# Research Papers — 2025-11 · bundle page 144 of 197

> Full-text markdown of papers #7151–7200 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/144
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/143.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/145.md)

### Shocks Under Control: Taming Transonic Compressible Flow over an RAE2822 Airfoil with Deep Reinforcement Learning

Authors: Trishit Mondal, Ricardo Vinuesa, Ameya D. Jagtap
Published: 2025-11-10
Categories: physics.flu-dyn, cs.LG
arXiv: https://arxiv.org/abs/2511.07564v1

Active flow control of compressible transonic shock-boundary layer interactions over a two-dimensional RAE2822 airfoil at Re = 50,000 is investigated using deep reinforcement learning (DRL). The flow field exhibits highly unsteady dynamics, including complex shock-boundary layer interactions, shock oscillations, and the generation of Kutta waves from the trailing edge. A high-fidelity CFD solver, employing a fifth-order spectral discontinuous Galerkin scheme in space and a strong-stability-preserving Runge-Kutta (5,4) method in time, together with adaptive mesh refinement capability, is used to obtain the accurate flow field. Synthetic jet actuation is employed to manipulate these unsteady flow features, while the DRL agent autonomously discovers effective control strategies through direct interaction with high-fidelity compressible flow simulations. The trained controllers effectively mitigate shock-induced separation, suppress unsteady oscillations, and manipulate aerodynamic forces under transonic conditions. In the first set of experiments, aimed at both drag reduction and lift enhancement, the DRL-based control reduces the average drag coefficient by 13.78% and increases lift by 131.18%, thereby improving the lift-to-drag ratio by 121.52%, which underscores its potential for managing complex flow dynamics. In the second set, targeting drag reduction while maintaining lift, the DRL-based control achieves a 25.62% reduction in drag and a substantial 196.30% increase in lift, accompanied by markedly diminished oscillations. In this case, the lift-to-drag ratio improves by 220.26%.

---

### EvoPS: Evolutionary Patch Selection for Whole Slide Image Analysis in Computational Pathology

Authors: Saya Hashemian, Azam Asilian Bidgoli
Published: 2025-11-10
Categories: eess.IV, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.07560v1

In computational pathology, the gigapixel scale of Whole-Slide Images (WSIs) necessitates their division into thousands of smaller patches. Analyzing these high-dimensional patch embeddings is computationally expensive and risks diluting key diagnostic signals with many uninformative patches. Existing patch selection methods often rely on random sampling or simple clustering heuristics and typically fail to explicitly manage the crucial trade-off between the number of selected patches and the accuracy of the resulting slide representation. To address this gap, we propose EvoPS (Evolutionary Patch Selection), a novel framework that formulates patch selection as a multi-objective optimization problem and leverages an evolutionary search to simultaneously minimize the number of selected patch embeddings and maximize the performance of a downstream similarity search task, generating a Pareto front of optimal trade-off solutions. We validated our framework across four major cancer cohorts from The Cancer Genome Atlas (TCGA) using five pretrained deep learning models to generate patch embeddings, including both supervised CNNs and large self-supervised foundation models. The results demonstrate that EvoPS can reduce the required number of training patch embeddings by over 90% while consistently maintaining or even improving the final classification F1-score compared to a baseline that uses all available patches' embeddings selected through a standard extraction pipeline. The EvoPS framework provides a robust and principled method for creating efficient, accurate, and interpretable WSI representations, empowering users to select an optimal balance between computational cost and diagnostic performance.

---

### N-ReLU: Zero-Mean Stochastic Extension of ReLU

Authors: Md Motaleb Hossen Manik, Md Zabirul Islam, Ge Wang
Published: 2025-11-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.07559v1

Activation functions are fundamental for enabling nonlinear representations in deep neural networks. However, the standard rectified linear unit (ReLU) often suffers from inactive or "dead" neurons caused by its hard zero cutoff. To address this issue, we introduce N-ReLU (Noise-ReLU), a zero-mean stochastic extension of ReLU that replaces negative activations with Gaussian noise while preserving the same expected output. This expectation-aligned formulation maintains gradient flow in inactive regions and acts as an annealing-style regularizer during training. Experiments on the MNIST dataset using both multilayer perceptron (MLP) and convolutional neural network (CNN) architectures show that N-ReLU achieves accuracy comparable to or slightly exceeding that of ReLU, LeakyReLU, PReLU, GELU, and RReLU at moderate noise levels (sigma = 0.05-0.10), with stable convergence and no dead neurons observed. These results demonstrate that lightweight Gaussian noise injection offers a simple yet effective mechanism to enhance optimization robustness without modifying network structures or introducing additional parameters.

---

### LLM Optimization Unlocks Real-Time Pairwise Reranking

Authors: Jingyu Wu, Aditya Shrivastava, Jing Zhu, Alfy Samuel, Anoop Kumar, Daben Liu
Published: 2025-11-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.07555v1

Efficiently reranking documents retrieved from information retrieval (IR) pipelines to enhance overall quality of Retrieval-Augmented Generation (RAG) system remains an important yet challenging problem. Recent studies have highlighted the importance of Large Language Models (LLMs) in reranking tasks. In particular, Pairwise Reranking Prompting (PRP) has emerged as a promising plug-and-play approach due to its usability and effectiveness. However, the inherent complexity of the algorithm, coupled with the high computational demands and latency incurred due to LLMs, raises concerns about its feasibility in real-time applications. To address these challenges, this paper presents a focused study on pairwise reranking, demonstrating that carefully applied optimization methods can significantly mitigate these issues. By implementing these methods, we achieve a remarkable latency reduction of up to 166 times, from 61.36 seconds to 0.37 seconds per query, with an insignificant drop in performance measured by Recall@k. Our study highlights the importance of design choices that were previously overlooked, such as using smaller models, limiting the reranked set, using lower precision, reducing positional bias with one-directional order inference, and restricting output tokens. These optimizations make LLM-based reranking substantially more efficient and feasible for latency-sensitive, real-world deployments.

---

### LiveNeRF: Efficient Face Replacement Through Neural Radiance Fields Integration

Authors: Tung Vu, Hai Nguyen, Cong Tran
Published: 2025-11-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.07552v1

Face replacement technology enables significant advancements in entertainment, education, and communication applications, including dubbing, virtual avatars, and cross-cultural content adaptation. Our LiveNeRF framework addresses critical limitations of existing methods by achieving real-time performance (33 FPS) with superior visual quality, enabling practical deployment in live streaming, video conferencing, and interactive media. The technology particularly benefits content creators, educators, and individuals with speech impairments through accessible avatar communication. While acknowledging potential misuse in unauthorized deepfake creation, we advocate for responsible deployment with user consent verification and integration with detection systems to ensure positive societal impact while minimizing risks.

---

### FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models

Authors: Pukang Ye, Junwei Luo, Xiaolei Dong, Yunbo Yang
Published: 2025-11-10
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.07505v1

Data duplication within large-scale corpora often impedes large language models' (LLMs) performance and privacy. In privacy-concerned federated learning scenarios, conventional deduplication methods typically rely on trusted third parties to perform uniform deletion, risking loss of informative samples while introducing privacy vulnerabilities. To address these gaps, we propose Federated ReWeighting (FedRW), the first privacy-preserving framework, to the best of our knowledge, that performs soft deduplication via sample reweighting instead of deletion in federated LLM training, without assuming a trusted third party. At its core, FedRW proposes a secure, frequency-aware reweighting protocol through secure multi-party computation, coupled with a parallel orchestration strategy to ensure efficiency and scalability. During training, FedRW utilizes an adaptive reweighting mechanism with global sample frequencies to adjust individual loss contributions, effectively improving generalization and robustness. Empirical results demonstrate that FedRW outperforms the state-of-the-art method by achieving up to 28.78x speedup in preprocessing and approximately 11.42% improvement in perplexity, while offering enhanced security guarantees. FedRW thus establishes a new paradigm for managing duplication in federated LLM training.

---

### Tractable Instances of Bilinear Maximization: Implementing LinUCB on Ellipsoids

Authors: Raymond Zhang, Hédi Hadiji, Richard Combes
Published: 2025-11-10
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.07504v1

We consider the maximization of $x^\top θ$ over $(x,θ) \in \mathcal{X} \times Θ$, with $\mathcal{X} \subset \mathbb{R}^d$ convex and $Θ\subset \mathbb{R}^d$ an ellipsoid. This problem is fundamental in linear bandits, as the learner must solve it at every time step using optimistic algorithms. We first show that for some sets $\mathcal{X}$ e.g. $\ell_p$ balls with $p>2$, no efficient algorithms exist unless $\mathcal{P} = \mathcal{NP}$. We then provide two novel algorithms solving this problem efficiently when $\mathcal{X}$ is a centered ellipsoid. Our findings provide the first known method to implement optimistic algorithms for linear bandits in high dimensions.

---

### Biologically-Informed Hybrid Membership Inference Attacks on Generative Genomic Models

Authors: Asia Belfiore, Jonathan Passerat-Palmbach, Dmitrii Usynin
Published: 2025-11-10
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.07503v3

The increased availability of genetic data has transformed genomics research, but raised many privacy concerns regarding its handling due to its sensitive nature. This work explores the use of language models (LMs) for the generation of synthetic genetic mutation profiles, leveraging differential privacy (DP) for the protection of sensitive genetic data. We empirically evaluate the privacy guarantees of our DP modes by introducing a novel Biologically-Informed Hybrid Membership Inference Attack (biHMIA), which combines traditional black box MIA with contextual genomics metrics for enhanced attack power. Our experiments show that both small and large transformer GPT-like models are viable synthetic variant generators for small-scale genomics, and that our hybrid attack leads, on average, to higher adversarial success compared to traditional metric-based MIAs.

---

### Methodological Precedence in Health Tech: Why ML/Big Data Analysis Must Follow Basic Epidemiological Consistency. A Case Study

Authors: Marco Roccetti
Published: 2025-11-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.07500v2

The integration of advanced analytical tools, including Machine Learning (ML) and massive data processing, has revolutionized health research, promising unprecedented accuracy in diagnosis and risk prediction. However, the rigor of these complex methods is fundamentally dependent on the quality and integrity of the underlying datasets and the validity of their statistical design. We propose an emblematic case where advanced analysis (ML/Big Data) must necessarily be subsequent to the verification of basic methodological coherence and adherence to established medical protocols, such as the STROBE Statement. This study highlights a crucial cautionary principle: sophisticated analyses amplify, rather than correct, severe methodological flaws rooted in basic design choices, leading to misleading or contradictory findings. By applying simple, standard descriptive statistical methods and established national epidemiological benchmarks to a recently published cohort study on COVID-19 vaccine outcomes and severe adverse events, like cancer, we expose multiple, statistically irreconcilable paradoxes. These paradoxes, specifically the contradictory finding of an increased cancer incidence within an exposure subgroup, concurrent with a suppressed overall Crude Incidence Rate compared to national standards, definitively invalidate the reported risk of increased cancer in the total population. We demonstrate that the observed effects are mathematical artifacts stemming from an uncorrected selection bias in the cohort construction. This analysis serves as a robust reminder that even the most complex health studies must first pass the test of basic epidemiological consistency before any conclusion drawn from subsequent advanced statistical modeling can be considered valid or publishable.

---

### Toward the Frontiers of Reliable Diffusion Sampling via Adversarial Sinkhorn Attention Guidance

Authors: Kwanyoung Kim
Published: 2025-11-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.07499v1

Diffusion models have demonstrated strong generative performance when using guidance methods such as classifier-free guidance (CFG), which enhance output quality by modifying the sampling trajectory. These methods typically improve a target output by intentionally degrading another, often the unconditional output, using heuristic perturbation functions such as identity mixing or blurred conditions. However, these approaches lack a principled foundation and rely on manually designed distortions. In this work, we propose Adversarial Sinkhorn Attention Guidance (ASAG), a novel method that reinterprets attention scores in diffusion models through the lens of optimal transport and intentionally disrupt the transport cost via Sinkhorn algorithm. Instead of naively corrupting the attention mechanism, ASAG injects an adversarial cost within self-attention layers to reduce pixel-wise similarity between queries and keys. This deliberate degradation weakens misleading attention alignments and leads to improved conditional and unconditional sample quality. ASAG shows consistent improvements in text-to-image diffusion, and enhances controllability and fidelity in downstream applications such as IP-Adapter and ControlNet. The method is lightweight, plug-and-play, and improves reliability without requiring any model retraining.

---

### Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models

Authors: Xin Liu, Qiyang Song, Qihang Zhou, Haichao Du, Shaowen Xu, Wenbo Jiang, Weijuan Zhang, Xiaoqi Jia
Published: 2025-11-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.07498v2

Large language models (LLMs) increasingly support multilingual understanding and generation. Meanwhile, efforts to interpret their internal mechanisms have emerged, offering insights to enhance multilingual performance. While multi-head self-attention (MHA) has proven critical in many areas, its role in multilingual capabilities remains underexplored. In this work, we study the contribution of MHA in supporting multilingual processing in LLMs. We propose Language Attention Head Importance Scores (LAHIS), an effective and efficient method that identifies attention head importance for multilingual capabilities via a single forward and backward pass through the LLM. Applying LAHIS to Aya-23-8B, Llama-3.2-3B, and Mistral-7B-v0.1, we reveal the existence of both language-specific and language-general heads. Language-specific heads enable cross-lingual attention transfer to guide the model toward target language contexts and mitigate off-target language generation issue, contributing to addressing challenges in multilingual LLMs. We also introduce a lightweight adaptation that learns a soft head mask to modulate attention outputs over language heads, requiring only 20 tunable parameters to improve XQuAD accuracy. Overall, our work enhances both the interpretability and multilingual capabilities of LLMs from the perspective of MHA.

---

### Laplacian Score Sharpening for Mitigating Hallucination in Diffusion Models

Authors: Barath Chandran. C, Srinivas Anumasa, Dianbo Liu
Published: 2025-11-10
Categories: cs.CV, cs.AI, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.07496v1

Diffusion models, though successful, are known to suffer from hallucinations that create incoherent or unrealistic samples. Recent works have attributed this to the phenomenon of mode interpolation and score smoothening, but they lack a method to prevent their generation during sampling. In this paper, we propose a post-hoc adjustment to the score function during inference that leverages the Laplacian (or sharpness) of the score to reduce mode interpolation hallucination in unconditional diffusion models across 1D, 2D, and high-dimensional image data. We derive an efficient Laplacian approximation for higher dimensions using a finite-difference variant of the Hutchinson trace estimator. We show that this correction significantly reduces the rate of hallucinated samples across toy 1D/2D distributions and a high-dimensional image dataset. Furthermore, our analysis explores the relationship between the Laplacian and uncertainty in the score.

---

### Enabling Automatic Self-Talk Detection via Earables

Authors: Euihyeok Lee, Seonghyeon Kim, SangHun Im, Heung-Seon Oh, Seungwoo Kang
Published: 2025-11-10
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2511.07493v1

Self-talk-an internal dialogue that can occur silently or be spoken aloud-plays a crucial role in emotional regulation, cognitive processing, and motivation, yet has remained largely invisible and unmeasurable in everyday life. In this paper, we present MutterMeter, a mobile system that automatically detects vocalized self-talk from audio captured by earable microphones in real-world settings. Detecting self-talk is technically challenging due to its diverse acoustic forms, semantic and grammatical incompleteness, and irregular occurrence patterns, which differ fundamentally from assumptions underlying conventional speech understanding models. To address these challenges, MutterMeter employs a hierarchical classification architecture that progressively integrates acoustic, linguistic, and contextual information through a sequential processing pipeline, adaptively balancing accuracy and computational efficiency. We build and evaluate MutterMeter using a first-of-its-kind dataset comprising 31.1 hours of audio collected from 25 participants. Experimental results demonstrate that MutterMeter achieves robust performance with a macro-averaged F1 score of 0.84, outperforming conventional approaches, including LLM-based and speech emotion recognition models.

---

### Quantifying the Impact of CU: A Systematic Literature Review

Authors: Thomas Compton
Published: 2025-11-10
Categories: cs.DL, cs.CL
arXiv: https://arxiv.org/abs/2511.07491v1

Community Unionism has served as a pivotal concept in debates on trade union renewal since the early 2000s, yet its theoretical coherence and political significance remain unresolved. This article investigates why CU has gained such prominence -- not by testing its efficacy, but by mapping how it is constructed, cited, and contested across the scholarly literature. Using two complementary systematic approaches -- a citation network analysis of 114 documents and a thematic review of 18 core CU case studies -- I examine how CU functions as both an empirical descriptor and a normative ideal. The analysis reveals CU's dual genealogy: positioned by British scholars as an indigenous return to historic rank-and-file practices, yet structurally aligned with transnational social movement unionism. Thematic coding shows near-universal emphasis on coalition-building and alliances, but deep ambivalence toward class politics. This tension suggests CU's significance lies less in operationalising a new union model, and more in managing contradictions -- between workplace and community, leadership and rank-and-file, reform and radicalism -- within a shrinking labour movement.

---

### Provably Efficient Sample Complexity for Robust CMDP

Authors: Sourav Ganguly, Arnob Ghosh
Published: 2025-11-10
Categories: cs.LG, eess.SY, stat.ML
arXiv: https://arxiv.org/abs/2511.07486v1

We study the problem of learning policies that maximize cumulative reward while satisfying safety constraints, even when the real environment differs from a simulator or nominal model. We focus on robust constrained Markov decision processes (RCMDPs), where the agent must maximize reward while ensuring cumulative utility exceeds a threshold under the worst-case dynamics within an uncertainty set. While recent works have established finite-time iteration complexity guarantees for RCMDPs using policy optimization, their sample complexity guarantees remain largely unexplored. In this paper, we first show that Markovian policies may fail to be optimal even under rectangular uncertainty sets unlike the {\em unconstrained} robust MDP. To address this, we introduce an augmented state space that incorporates the remaining utility budget into the state representation. Building on this formulation, we propose a novel Robust constrained Value iteration (RCVI) algorithm with a sample complexity of $\mathcal{\tilde{O}}(|S||A|H^5/ε^2)$ achieving at most $ε$ violation using a generative model where $|S|$ and $|A|$ denote the sizes of the state and action spaces, respectively, and $H$ is the episode length. To the best of our knowledge, this is the {\em first sample complexity guarantee} for RCMDP. Empirical results further validate the effectiveness of our approach.

---

### Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs

Authors: Zhongyang Li, Ziyue Li, Tianyi Zhou
Published: 2025-11-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.07419v2

Sparse Mixture-of-Experts (MoE) have been widely adopted in recent large language models since it can efficiently scale up the model capability without increasing the inference cost. However, evaluations on broad downstream tasks reveal a consistent suboptimality of the routers in existing MoE LLMs, which results in a severe performance gap (e.g., 10-20% in accuracy) to the optimal routing. In this paper, we show that aligning the manifold of routing weights with that of task embedding can effectively reduce the gap and improve MoE LLMs' generalization performance. Our method, "Routing Manifold Alignment (RoMA)", introduces an additional manifold regularization term in the post-training objective and only requires lightweight finetuning of routers (with other parameters frozen). Specifically, the regularization encourages the routing weights of each sample to be close to those of its successful neighbors (whose routing weights lead to correct answers) in a task embedding space. Consequently, samples targeting similar tasks will share similar expert choices across layers. Building such bindings between tasks and experts over different samples is essential to achieve better generalization. Moreover, RoMA demonstrates the advantage of unifying the task understanding (by embedding models) with solution generation (by MoE LLMs). In experiments, we finetune routers in OLMoE, DeepSeekMoE, and Qwen3-MoE using RoMA. Evaluations on diverse benchmarks and extensive comparisons with baselines show the substantial improvement brought by RoMA.

---

### Lightning Grasp: High Performance Procedural Grasp Synthesis with Contact Fields

Authors: Zhao-Heng Yin, Pieter Abbeel
Published: 2025-11-10
Categories: cs.RO, cs.AI, cs.CV, cs.DC, cs.GR
arXiv: https://arxiv.org/abs/2511.07418v1

Despite years of research, real-time diverse grasp synthesis for dexterous hands remains an unsolved core challenge in robotics and computer graphics. We present Lightning Grasp, a novel high-performance procedural grasp synthesis algorithm that achieves orders-of-magnitude speedups over state-of-the-art approaches, while enabling unsupervised grasp generation for irregular, tool-like objects. The method avoids many limitations of prior approaches, such as the need for carefully tuned energy functions and sensitive initialization. This breakthrough is driven by a key insight: decoupling complex geometric computation from the search process via a simple, efficient data structure - the Contact Field. This abstraction collapses the problem complexity, enabling a procedural search at unprecedented speeds. We open-source our system to propel further innovation in robotic manipulation.

---

### Language Generation with Infinite Contamination

Authors: Anay Mehrotra, Grigoris Velegkas, Xifan Yu, Felix Zhou
Published: 2025-11-10
Categories: stat.ML, cs.AI, cs.CL, cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2511.07417v1

We study language generation in the limit, where an algorithm observes an adversarial enumeration of strings from an unknown target language $K$ and must eventually generate new, unseen strings from $K$. Kleinberg and Mullainathan (KM24) proved that generation is achievable in surprisingly general settings. But their generator suffers from ``mode collapse,'' producing from an ever-smaller subset of the target. To address this, Kleinberg and Wei (KW25) require the generator's output to be ``dense'' in the target language. They showed that generation with density, surprisingly, remains achievable at the same generality. Both results assume perfect data: no noisy insertions and no omissions. This raises a central question: how much contamination can generation tolerate? Recent works made partial progress on this question by studying (non-dense) generation with either finite amounts of noise (but no omissions) or omissions (but no noise). We characterize robustness under contaminated enumerations: 1. Generation under Contamination: Language generation in the limit is achievable for all countable collections iff the fraction of contaminated examples converges to zero. When this fails, we characterize which collections are generable. 2. Dense Generation under Contamination: Dense generation is strictly less robust to contamination than generation. As a byproduct, we resolve an open question of Raman and Raman (ICML25) by showing that generation is possible with only membership oracle access under finitely many contaminated examples. Finally, we introduce a beyond-worst-case model inspired by curriculum learning and prove that dense generation is achievable even with infinite contamination provided the fraction of contaminated examples converges to zero. This suggests curriculum learning may be crucial for learning from noisy web data.

---

### Robot Learning from a Physical World Model

Authors: Jiageng Mao, Sicheng He, Hao-Ning Wu, Yang You, Shuyang Sun, Zhicheng Wang, Yanan Bao, Huizhong Chen, Leonidas Guibas, Vitor Guizilini, Howard Zhou, Yue Wang
Published: 2025-11-10
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2511.07416v1

We introduce PhysWorld, a framework that enables robot learning from video generation through physical world modeling. Recent video generation models can synthesize photorealistic visual demonstrations from language commands and images, offering a powerful yet underexplored source of training signals for robotics. However, directly retargeting pixel motions from generated videos to robots neglects physics, often resulting in inaccurate manipulations. PhysWorld addresses this limitation by coupling video generation with physical world reconstruction. Given a single image and a task command, our method generates task-conditioned videos and reconstructs the underlying physical world from the videos, and the generated video motions are grounded into physically accurate actions through object-centric residual reinforcement learning with the physical world model. This synergy transforms implicit visual guidance into physically executable robotic trajectories, eliminating the need for real robot data collection and enabling zero-shot generalizable robotic manipulation. Experiments on diverse real-world tasks demonstrate that PhysWorld substantially improves manipulation accuracy compared to previous approaches. Visit \href{https://pointscoder.github.io/PhysWorld_Web/}{the project webpage} for details.

---

### Wasserstein-Cramér-Rao Theory of Unbiased Estimation

Authors: Nicolás García Trillos, Adam Quinn Jaffe, Bodhisattva Sen
Published: 2025-11-10
Categories: math.ST, math.OC, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2511.07414v1

The quantity of interest in the classical Cramér-Rao theory of unbiased estimation (e.g., the Cramér-Rao lower bound, its exact attainment for exponential families, and asymptotic efficiency of maximum likelihood estimation) is the variance, which represents the instability of an estimator when its value is compared to the value for an independently-sampled data set from the same distribution. In this paper we are interested in a quantity which represents the instability of an estimator when its value is compared to the value for an infinitesimal additive perturbation of the original data set; we refer to this as the "sensitivity" of an estimator. The resulting theory of sensitivity is based on the Wasserstein geometry in the same way that the classical theory of variance is based on the Fisher-Rao (equivalently, Hellinger) geometry, and this insight allows us to determine a collection of results which are analogous to the classical case: a Wasserstein-Cramér-Rao lower bound for the sensitivity of any unbiased estimator, a characterization of models in which there exist unbiased estimators achieving the lower bound exactly, and some concrete results that show that the Wasserstein projection estimator achieves the lower bound asymptotically. We use these results to treat many statistical examples, sometimes revealing new optimality properties for existing estimators and other times revealing entirely new estimators.

---

### DigiData: Training and Evaluating General-Purpose Mobile Control Agents

Authors: Yuxuan Sun, Manchen Wang, Shengyi Qian, William R. Wong, Eric Gan, Pierluca D'Oro, Alejandro Castillejo Munoz, Sneha Silwal, Pedro Matias, Nitin Kamra, Satwik Kottur, Nick Raines et al.
Published: 2025-11-10
Categories: cs.AI, cs.CL, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2511.07413v2

AI agents capable of controlling user interfaces have the potential to transform human interaction with digital devices. To accelerate this transformation, two fundamental building blocks are essential: high-quality datasets that enable agents to achieve complex and human-relevant goals, and robust evaluation methods that allow researchers and practitioners to rapidly enhance agent performance. In this paper, we introduce DigiData, a large-scale, high-quality, diverse, multi-modal dataset designed for training mobile control agents. Unlike existing datasets, which derive goals from unstructured interactions, DigiData is meticulously constructed through comprehensive exploration of app features, resulting in greater diversity and higher goal complexity. Additionally, we present DigiData-Bench, a benchmark for evaluating mobile control agents on real-world complex tasks. We demonstrate that the commonly used step-accuracy metric falls short in reliably assessing mobile control agents and, to address this, we propose dynamic evaluation protocols and AI-powered evaluations as rigorous alternatives for agent assessment. Our contributions aim to significantly advance the development of mobile control agents, paving the way for more intuitive and effective human-device interactions.

---

### TwinOR: Photorealistic Digital Twins of Dynamic Operating Rooms for Embodied AI Research

Authors: Han Zhang, Yiqing Shen, Roger D. Soberanis-Mukul, Ankita Ghosh, Hao Ding, Lalithkumar Seenivasan, Jose L. Porras, Zhekai Mao, Chenjia Li, Wenjie Xiao, Lonny Yarmus, Angela Christine Argento et al.
Published: 2025-11-10
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2511.07412v2

Developing embodied AI for intelligent surgical systems requires safe, controllable environments for continual learning and evaluation. However, safety regulations and operational constraints in operating rooms (ORs) limit agents from freely perceiving and interacting in realistic settings. Digital twins provide high-fidelity, risk-free environments for exploration and training. How we may create dynamic digital representations of ORs that capture relevant spatial, visual, and behavioral complexity remains an open challenge. We introduce TwinOR, a real-to-sim infrastructure for constructing photorealistic and dynamic digital twins of ORs. The system reconstructs static geometry and continuously models human and equipment motion. The static and dynamic components are fused into an immersive 3D environment that supports controllable simulation and facilitates future embodied exploration. The proposed framework reconstructs complete OR geometry with centimeter-level accuracy while preserving dynamic interaction across surgical workflows. In our experiments, TwinOR synthesizes stereo and monocular RGB streams as well as depth observations for geometry understanding and visual localization tasks. Models such as FoundationStereo and ORB-SLAM3 evaluated on TwinOR-synthesized data achieve performance within their reported accuracy ranges on real-world indoor datasets, demonstrating that TwinOR provides sensor-level realism sufficient for emulating real-world perception and localization challenge. By establishing a perception-grounded real-to-sim pipeline, TwinOR enables the automatic construction of dynamic, photorealistic digital twins of ORs. As a safe and scalable environment for experimentation, TwinOR opens new opportunities for translating embodied intelligence from simulation to real-world clinical environments.

---

### Using Language Models as Closed-Loop High-Level Planners for Robotics Applications: A Brief Overview and Benchmarks

Authors: Hao Wang, Sathwik Karnik, Bea Lim, Somil Bansal
Published: 2025-11-10
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2511.07410v2

Large Language Models (LLMs) and Vision Language Models (VLMs) have become popular tools for embodied high-level planning. However, their deployment in black-box settings often leads to unpredictable or costly errors. To harness their capabilities more reliably in robotic systems, we empirically investigate practical strategies for integrating language models as closed-loop planners. Concretely, we study how the control horizon and warm-starting impact the performance of language model-based planners. We design and conduct controlled experiments to extract actionable insights, providing recommendations that can help improve the performance and robustness of language model-based embodied planning. The full implementation and experiments are available on the project website

---

### DIMO: Diverse 3D Motion Generation for Arbitrary Objects

Authors: Linzhan Mou, Jiahui Lei, Chen Wang, Lingjie Liu, Kostas Daniilidis
Published: 2025-11-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.07409v1

We present DIMO, a generative approach capable of generating diverse 3D motions for arbitrary objects from a single image. The core idea of our work is to leverage the rich priors in well-trained video models to extract the common motion patterns and then embed them into a shared low-dimensional latent space. Specifically, we first generate multiple videos of the same object with diverse motions. We then embed each motion into a latent vector and train a shared motion decoder to learn the distribution of motions represented by a structured and compact motion representation, i.e., neural key point trajectories. The canonical 3D Gaussians are then driven by these key points and fused to model the geometry and appearance. During inference time with learned latent space, we can instantly sample diverse 3D motions in a single-forward pass and support several interesting applications including 3D motion interpolation and language-guided motion generation. Our project page is available at https://linzhanm.github.io/dimo.

---

### Entangled Schrödinger Bridge Matching

Authors: Sophia Tang, Yinuo Zhang, Pranam Chatterjee
Published: 2025-11-10
Categories: cs.LG, q-bio.BM
arXiv: https://arxiv.org/abs/2511.07406v1

Simulating trajectories of multi-particle systems on complex energy landscapes is a central task in molecular dynamics (MD) and drug discovery, but remains challenging at scale due to computationally expensive and long simulations. Previous approaches leverage techniques such as flow or Schrödinger bridge matching to implicitly learn joint trajectories through data snapshots. However, many systems, including biomolecular systems and heterogeneous cell populations, undergo dynamic interactions that evolve over their trajectory and cannot be captured through static snapshots. To close this gap, we introduce Entangled Schrödinger Bridge Matching (EntangledSBM), a framework that learns the first- and second-order stochastic dynamics of interacting, multi-particle systems where the direction and magnitude of each particle's path depend dynamically on the paths of the other particles. We define the Entangled Schrödinger Bridge (EntangledSB) problem as solving a coupled system of bias forces that entangle particle velocities. We show that our framework accurately simulates heterogeneous cell populations under perturbations and rare transitions in high-dimensional biomolecular systems.

---

### SPOT: An Annotated French Corpus and Benchmark for Detecting Critical Interventions in Online Conversations

Authors: Manon Berriche, Célia Nouri, Chloée Clavel, Jean-Philippe Cointet
Published: 2025-11-10
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2511.07405v4

We introduce SPOT (Stopping Points in Online Threads), the first annotated corpus translating the sociological concept of stopping point into a reproducible NLP task. Stopping points are ordinary critical interventions that pause or redirect online discussions through a range of forms (irony, subtle doubt or fragmentary arguments) that frameworks like counterspeech or social correction often overlook. We operationalize this concept as a binary classification task and provide reliable annotation guidelines. The corpus contains 43,305 manually annotated French Facebook comments linked to URLs flagged as false information by social media users, enriched with contextual metadata (article, post, parent comment, page or group, and source). We benchmark fine-tuned encoder models (CamemBERT) and instruction-tuned LLMs under various prompting strategies. Results show that fine-tuned encoders outperform prompted LLMs in F1 score by more than 10 percentage points, confirming the importance of supervised learning for emerging non-English social media tasks. Incorporating contextual metadata further improves encoder models F1 scores from 0.75 to 0.78. We release the anonymized dataset, along with the annotation guidelines and code in our code repository, to foster transparency and reproducible research.

---

### SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Authors: Hunar Batra, Haoqin Tu, Hardy Chen, Yuanze Lin, Cihang Xie, Ronald Clark
Published: 2025-11-10
Categories: cs.CV, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.07403v2

Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial reasoning. Existing spatial MLLMs rely on large-scale datasets, explicit 3D inputs, architecture-specific modifications, or sparse Reinforcement Learning (RL) methods that provide insufficient guidance for spatially-grounded reasoning. We introduce SpatialThinker. To our knowledge, it is the first MLLM unifying Scene Graph Generation (SGG) and visual reasoning in a single pass via online RL. The model simulates human-like spatial perception by constructing a mental scene graph of task-relevant objects and relations, and reasoning toward an answer via dense spatial rewards. Our contributions are threefold: (1) SGG-grounded reasoning: integrating SGG directly within the reasoning chain rather than as a disjoint preprocessing step; (2) STVQA-7K: a high-quality spatial VQA training dataset via a scalable synthesis pipeline; and (3) a dense spatial reward design that enforces structured grounding during RL and generalizes to improve broad visual perception. SpatialThinker-7B achieves 3.6$\times$ larger gains over SFT and $1.7\times$ better in- and out-of-distribution generalization than sparse RL. Trained on only 7K samples, SpatialThinker-7B matches GPT-5 and outperforms GPT-4o, while SpatialThinker-30B surpasses both GPT-5 and Claude 4 Sonnet on average across 14 spatial and real-world benchmarks, demonstrating that structured spatial grounding with reward-aligned reasoning enables robust spatial understanding with limited data.

---

### StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation

Authors: Tianrui Feng, Zhi Li, Shuo Yang, Haocheng Xi, Muyang Li, Xiuyu Li, Lvmin Zhang, Keting Yang, Kelly Peng, Song Han, Maneesh Agrawala, Kurt Keutzer et al.
Published: 2025-11-10
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.07399v2

Generative models are reshaping the live-streaming industry by redefining how content is created, styled, and delivered. Previous image-based streaming diffusion models have powered efficient and creative live streaming products but have hit limits on temporal consistency due to the foundation of image-based designs. Recent advances in video diffusion have markedly improved temporal consistency and sampling efficiency for offline generation. However, offline generation systems primarily optimize throughput by batching large workloads. In contrast, live online streaming operates under strict service-level objectives (SLOs): time-to-first-frame must be minimal, and every frame must meet a per-frame deadline with low jitter. Besides, scalable multi-GPU serving for real-time streams remains largely unresolved so far. To address this, we present StreamDiffusionV2, a training-free pipeline for interactive live streaming with video diffusion models. StreamDiffusionV2 integrates an SLO-aware batching scheduler and a block scheduler, together with a sink-token--guided rolling KV cache, a motion-aware noise controller, and other system-level optimizations. Moreover, we introduce a scalable pipeline orchestration that parallelizes the diffusion process across denoising steps and network layers, achieving near-linear FPS scaling without violating latency guarantees. The system scales seamlessly across heterogeneous GPU environments and supports flexible denoising steps (e.g., 1--4), enabling both ultra-low-latency and higher-quality modes. Without TensorRT or quantization, StreamDiffusionV2 renders the first frame within 0.5s and attains 58.28 FPS with a 14B-parameter model and 64.52 FPS with a 1.3B-parameter model on four H100 GPUs, making state-of-the-art generative live streaming practical and accessible--from individual creators to enterprise-scale platforms.

---

### Solving bilevel optimization via sequential minimax optimization

Authors: Zhaosong Lu, Sanyou Mei
Published: 2025-11-10
Categories: math.OC, cs.LG, math.NA, stat.ML
arXiv: https://arxiv.org/abs/2511.07398v1

In this paper we propose a sequential minimax optimization (SMO) method for solving a class of constrained bilevel optimization problems in which the lower-level part is a possibly nonsmooth convex optimization problem, while the upper-level part is a possibly nonconvex optimization problem. Specifically, SMO applies a first-order method to solve a sequence of minimax subproblems, which are obtained by employing a hybrid of modified augmented Lagrangian and penalty schemes on the bilevel optimization problems. Under suitable assumptions, we establish an operation complexity of $O(\varepsilon^{-7}\log\varepsilon^{-1})$ and $O(\varepsilon^{-6}\log\varepsilon^{-1})$, measured in terms of fundamental operations, for SMO in finding an $\varepsilon$-KKT solution of the bilevel optimization problems with merely convex and strongly convex lower-level objective functions, respectively. The latter result improves the previous best-known operation complexity by a factor of $\varepsilon^{-1}$. Preliminary numerical results demonstrate significantly superior computational performance compared to the recently developed first-order penalty method.

---

### Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents

Authors: Vidya Srinivas, Zachary Englhardt, Vikram Iyer, Shwetak Patel
Published: 2025-11-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.07397v3

Voice agents face a fundamental tension: the reasoning, retrieval, and tool use that make foundation models capable are iterative and slow, while conversational interaction demands responses on a millisecond timescale. Smaller, real-time models meet the latency bar but cannot match foundation models on complex tasks, leaving current voice agents to trade away either responsiveness or capability. We introduce conversational infill, where a small talker model both immediately generates contextually grounded responses to hide the latency of an external reasoner model and fluently integrates streamed reasoner knowledge into its responses during inference. We curate a 290,571-example synthetic dataset spanning six domains and demonstrate that this task is learnable across seven widely used small language models ranging from 135M to 1.7B parameters. Our system implementation, ConvFill, sustains millisecond-level time-to-first-response while closing the accuracy gap to within 6.3% of the corresponding frontier reasoner performance. In a live user study (n=18) with talker deployments running on an Apple M2 SoC, participants rank ConvFill on par with frontier models overall, prefer it for retrieval-heavy tasks, and rate it significantly more responsive. These results show that conversational infill unlocks a new point on the latency-capability Pareto frontier, offering a practical path toward voice agents that are both responsive and highly capable. Code, models, and datasets are available at https://github.com/vysri/conversational-infill.

---

### C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning

Authors: Antonios Valkanas, Soumyasundar Pal, Pavel Rumiantsev, Yingxue Zhang, Mark Coates
Published: 2025-11-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.07396v1

Large language models (LLMs) have achieved impressive results on complex reasoning tasks, but their high inference cost remains a major barrier to real-world deployment. A promising solution is to use cascaded inference, where small, cheap models handle easy queries, and only the hardest examples are escalated to more powerful models. However, existing cascade methods typically rely on supervised training with labeled data, offer no theoretical generalization guarantees, and provide limited control over test-time computational cost. We introduce C3PO (Cost Controlled Cascaded Prediction Optimization), a self-supervised framework for optimizing LLM cascades under probabilistic cost constraints. By focusing on minimizing regret with respect to the most powerful model (MPM), C3PO avoids the need for labeled data by constructing a cascade using only unlabeled model outputs. It leverages conformal prediction to bound the probability that inference cost exceeds a user-specified budget. We provide theoretical guarantees on both cost control and generalization error, and show that our optimization procedure is effective even with small calibration sets. Empirically, C3PO achieves state-of-the-art performance across a diverse set of reasoning benchmarks including GSM8K, MATH-500, BigBench-Hard and AIME, outperforming strong LLM cascading baselines in both accuracy and cost-efficiency. Our results demonstrate that principled, label-free cascade optimization can enable scalable LLM deployment.

---

### Voice-Interactive Surgical Agent for Multimodal Patient Data Control

Authors: Hyeryun Park, Byung Mo Gu, Jun Hee Lee, Byeong Hyeon Choi, Sekeun Kim, Hyun Koo Kim, Kyungsang Kim
Published: 2025-11-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.07392v3

In robotic surgery, surgeons fully engage their hands and visual attention in procedures, making it difficult to access and manipulate multimodal patient data without interrupting the workflow. To overcome this problem, we propose a Voice-Interactive Surgical Agent (VISA) built on a hierarchical multi-agent framework consisting of an orchestration agent and three task-specific agents driven by Large Language Models (LLMs). These LLM-based agents autonomously plan, refine, validate, and reason to interpret voice commands and execute tasks such as retrieving clinical information, manipulating CT scans, or navigating 3D anatomical models within surgical video. We construct a dataset of 240 user commands organized into hierarchical categories and introduce the Multi-level Orchestration Evaluation Metric (MOEM) that evaluates the performance and robustness at both the command and category levels. Experimental results demonstrate that VISA achieves high stage-level accuracy and workflow-level success rates, while also enhancing its robustness by correcting transcription errors, resolving linguistic ambiguity, and interpreting diverse free-form expressions. These findings highlight the strong potential of VISA to support robotic surgery and its scalability for integrating new functions and agents.

---

### A Diffusion Model to Shrink Proteins While Maintaining Their Function

Authors: Ethan Baron, Alan N. Amin, Ruben Weitzman, Debora Marks, Andrew Gordon Wilson
Published: 2025-11-10
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2511.07390v2

Many proteins useful in modern medicine or bioengineering are challenging to make in the lab, fuse with other proteins in cells, or deliver to tissues in the body, because their sequences are too long. Shortening these sequences typically involves costly, time-consuming experimental campaigns. Ideally, we could instead use modern models of massive databases of sequences from nature to learn how to propose shrunken proteins that resemble sequences found in nature. Unfortunately, these models struggle to efficiently search the combinatorial space of all deletions, and are not trained with inductive biases to learn how to delete. To address this gap, we propose SCISOR, a novel discrete diffusion model that deletes letters from sequences to generate protein samples that resemble those found in nature. To do so, SCISOR trains a de-noiser to reverse a forward noising process that adds random insertions to natural sequences. As a generative model, SCISOR fits evolutionary sequence data competitively with previous large models. In evaluation, SCISOR achieves state-of-the-art predictions of the functional effects of deletions on ProteinGym. Finally, we use the SCISOR de-noiser to shrink long protein sequences, and show that its suggested deletions result in significantly more realistic proteins and more often preserve functional motifs than previous models of evolutionary sequences.

---

### Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence

Authors: Sean McLeish, Ang Li, John Kirchenbauer, Dayal Singh Kalra, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Jonas Geiping, Tom Goldstein, Micah Goldblum
Published: 2025-11-10
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.07384v1

Recent advances in depth-recurrent language models show that recurrence can decouple train-time compute and parameter count from test-time compute. In this work, we study how to convert existing pretrained non-recurrent language models into depth-recurrent models. We find that using a curriculum of recurrences to increase the effective depth of the model over the course of training preserves performance while reducing total computational cost. In our experiments, on mathematics, we observe that converting pretrained models to recurrent ones results in better performance at a given compute budget than simply post-training the original non-recurrent language model.

---

### Retriv at BLP-2025 Task 2: Test-Driven Feedback-Guided Framework for Bangla-to-Python Code Generation

Authors: K M Nafi Asib, Sourav Saha, Mohammed Moshiul Hoque
Published: 2025-11-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.07382v1

Large Language Models (LLMs) have advanced the automated generation of code from natural language prompts. However, low-resource languages (LRLs) like Bangla remain underrepresented due to the limited availability of instruction-to-code datasets and evaluation benchmarks. To address this, the BLP Workshop at IJCNLP-AACL 2025 introduced a shared task on "Code Generation in Bangla". In this work, we propose a method that combines instruction prompting with a test-driven, feedback-guided iterative refinement process using a fine-tuned Qwen2.5-14B model. The model generates code from Bangla instructions, tests it against unit tests, and iteratively refines any failing outputs through three evaluation passes, using test feedback to guide each step. This approach helped our team "Retriv" to secure 2nd place in the shared task with a Pass@1 score of 0.934. The analysis highlights challenges in Bangla instruction understanding and Python code generation, emphasizing the need for targeted methods in LRLs. We made experimental scripts publicly available for the community.

---

### Mining Useful General Data for Low-Resource Domain Adaptation

Authors: Pingjie Wang, Hongcheng Liu, Yusheng Liao, Ziqing Fan, Yaxin Du, Shuo Tang, Yanfeng Wang, Yu Wang
Published: 2025-11-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.07380v2

Adapting large language models (LLMs) to low-resource domains remains challenging due to the scarcity of domain-specific data. While in-domain data is limited, there exists a vast amount of general-domain data that shares similar question-answer formats and reasoning patterns with domain tasks. This observation raises an important question: can useful general-domain data be mined to improve low-resource domain adaptation? Our initial findings show that general-domain chain-of-thought data contains useful auxiliary signals for domain adaptation, even without careful selection. This observation motivates a new paradigm for domain adaptation beyond exclusive reliance on domain-specific data. To systematically identify the most beneficial general-domain samples, we propose NTK-Selector, motivated by the Neural Tangent Kernel's ability to capture alignment in training dynamics. Since directly applying NTK to pretrained LLMs is impractical, we introduce a Jacobian-free NTK approximation and empirically demonstrate stable NTK-like behavior during fine-tuning. Extensive experiments across medical, financial, legal, and psychological domains demonstrate that NTK-Selector consistently outperforms domain-only fine-tuning and existing data selection baselines. In particular, NTK-Selector achieves gains of +8.7 and +5.1 points on Llama3-8B-Instruct and Qwen3-8B, respectively, compared to only +0.8 and +0.9 points from domain-only fine-tuning.

---

### LoReTTA: A Low Resource Framework To Poison Continuous Time Dynamic Graphs

Authors: Himanshu Pal, Venkata Sai Pranav Bachina, Ankit Gangwal, Charu Sharma
Published: 2025-11-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.07379v1

Temporal Graph Neural Networks (TGNNs) are increasingly used in high-stakes domains, such as financial forecasting, recommendation systems, and fraud detection. However, their susceptibility to poisoning attacks poses a critical security risk. We introduce LoReTTA (Low Resource Two-phase Temporal Attack), a novel adversarial framework on Continuous-Time Dynamic Graphs, which degrades TGNN performance by an average of 29.47% across 4 widely benchmark datasets and 4 State-of-the-Art (SotA) models. LoReTTA operates through a two-stage approach: (1) sparsify the graph by removing high-impact edges using any of the 16 tested temporal importance metrics, (2) strategically replace removed edges with adversarial negatives via LoReTTA's novel degree-preserving negative sampling algorithm. Our plug-and-play design eliminates the need for expensive surrogate models while adhering to realistic unnoticeability constraints. LoReTTA degrades performance by upto 42.0% on MOOC, 31.5% on Wikipedia, 28.8% on UCI, and 15.6% on Enron. LoReTTA outperforms 11 attack baselines, remains undetectable to 4 leading anomaly detection systems, and is robust to 4 SotA adversarial defense training methods, establishing its effectiveness, unnoticeability, and robustness.

---

### Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization

Authors: Yu Huang, Zixin Wen, Aarti Singh, Yuejie Chi, Yuxin Chen
Published: 2025-11-10
Categories: cs.LG, cs.AI, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2511.07378v1

The ability to reason lies at the core of artificial intelligence (AI), and challenging problems usually call for deeper and longer reasoning to tackle. A crucial question about AI reasoning is whether models can extrapolate learned reasoning patterns to solve harder tasks with longer chain-of-thought (CoT). In this work, we present a theoretical analysis of transformers learning on synthetic state-tracking tasks with gradient descent. We mathematically prove how the algebraic structure of state-tracking problems governs the degree of extrapolation of the learned CoT. Specifically, our theory characterizes the length generalization of transformers through the mechanism of attention concentration, linking the retrieval robustness of the attention layer to the state-tracking task structure of long-context reasoning. Moreover, for transformers with limited reasoning length, we prove that a recursive self-training scheme can progressively extend the range of solvable problem lengths. To our knowledge, we provide the first optimization guarantee that constant-depth transformers provably learn $\mathsf{NC}^1$-complete problems with CoT, significantly going beyond prior art confined in $\mathsf{TC}^0$, unless the widely held conjecture $\mathsf{TC}^0 \neq \mathsf{NC}^1$ fails. Finally, we present a broad set of experiments supporting our theoretical results, confirming the length generalization behaviors and the mechanism of attention concentration.

---

### Real-Time LiDAR Super-Resolution via Frequency-Aware Multi-Scale Fusion

Authors: June Moh Goo, Zichao Zeng, Jan Boehm
Published: 2025-11-10
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2511.07377v1

LiDAR super-resolution addresses the challenge of achieving high-quality 3D perception from cost-effective, low-resolution sensors. While recent transformer-based approaches like TULIP show promise, they remain limited to spatial-domain processing with restricted receptive fields. We introduce FLASH (Frequency-aware LiDAR Adaptive Super-resolution with Hierarchical fusion), a novel framework that overcomes these limitations through dual-domain processing. FLASH integrates two key innovations: (i) Frequency-Aware Window Attention that combines local spatial attention with global frequency-domain analysis via FFT, capturing both fine-grained geometry and periodic scanning patterns at log-linear complexity. (ii) Adaptive Multi-Scale Fusion that replaces conventional skip connections with learned position-specific feature aggregation, enhanced by CBAM attention for dynamic feature selection. Extensive experiments on KITTI demonstrate that FLASH achieves state-of-the-art performance across all evaluation metrics, surpassing even uncertainty-enhanced baselines that require multiple forward passes. Notably, FLASH outperforms TULIP with Monte Carlo Dropout while maintaining single-pass efficiency, which enables real-time deployment. The consistent superiority across all distance ranges validates that our dual-domain approach effectively handles uncertainty through architectural design rather than computationally expensive stochastic inference, making it practical for autonomous systems.

---

### Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training

Authors: Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Hau-San Wong, Qingfu Zhang, Taiji Suzuki
Published: 2025-11-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.07372v3

Recent curriculum techniques in the post-training stage of LLMs have been empirically observed to outperform non-curriculum approaches in improving reasoning performance, yet a principled understanding of their effectiveness and limitations remains incomplete. To bridge this gap, we develop an abstract theoretical framework and identify sufficient conditions under which curriculum post-training yields exponential improvements in sample complexity. To substantiate this framework, we model the base model's Chain-of-Thought generation as a state-conditioned autoregressive reasoning tree, and formalize curriculum subtasks as either depth-increasing curricula that progressively extend reasoning horizons or hint-decreasing curricula that gradually remove partial hints. Our analysis shows that reinforcement learning finetuning with both curriculum strategies achieves high accuracy with polynomial sample complexity, whereas non-curriculum counterpart encounters an exponential complexity bottleneck. We further establish analogous guarantees for test-time scaling. Empirical simulations support our theoretical findings. Code is available at https://github.com/DakeBU/Curriculum-Post-training.

---

### Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories

Authors: Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Bo Xue, Qingfu Zhang, Hau-San Wong, Taiji Suzuki
Published: 2025-11-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.07368v3

Foundation models exhibit broad knowledge but limited task-specific reasoning, motivating post-training strategies such as RL with verifiable rewards (RLVR) and test-time scaling (TTS). While recent work highlights the role of exploration in improving pass@K, empirical evidence points to a paradox: RLVR and ORM/PRM typically reinforce existing paths rather than expanding the reasoning scope, raising the question of why exploration helps if no new patterns emerge. To reconcile this paradox, we adopt the perspective of Kim et al. (2025), viewing easy (e.g., simplifying a fraction) versus hard (e.g., discovering the some symmetry) reasoning steps as low versus high probability Markov transitions. In this tractable model, pretraining corresponds to tree-graph discovering, while post-training corresponds to CoT reweighting. We provably show that, both RLVR and ORM/PRM would favor heavily to several high-probability paths, and thereby forget rare-but-crucial CoTs. Building on this, we further prove that exploration strategies such as rejecting easy instances and KL regularization help preserve rare CoTs. Empirical simulations corroborate our theoretical results.

---

### Reduced Density Matrices Through Machine Learning

Authors: Awwab A. Azam, Lexu Zhao, Jiabin Yu
Published: 2025-11-10
Categories: cond-mat.str-el, cs.AI
arXiv: https://arxiv.org/abs/2511.07367v2

$n$-particle reduced density matrices ($n$-RDMs) play a central role in understanding correlated phases of matter, but their calculation is often computationally inefficient for strongly-correlated states at large system sizes. In this work, we use neural network (NN) architectures to accelerate and even predict $n$-RDMs for large systems. Our underlying intuition is that, for gapped states, $n$-RDMs are often smooth functions over the Brillouin zone (BZ) and are therefore interpolable, allowing NNs trained on small-size systems to predict large-size ones. Building on this, we devise two NNs: (i) a self-attention NN that maps random RDMs to physical ones, and (ii) a Sinusoidal Representation Network (SIREN) that directly maps momentum-space coordinates to RDM values. We test the NNs on RDMs in three 2D models: the pair-pair correlation functions of the Richardson model of superconductivity, the translationally-invariant Hartree-Fock (HF) 1-RDM in a four-band repulsive model, and the translation-breaking HF 1-RDM in the half-filled Hubbard model. We find that a SIREN trained on a $6\times 6$ momentum mesh and a SIREN trained on $4$ tilted meshes (each of which has $12$ momentum points) can predict the $18\times 18$ pair-pair correlation function with a relative accuracy of $94.29\%$ and $93.77\%$, respectively. NNs trained on $6\times 6$ and $8\times 8$ meshes provide high-quality initial guesses for $50\times 50$ translation-invariant HF and $30\times 30$ fully translation-breaking-allowed HF, reducing the required number of iterations by up to $91.63\%$ and $92.78\%$, respectively, compared to random initializations. Our results illustrate the potential of NN-based methods for interpolable $n$-RDMs, which might open a new avenue for future research on strongly correlated phases.

---

### UAV-Assisted Resilience in 6G and Beyond Network Energy Saving: A Multi-Agent DRL Approach

Authors: Dao Lan Vy Dinh, Anh Nguyen Thi Mai, Hung Tran, Giang Quynh Le Vu, Tu Dac Ho, Zhenni Pan, Vo Nhan Van, Symeon Chatzinotas, Dinh-Hieu Tran
Published: 2025-11-10
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2511.07366v3

This paper investigates the unmanned aerial vehicle (UAV)-assisted resilience perspective in the 6G network energy saving (NES) scenario. More specifically, we consider multiple ground base stations (GBSs) and each GBS has three different sectors/cells in the terrestrial networks, and multiple cells may become inactive due to unexpected events such as power outages, disasters, hardware failures, or erroneous energy-saving decisions made by external network management systems. During the time required to reactivate these cells, UAVs are deployed to temporarily restore user service. To address this, we propose a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) framework to enable UAV-assisted communication by jointly optimizing UAV trajectories, transmission power, and user-UAV association under a sleeping ground base station (GBS) strategy. This framework aims to ensure the resilience of active users in the network and the long-term operability of UAVs. Specifically, it maximizes service coverage for users during power outages or NES zones, while minimizing the energy consumption of UAVs. Simulation results demonstrate that the proposed MADDPG policy consistently achieves high coverage ratio across different testing episodes, outperforming other baselines. Moreover, the MADDPG framework attains the lowest total energy consumption, while maintaining a comparable user service rate. These results confirm the effectiveness of the proposed approach in achieving a superior trade-off between energy efficiency and service performance, supporting the development of sustainable and resilient UAV-assisted cellular networks.

---

### Private Sketches for Linear Regression

Authors: Shrutimoy Das, Debanuj Nayak, Anirban Dasgupta
Published: 2025-11-10
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.07365v2

Linear regression is frequently applied in a variety of domains, some of which might contain sensitive information. This necessitates that the application of these methods does not reveal private information. Differentially private (DP) linear regression methods, developed for this purpose, compute private estimates of the solution. These techniques typically involve computing a noisy version of the solution vector. Instead, we propose releasing private sketches of the datasets, which can then be used to compute an approximate solution to the regression problem. This is motivated by the \emph{sketch-and-solve} paradigm, where the regression problem is solved on a smaller sketch of the dataset instead of on the original problem space. The solution obtained on the sketch can also be shown to have good approximation guarantees to the original problem. Various sketching methods have been developed for improving the computational efficiency of linear regression problems under this paradigm. We adopt this paradigm for the purpose of releasing private sketches of the data. We construct differentially private sketches for the problems of least squares regression, as well as least absolute deviations regression. We show that the privacy constraints lead to sketched versions of regularized regression. We compute the bounds on the regularization parameter required for guaranteeing privacy. The availability of these private sketches facilitates the application of commonly available solvers for regression, without the risk of privacy leakage.

---

### Self-Evaluating LLMs for Multi-Step Tasks: Stepwise Confidence Estimation for Failure Detection

Authors: Vaibhav Mavi, Shubh Jaroria, Weiqi Sun
Published: 2025-11-10
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.07364v1

Reliability and failure detection of large language models (LLMs) is critical for their deployment in high-stakes, multi-step reasoning tasks. Prior work explores confidence estimation for self-evaluating LLM-scorer systems, with confidence scorers estimating the likelihood of errors in LLM responses. However, most methods focus on single-step outputs and overlook the challenges of multi-step reasoning. In this work, we extend self-evaluation techniques to multi-step tasks, testing two intuitive approaches: holistic scoring and step-by-step scoring. Using two multi-step benchmark datasets, we show that stepwise evaluation generally outperforms holistic scoring in detecting potential errors, with up to 15% relative increase in AUC-ROC. Our findings demonstrate that self-evaluating LLM systems provide meaningful confidence estimates in complex reasoning, improving their trustworthiness and providing a practical framework for failure detection.

---

### Inference-Time Scaling of Diffusion Models for Infrared Data Generation

Authors: Kai A. Horstmann, Maxim Clouser, Kia Khezeli
Published: 2025-11-10
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.07362v1

Infrared imagery enables temperature-based scene understanding using passive sensors, particularly under conditions of low visibility where traditional RGB imaging fails. Yet, developing downstream vision models for infrared applications is hindered by the scarcity of high-quality annotated data, due to the specialized expertise required for infrared annotation. While synthetic infrared image generation has the potential to accelerate model development by providing large-scale, diverse training data, training foundation-level generative diffusion models in the infrared domain has remained elusive due to limited datasets. In light of such data constraints, we explore an inference-time scaling approach using a domain-adapted CLIP-based verifier for enhanced infrared image generation quality. We adapt FLUX.1-dev, a state-of-the-art text-to-image diffusion model, to the infrared domain by finetuning it on a small sample of infrared images using parameter-efficient techniques. The trained verifier is then employed during inference to guide the diffusion sampling process toward higher quality infrared generations that better align with input text prompts. Empirically, we find that our approach leads to consistent improvements in generation quality, reducing FID scores on the KAIST Multispectral Pedestrian Detection Benchmark dataset by 10% compared to unguided baseline samples. Our results suggest that inference-time guidance offers a promising direction for bridging the domain gap in low-data infrared settings.

---

### Walsh-Hadamard Neural Operators for Solving PDEs with Discontinuous Coefficients

Authors: Giorgio M. Cavallazzi, Miguel Pérez Cuadrado, Alfredo Pinelli
Published: 2025-11-10
Categories: physics.comp-ph, cs.LG
arXiv: https://arxiv.org/abs/2511.07347v2

Neural operators have emerged as powerful tools for learning solution operators of partial differential equations (PDEs). However, standard spectral methods based on Fourier transforms struggle with problems involving discontinuous coefficients due to the Gibbs phenomenon and poor representation of sharp interfaces. We introduce the Walsh-Hadamard Neural Operator (WHNO), which leverages Walsh-Hadamard transforms-a spectral basis of rectangular wave functions naturally suited for piecewise constant fields-combined with learnable spectral weights that transform low-sequency Walsh coefficients to capture global dependencies efficiently. We validate WHNO on three problems: steady-state Darcy flow (preliminary validation), heat conduction with discontinuous thermal conductivity, and the 2D Burgers equation with discontinuous initial conditions. In controlled comparisons with Fourier Neural Operators (FNO) under identical conditions, WHNO demonstrates superior accuracy with better preservation of sharp solution features at material interfaces. Critically, we discover that weighted ensemble combinations of WHNO and FNO achieve substantial improvements over either model alone: for both heat conduction and Burgers equation, optimal ensembles reduce mean squared error by 35-40 percent and maximum error by up to 25 percent compared to individual models. This demonstrates that Walsh-Hadamard and Fourier representations capture complementary aspects of discontinuous PDE solutions, with WHNO excelling at sharp interfaces while FNO captures smooth features effectively.

---

### TNT: Improving Chunkwise Training for Test-Time Memorization

Authors: Zeman Li, Ali Behrouz, Yuan Deng, Peilin Zhong, Praneeth Kacham, Mahdi Karami, Meisam Razaviyayn, Vahab Mirrokni
Published: 2025-11-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.07343v1

Recurrent neural networks (RNNs) with deep test-time memorization modules, such as Titans and TTT, represent a promising, linearly-scaling paradigm distinct from Transformers. While these expressive models do not yet match the peak performance of state-of-the-art Transformers, their potential has been largely untapped due to prohibitively slow training and low hardware utilization. Existing parallelization methods force a fundamental conflict governed by the chunksize hyperparameter: large chunks boost speed but degrade performance, necessitating a fixed, suboptimal compromise. To solve this challenge, we introduce TNT, a novel training paradigm that decouples training efficiency from inference performance through a two-stage process. Stage one is an efficiency-focused pre-training phase utilizing a hierarchical memory. A global module processes large, hardware-friendly chunks for long-range context, while multiple parallel local modules handle fine-grained details. Crucially, by periodically resetting local memory states, we break sequential dependencies to enable massive context parallelization. Stage two is a brief fine-tuning phase where only the local memory modules are adapted to a smaller, high-resolution chunksize, maximizing accuracy with minimal overhead. Evaluated on Titans and TTT models, TNT achieves a substantial acceleration in training speed-up to 17 times faster than the most accurate baseline configuration - while simultaneously improving model accuracy. This improvement removes a critical scalability barrier, establishing a practical foundation for developing expressive RNNs and facilitating future work to close the performance gap with Transformers.

---

### DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas

Authors: Zhen Wang, Yufan Zhou, Zhongyan Luo, Lyumanshan Ye, Adam Wood, Man Yao, Saab Mansour, Luoshang Pan
Published: 2025-11-10
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.07338v3

Simulating human profiles by instilling personas into large language models (LLMs) is rapidly transforming research in agentic behavioral simulation, LLM personalization, and human-AI alignment. However, most existing synthetic personas remain shallow and simplistic, capturing minimal attributes and failing to reflect the rich complexity and diversity of real human identities. We introduce DEEPPERSONA, a scalable generative engine for synthesizing narrative-complete synthetic personas through a two-stage, taxonomy-guided method. First, we algorithmically construct the largest-ever human-attribute taxonomy, comprising over hundreds of hierarchically organized attributes, by mining thousands of real user-ChatGPT conversations. Second, we progressively sample attributes from this taxonomy, conditionally generating coherent and realistic personas that average hundreds of structured attributes and roughly 1 MB of narrative text, two orders of magnitude deeper than prior works. Intrinsic evaluations confirm significant improvements in attribute diversity (32 percent higher coverage) and profile uniqueness (44 percent greater) compared to state-of-the-art baselines. Extrinsically, our personas enhance GPT-4.1-mini's personalized question answering accuracy by 11.6 percent on average across ten metrics and substantially narrow (by 31.7 percent) the gap between simulated LLM citizens and authentic human responses in social surveys. Our generated national citizens reduced the performance gap on the Big Five personality test by 17 percent relative to LLM-simulated citizens. DEEPPERSONA thus provides a rigorous, scalable, and privacy-free platform for high-fidelity human simulation and personalized AI research.

---

### Grounding Computer Use Agents on Human Demonstrations

Authors: Aarash Feizi, Shravan Nayak, Xiangru Jian, Kevin Qinghong Lin, Kaixin Li, Rabiul Awal, Xing Han Lù, Johan Obando-Ceron, Juan A. Rodriguez, Nicolas Chapados, David Vazquez, Adriana Romero-Soriano et al.
Published: 2025-11-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.07332v2

Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements. While large datasets exist for web and mobile interactions, high-quality resources for desktop environments are limited. To address this gap, we introduce GroundCUA, a large-scale desktop grounding dataset built from expert human demonstrations. It covers 87 applications across 12 categories and includes 56K screenshots, with every on-screen element carefully annotated for a total of over 3.56M human-verified annotations. From these demonstrations, we generate diverse instructions that capture a wide range of real-world tasks, providing high-quality data for model training. Using GroundCUA, we develop the GroundNext family of models that map instructions to their target UI elements. At both 3B and 7B scales, GroundNext achieves state-of-the-art results across five benchmarks using supervised fine-tuning, while requiring less than one-tenth the training data of prior work. Reinforcement learning post-training further improves performance, and when evaluated in an agentic setting on the OSWorld benchmark using o3 as planner, GroundNext attains comparable or superior results to models trained with substantially more data,. These results demonstrate the critical role of high-quality, expert-driven datasets in advancing general-purpose computer-use agents.

---