abs/2511.20689v1

Large language models (LLMs) increasingly mediate human decision-making and behaviour. Ensuring LLM processing of moral meaning therefore has become a critical challenge. Current approaches rely predominantly on bottom-up methods such as fine-tuning and reinforcement learning from human feedback. We propose a fundamentally different approach: embedding moral meaning processing directly into the architectural mechanisms and frameworks of transformer-based models through top-down design principles. We first sketch a framework that conceptualizes attention as a dynamic interface mediating between structure and processing, contrasting with existing linear attention frameworks in psychology. We start from established biological-artificial attention analogies in neural architecture design to improve cognitive processing. We extend this analysis to moral processing, using Iris Murdoch's theory of loving attention (sustained, just observation that enables moral transformation by reseeing others with clarity and compassion) to philosophically discuss functional analogies between human and LLM moral processing. We formulate and evaluate potentially promising technical operationalizations to embed morality in LLM architectures and frameworks. We acknowledge the limitations of our exploration and give three key contributions. (1) We conceptualize attention as a dynamic system mechanism mediating between structure and processing. (2) Drawing on the Murdoch notion of loving attention, we outline technical pathways for embedding morality in LLMs, through modified training objectives, runtime weight adjustments, and architectural refinements to attention. (3) We argue that integrating morality into architectures and frameworks complements external, constraint-based methods. We conclude with a call for collaboration between transformer designers and philosophers engaged in AI ethics.

---

### SG-OIF: A Stability-Guided Online Influence Framework for Reliable Vision Data

Authors: Penghao Rao, Runmin Jiang, Min Xu
Published: 2025-11-21
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.19466v1

Approximating training-point influence on test predictions is critical for deploying deep-learning vision models, essential for locating noisy data. Though the influence function was proposed for attributing how infinitesimal up-weighting or removal of individual training examples affects model outputs, its implementation is still challenging in deep-learning vision models: inverse-curvature computations are expensive, and training non-stationarity invalidates static approximations. Prior works use iterative solvers and low-rank surrogates to reduce cost, but offline computation lags behind training dynamics, and missing confidence calibration yields fragile rankings that misidentify critical examples. To address these challenges, we introduce a Stability-Guided Online Influence Framework (SG-OIF), the first framework that treats algorithmic stability as a real-time controller, which (i) maintains lightweight anchor IHVPs via stochastic Richardson and preconditioned Neumann; (ii) proposes modular curvature backends to modulate per-example influence scores using stability-guided residual thresholds, anomaly gating, and confidence. Experimental results show that SG-OIF achieves SOTA (State-Of-The-Art) on noise-label and out-of-distribution detection tasks across multiple datasets with various corruption. Notably, our approach achieves 91.1\% accuracy in the top 1\% prediction samples on the CIFAR-10 (20\% asym), and gets 99.8\% AUPR score on MNIST, effectively demonstrating that this framework is a practical controller for online influence estimation.

---

### Hidden markov model to predict tourists visited place

Authors: Theo Demessance, Chongke Bi, Sonia Djebali, Guillaume Guerard
Published: 2025-11-21
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.19465v1

Nowadays, social networks are becoming a popular way of analyzing tourist behavior, thanks to the digital traces left by travelers during their stays on these networks. The massive amount of data generated; by the propensity of tourists to share comments and photos during their trip; makes it possible to model their journeys and analyze their behavior. Predicting the next movement of tourists plays a key role in tourism marketing to understand demand and improve decision support. In this paper, we propose a method to understand and to learn tourists' movements based on social network data analysis to predict future movements. The method relies on a machine learning grammatical inference algorithm. A major contribution in this paper is to adapt the grammatical inference algorithm to the context of big data. Our method produces a hidden Markov model representing the movements of a group of tourists. The hidden Markov model is flexible and editable with new data. The capital city of France, Paris is selected to demonstrate the efficiency of the proposed methodology.

---

### Temperature in SLMs: Impact on Incident Categorization in On-Premises Environments

Authors: Marcio Pohlmann, Alex Severo, Gefté Almeida, Diego Kreutz, Tiago Heinrich, Lourenço Pereira
Published: 2025-11-21
Categories: cs.DC, cs.AI, cs.CR, cs.LG, cs.PF
arXiv: https://arxiv.org/abs/2511.19464v1

SOCs and CSIRTs face increasing pressure to automate incident categorization, yet the use of cloud-based LLMs introduces costs, latency, and confidentiality risks. We investigate whether locally executed SLMs can meet this challenge. We evaluated 21 models ranging from 1B to 20B parameters, varying the temperature hyperparameter and measuring execution time and precision across two distinct architectures. The results indicate that temperature has little influence on performance, whereas the number of parameters and GPU capacity are decisive factors.

---

### Systemic approach for modeling a generic smart grid

Authors: Sofiane Ben Amor, Guillaume Guerard, Loup-Noé Levy
Published: 2025-11-21
Categories: cs.DC, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2511.19460v1

Smart grid technological advances present a recent class of complex interdisciplinary modeling and increasingly difficult simulation problems to solve using traditional computational methods. To simulate a smart grid requires a systemic approach to integrated modeling of power systems, energy markets, demand-side management, and much other resources and assets that are becoming part of the current paradigm of the power grid. This paper presents a backbone model of a smart grid to test alternative scenarios for the grid. This tool simulates disparate systems to validate assumptions before the human scale model. Thanks to a distributed optimization of subsystems, the production and consumption scheduling is achieved while maintaining flexibility and scalability.

---

### Personalized Reward Modeling for Text-to-Image Generation

Authors: Jeongeun Lee, Ryang Heo, Dongha Lee
Published: 2025-11-21
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.19458v1

Recent text-to-image (T2I) models generate semantically coherent images from textual prompts, yet evaluating how well they align with individual user preferences remains an open challenge. Conventional evaluation methods, general reward functions or similarity-based metrics, fail to capture the diversity and complexity of personal visual tastes. In this work, we present PIGReward, a personalized reward model that dynamically generates user-conditioned evaluation dimensions and assesses images through CoT reasoning. To address the scarcity of user data, PIGReward adopt a self-bootstrapping strategy that reasons over limited reference data to construct rich user contexts, enabling personalization without user-specific training. Beyond evaluation, PIGReward provides personalized feedback that drives user-specific prompt optimization, improving alignment between generated images and individual intent. We further introduce PIGBench, a per-user preference benchmark capturing diverse visual interpretations of shared prompts. Extensive experiments demonstrate that PIGReward surpasses existing methods in both accuracy and interpretability, establishing a scalable and reasoning-based foundation for personalized T2I evaluation and optimization. Taken together, our findings highlight PIGReward as a robust steptoward individually aligned T2I generation.

---

### SparOA: Sparse and Operator-aware Hybrid Scheduling for Edge DNN Inference

Authors: Ziyang Zhang, Jie Liu, Luca Mottola
Published: 2025-11-21
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2511.19457v1

The resource demands of deep neural network (DNN) models introduce significant performance challenges, especially when deployed on resource-constrained edge devices. Existing solutions like model compression often sacrifice accuracy, while specialized hardware remains costly and inflexible. Hybrid inference methods, however, typically overlook how operator characteristics impact performance. In this work, we present SparOA, a CPU-GPU hybrid inference framework, which leverages both sparsity and computational intensity to optimize operator scheduling. SparOA embraces aforementioned challenges through three key components: (1) a threshold predictor that accurately determines optimal sparsity and computational intensity thresholds; (2) a reinforcement learning-based scheduler that dynamically optimizes resource allocation based on real-time hardware states; and (3) a hybrid inference engine that enhances efficiency through asynchronous execution and batch size optimization.Extensive results show that SparOA achieves an average speedup of 1.22-1.31x compared to all baselines, and outperforms the CPU-Only by up to 50.7x. Also, SparOA achieves optimal energy-per-inference, consuming 7\%-16\% less energy than the SOTA co-execution baseline.

---

### Less is More: Data-Efficient Adaptation for Controllable Text-to-Video Generation

Authors: Shihan Cheng, Nilesh Kulkarni, David Hyde, Dmitriy Smirnov
Published: 2025-11-21
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.17844v4

Fine-tuning large-scale text-to-video diffusion models to add new generative controls, such as those over physical camera parameters (e.g., shutter speed or aperture), typically requires vast, high-fidelity datasets that are difficult to acquire. In this work, we propose a data-efficient fine-tuning strategy that learns these controls from sparse, low-quality synthetic data. We show that not only does fine-tuning on such simple data enable the desired controls, it actually yields superior results to models fine-tuned on photorealistic "real" data. Beyond demonstrating these results, we provide a framework that justifies this phenomenon both intuitively and quantitatively.

---

### JigsawComm: Joint Semantic Feature Encoding and Transmission for Communication-Efficient Cooperative Perception

Authors: Chenyi Wang, Zhaowei Li, Ming F. Li, Wujie Wen
Published: 2025-11-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.17843v2

Multi-agent cooperative perception (CP) promises to overcome the inherent occlusion and range limitations of single-agent systems in autonomous driving, yet its practicality is severely constrained by limited Vehicle-to-Everything (V2X) communication bandwidth. Existing approaches attempt to improve bandwidth efficiency via compression or heuristic message selection, but neglect the semantic relevance and cross-agent redundancy of the transmitted data. In this paper, we formulate a joint semantic feature encoding and transmission problem that maximizes CP accuracy under a communication budget, and introduce JigsawComm, an end-to-end semantic-aware framework that learns to ``assemble the puzzle'' of multi-agent feature transmission. JigsawComm uses a regularized encoder to extract \emph{sparse, semantically relevant features}, and a lightweight Feature Utility Estimator (FUE) to predict each agent's per-cell contribution to the downstream perception task. The FUE-generated compact meta utility maps are exchanged among agents and used to compute an optimal transmission policy under the learned utility proxy. This policy inherently \emph{eliminates cross-agent redundancy}, bounding the feature transmission payload to $\mathcal{O}(1)$ as the number of agents grows, while the meta information overhead remains negligible. The whole pipeline is trained end-to-end through a differentiable scheduling module, informing the FUE to be aligned with the task objective. On the OPV2V and DAIR-V2X benchmarks, JigsawComm reduces total data volume by over 20--500${\times}$ while matching or exceeding the accuracy of state-of-the-art methods.

---

### Internalizing Tools as Morphisms in Graded Transformers

Authors: Tony Shaska
Published: 2025-11-21
Categories: cs.LG, math.CT
arXiv: https://arxiv.org/abs/2511.17840v1

We introduce a graded formulation of internal symbolic computation for transformers. The hidden space is endowed with a grading $V=\bigoplus_{g\in G}V_g$, and symbolic operations are realized as typed block maps (morphisms) $φ_{h\leftarrow g}:V_g\to V_h$ that are activated selectively by a differentiable routing policy. A self-supervised \emph{graded utility functional}, defined as the loss reduction induced by a candidate morphism, governs activation and yields sparse, interpretable behavior. We develop the algebraic and geometric foundations: an internal model category whose objects are homogeneous components and whose morphisms are admissible grade transitions; adjoint pairs encoding typed round trips; and information-geometric interpretations in terms of KL gain, mirror descent with Bregman divergences, and Fisher natural gradients. Methodologically, we specify a utility--aware routing mechanism and objective that remain fully end-to-end differentiable. Analytic case studies and lightweight sanity checks illustrate selective morphic activation on hybrid symbolic-linguistic tasks. The framework unifies symbolic computation, geometry, and self--supervised learning within the \emph{graded transformer} formalism \cite{sh-89,sh-95}, while subsuming prior external-tool paradigms (e.g., Toolformer \cite{toolformer2023}) as a special case via functorial internalization.

---

### Show Me: Unifying Instructional Image and Video Generation with Diffusion Models

Authors: Yujiang Pu, Zhanbo Huang, Vishnu Boddeti, Yu Kong
Published: 2025-11-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.17839v1

Generating visual instructions in a given context is essential for developing interactive world simulators. While prior works address this problem through either text-guided image manipulation or video prediction, these tasks are typically treated in isolation. This separation reveals a fundamental issue: image manipulation methods overlook how actions unfold over time, while video prediction models often ignore the intended outcomes. To this end, we propose ShowMe, a unified framework that enables both tasks by selectively activating the spatial and temporal components of video diffusion models. In addition, we introduce structure and motion consistency rewards to improve structural fidelity and temporal coherence. Notably, this unification brings dual benefits: the spatial knowledge gained through video pretraining enhances contextual consistency and realism in non-rigid image edits, while the instruction-guided manipulation stage equips the model with stronger goal-oriented reasoning for video prediction. Experiments on diverse benchmarks demonstrate that our method outperforms expert models in both instructional image and video generation, highlighting the strength of video diffusion models as a unified action-object state transformer.

---

### Learning to Debug: LLM-Organized Knowledge Trees for Solving RTL Assertion Failures

Authors: Yunsheng Bai, Haoxing Ren
Published: 2025-11-21
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2511.17833v2

Debugging is the dominant cost in modern hardware verification, where assertion failures are among the most frequent and expensive to resolve. While Large Language Models (LLMs) show promise, they often fail to capture the precise, reusable expertise that engineers apply, leading to inaccurate responses. We propose GROVE, a hierarchical knowledge management framework that learns and organizes reusable debugging expertise into an LLM-organized knowledge tree for solving assertion failures. GROVE distills debugging knowledge from prior cases and organizes it into a vertical tree of configurable depth, with each node encoding a concise knowledge item and explicit applicability conditions. During training, GROVE uses a parallel, gradient-free loop where an LLM proposes tree modifications as structured JSON edits by learning from the cases. At test time, a budget-aware iterative zoom is performed to navigate the tree, retrieving a small set of applicable knowledge items that guide a base LLM's hypothesis generation and fix proposals. Evaluated on a suite of assertion-failure cases, GROVE delivers consistent gains in pass@1 and pass@5, demonstrating the value of structured knowledge evolution.

---

### Unified Class and Domain Incremental Learning with Mixture of Experts for Indoor Localization

Authors: Akhil Singampalli, Sudeep Pasricha
Published: 2025-11-21
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.17829v1

Indoor localization using machine learning has gained traction due to the growing demand for location-based services. However, its long-term reliability is hindered by hardware/software variations across mobile devices, which shift the model's input distribution to create domain shifts. Further, evolving indoor environments can introduce new locations over time, expanding the output space to create class shifts, making static machine learning models ineffective over time. To address these challenges, we propose a novel unified continual learning framework for indoor localization called MOELO that, for the first time, jointly addresses domain-incremental and class-incremental learning scenarios. MOELO enables a lightweight, robust, and adaptive localization solution that can be deployed on resource-limited mobile devices and is capable of continual learning in dynamic, heterogeneous real-world settings. This is made possible by a mixture-of-experts architecture, where experts are incrementally trained per region and selected through an equiangular tight frame based gating mechanism ensuring efficient routing, and low-latency inference, all within a compact model footprint. Experimental evaluations show that MOELO achieves improvements of up to 25.6x in mean localization error, 44.5x in worst-case localization error, and 21.5x lesser forgetting compared to state-of-the-art frameworks across diverse buildings, mobile devices, and learning scenarios.

---

### Toward explainable AI approaches for breast imaging: adapting foundation models to diverse populations

Authors: Guilherme J. Cavalcante, José Gabriel A. Moreira, Gabriel A. B. do Nascimento, Vincent Dong, Alex Nguyen, Thaís G. do Rêgo, Yuri Malheiros, Telmo M. Silva Filho, Carla R. Zeballos Torrez, James C. Gee, Anne Marie McCarthy, Andrew D. A. Maidment et al.
Published: 2025-11-21
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.17828v1

Foundation models hold promise for specialized medical imaging tasks, though their effectiveness in breast imaging remains underexplored. This study leverages BiomedCLIP as a foundation model to address challenges in model generalization. BiomedCLIP was adapted for automated BI-RADS breast density classification using multi-modality mammographic data (synthesized 2D images, digital mammography, and digital breast tomosynthesis). Using 96,995 images, we compared single-modality (s2D only) and multi-modality training approaches, addressing class imbalance through weighted contrastive learning. Both approaches achieved similar accuracy (multi-modality: 0.74, single-modality: 0.73), with the multi-modality model offering broader applicability across different imaging modalities and higher AUC values consistently above 0.84 across BI-RADS categories. External validation on the RSNA and EMBED datasets showed strong generalization capabilities (AUC range: 0.80-0.93). GradCAM visualizations confirmed consistent and clinically relevant attention patterns, highlighting the models interpretability and robustness. This research underscores the potential of foundation models for breast imaging applications, paving the way for future extensions for diagnostic tasks.

---

### Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch

Authors: Ziyang Zhang, Xinheng Ding, Jiayi Yuan, Rixin Liu, Huizi Mao, Jiarong Xing, Zirui Liu
Published: 2025-11-21
Categories: cs.LG, cs.CL, stat.ML
arXiv: https://arxiv.org/abs/2511.17826v2

Deterministic inference is increasingly critical for large language model (LLM) applications such as LLM-as-a-judge evaluation, multi-agent systems, and Reinforcement Learning (RL). However, existing LLM serving frameworks exhibit non-deterministic behavior: identical inputs can yield different outputs when system configurations (e.g., tensor parallel (TP) size, batch size) vary, even under greedy decoding. This arises from the non-associativity of floating-point arithmetic and inconsistent reduction orders across GPUs. While prior work has addressed batch-size-related nondeterminism through batch-invariant kernels, determinism across different TP sizes remains an open problem, particularly in RL settings, where the training engine typically uses Fully Sharded Data Parallel (i.e., TP = 1) while the rollout engine relies on multi-GPU TP to maximize the inference throughput, creating a natural mismatch between the two. This precision mismatch problem may lead to suboptimal performance or even collapse for RL training. We identify and analyze the root causes of TP-induced inconsistency and propose Tree-Based Invariant Kernels (TBIK), a set of TP-invariant matrix multiplication and reduction primitives that guarantee bit-wise identical results regardless of TP size. Our key insight is to align intra- and inter-GPU reduction orders through a unified hierarchical binary tree structure. We implement these kernels in Triton and integrate them into vLLM and FSDP. Experiments confirm zero probability divergence and bit-wise reproducibility for deterministic inference across different TP sizes. Also, we achieve bit-wise identical results between vLLM and FSDP in RL training pipelines with different parallel strategy. Code is available at https://github.com/nanomaoli/llm_reproducibility.

---

### Analog Physical Systems Can Exhibit Double Descent

Authors: Sam Dillavou, Jason W Rocks, Jacob F Wycoff, Andrea J Liu, Douglas J Durian
Published: 2025-11-21
Categories: cond-mat.dis-nn, cs.LG
arXiv: https://arxiv.org/abs/2511.17825v1

An important component of the success of large AI models is double descent, in which networks avoid overfitting as they grow relative to the amount of training data, instead improving their performance on unseen data. Here we demonstrate double descent in a decentralized analog network of self-adjusting resistive elements. This system trains itself and performs tasks without a digital processor, offering potential gains in energy efficiency and speed -- but must endure component non-idealities. We find that standard training fails to yield double descent, but a modified protocol that accommodates this inherent imperfection succeeds. Our findings show that analog physical systems, if appropriately trained, can exhibit behaviors underlying the success of digital AI. Further, they suggest that biological systems might similarly benefit from over-parameterization.

---

### QAL: A Loss for Recall Precision Balance in 3D Reconstruction

Authors: Pranay Meshram, Yash Turkar, Kartikeya Singh, Praveen Raj Masilamani, Charuvahan Adhivarahan, Karthik Dantu
Published: 2025-11-21
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2511.17824v1

Volumetric learning underpins many 3D vision tasks such as completion, reconstruction, and mesh generation, yet training objectives still rely on Chamfer Distance (CD) or Earth Mover's Distance (EMD), which fail to balance recall and precision. We propose Quality-Aware Loss (QAL), a drop-in replacement for CD/EMD that combines a coverage-weighted nearest-neighbor term with an uncovered-ground-truth attraction term, explicitly decoupling recall and precision into tunable components. Across diverse pipelines, QAL achieves consistent coverage gains, improving by an average of +4.3 pts over CD and +2.8 pts over the best alternatives. Though modest in percentage, these improvements reliably recover thin structures and under-represented regions that CD/EMD overlook. Extensive ablations confirm stable performance across hyperparameters and across output resolutions, while full retraining on PCN and ShapeNet demonstrates generalization across datasets and backbones. Moreover, QAL-trained completions yield higher grasp scores under GraspNet evaluation, showing that improved coverage translates directly into more reliable robotic manipulation. QAL thus offers a principled, interpretable, and practical objective for robust 3D vision and safety-critical robotics pipelines

---

### A novel k-means clustering approach using two distance measures for Gaussian data

Authors: Naitik Gada
Published: 2025-11-21
Categories: cs.LG, cs.CE, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2511.17823v2

Clustering algorithms have long been the topic of research, representing the more popular side of unsupervised learning. Since clustering analysis is one of the best ways to find some clarity and structure within raw data, this paper explores a novel approach to k-means clustering. Here we present a k-means clustering algorithm that takes both the within cluster distance (WCD) and the inter cluster distance (ICD) as the distance metric to cluster the data into k clusters pre-determined by the Calinski-Harabasz criterion in order to provide a more robust output for the clustering analysis. The idea with this approach is that by including both the measurement metrics, the convergence of the data into their clusters becomes solidified and more robust. We run the algorithm with some synthetically produced data and also some benchmark data sets obtained from the UCI repository. The results show that the convergence of the data into their respective clusters is more accurate by using both WCD and ICD measurement metrics. The algorithm is also better at clustering the outliers into their true clusters as opposed to the traditional k means method. We also address some interesting possible research topics that reveal themselves as we answer the questions we initially set out to address.

---

### High-Accuracy List-Decodable Mean Estimation

Authors: Ziyun Chen, Spencer Compton, Daniel Kane, Jerry Li
Published: 2025-11-21
Categories: cs.LG, cs.DS, stat.ML
arXiv: https://arxiv.org/abs/2511.17822v1

In list-decodable learning, we are given a set of data points such that an $α$-fraction of these points come from a nice distribution $D$, for some small $α\ll 1$, and the goal is to output a short list of candidate solutions, such that at least one element of this list recovers some non-trivial information about $D$. By now, there is a large body of work on this topic; however, while many algorithms can achieve optimal list size in terms of $α$, all known algorithms must incur error which decays, in some cases quite poorly, with $1 / α$. In this paper, we ask if this is inherent: is it possible to trade off list size with accuracy in list-decodable learning? More formally, given $ε> 0$, can we can output a slightly larger list in terms of $α$ and $ε$, but so that one element of this list has error at most $ε$ with the ground truth? We call this problem high-accuracy list-decodable learning. Our main result is that non-trivial high-accuracy guarantees, both information-theoretically and algorithmically, are possible for the canonical setting of list-decodable mean estimation of identity-covariance Gaussians. Specifically, we demonstrate that there exists a list of candidate means of size at most $L = \exp \left( O\left( \tfrac{\log^2 1 / α}{ε^2} \right)\right)$ so that one of the elements of this list has $\ell_2$ distance at most $ε$ to the true mean. We also design an algorithm that outputs such a list with runtime and sample complexity $n = d^{O(\log L)} + \exp \exp (\widetilde{O}(\log L))$. We do so by demonstrating a completely novel proof of identifiability, as well as a new algorithmic way of leveraging this proof without the sum-of-squares hierarchy, which may be of independent technical interest.

---

### APRIL: Annotations for Policy evaluation with Reliable Inference from LLMs

Authors: Aishwarya Mandyam, Kalyani Limaye, Barbara E. Engelhardt, Emily Alsentzer
Published: 2025-11-21
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.17818v1

Off-policy evaluation (OPE) estimates the value of a contextual bandit policy prior to deployment. As such, OPE plays a critical role in ensuring safety in high-stakes domains such as healthcare. However, standard OPE approaches are limited by the size and coverage of the behavior dataset. While previous work has explored using expert-labeled counterfactual annotations to enhance dataset coverage, obtaining such annotations is expensive, limiting the scalability of prior approaches. We propose leveraging large language models (LLMs) to generate counterfactual annotations for OPE in medical domains. Our method uses domain knowledge to guide LLMs in predicting how key clinical features evolve under alternate treatments. These predicted features can then be transformed using known reward functions to create counterfactual annotations. We first evaluate the ability of several LLMs to predict clinical features across two patient subsets in MIMIC-IV, finding that state-of-the-art LLMs achieve comparable performance. Building on this capacity to predict clinical features, we generate LLM-based counterfactual annotations and incorporate them into an OPE estimator. Our empirical results analyze the benefits of counterfactual annotations under varying degrees of shift between the behavior and target policies. We find that in most cases, the LLM-based counterfactual annotations significantly improve OPE estimates up to a point. We provide an entropy-based metric to identify when additional annotations cease to be useful. Our results demonstrate that LLM-based counterfactual annotations offer a scalable approach for addressing coverage limitations in healthcare datasets, enabling safer deployment of decision-making policies in clinical settings.

---

### Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberation

Authors: Scott Merrill, Shashank Srivastava
Published: 2025-11-21
Categories: cs.CL, cs.AI, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2511.17813v3

LLM-based simulations can enable controlled studies of civic deliberation, but current systems lack speaker-attributed data and methods for evaluating long-form institutional behavior. ASR transcripts typically use anonymous labels such as $Speaker\_1$, preventing models from learning stable participant behavior across meetings. We present a reproducible pipeline that converts public Zoom recordings into speaker-attributed transcripts enriched with persona profiles, topics, and pragmatic "action tags" such as $(propose\_motion)$. Using this pipeline, we release three public datasets of government deliberation (Appellate Court hearings, School Board meetings, and Municipal Council sessions) and fine-tune LLM personas on this action-aware data. We evaluate simulations along four dimensions: persona fidelity, persona consistency, institutional fidelity, and behavioral coherence. Action-aware fine-tuning cuts perplexity by 67%, doubles classifier-based persona fidelity, increases vote attempts by up to $3.6\times$, and improves deliberative responsiveness by up to 70%. Human evaluations show that simulated excerpts are often hard to distinguish from real deliberations, indicating a practical foundation for data-grounded civic simulation studies.

---

### Score-Regularized Joint Sampling with Importance Weights for Flow Matching

Authors: Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei, Truong Nguyen
Published: 2025-11-21
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.17812v3

Flow matching models effectively represent complex distributions, yet estimating expectations of functions of their outputs remains challenging under limited sampling budgets. Independent sampling often yields high-variance estimates, especially when rare but high-impact outcomes dominate the expectation. We propose a non-IID sampling framework that jointly draws multiple samples to cover diverse, salient regions of a flow matching model's generative distribution. To balance diversity and quality, we introduce a score-based regularization for the diversity mechanism (SR), which uses the score function, i.e., the gradient of the log probability, to ensure samples are pushed apart within high-density regions of the data manifold, mitigating off-manifold drift. To enable unbiased estimation when desired, we further develop an approach for importance weighting of non-IID flow samples by learning a residual velocity field that reproduces the marginal distribution of the non-IID samples and by evolving importance weights along trajectories. Empirically, our method produces diverse, high-quality samples and accurate importance-weight estimates and debiased expectation estimates, advancing the reliable characterization of flow matching model outputs.

---

### Adaptive Layer-Wise Transformations for Post-Training Quantization of Large Language Models

Authors: Cuong Pham, Hoang Anh Dung, Cuong C. Nguyen, Trung Le, Gustavo Carneiro, Jianfei Cai, Thanh-Toan Do
Published: 2025-11-21
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.17809v1

Large language models require significant computational resources for deployment, making quantization essential for practical applications. However, the main obstacle to effective quantization lies in systematic outliers in activations and weights, which cause substantial LLM performance degradation, especially at low-bit settings. While existing transformation-based methods like affine and rotation transformations successfully mitigate outliers, they apply the homogeneous transformation setting, i.e., using the same transformation types across all layers, ignoring the heterogeneous distribution characteristics within LLMs. In this paper, we propose an adaptive transformation selection framework that systematically determines optimal transformations on a per-layer basis. To this end, we first formulate transformation selection as a differentiable optimization problem to achieve the accurate transformation type for each layer. However, searching for optimal layer-wise transformations for every model is computationally expensive. To this end, we establish the connection between weight distribution kurtosis and accurate transformation type. Specifically, we propose an outlier-guided layer selection method using robust $z$-score normalization that achieves comparable performance to differentiable search with significantly reduced overhead. Comprehensive experiments on LLaMA family models demonstrate that our adaptive approach consistently outperforms the widely-used fixed transformation settings. For example, our method achieves an improvement of up to 4.58 perplexity points and a 2.11% gain in average six-task zero-shot accuracy under aggressive W3A3K2V2 quantization settings for the LLaMA-3-8B model compared to the current best existing method, FlatQuant, demonstrating the necessity of heterogeneous transformation selection for optimal LLM quantization.

---

### PoETa v2: Toward More Robust Evaluation of Large Language Models in Portuguese

Authors: Thales Sales Almeida, Ramon Pires, Hugo Abonizio, Rodrigo Nogueira, Hélio Pedrini
Published: 2025-11-21
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.17808v2

Large Language Models (LLMs) exhibit significant variations in performance across linguistic and cultural contexts, underscoring the need for systematic evaluation in diverse languages. In this work, we present the most extensive evaluation of LLMs for the Portuguese language to date. Leveraging our newly introduced PoETa v2 benchmark -- a comprehensive suite of over 40 tasks in Portuguese -- we assess more than 20 models covering a broad spectrum of training scales and computational resources. Our study reveals how computational investment and language-specific adaptation impact performance in Portuguese, while also analyzing performance gaps in comparison to equivalent tasks in English. Through this benchmark and analysis, PoETa v2 lays the groundwork for future research on Portuguese language modeling and evaluation. The benchmark is available at https://github.com/PoETaV2/PoETaV2.

---

### REXO: Indoor Multi-View Radar Object Detection via 3D Bounding Box Diffusion

Authors: Ryoma Yataka, Pu Perry Wang, Petros Boufounos, Ryuhei Takahashi
Published: 2025-11-21
Categories: cs.CV, cs.AI, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2511.17806v2

Multi-view indoor radar perception has drawn attention due to its cost-effectiveness and low privacy risks. Existing methods often rely on {implicit} cross-view radar feature association, such as proposal pairing in RFMask or query-to-feature cross-attention in RETR, which can lead to ambiguous feature matches and degraded detection in complex indoor scenes. To address these limitations, we propose \textbf{REXO} (multi-view Radar object dEtection with 3D bounding boX diffusiOn), which lifts the 2D bounding box (BBox) diffusion process of DiffusionDet into the 3D radar space. REXO utilizes these noisy 3D BBoxes to guide an {explicit} cross-view radar feature association, enhancing the cross-view radar-conditioned denoising process. By accounting for prior knowledge that the person is in contact with the ground, REXO reduces the number of diffusion parameters by determining them from this prior. Evaluated on two open indoor radar datasets, our approach surpasses state-of-the-art methods by a margin of +4.22 AP on the HIBER dataset and +11.02 AP on the MMVR dataset. The REXO implementation is available at https://github.com/merlresearch/radar-bbox-diffusion.

---

### A Stitch in Time: Learning Procedural Workflow via Self-Supervised Plackett-Luce Ranking

Authors: Chengan Che, Chao Wang, Xinyue Chen, Sophia Tsoka, Luis C. Garcia-Peraza-Herrera
Published: 2025-11-21
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.17805v2

Procedural activities, ranging from routine cooking to complex surgical operations, are highly structured sequences of actions performed in a specific temporal order. Despite the success of current self-supervised learning (SSL) methods on static images and short clips, these models often overlook the underlying sequential structure of such activities. We expose this lack of procedural awareness with a motivating experiment: models pretrained on forward and time-reversed sequences produce highly similar features, confirming that their representations are blind to the underlying procedural order. To address this shortcoming, we propose PL-Stitch, a self-supervised framework that harnesses the inherent temporal order of video frames as a powerful supervisory signal. Our approach integrates two novel probabilistic objectives based on the Plackett-Luce (PL) model. The primary PL objective trains the model to sort sampled frames chronologically, compelling it to learn the global workflow progression. The secondary objective, a spatio-temporal jigsaw loss, complements the learning by capturing fine-grained, cross-frame object correspondences. Our approach consistently achieves superior performance across five surgical and cooking benchmarks. Specifically, PL-Stitch yields significant gains in surgical phase recognition (e.g., +11.4 pp in k-NN accuracy on Cholec80) and cooking action segmentation (e.g., +5.7 pp in linear probing accuracy on Breakfast), demonstrating its effectiveness for procedural video representation learning. Code and models are available at https://github.com/visurg-ai/PL-Stitch.

---

### Pillar-0: A New Frontier for Radiology Foundation Models

Authors: Kumar Krishna Agrawal, Longchao Liu, Long Lian, Michael Nercessian, Natalia Harguindeguy, Yufu Wu, Peter Mikhael, Gigin Lin, Lecia V. Sequist, Florian Fintelmann, Trevor Darrell, Yutong Bai et al.
Published: 2025-11-21
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.17803v1

Radiology plays an integral role in modern medicine, yet rising imaging volumes have far outpaced workforce growth. Foundation models offer a path toward assisting with the full spectrum of radiology tasks, but existing medical models remain limited: they process volumetric CT and MRI as low-fidelity 2D slices, discard critical grayscale contrast information, and lack evaluation frameworks that reflect real clinical practice. We introduce Pillar-0, a radiology foundation model pretrained on 42,990 abdomen-pelvis CTs, 86,411 chest CTs, 14,348 head CTs, and 11,543 breast MRIs from a large academic center, together with RATE, a scalable framework that extracts structured labels for 366 radiologic findings with near-perfect accuracy using LLMs. Across internal test sets of 14,230 abdomen-pelvis CTs, 10,646 chest CTs, 4,906 head CTs, and 1,585 breast MRIs, Pillar-0 establishes a new performance frontier, achieving mean AUROCs of 86.4, 88.0, 90.1, and 82.9, outperforming MedGemma (Google), MedImageInsight (Microsoft), Lingshu (Alibaba), and Merlin (Stanford) by 7.8-15.8 AUROC points and ranking best in 87.2\% (319/366) tasks. Pillar-0 similarly outperforms all baselines in an external validation on the Stanford Abdominal CT dataset, including Merlin (82.2 vs 80.6 AUROC). Pillar-0 extends to tasks beyond its pretraining, such as long-horizon lung cancer risk prediction, where it improves upon the state-of-the-art Sybil by 3.0 C-index points on NLST, and generalizes with gains of 5.9 (MGH) and 1.9 (CGMH). In brain hemorrhage detection, Pillar-0 obtained a >95 AUROC when using only 1/20th of the data of the next most sample efficient baseline. Pillar-0 and RATE together provide an open, clinically rigorous foundation for building high-performance radiology systems, enabling applications that were previously infeasible due to computational, data, and evaluation constraints.

---

### Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models

Authors: Cuong Pham, Hoang Anh Dung, Cuong C. Nguyen, Trung Le, Gustavo Carneiro, Thanh-Toan Do
Published: 2025-11-21
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.17801v1

Large language models (LLMs) have significantly advanced natural language processing, but their massive parameter counts create substantial computational and memory challenges during deployment. Post-training quantization (PTQ) has emerged as a promising approach to mitigate these challenges with minimal overhead. While existing PTQ methods can effectively quantize LLMs, they experience substantial accuracy loss at extremely low bit-widths, primarily due to high-impact parameters that significantly influence quantization performance. Several approaches address these issues by identifying and retaining the high-impact parameters in FP16 format. However, they apply fixed ratios of high-impact parameters across all layers, overlooking layer-wise sensitivity variations. In this paper, we propose a quadratic optimization framework that determines layer-specific ratios of high-impact parameters while considering inter-layer dependencies. We quantize high-impact parameters to moderate bit-widths, which often result in negligible performance degradation in quantized LLMs, while the remaining parameters can be quantized to extremely low bit-widths. Under the same resource-constrained budget, this allows for preserving more high-impact parameters than methods that keep selecting a few in FP16 format. Additionally, the proposed framework allows us to leverage an advanced quantization method that often requires extensive learnable parameters solely for high-impact parameters, while applying a computationally efficient method to the rest. Our approach achieves an effective balance between computational efficiency and model accuracy while maintaining high performance compared to state-of-the-art methods.

---

### Semi-Supervised Federated Multi-Label Feature Selection with Fuzzy Information Measures

Authors: Afsaneh Mahanipour, Hana Khamfroush
Published: 2025-11-21
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.17796v1

Multi-label feature selection (FS) reduces the dimensionality of multi-label data by removing irrelevant, noisy, and redundant features, thereby boosting the performance of multi-label learning models. However, existing methods typically require centralized data, which makes them unsuitable for distributed and federated environments where each device/client holds its own local dataset. Additionally, federated methods often assume that clients have labeled data, which is unrealistic in cases where clients lack the expertise or resources to label task-specific data. To address these challenges, we propose a Semi-Supervised Federated Multi-Label Feature Selection method, called SSFMLFS, where clients hold only unlabeled data, while the server has limited labeled data. SSFMLFS adapts fuzzy information theory to a federated setting, where clients compute fuzzy similarity matrices and transmit them to the server, which then calculates feature redundancy and feature-label relevancy degrees. A feature graph is constructed by modeling features as vertices, assigning relevancy and redundancy degrees as vertex weights and edge weights, respectively. PageRank is then applied to rank the features by importance. Extensive experiments on five real-world datasets from various domains, including biology, images, music, and text, demonstrate that SSFMLFS outperforms other federated and centralized supervised and semi-supervised approaches in terms of three different evaluation metrics in non-IID data distribution setting.

---

### Attention Guided Alignment in Efficient Vision-Language Models

Authors: Shweta Mahajan, Hoang Le, Hyojin Park, Farzad Farhadzadeh, Munawar Hayat, Fatih Porikli
Published: 2025-11-21
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.17793v1

Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs) to integrate visual and textual information. This paper presents a comprehensive analysis of attention patterns in efficient VLMs, revealing that concatenation-based architectures frequently fail to distinguish between semantically matching and non-matching image-text pairs. This is a key factor for object hallucination in these models. To address this, we introduce Attention-Guided Efficient Vision-Language Models (AGE-VLM), a novel framework that enhances visual grounding through interleaved cross-attention layers to instill vision capabilities in pretrained small language models. This enforces in VLM the ability "look" at the correct image regions by leveraging spatial knowledge distilled from the Segment Anything Model (SAM), significantly reducing hallucination. We validate our approach across different vision-centric benchmarks where our method is better or comparable to prior work on efficient VLMs. Our findings provide valuable insights for future research aimed at achieving enhanced visual and linguistic understanding in VLMs.

---

### Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?

Authors: Dingrui Wang, Zhihao Liang, Hongyuan Ye, Zhexiao Sun, Zhaowei Lu, Yuchen Zhang, Yuyu Zhao, Yuan Gao, Marvin Seegert, Finn Schäfer, Haotong Qin, Wei Li et al.
Published: 2025-11-21
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2511.17792v2

While recent video world models can generate highly realistic videos, their ability to perform semantic reasoning and planning remains unclear and unquantified. We introduce Target-Bench, the first benchmark that enables comprehensive evaluation of video world models' semantic reasoning, spatial estimation, and planning capabilities. Target-Bench provides 450 robot-collected scenarios spanning 47 semantic categories, with SLAM-based trajectories serving as motion tendency references. Our benchmark reconstructs motion from generated videos with a metric scale recovery mechanism, enabling the evaluation of planning performance with five complementary metrics that focus on target-approaching capability and directional consistency. Our evaluation result shows that the best off-the-shelf model achieves only a 0.341 overall score, revealing a significant gap between realistic visual generation and semantic reasoning in current video world models. Furthermore, we demonstrate that fine-tuning process on a relatively small real-world robot dataset can significantly improve task-level planning performance.

---

### Physical Reinforcement Learning

Authors: Sam Dillavou, Shruti Mishra
Published: 2025-11-21
Categories: cs.LG, cond-mat.dis-nn
arXiv: https://arxiv.org/abs/2511.17789v1

Digital computers are power-hungry and largely intolerant of damaged components, making them potentially difficult tools for energy-limited autonomous agents in uncertain environments. Recently developed Contrastive Local Learning Networks (CLLNs) - analog networks of self-adjusting nonlinear resistors - are inherently low-power and robust to physical damage, but were constructed to perform supervised learning. In this work we demonstrate success on two simple RL problems using Q-learning adapted for simulated CLLNs. Doing so makes explicit the components (beyond the network being trained) required to enact various tools in the RL toolbox, some of which (policy function and value function) are more natural in this system than others (replay buffer). We discuss assumptions such as the physical safety that digital hardware requires, CLLNs can forgo, and biological systems cannot rely on, and highlight secondary goals that are important in biology and trainable in CLLNs, but make little sense in digital computers.

---

### Data-Driven Predictive Modeling of Microfluidic Cancer Cell Separation Using a Deterministic Lateral Displacement Device

Authors: Elizabeth Chen, Andrew Lee, Tanbir Sarowar, Xiaolin Chen
Published: 2025-11-21
Categories: cs.LG, physics.med-ph, q-bio.QM
arXiv: https://arxiv.org/abs/2511.17787v1

Deterministic Lateral Displacement (DLD) devices are widely used in microfluidics for label-free, size-based separation of particles and cells, with particular promise in isolating circulating tumor cells (CTCs) for early cancer diagnostics. This study focuses on the optimization of DLD design parameters, such as row shift fraction, post size, and gap distance, to enhance the selective isolation of lung cancer cells based on their physical properties. To overcome the challenges of rare CTC detection and reduce reliance on computationally intensive simulations, machine learning models including gradient boosting, k-nearest neighbors, random forest, and multilayer perceptron (MLP) regressors are employed. Trained on a large, numerically validated dataset, these models predict particle trajectories and identify optimal device configurations, enabling high-throughput and cost-effective DLD design. Beyond trajectory prediction, the models aid in isolating critical design variables, offering a systematic, data-driven framework for automated DLD optimization. This integrative approach advances the development of scalable and precise microfluidic systems for cancer diagnostics, contributing to the broader goals of early detection and personalized medicine.

---

### A Variance-Based Analysis of Sample Complexity for Grid Coverage

Authors: Lyu Yuhuan
Published: 2025-11-21
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.17784v2

Verifying uniform conditions over continuous spaces through random sampling is fundamental in machine learning and control theory, yet classical coverage analyses often yield conservative bounds, particularly at small failure probabilities. We study uniform random sampling on the $d$-dimensional unit hypercube and analyze the number of uncovered subcubes after discretization. By applying a concentration inequality to the uncovered-count statistic, we derive a sample complexity bound with a logarithmic dependence on the failure probability ($δ$), i.e., $M =O( \tilde{C}\ln(\frac{2\tilde{C}}δ))$, which contrasts sharply with the classical linear $1/δ$ dependence. Under standard Lipschitz and uniformity assumptions, we present a self-contained derivation and compare our result with classical coupon-collector rates. Numerical studies across dimensions, precision levels, and confidence targets indicate that our bound tracks practical coverage requirements more tightly and scales favorably as $δ\to 0$. Our findings offer a sharper theoretical tool for algorithms that rely on grid-based coverage guarantees, enabling more efficient sampling, especially in high-confidence regimes.

---

### Variational Estimators for Node Popularity Models

Authors: Jony Karki, Dongzhou Huang, Yunpeng Zhao
Published: 2025-11-21
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.17783v1

Node popularity is recognized as a key factor in modeling real-world networks, capturing heterogeneity in connectivity across communities. This concept is equally important in bipartite networks, where nodes in different partitions may exhibit varying popularity patterns, motivating models such as the Two-Way Node Popularity Model (TNPM). Existing methods, such as the Two-Stage Divided Cosine (TSDC) algorithm, provide a scalable estimation approach but may have limitations in terms of accuracy or applicability across different types of networks. In this paper, we develop a computationally efficient and theoretically justified variational expectation-maximization (VEM) framework for the TNPM. We establish label consistency for the estimated community assignments produced by the proposed variational estimator in bipartite networks. Through extensive simulation studies, we show that our method achieves superior estimation accuracy across a range of bipartite as well as undirected networks compared to existing algorithms. Finally, we evaluate our method on real-world bipartite and undirected networks, further demonstrating its practical effectiveness and robustness.

---

### Smoothed Agnostic Learning of Halfspaces over the Hypercube

Authors: Yiwen Kou, Raghu Meka
Published: 2025-11-21
Categories: cs.LG, cs.CC, stat.ML
arXiv: https://arxiv.org/abs/2511.17782v1

Agnostic learning of Boolean halfspaces is a fundamental problem in computational learning theory, but it is known to be computationally hard even for weak learning. Recent work (CKKMK24) proposed smoothed analysis as a way to bypass such hardness, but existing frameworks rely on additive Gaussian perturbations, making them unsuitable for discrete domains. We introduce a new smoothed agnostic learning framework for Boolean inputs, where perturbations are modeled via random bit flips. This defines a natural discrete analogue of smoothed optimality generalizing the Gaussian case. Under strictly subexponential assumptions on the input distribution, we give an efficient algorithm for learning halfspaces in this model, with runtime and sample complexity approximately n raised to a poly(1/(sigma * epsilon)) factor. Previously, such algorithms were known only with strong structural assumptions for the discrete hypercube, for example, independent coordinates or symmetric distributions. Our result provides the first computationally efficient guarantee for smoothed agnostic learning of halfspaces over the Boolean hypercube, bridging the gap between worst-case intractability and practical learnability in discrete settings.

---

### PrismSSL: One Interface, Many Modalities; A Single-Interface Library for Multimodal Self-Supervised Learning

Authors: Melika Shirian, Kianoosh Vadaei, Kian Majlessi, Audrina Ebrahimi, Peyman Adibi, Hossein Karshenas
Published: 2025-11-21
Categories: cs.LG, cs.MM
arXiv: https://arxiv.org/abs/2511.17776v2

We present PrismSSL, a Python library that unifies state-of-the-art self-supervised learning (SSL) methods across audio, vision, graphs, and cross-modal settings in a single, modular codebase. The goal of the demo is to show how researchers and practitioners can: (i) install, configure, and run pretext training with a few lines of code; (ii) reproduce compact benchmarks; and (iii) extend the framework with new modalities or methods through clean trainer and dataset abstractions. PrismSSL is packaged on PyPI, released under the MIT license, integrates tightly with HuggingFace Transformers, and provides quality-of-life features such as distributed training in PyTorch, Optuna-based hyperparameter search, LoRA fine-tuning for Transformer backbones, animated embedding visualizations for sanity checks, Weights & Biases logging, and colorful, structured terminal logs for improved usability and clarity. In addition, PrismSSL offers a graphical dashboard - built with Flask and standard web technologies - that enables users to configure and launch training pipelines with minimal coding. The artifact (code and data recipes) will be publicly available and reproducible.

---

### Episodic Memory in Agentic Frameworks: Suggesting Next Tasks

Authors: Sandro Rama Fiorini, Leonardo G. Azevedo, Raphael M. Thiago, Valesca M. de Sousa, Anton B. Labate, Viviane Torres da Silva
Published: 2025-11-21
Categories: cs.MA, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.17775v1

Agentic frameworks powered by Large Language Models (LLMs) can be useful tools in scientific workflows by enabling human-AI co-creation. A key challenge is recommending the next steps during workflow creation without relying solely on LLMs, which risk hallucination and require fine-tuning with scarce proprietary data. We propose an episodic memory architecture that stores and retrieves past workflows to guide agents in suggesting plausible next tasks. By matching current workflows with historical sequences, agents can recommend steps based on prior patterns.

---

### Weighted Birkhoff Averages Accelerate Data-Driven Methods

Authors: Maria Bou-Sakr-El-Tayar, Jason J. Bramburger, Matthew J. Colbrook
Published: 2025-11-21
Categories: math.DS, cs.LG, nlin.CD
arXiv: https://arxiv.org/abs/2511.17772v2

Many data-driven algorithms in dynamical systems rely on ergodic averages that converge painfully slowly. One simple idea changes this: taper the ends. Weighted Birkhoff averages can converge much faster (sometimes superpolynomially, even exponentially) and can be incorporated seamlessly into existing methods. We demonstrate this with five weighted algorithms: weighted Dynamic Mode Decomposition (wtDMD), weighted Extended DMD (wtEDMD), weighted Sparse Identification of Nonlinear Dynamics (wtSINDy), weighted spectral measure estimation, and weighted diffusion forecasting. Across examples ranging from fluid flows to El Niño data, the message is clear: weighting costs nothing, is easy to implement, and often delivers markedly better results from the same data.

---

### Deepfake Geography: Detecting AI-Generated Satellite Images

Authors: Mansur Yerzhanuly
Published: 2025-11-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.17766v1

The rapid advancement of generative models such as StyleGAN2 and Stable Diffusion poses a growing threat to the authenticity of satellite imagery, which is increasingly vital for reliable analysis and decision-making across scientific and security domains. While deepfake detection has been extensively studied in facial contexts, satellite imagery presents distinct challenges, including terrain-level inconsistencies and structural artifacts. In this study, we conduct a comprehensive comparison between Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) for detecting AI-generated satellite images. Using a curated dataset of over 130,000 labeled RGB images from the DM-AER and FSI datasets, we show that ViTs significantly outperform CNNs in both accuracy (95.11 percent vs. 87.02 percent) and overall robustness, owing to their ability to model long-range dependencies and global semantic structures. We further enhance model transparency using architecture-specific interpretability methods, including Grad-CAM for CNNs and Chefer's attention attribution for ViTs, revealing distinct detection behaviors and validating model trustworthiness. Our results highlight the ViT's superior performance in detecting structural inconsistencies and repetitive textural patterns characteristic of synthetic imagery. Future work will extend this research to multispectral and SAR modalities and integrate frequency-domain analysis to further strengthen detection capabilities and safeguard satellite imagery integrity in high-stakes applications.

---

### LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation

Authors: Darren Chiu, Zhehui Huang, Ruohai Ge, Gaurav S. Sukhatme
Published: 2025-11-21
Categories: cs.RO, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2511.17765v1

Nano-UAV teams offer great agility yet face severe navigation challenges due to constrained onboard sensing, communication, and computation. Existing approaches rely on high-resolution vision or compute-intensive planners, rendering them infeasible for these platforms. We introduce LEARN, a lightweight, two-stage safety-guided reinforcement learning (RL) framework for multi-UAV navigation in cluttered spaces. Our system combines low-resolution Time-of-Flight (ToF) sensors and a simple motion planner with a compact, attention-based RL policy. In simulation, LEARN outperforms two state-of-the-art planners by $10\%$ while using substantially fewer resources. We demonstrate LEARN's viability on six Crazyflie quadrotors, achieving fully onboard flight in diverse indoor and outdoor environments at speeds up to $2.0 m/s$ and traversing $0.2 m$ gaps.

---

### When Active Learning Fails, Uncalibrated Out of Distribution Uncertainty Quantification Might Be the Problem

Authors: Ashley S. Dale, Kangming Li, Brian DeCost, Hao Wan, Yuchen Han, Yao Fehlis, Jason Hattrick-Simpers
Published: 2025-11-21
Categories: cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2511.17760v1

Efficiently and meaningfully estimating prediction uncertainty is important for exploration in active learning campaigns in materials discovery, where samples with high uncertainty are interpreted as containing information missing from the model. In this work, the effect of different uncertainty estimation and calibration methods are evaluated for active learning when using ensembles of ALIGNN, eXtreme Gradient Boost, Random Forest, and Neural Network model architectures. We compare uncertainty estimates from ALIGNN deep ensembles to loss landscape uncertainty estimates obtained for solubility, bandgap, and formation energy prediction tasks. We then evaluate how the quality of the uncertainty estimate impacts an active learning campaign that seeks model generalization to out-of-distribution data. Uncertainty calibration methods were found to variably generalize from in-domain data to out-of-domain data. Furthermore, calibrated uncertainties were generally unsuccessful in reducing the amount of data required by a model to improve during an active learning campaign on out-of-distribution data when compared to random sampling and uncalibrated uncertainties. The impact of poor-quality uncertainty persists for random forest and eXtreme Gradient Boosting models trained on the same data for the same tasks, indicating that this is at least partially intrinsic to the data and not due to model capacity alone. Analysis of the target, in-distribution uncertainty, out-of-distribution uncertainty, and training residual distributions suggest that future work focus on understanding empirical uncertainties in the feature input space for cases where ensemble prediction variances do not accurately capture the missing information required for the model to generalize.

---

### Latent Dirichlet Transformer VAE for Hyperspectral Unmixing with Bundled Endmembers

Authors: Giancarlo Giannetti, Faisal Z. Qureshi
Published: 2025-11-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.17757v1

Hyperspectral images capture rich spectral information that enables per-pixel material identification; however, spectral mixing often obscures pure material signatures. To address this challenge, we propose the Latent Dirichlet Transformer Variational Autoencoder (LDVAE-T) for hyperspectral unmixing. Our model combines the global context modeling capabilities of transformer architectures with physically meaningful constraints imposed by a Dirichlet prior in the latent space. This prior naturally enforces the sum-to-one and non-negativity conditions essential for abundance estimation, thereby improving the quality of predicted mixing ratios. A key contribution of LDVAE-T is its treatment of materials as bundled endmembers, rather than relying on fixed ground truth spectra. In the proposed method our decoder predicts, for each endmember and each patch, a mean spectrum together with a structured (segmentwise) covariance that captures correlated spectral variability. Reconstructions are formed by mixing these learned bundles with Dirichlet-distributed abundances garnered from a transformer encoder, allowing the model to represent intrinsic material variability while preserving physical interpretability. We evaluate our approach on three benchmark datasets, Samson, Jasper Ridge, and HYDICE Urban and show that LDVAE-T consistently outperforms state-of-the-art models in abundance estimation and endmember extraction, as measured by root mean squared error and spectral angle distance, respectively.

---

### CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentation

Authors: Prantik Howlader, Hoang Nguyen-Canh, Srijan Das, Jingyi Xu, Hieu Le, Dimitris Samaras
Published: 2025-11-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.17755v1

Reasoning segmentation seeks pixel-accurate masks for targets referenced by complex, often implicit instructions, requiring context-dependent reasoning over the scene. Recent multimodal language models have advanced instruction following segmentation, yet generalization remains limited. The key bottleneck is the high cost of curating diverse, high-quality pixel annotations paired with rich linguistic supervision leading to brittle performance under distribution shift. Therefore, we present CORA, a semi-supervised reasoning segmentation framework that jointly learns from limited labeled data and a large corpus of unlabeled images. CORA introduces three main components: 1) conditional visual instructions that encode spatial and contextual relationships between objects; 2) a noisy pseudo-label filter based on the consistency of Multimodal LLM's outputs across semantically equivalent queries; and 3) a token-level contrastive alignment between labeled and pseudo-labeled samples to enhance feature consistency. These components enable CORA to perform robust reasoning segmentation with minimal supervision, outperforming existing baselines under constrained annotation settings. CORA achieves state-of-the-art results, requiring as few as 100 labeled images on Cityscapes, a benchmark dataset for urban scene understanding, surpassing the baseline by $+2.3\%$. Similarly, CORA improves performance by $+2.4\%$ with only 180 labeled images on PanNuke, a histopathology dataset.

---