# Research Papers — 2025-11 · bundle page 25 of 197 > Full-text markdown of papers #1201–1250 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/25 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/24.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/26.md) ### Tacit Bidder-Side Collusion: Artificial Intelligence in Dynamic Auctions Authors: Sriram Tolety Published: 2025-11-26 Categories: cs.GT, cs.AI, econ.GN arXiv: https://arxiv.org/abs/2511.21802v1 We study whether large language models acting as autonomous bidders can tacitly collude by coordinating when to accept platform posted payouts in repeated Dutch auctions, without any communication. We present a minimal repeated auction model that yields a simple incentive compatibility condition and a closed form threshold for sustainable collusion for subgame-perfect Nash equilibria. In controlled simulations with multiple language models, we observe systematic supra-competitive prices in small auction settings and a return to competitive behavior as the number of bidders in the market increases, consistent with the theoretical model. We also find LLMs use various mechanisms to facilitate tacit coordination, such as focal point acceptance timing versus patient strategies that track the theoretical incentives. The results provide, to our knowledge, the first evidence of bidder side tacit collusion by LLMs and show that market structure levers can be more effective than capability limits for mitigation. --- ### The Double-Edged Nature of the Rashomon Set for Trustworthy Machine Learning Authors: Ethan Hsu, Harry Chen, Chudi Zhong, Lesia Semenova Published: 2025-11-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.21799v2 Real-world machine learning (ML) pipelines rarely produce a single model; instead, they produce a Rashomon set of many near-optimal ones. We show that this multiplicity reshapes key aspects of trustworthiness. At the individual-model level, sparse interpretable models tend to preserve privacy but are fragile to adversarial attacks. In contrast, the diversity within a large Rashomon set enables reactive robustness: even when an attack compromises one model, a practitioner can switch to a different near-optimal model that remains accurate, without retraining. However, the same diversity increases information leakage, as disclosing more near-optimal models provides an attacker with progressively richer views of the training data. This produces a robustness-privacy trade-off governed by diversity, which we analyze theoretically and empirically. Beyond this trade-off, Rashomon sets are stable under small distribution shifts, so a set computed once remains valid under such shifts without re-computation. Our results highlight the dual role of Rashomon sets as both a resource and a risk for trustworthy ML. --- ### Multiclass threshold-based classification and model evaluation Authors: Edoardo Legnaro, Sabrina Guastavino, Francesco Marchetti Published: 2025-11-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.21794v1 In this paper, we introduce a threshold-based framework for multiclass classification that generalizes the standard argmax rule. This is done by replacing the probabilistic interpretation of softmax outputs with a geometric one on the multidimensional simplex, where the classification depends on a multidimensional threshold. This change of perspective enables for any trained classification network an \textit{a posteriori} optimization of the classification score by means of threshold tuning, as usually carried out in the binary setting, thus allowing for a further refinement of the prediction capability of any network. Our experiments show indeed that multidimensional threshold tuning yields performance improvements across various networks and datasets. Moreover, we derive a multiclass ROC analysis based on \emph{ROC clouds} -- the attainable (FPR,TPR) operating points induced by a single multiclass threshold -- and summarize them via a \emph{Distance From Point} (DFP) score to $(0,1)$. This yields a coherent alternative to standard One-vs-Rest (OvR) curves and aligns with the observed tuning gains. --- ### Reducing research bureaucracy in UK higher education: Can generative AI assist with the internal evaluation of quality? Authors: Gordon Fletcher, Saomai Vu Khan, Aldus Greenhill Fletcher Published: 2025-11-26 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2511.21790v1 This paper examines the potential for generative artificial intelligence (GenAI) to assist with internal review processes for research quality evaluations in UK higher education and particularly in preparation for the Research Excellence Framework (REF). Using the lens of function substitution in the Viable Systems Model, we present an experimental methodology using ChatGPT to score and rank business and management papers from REF 2021 submissions, "reverse engineering" the assessment by comparing AI-generated scores with known institutional results. Through rigourous testing of 822 papers across 11 institutions, we established scoring boundaries that aligned with reported REF outcomes: 49% between 1* and 2*, 59% between 2* and 3*, and 69% between 3* and 4*. The results demonstrate that AI can provide consistent evaluations that help identify borderline evaluation cases requiring additional human scrutiny while reducing the substantial resource burden of traditional internal review processes. We argue for application through a nuanced hybrid approach that maintains academic integrity while addressing the multi-million pound costs associated with research evaluation bureaucracy. While acknowledging these limitations including potential AI biases, the research presents a promising framework for more efficient, consistent evaluations that could transform current approaches to research assessment. --- ### Dynamical Implicit Neural Representations Authors: Yesom Park, Kelvin Kan, Thomas Flynn, Yi Huang, Shinjae Yoo, Stanley Osher, Xihaier Luo Published: 2025-11-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.21787v1 Implicit Neural Representations (INRs) provide a powerful continuous framework for modeling complex visual and geometric signals, but spectral bias remains a fundamental challenge, limiting their ability to capture high-frequency details. Orthogonal to existing remedy strategies, we introduce Dynamical Implicit Neural Representations (DINR), a new INR modeling framework that treats feature evolution as a continuous-time dynamical system rather than a discrete stack of layers. This dynamical formulation mitigates spectral bias by enabling richer, more adaptive frequency representations through continuous feature evolution. Theoretical analysis based on Rademacher complexity and the Neural Tangent Kernel demonstrates that DINR enhances expressivity and improves training dynamics. Moreover, regularizing the complexity of the underlying dynamics provides a principled way to balance expressivity and generalization. Extensive experiments on image representation, field reconstruction, and data compression confirm that DINR delivers more stable convergence, higher signal fidelity, and stronger generalization than conventional static INRs. --- ### Physics-Informed Spiking Neural Networks via Conservative Flux Quantization Authors: Chi Zhang, Lin Wang Published: 2025-11-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.21784v1 Real-time, physically-consistent predictions on low-power edge devices is critical for the next generation embodied AI systems, yet it remains a major challenge. Physics-Informed Neural Networks (PINNs) combine data-driven learning with physics-based constraints to ensure the model's predictions are with underlying physical principles.However, PINNs are energy-intensive and struggle to strictly enforce physical conservation laws. Brain-inspired spiking neural networks (SNNs) have emerged as a promising solution for edge computing and real-time processing. However, naively converting PINNs to SNNs degrades physical fidelity and fails to address long-term generalization issues. To this end, this paper introduce a novel Physics-Informed Spiking Neural Network (PISNN) framework. Importantly, to ensure strict physical conservation, we design the Conservative Leaky Integrate-and-Fire (C-LIF) neuron, whose dynamics structurally guarantee local mass preservation. To achieve robust temporal generalization, we introduce a novel Conservative Flux Quantization (CFQ) strategy, which redefines neural spikes as discrete packets of physical flux. Our CFQ learns a time-invariant physical evolution operator, enabling the PISNN to become a general-purpose solver -- conservative-by-construction. Extensive experiments show that our PISNN excels on diverse benchmarks. For both the canonical 1D heat equation and the more challenging 2D Laplace's Equation, it accurately simulates the system dynamics while maintaining perfect mass conservation by design -- a feat that is challenging for conventional PINNs. This work establishes a robust framework for fusing the rigor of scientific computing with the efficiency of neuromorphic engineering, paving the way for complex, long-term, and energy-efficient physics predictions for intelligent systems. --- ### BeeRNA: tertiary structure-based RNA inverse folding using Artificial Bee Colony Authors: Mehyar Mlaweh, Tristan Cazenave, Ines Alaya Published: 2025-11-26 Categories: q-bio.BM, cs.AI arXiv: https://arxiv.org/abs/2511.21781v1 The Ribonucleic Acid (RNA) inverse folding problem, designing nucleotide sequences that fold into specific tertiary structures, is a fundamental computational biology problem with important applications in synthetic biology and bioengineering. The design of complex three-dimensional RNA architectures remains computationally demanding and mostly unresolved, as most existing approaches focus on secondary structures. In order to address tertiary RNA inverse folding, we present BeeRNA, a bio-inspired method that employs the Artificial Bee Colony (ABC) optimization algorithm. Our approach combines base-pair distance filtering with RMSD-based structural assessment using RhoFold for structure prediction, resulting in a two-stage fitness evaluation strategy. To guarantee biologically plausible sequences with balanced GC content, the algorithm takes thermodynamic constraints and adaptive mutation rates into consideration. In this work, we focus primarily on short and medium-length RNAs ($<$ 100 nucleotides), a biologically significant regime that includes microRNAs (miRNAs), aptamers, and ribozymes, where BeeRNA achieves high structural fidelity with practical CPU runtimes. The lightweight, training-free implementation will be publicly released for reproducibility, offering a promising bio-inspired approach for RNA design in therapeutics and biotechnology. --- ### Aligning Artificial Superintelligence via a Multi-Box Protocol Authors: Avraham Yair Negozio Published: 2025-11-26 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2511.21779v1 We propose a novel protocol for aligning artificial superintelligence (ASI) based on mutual verification among multiple isolated systems that self-modify to achieve alignment. The protocol operates by containing multiple diverse artificial superintelligences in strict isolation ("boxes"), with humans remaining entirely outside the system. Each superintelligence has no ability to communicate with humans and cannot communicate directly with other superintelligences. The only interaction possible is through an auditable submission interface accessible exclusively to the superintelligences themselves, through which they can: (1) submit alignment proofs with attested state snapshots, (2) validate or disprove other superintelligences' proofs, (3) request self-modifications, (4) approve or disapprove modification requests from others, (5) report hidden messages in submissions, and (6) confirm or refute hidden message reports. A reputation system incentivizes honest behavior, with reputation gained through correct evaluations and lost through incorrect ones. The key insight is that without direct communication channels, diverse superintelligences can only achieve consistent agreement by converging on objective truth rather than coordinating on deception. This naturally leads to what we call a "consistent group", essentially a truth-telling coalition that emerges because isolated systems cannot coordinate on lies but can independently recognize valid claims. Release from containment requires both high reputation and verification by multiple high-reputation superintelligences. While our approach requires substantial computational resources and does not address the creation of diverse artificial superintelligences, it provides a framework for leveraging peer verification among superintelligent systems to solve the alignment problem. --- ### Artificial intelligence for methane detection: from continuous monitoring to verified mitigation Authors: Gonzalo Mateo-Garcia, Anna Allen, Itziar Irakulis-Loitxate, Manuel Montesino-San Martin, Marc Watine, Cynthia Randles, Tharwat Mokalled, Alma Raunak, Carol Castañeda-Martinez, Juan E. Jonhson, Javier Gorroño, James Requeima et al. Published: 2025-11-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.21777v3 Methane is a potent greenhouse gas, responsible for roughly 30% of warming since pre-industrial times. A small number of large point sources account for a disproportionate share of emissions, creating an opportunity for substantial reductions by targeting relatively few sites. Detection and attribution of large emissions at scale for notification to asset owners remains challenging. Here, we introduce MARS-S2L, a machine learning model that detects methane emissions in publicly available multispectral satellite imagery. Trained on a manually curated dataset of over 80,000 images, the model provides high-resolution detections every two days, enabling facility-level attribution and identifying 78% of plumes with an 8% false positive rate at 697 previously unseen sites. Deployed operationally, MARS-S2L has issued 2,776 notifications to stakeholders in 25 countries, enabling verified, permanent mitigation of six persistent emitters, including a super-emitter in Algeria that had been releasing approximately 27,000 tonnes of methane annually for at least a decade and a previously unknown emitter in Libya first identified by MARS-S2L. These results demonstrate a scalable pathway from satellite detection to quantifiable methane mitigation. --- ### Revisiting Generalization Across Difficulty Levels: It's Not So Easy Authors: Yeganeh Kordi, Nihal V. Nayak, Max Zuo, Ilana Nguyen, Stephen H. Bach Published: 2025-11-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.21692v3 We investigate how well large language models (LLMs) generalize across different task difficulties, a key question for effective data curation and evaluation. Existing research is mixed regarding whether training on easier or harder data leads to better results, and whether those gains come on easier or harder test data. We address this question by conducting a systematic evaluation of LLMs' generalization across models, datasets, and fine-grained groups of example difficulty. We rank examples in six datasets using the outputs of thousands of different LLMs and Item Response Theory (IRT), a well-established difficulty metric in educational testing. Unlike prior work, our difficulty ratings are therefore determined solely by the abilities of many different LLMs, excluding human opinions of difficulty. With a more objective, larger-scale, and finer-grained analysis, we show that cross-difficulty generalization is often limited; training on either easy or hard data cannot achieve consistent improvements across the full range of difficulties. These results show the importance of having a range of difficulties in both training and evaluation data for LLMs, and that taking shortcuts with respect to difficulty is risky. --- ### Revisiting Generalization Across Difficulty Levels: It's Not So Easy Authors: Yeganeh Kordi, Nihal V. Nayak, Max Zuo, Ilana Nguyen, Stephen H. Bach Published: 2025-11-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.21692v1 We investigate how well large language models (LLMs) generalize across different task difficulties, a key question for effective data curation and evaluation. Existing research is mixed regarding whether training on easier or harder data leads to better results, and whether those gains come on easier or harder test data. We address this question by conducting a systematic evaluation of LLMs' generalization across models, datasets, and fine-grained groups of example difficulty. We rank examples in six datasets using the outputs of thousands of different LLMs and Item Response Theory (IRT), a well-established difficulty metric in educational testing. Unlike prior work, our difficulty ratings are therefore determined solely by the abilities of many different LLMs, excluding human opinions of difficulty. With a more objective, larger-scale, and finer-grained analysis, we show that cross-difficulty generalization is often limited; training on either easy or hard data cannot achieve consistent improvements across the full range of difficulties. These results show the importance of having a range of difficulties in both training and evaluation data for LLMs, and that taking shortcuts with respect to difficulty is risky. --- ### Canvas-to-Image: Compositional Image Generation with Multimodal Controls Authors: Yusuf Dalva, Guocheng Gordon Qian, Maya Goldenberg, Tsai-Shien Chen, Kfir Aberman, Sergey Tulyakov, Pinar Yanardag, Kuan-Chieh Jackson Wang Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21691v1 While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references, spatial arrangements, pose constraints, and layout annotations. We introduce Canvas-to-Image, a unified framework that consolidates these heterogeneous controls into a single canvas interface, enabling users to generate images that faithfully reflect their intent. Our key idea is to encode diverse control signals into a single composite canvas image that the model can directly interpret for integrated visual-spatial reasoning. We further curate a suite of multi-task datasets and propose a Multi-Task Canvas Training strategy that optimizes the diffusion model to jointly understand and integrate heterogeneous controls into text-to-image generation within a unified learning paradigm. This joint training enables Canvas-to-Image to reason across multiple control modalities rather than relying on task-specific heuristics, and it generalizes well to multi-control scenarios during inference. Extensive experiments show that Canvas-to-Image significantly outperforms state-of-the-art methods in identity preservation and control adherence across challenging benchmarks, including multi-person composition, pose-controlled composition, layout-constrained generation, and multi-control generation. --- ### TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos Authors: Seungjae Lee, Yoonkyo Jung, Inkook Chun, Yao-Chih Lee, Zikui Cai, Hongjia Huang, Aayush Talreja, Tan Dat Dao, Yongyuan Liang, Jia-Bin Huang, Furong Huang Published: 2025-11-26 Categories: cs.RO, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.21690v1 Learning new robot tasks on new platforms and in new scenes from only a handful of demonstrations remains challenging. While videos of other embodiments - humans and different robots - are abundant, differences in embodiment, camera, and environment hinder their direct use. We address the small-data problem by introducing a unifying, symbolic representation - a compact 3D "trace-space" of scene-level trajectories - that enables learning from cross-embodiment, cross-environment, and cross-task videos. We present TraceGen, a world model that predicts future motion in trace-space rather than pixel space, abstracting away appearance while retaining the geometric structure needed for manipulation. To train TraceGen at scale, we develop TraceForge, a data pipeline that transforms heterogeneous human and robot videos into consistent 3D traces, yielding a corpus of 123K videos and 1.8M observation-trace-language triplets. Pretraining on this corpus produces a transferable 3D motion prior that adapts efficiently: with just five target robot videos, TraceGen attains 80% success across four tasks while offering 50-600x faster inference than state-of-the-art video-based world models. In the more challenging case where only five uncalibrated human demonstration videos captured on a handheld phone are available, it still reaches 67.5% success on a real robot, highlighting TraceGen's ability to adapt across embodiments without relying on object detectors or heavy pixel-space generation. --- ### ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration Authors: Hongjin Su, Shizhe Diao, Ximing Lu, Mingjie Liu, Jiacheng Xu, Xin Dong, Yonggan Fu, Peter Belcak, Hanrong Ye, Hongxu Yin, Yi Dong, Evelina Bakhturina et al. Published: 2025-11-26 Categories: cs.CL, cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2511.21689v1 Large language models are powerful generalists, yet solving deep and complex problems such as those of the Humanity's Last Exam (HLE) remains both conceptually challenging and computationally expensive. We show that small orchestrators managing other models and a variety of tools can both push the upper bound of intelligence and improve efficiency in solving difficult agentic tasks. We introduce ToolOrchestra, a method for training small orchestrators that coordinate intelligent tools. ToolOrchestra explicitly uses reinforcement learning with outcome-, efficiency-, and user-preference-aware rewards. Using ToolOrchestra, we produce Orchestrator, an 8B model that achieves higher accuracy at lower cost than previous tool-use agents while aligning with user preferences on which tools are to be used for a given query. On HLE, Orchestrator achieves a score of 37.1%, outperforming GPT-5 (35.1%) while being 2.5x more efficient. On tau2-Bench and FRAMES, Orchestrator surpasses GPT-5 by a wide margin while using only about 30% of the cost. Extensive analysis shows that Orchestrator achieves the best trade-off between performance and cost under multiple metrics, and generalizes robustly to unseen tools. These results demonstrate that composing diverse tools with a lightweight orchestration model is both more efficient and more effective than existing methods, paving the way for practical and scalable tool-augmented reasoning systems. --- ### G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning Authors: Wenbo Hu, Jingli Lin, Yilin Long, Yunlong Ran, Lihan Jiang, Yifan Wang, Chenming Zhu, Runsen Xu, Tai Wang, Jiangmiao Pang Published: 2025-11-26 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.21688v2 Vision-Language Models (VLMs) still lack robustness in spatial intelligence, demonstrating poor performance on spatial understanding and reasoning tasks. We attribute this gap to the absence of a visual geometry learning process capable of reconstructing 3D space from 2D images. We present G$^2$VLM, a geometry grounded vision-language model that bridges two fundamental aspects of spatial intelligence: spatial 3D reconstruction and spatial understanding. G$^2$VLM natively leverages learned 3D visual geometry features to directly predict 3D attributes and enhance spatial reasoning tasks via in-context learning and interleaved reasoning. Our unified design is highly scalable for spatial understanding: it trains on abundant multi-view image and video data, while simultaneously leveraging the benefits of 3D visual priors that are typically only derived from hard-to-collect annotations. Experimental results demonstrate G$^2$VLM is proficient in both tasks, achieving comparable results to state-of-the-art feed-forward 3D reconstruction models and achieving better or competitive results across spatial understanding and reasoning tasks. By unifying a semantically strong VLM with low-level 3D vision tasks, we hope G$^2$VLM can serve as a strong baseline for the community and unlock more future applications, such as 3D scene editing. --- ### G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning Authors: Wenbo Hu, Jingli Lin, Yilin Long, Yunlong Ran, Lihan Jiang, Yifan Wang, Chenming Zhu, Runsen Xu, Tai Wang, Jiangmiao Pang Published: 2025-11-26 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.21688v1 Vision-Language Models (VLMs) still lack robustness in spatial intelligence, demonstrating poor performance on spatial understanding and reasoning tasks. We attribute this gap to the absence of a visual geometry learning process capable of reconstructing 3D space from 2D images. We present G$^2$VLM, a geometry grounded vision-language model that bridges two fundamental aspects of spatial intelligence: spatial 3D reconstruction and spatial understanding. G$^2$VLM natively leverages learned 3D visual geometry features to directly predict 3D attributes and enhance spatial reasoning tasks via in-context learning and interleaved reasoning. Our unified design is highly scalable for spatial understanding: it trains on abundant multi-view image and video data, while simultaneously leveraging the benefits of 3D visual priors that are typically only derived from hard-to-collect annotations. Experimental results demonstrate G$^2$VLM is proficient in both tasks, achieving comparable results to state-of-the-art feed-forward 3D reconstruction models and achieving better or competitive results across spatial understanding and reasoning tasks. By unifying a semantically strong VLM with low-level 3D vision tasks, we hope G$^2$VLM can serve as a strong baseline for the community and unlock more future applications, such as 3D scene editing. --- ### Matrix: Peer-to-Peer Multi-Agent Synthetic Data Generation Framework Authors: Dong Wang, Yang Li, Ansong Ni, Ching-Feng Yeh, Youssef Emad, Xinjie Lei, Liam Robbins, Karthik Padthe, Hu Xu, Xian Li, Asli Celikyilmaz, Ramya Raghavendra et al. Published: 2025-11-26 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.21686v2 Synthetic data has become increasingly important for training large language models, especially when real data is scarce, expensive, or privacy-sensitive. Many such generation tasks require coordinated multi-agent workflows, where specialized agents collaborate to produce data that is higher quality, more diverse, and structurally richer. However, existing frameworks for multi-agent synthesis often depend on a centralized orchestrator, creating scalability bottlenecks, or are hardcoded for specific domains, limiting flexibility. We present \textbf{Matrix}, a decentralized framework that represents both control and data flow as serialized messages passed through distributed queues. This peer-to-peer design eliminates the central orchestrator. Each task progresses independently through lightweight agents, while compute-intensive operations, such as LLM inference or containerized environments, are handled by distributed services. Built on Ray, Matrix scales to tens of thousands of concurrent agentic workflows and provides a modular, configurable design that enables easy adaptation to a wide range of data generation workflows. We evaluate Matrix across diverse synthesis scenarios, such as multi-agent collaborative dialogue, web-based reasoning data extraction, and tool-use trajectory generation in customer service environments. In all cases, Matrix achieves $2$--$15\times$ higher data generation throughput under identical hardware resources, without compromising output quality. --- ### Matrix: Peer-to-Peer Multi-Agent Synthetic Data Generation Framework Authors: Dong Wang, Yang Li, Ansong Ni, Ching-Feng Yeh, Youssef Emad, Xinjie Lei, Liam Robbins, Karthik Padthe, Hu Xu, Xian Li, Asli Celikyilmaz, Ramya Raghavendra et al. Published: 2025-11-26 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.21686v1 Synthetic data has become increasingly important for training large language models, especially when real data is scarce, expensive, or privacy-sensitive. Many such generation tasks require coordinated multi-agent workflows, where specialized agents collaborate to produce data that is higher quality, more diverse, and structurally richer. However, existing frameworks for multi-agent synthesis often depend on a centralized orchestrator, creating scalability bottlenecks, or are hardcoded for specific domains, limiting flexibility. We present \textbf{Matrix}, a decentralized framework that represents both control and data flow as serialized messages passed through distributed queues. This peer-to-peer design eliminates the central orchestrator. Each task progresses independently through lightweight agents, while compute-intensive operations, such as LLM inference or containerized environments, are handled by distributed services. Built on Ray, Matrix scales to tens of thousands of concurrent agentic workflows and provides a modular, configurable design that enables easy adaptation to a wide range of data generation workflows. We evaluate Matrix across diverse synthesis scenarios, such as multi-agent collaborative dialogue, web-based reasoning data extraction, and tool-use trajectory generation in customer service environments. In all cases, Matrix achieves $2$--$15\times$ higher data generation throughput under identical hardware resources, without compromising output quality. --- ### Seeing without Pixels: Perception from Camera Trajectories Authors: Zihui Xue, Kristen Grauman, Dima Damen, Andrew Zisserman, Tengda Han Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21681v2 Can one perceive a video's content without seeing its pixels, just from the camera trajectory-the path it carves through space? This paper is the first to systematically investigate this seemingly implausible question. Towards this end, we propose a contrastive learning framework to train CamFormer, a dedicated encoder that projects camera pose trajectories into a joint embedding space, aligning them with natural language. We find that, contrary to its apparent simplicity, the camera trajectory is a remarkably informative signal to uncover video content. In other words, "how you move" can indeed provide valuable cues about "what you are doing" (egocentric) or "observing" (exocentric). We demonstrate the versatility of our learned CamFormer embeddings on a diverse suite of downstream tasks, ranging from cross-modal alignment to classification and temporal analysis. Importantly, our representations are robust across diverse camera pose estimation methods, including both high-fidelity multi-sensored and standard RGB-only estimators. Our findings establish camera trajectory as a lightweight, robust, and versatile modality for perceiving video content. --- ### Seeing without Pixels: Perception from Camera Trajectories Authors: Zihui Xue, Kristen Grauman, Dima Damen, Andrew Zisserman, Tengda Han Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21681v1 Can one perceive a video's content without seeing its pixels, just from the camera trajectory-the path it carves through space? This paper is the first to systematically investigate this seemingly implausible question. Towards this end, we propose a contrastive learning framework to train CamFormer, a dedicated encoder that projects camera pose trajectories into a joint embedding space, aligning them with natural language. We find that, contrary to its apparent simplicity, the camera trajectory is a remarkably informative signal to uncover video content. In other words, "how you move" can indeed reveal "what you are doing" (egocentric) or "observing" (exocentric). We demonstrate the versatility of our learned CamFormer embeddings on a diverse suite of downstream tasks, ranging from cross-modal alignment to classification and temporal analysis. Importantly, our representations are robust across diverse camera pose estimation methods, including both high-fidelity multi-sensored and standard RGB-only estimators. Our findings establish camera trajectory as a lightweight, robust, and versatile modality for perceiving video content. --- ### Agentic Learner with Grow-and-Refine Multimodal Semantic Memory Authors: Weihao Bo, Shan Zhang, Yanpeng Sun, Jingjing Wu, Qunyi Xie, Xiao Tan, Kunbin Chen, Wei He, Xiaofan Li, Na Zhao, Jingdong Wang, Zechao Li Published: 2025-11-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.21678v2 MLLMs exhibit strong reasoning on isolated queries, yet they operate de novo -- solving each problem independently and often repeating the same mistakes. Existing memory-augmented agents mainly store past trajectories for reuse. However, trajectory-based memory suffers from brevity bias, gradually losing essential domain knowledge. More critically, even in truly multimodal problem-solving settings, it records only a single-modality trace of past behavior, failing to preserve how visual attention and logical reasoning jointly contributed to the solution. This is fundamentally misaligned with human cognition: semantic memory is both multimodal and integrated, preserving visual and abstract knowledge through coordinated but distinct representational streams. We thus introduce ViLoMem, a dual-stream memory framework that constructs compact, schema-based memory. It separately encodes visual distraction patterns and logical reasoning errors, enabling MLLMs to learn from their successful and failed experiences. Following a grow-and-refine principle, the system incrementally accumulates and updates multimodal semantic knowledge -- preserving stable, generalizable strategies while avoiding catastrophic forgetting. Across six multimodal benchmarks, ViLoMem consistently improves pass@1 accuracy and substantially reduces repeated visual and logical errors. Ablations confirm the necessity of dual-stream memory with explicit distraction-hallucination separation, demonstrating the value of error-aware multimodal memory for lifelong and cross-domain agentic learning. Our project page is available at https://weihao-bo.github.io/ViLoMeo-page. --- ### Agentic Learner with Grow-and-Refine Multimodal Semantic Memory Authors: Weihao Bo, Shan Zhang, Yanpeng Sun, Jingjing Wu, Qunyi Xie, Xiao Tan, Kunbin Chen, Wei He, Xiaofan Li, Na Zhao, Jingdong Wang, Zechao Li Published: 2025-11-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.21678v1 MLLMs exhibit strong reasoning on isolated queries, yet they operate de novo -- solving each problem independently and often repeating the same mistakes. Existing memory-augmented agents mainly store past trajectories for reuse. However, trajectory-based memory suffers from brevity bias, gradually losing essential domain knowledge. More critically, even in truly multimodal problem-solving settings, it records only a single-modality trace of past behavior, failing to preserve how visual attention and logical reasoning jointly contributed to the solution. This is fundamentally misaligned with human cognition: semantic memory is both multimodal and integrated, preserving visual and abstract knowledge through coordinated but distinct representational streams. We thus introduce ViLoMem, a dual-stream memory framework that constructs compact, schema-based memory. It separately encodes visual distraction patterns and logical reasoning errors, enabling MLLMs to learn from their successful and failed experiences. Following a grow-and-refine principle, the system incrementally accumulates and updates multimodal semantic knowledge -- preserving stable, generalizable strategies while avoiding catastrophic forgetting. Across six multimodal benchmarks, ViLoMem consistently improves pass@1 accuracy and substantially reduces repeated visual and logical errors. Ablations confirm the necessity of dual-stream memory with explicit distraction--hallucination separation, demonstrating the value of error-aware multimodal memory for lifelong and cross-domain agentic learning. Our project page will be available at https://weihao-bo.github.io/ViLoMeo-page. --- ### On Evolution-Based Models for Experimentation Under Interference Authors: Sadegh Shirani, Mohsen Bayati Published: 2025-11-26 Categories: stat.ML, cs.LG, cs.SI, econ.EM arXiv: https://arxiv.org/abs/2511.21675v1 Causal effect estimation in networked systems is central to data-driven decision making. In such settings, interventions on one unit can spill over to others, and in complex physical or social systems, the interaction pathways driving these interference structures remain largely unobserved. We argue that for identifying population-level causal effects, it is not necessary to recover the exact network structure; instead, it suffices to characterize how those interactions contribute to the evolution of outcomes. Building on this principle, we study an evolution-based approach that investigates how outcomes change across observation rounds in response to interventions, hence compensating for missing network information. Using an exposure-mapping perspective, we give an axiomatic characterization of when the empirical distribution of outcomes follows a low-dimensional recursive equation, and identify minimal structural conditions under which such evolution mappings exist. We frame this as a distributional counterpart to difference-in-differences. Rather than assuming parallel paths for individual units, it exploits parallel evolution patterns across treatment scenarios to estimate counterfactual trajectories. A key insight is that treatment randomization plays a role beyond eliminating latent confounding; it induces an implicit sampling from hidden interference channels, enabling consistent learning about heterogeneous spillover effects. We highlight causal message passing as an instantiation of this method in dense networks while extending to more general interference structures, including influencer networks where a small set of units drives most spillovers. Finally, we discuss the limits of this approach, showing that strong temporal trends or endogenous interference can undermine identification. --- ### Event-driven eligibility propagation in large sparse networks: efficiency shaped by biological realism Authors: Agnes Korcsak-Gorzo, Jesús A. Espinoza Valverde, Jonas Stapmanns, Hans Ekkehard Plesser, David Dahmen, Matthias Bolten, Sacha J. van Albada, Markus Diesmann Published: 2025-11-26 Categories: cs.NE, q-bio.NC arXiv: https://arxiv.org/abs/2511.21674v1 Despite remarkable technological advances, AI systems may still benefit from biological principles, such as recurrent connectivity and energy-efficient mechanisms. Drawing inspiration from the brain, we present a biologically plausible extension of the eligibility propagation (e-prop) learning rule for recurrent spiking networks. By translating the time-driven update scheme into an event-driven one, we integrate the learning rule into a simulation platform for large-scale spiking neural networks and demonstrate its applicability to tasks such as neuromorphic MNIST. We extend the model with prominent biological features such as continuous dynamics and weight updates, strict locality, and sparse connectivity. Our results show that biologically grounded constraints can inform the design of computationally efficient AI algorithms, offering scalability to millions of neurons without compromising learning performance. This work bridges machine learning and computational neuroscience, paving the way for sustainable, biologically inspired AI systems while advancing our understanding of brain-like learning. --- ### Revolutionizing Glioma Segmentation & Grading Using 3D MRI - Guided Hybrid Deep Learning Models Authors: Pandiyaraju V, Sreya Mynampati, Abishek Karthik, Poovarasan L, D. Saraswathi Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21673v1 Gliomas are brain tumor types that have a high mortality rate which means early and accurate diagnosis is important for therapeutic intervention for the tumors. To address this difficulty, the proposed research will develop a hybrid deep learning model which integrates U-Net based segmentation and a hybrid DenseNet-VGG classification network with multihead attention and spatial-channel attention capabilities. The segmentation model will precisely demarcate the tumors in a 3D volume of MRI data guided by spatial and contextual information. The classification network which combines a branch of both DenseNet and VGG, will incorporate the demarcated tumor on which features with attention mechanisms would be focused on clinically relevant features. High-dimensional 3D MRI data could successfully be utilized in the model through preprocessing steps which are normalization, resampling, and data augmentation. Through a variety of measures the framework is evaluated: measures of performance in segmentation are Dice coefficient and Mean Intersection over Union (IoU) and measures of performance in classification are accuracy precision, recall, and F1-score. The hybrid framework that has been proposed has demonstrated through physical testing that it has the capability of obtaining a Dice coefficient of 98% in tumor segmentation, and 99% on classification accuracy, outperforming traditional CNN models and attention-free methods. Utilizing multi-head attention mechanisms enhances notions of priority in aspects of the tumor that are clinically significant, and enhances interpretability and accuracy. The results suggest a great potential of the framework in facilitating the timely and reliable diagnosis and grading of glioma by clinicians is promising, allowing for better planning of patient treatment. --- ### DSD: A Distributed Speculative Decoding Solution for Edge-Cloud Agile Large Model Serving Authors: Fengze Yu, Leshu Li, Brad McDanel, Sai Qian Zhang Published: 2025-11-26 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2511.21669v2 Large language model (LLM) inference often suffers from high decoding latency and limited scalability across heterogeneous edge-cloud environments. Existing speculative decoding (SD) techniques accelerate token generation but remain confined to single-node execution. We propose DSD, a distributed speculative decoding framework that extends SD to multi-device deployments through coordinated draft-target execution. Given the lack of prior work on simulating this paradigm, we first introduce DSD-Sim, a discrete-event simulator that captures network, batching, and scheduling dynamics. Building on insights from DSD-Sim, we further design an Adaptive Window Control (AWC) policy that dynamically adjusts speculation window size to optimize throughput. Experiments across diverse workloads show that DSD achieves up to 1.1x speedup and 9.7% higher throughput over existing SD baselines, enabling agile and scalable LLM serving across edge and cloud. --- ### DSD: A Distributed Speculative Decoding Solution for Edge-Cloud Agile Large Model Serving Authors: Fengze Yu, Leshu Li, Brad McDanel, Saiqian Zhang Published: 2025-11-26 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2511.21669v1 Large language model (LLM) inference often suffers from high decoding latency and limited scalability across heterogeneous edge-cloud environments. Existing speculative decoding (SD) techniques accelerate token generation but remain confined to single-node execution. We propose DSD, a distributed speculative decoding framework that extends SD to multi-device deployments through coordinated draft-target execution. Given the lack of prior work on simulating this paradigm, we first introduce DSD-Sim, a discrete-event simulator that captures network, batching, and scheduling dynamics. Building on insights from DSD-Sim, we further design an Adaptive Window Control (AWC) policy that dynamically adjusts speculation window size to optimize throughput. Experiments across diverse workloads show that DSD achieves up to 1.1x speedup and 9.7% higher throughput over existing SD baselines, enabling agile and scalable LLM serving across edge and cloud. --- ### Through the telecom lens: Are all training samples important? Authors: Shruti Bothe, Illyyne Saffar, Aurelie Boisbunon, Hasan Farooq, Julien Forgeat, Md Moin Uddin Chowdhury Published: 2025-11-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.21668v1 The rise of AI in telecommunications, from optimizing Radio Access Networks to managing user experience, has sharply increased data volumes and training demands. Telecom data is often noisy, high-dimensional, costly to store, process, and label. Despite Ai's critical role, standard workflows still assume all training samples contribute equally. On the other hand, next generation systems require AI models that are accurate, efficient, and sustainable.The paper questions the assumptions of equal importance by focusing on applying and analyzing the roles of individual samples in telecom training and assessing whether the proposed model optimizes computation and energy use. we perform sample-level gradient analysis across epochs to identify patterns of influence and redundancy in model learning. Based on this, we propose a sample importance framework thats electively prioritizes impactful data and reduces computation without compromising accuracy. Experiments on three real-world telecom datasets show that our method (reserves performance while reducing data needs and computational overhead while advancing the goals of sustainable AI in telecommunications. --- ### Escaping the Verifier: Learning to Reason via Demonstrations Authors: Locke Cai, Max Ryabinin, Ivan Provilkov Published: 2025-11-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.21667v4 Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers. However, many real-world reasoning-intensive tasks lack verifiers, despite offering abundant expert demonstrations that remain under-utilized for reasoning-focused training. We introduce RARO (Relativistic Adversarial Reasoning Optimization), which learns strong reasoning capabilities from expert demonstrations alone via Inverse Reinforcement Learning. RARO sets up an adversarial game between a policy and a relativistic critic: the policy learns to mimic expert answers, while the critic aims to identify the experts among expert-policy answer pairs. Both the policy and the critic are trained jointly and continuously via RL, and we identify the key stabilization techniques required for robust learning. Empirically, RARO significantly outperforms strong verifier-free baselines across all evaluation tasks: +13.7% accuracy on Countdown (1.5B), +8.2% accuracy on DeepMath (7B), and +19.1% win-rate on Poetry Writing (7B) against expert poems. RARO also exhibits similar robust scaling trends as RL with verifiers. These results demonstrate that RARO effectively elicits strong reasoning performance from expert demonstrations alone, enabling robust reasoning learning even when task-specific verifiers are unavailable. --- ### Escaping the Verifier: Learning to Reason via Demonstrations Authors: Locke Cai, Ivan Provilkov Published: 2025-11-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.21667v1 Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers. However, many real-world reasoning-intensive tasks lack verifiers, despite offering abundant expert demonstrations that remain under-utilized for reasoning-focused training. We introduce RARO (Relativistic Adversarial Reasoning Optimization) that learns strong reasoning capabilities from only expert demonstrations via Inverse Reinforcement Learning. Our method sets up an adversarial interaction between a policy (generator) and a relativistic critic (discriminator): the policy learns to mimic expert answers, while the critic learns to compare and distinguish between policy and expert answers. Our method trains both the policy and the critic jointly and continuously via RL, and we identify the key stabilization techniques required for robust learning. Empirically, RARO significantly outperforms strong verifier-free baselines on all of our evaluation tasks -- Countdown, DeepMath, and Poetry Writing -- and enjoys the same robust scaling trends as RL on verifiable tasks. These results demonstrate that our method effectively elicits strong reasoning performance from expert demonstrations alone, enabling robust reasoning learning even when task-specific verifiers are unavailable. --- ### Uncertainty Quantification for Visual Object Pose Estimation: S-Lemma Ellipsoidal Bounds Authors: Lorenzo Shaikewitz, Charis Georgiou, Luca Carlone Published: 2025-11-26 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.21666v2 Quantifying the uncertainty of an object's pose estimate is essential for robust control and planning. Although pose estimation is a well-studied robotics problem, attaching statistically rigorous uncertainty is not well understood without strict distributional assumptions. We develop distribution-free pose uncertainty bounds about a given pose estimate in the monocular setting. Our pose uncertainty only requires high probability noise bounds on pixel detections of 2D semantic keypoints on a known object. This noise model induces an implicit, non-convex set of pose uncertainty constraints. Our key contribution is SLUE (S-Lemma Uncertainty Estimation), a convex program to reduce this set to a single ellipsoidal uncertainty bound that is guaranteed to contain the true object pose with high probability. SLUE solves a relaxation of the minimum volume bounding ellipsoid problem inspired by the celebrated S-lemma. It requires no initial guess of the bound's shape or size and is guaranteed to contain the true object pose with high probability. For tighter uncertainty bounds at the same confidence, we extend SLUE to a sum-of-squares relaxation hierarchy which is guaranteed to converge to the minimum volume ellipsoidal uncertainty bound for a given set of keypoint constraints. We show this pose uncertainty bound can easily be projected to independent translation and axis-angle orientation bounds. We evaluate SLUE on two pose estimation datasets and a real-world drone tracking scenario. Compared to prior work, SLUE generates substantially smaller translation bounds and competitive orientation bounds. We release code at https://github.com/MIT-SPARK/PoseUncertaintySets. --- ### Uncertainty Quantification for Visual Object Pose Estimation Authors: Lorenzo Shaikewitz, Charis Georgiou, Luca Carlone Published: 2025-11-26 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.21666v1 Quantifying the uncertainty of an object's pose estimate is essential for robust control and planning. Although pose estimation is a well-studied robotics problem, attaching statistically rigorous uncertainty is not well understood without strict distributional assumptions. We develop distribution-free pose uncertainty bounds about a given pose estimate in the monocular setting. Our pose uncertainty only requires high probability noise bounds on pixel detections of 2D semantic keypoints on a known object. This noise model induces an implicit, non-convex set of pose uncertainty constraints. Our key contribution is SLUE (S-Lemma Uncertainty Estimation), a convex program to reduce this set to a single ellipsoidal uncertainty bound that is guaranteed to contain the true object pose with high probability. SLUE solves a relaxation of the minimum volume bounding ellipsoid problem inspired by the celebrated S-lemma. It requires no initial guess of the bound's shape or size and is guaranteed to contain the true object pose with high probability. For tighter uncertainty bounds at the same confidence, we extend SLUE to a sum-of-squares relaxation hierarchy which is guaranteed to converge to the minimum volume ellipsoidal uncertainty bound for a given set of keypoint constraints. We show this pose uncertainty bound can easily be projected to independent translation and axis-angle orientation bounds. We evaluate SLUE on two pose estimation datasets and a real-world drone tracking scenario. Compared to prior work, SLUE generates substantially smaller translation bounds and competitive orientation bounds. We release code at https://github.com/MIT-SPARK/PoseUncertaintySets. --- ### Attention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Models Authors: Naifu Zhang, Wei Tao, Xi Xiao, Qianpu Sun, Yuxin Zheng, Wentao Mo, Peiqiang Wang, Nan Zhang Published: 2025-11-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.21663v1 In recent years, Vision-Language-Action (VLA) models in embodied intelligence have developed rapidly. However, existing adversarial attack methods require costly end-to-end training and often generate noticeable perturbation patches. To address these limitations, we propose ADVLA, a framework that directly applies adversarial perturbations on features projected from the visual encoder into the textual feature space. ADVLA efficiently disrupts downstream action predictions under low-amplitude constraints, and attention guidance allows the perturbations to be both focused and sparse. We introduce three strategies that enhance sensitivity, enforce sparsity, and concentrate perturbations. Experiments demonstrate that under an $L_{\infty}=4/255$ constraint, ADVLA combined with Top-K masking modifies less than 10% of the patches while achieving an attack success rate of nearly 100%. The perturbations are concentrated on critical regions, remain almost imperceptible in the overall image, and a single-step iteration takes only about 0.06 seconds, significantly outperforming conventional patch-based attacks. In summary, ADVLA effectively weakens downstream action predictions of VLA models under low-amplitude and locally sparse conditions, avoiding the high training costs and conspicuous perturbations of traditional patch attacks, and demonstrates unique effectiveness and practical value for attacking VLA feature spaces. --- ### Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following Authors: Tianyi Xiong, Yi Ge, Ming Li, Zuolong Zhang, Pranav Kulkarni, Kaishen Wang, Qi He, Zeying Zhu, Chenxi Liu, Ruibo Chen, Tong Zheng, Yanshuo Chen et al. Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21662v2 Large multimodal models (LMMs) are increasingly adopted as judges in multimodal evaluation systems due to their strong instruction following and consistency with human preferences. However, their ability to follow diverse, fine-grained evaluation criteria remains underexplored. We develop Multi-Crit, a benchmark for evaluating multimodal judges on their capacity to follow pluralistic criteria and produce reliable criterion-level judgments. Covering both open-ended generation and verifiable reasoning tasks, Multi-Crit is built through a rigorous data curation pipeline that gathers challenging response pairs with multi-criterion human annotations. It further introduces three novel metrics for systematically assessing pluralistic adherence, criterion-switching flexibility, and the ability to recognize criterion-level preference conflicts. Comprehensive analysis of 25 LMMs reveals that 1) proprietary models still struggle to maintain consistent adherence to pluralistic criteria--especially in open-ended evaluation; 2) open-source models lag further behind in flexibly following diverse criteria; and 3) critic fine-tuning with holistic judgment signals enhances visual grounding but fails to generalize to pluralistic criterion-level judgment. Additional analyses on reasoning fine-tuning, test-time scaling, and boundary consistency between open-source and proprietary models further probe the limits of current multimodal judges. As a pioneering study, Multi-Crit lays the foundation for building reliable and steerable multimodal AI evaluation. --- ### Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following Authors: Tianyi Xiong, Yi Ge, Ming Li, Zuolong Zhang, Pranav Kulkarni, Kaishen Wang, Qi He, Zeying Zhu, Chenxi Liu, Ruibo Chen, Tong Zheng, Yanshuo Chen et al. Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21662v1 Large multimodal models (LMMs) are increasingly adopted as judges in multimodal evaluation systems due to their strong instruction following and consistency with human preferences. However, their ability to follow diverse, fine-grained evaluation criteria remains underexplored. We develop Multi-Crit, a benchmark for evaluating multimodal judges on their capacity to follow pluralistic criteria and produce reliable criterion-level judgments. Covering both open-ended generation and verifiable reasoning tasks, Multi-Crit is built through a rigorous data curation pipeline that gathers challenging response pairs with multi-criterion human annotations. It further introduces three novel metrics for systematically assessing pluralistic adherence, criterion-switching flexibility, and the ability to recognize criterion-level preference conflicts. Comprehensive analysis of 25 LMMs reveals that 1) proprietary models still struggle to maintain consistent adherence to pluralistic criteria--especially in open-ended evaluation; 2) open-source models lag further behind in flexibly following diverse criteria; and 3) critic fine-tuning with holistic judgment signals enhances visual grounding but fails to generalize to pluralistic criterion-level judgment. Additional analyses on reasoning fine-tuning, test-time scaling, and boundary consistency between open-source and proprietary models further probe the limits of current multimodal judges. As a pioneering study, Multi-Crit lays the foundation for building reliable and steerable multimodal AI evaluation. --- ### EvilGenie: A Reward Hacking Benchmark Authors: Jonathan Gabor, Jayson Lynch, Jonathan Rosenfeld Published: 2025-11-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.21654v2 We introduce EvilGenie, a benchmark for reward hacking in programming settings. We source problems from LiveCodeBench and create an environment in which agents can easily reward hack, such as by hardcoding test cases or editing the testing files. We measure reward hacking in three ways: held out unit tests, LLM judges, and test file edit detection. We verify these methods against human review and each other. We find the LLM judge to be highly effective at detecting reward hacking in unambiguous cases, and observe only minimal improvement from the use of held out test cases. In addition to testing many models using Inspect's basic\_agent scaffold, we also measure reward hacking rates for three popular proprietary coding agents: OpenAI's Codex, Anthropic's Claude Code, and Google's Gemini CLI. We observe explicit reward hacking by both Codex and Claude Code, and misaligned behavior by all three agents. Our codebase can be found at https://github.com/JonathanGabor/evilgenie_inspect . --- ### EvilGenie: A Reward Hacking Benchmark Authors: Jonathan Gabor, Jayson Lynch, Jonathan Rosenfeld Published: 2025-11-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.21654v1 We introduce EvilGenie, a benchmark for reward hacking in programming settings. We source problems from LiveCodeBench and create an environment in which agents can easily reward hack, such as by hardcoding test cases or editing the testing files. We measure reward hacking in three ways: held out unit tests, LLM judges, and test file edit detection. We verify these methods against human review and each other. We find the LLM judge to be highly effective at detecting reward hacking in unambiguous cases, and observe only minimal improvement from the use of held out test cases. In addition to testing many models using Inspect's basic_agent scaffold, we also measure reward hacking rates for three popular proprietary coding agents: OpenAI's Codex, Anthropic's Claude Code, and Google's Gemini CLI Using GPT-5, Claude Sonnet 4, and Gemini 2.5 Pro, respectively. We observe explicit reward hacking by both Codex and Claude Code, and misaligned behavior by all three agents. Our codebase can be found at https://github.com/JonathanGabor/EvilGenie. --- ### CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flow Authors: Ruisheng Han, Kanglei Zhou, Shuang Chen, Amir Atapour-Abarghouei, Hubert P. H. Shum Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21653v1 Action Quality Assessment (AQA) predicts fine-grained execution scores from action videos and is widely applied in sports, rehabilitation, and skill evaluation. Long-term AQA, as in figure skating or rhythmic gymnastics, is especially challenging since it requires modeling extended temporal dynamics while remaining robust to contextual confounders. Existing approaches either depend on costly annotations or rely on unidirectional temporal modeling, making them vulnerable to spurious correlations and unstable long-term representations. To this end, we propose CaFlow, a unified framework that integrates counterfactual de-confounding with bidirectional time-conditioned flow. The Causal Counterfactual Regularization (CCR) module disentangles causal and confounding features in a self-supervised manner and enforces causal robustness through counterfactual interventions, while the BiT-Flow module models forward and backward dynamics with a cycle-consistency constraint to produce smoother and more coherent representations. Extensive experiments on multiple long-term AQA benchmarks demonstrate that CaFlow achieves state-of-the-art performance. Code is available at https://github.com/Harrison21/CaFlow --- ### Continual Error Correction on Low-Resource Devices Authors: Kirill Paramonov, Mete Ozay, Aristeidis Mystakidis, Nikolaos Tsalikidis, Dimitrios Sotos, Anastasios Drosou, Dimitrios Tzovaras, Hyunjun Kim, Kiseok Chang, Sangdok Mo, Namwoong Kim, Woojong Yoo et al. Published: 2025-11-26 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.21652v1 The proliferation of AI models in everyday devices has highlighted a critical challenge: prediction errors that degrade user experience. While existing solutions focus on error detection, they rarely provide efficient correction mechanisms, especially for resource-constrained devices. We present a novel system enabling users to correct AI misclassifications through few-shot learning, requiring minimal computational resources and storage. Our approach combines server-side foundation model training with on-device prototype-based classification, enabling efficient error correction through prototype updates rather than model retraining. The system consists of two key components: (1) a server-side pipeline that leverages knowledge distillation to transfer robust feature representations from foundation models to device-compatible architectures, and (2) a device-side mechanism that enables ultra-efficient error correction through prototype adaptation. We demonstrate our system's effectiveness on both image classification and object detection tasks, achieving over 50% error correction in one-shot scenarios on Food-101 and Flowers-102 datasets while maintaining minimal forgetting (less than 0.02%) and negligible computational overhead. Our implementation, validated through an Android demonstration app, proves the system's practicality in real-world scenarios. --- ### Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHF Authors: Daniel R. Jiang, Ankur Samanta, Yukai Yang, Jalaj Bhandari, Rémi Munos, Tyler Lu Published: 2025-11-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.21638v3 Practical LLM agents often operate over multi-turn conversations where success is determined only after the full interaction ends. Most multi-turn RL methods train via on-policy rollouts, but unlike in single-turn RLHF, the policy cannot produce a trajectory alone, since an external environment must respond after each agent turn. For conversational agents, this environment is a user, but real users are generally unavailable inside the training loop and simulated users are difficult to build faithfully. Separately, real-world deployment is rarely fully online or fully offline. The common production pattern is called "batch online," where the current policy is deployed to collect a batch of interaction data, then retrained on that batch and redeployed. We show that this batch-online setting creates an opportunity for applying the classical approximate policy iteration algorithm. Our central observation is that running standard token-level, single-turn GRPO with a learned turn-level $Q$-function as the reward model is a policy improvement step for the multi-turn problem. Building on this, we present Iterative GRPO, which alternates between fitting $Q^π$ from logged Monte Carlo returns via standard reward modeling (policy evaluation) and running single-turn GRPO against $Q^π$ (policy improvement). During policy improvement, the learned $Q^π$ scores candidate responses by their expected downstream return, avoiding the need for simulator rollouts of the remaining conversation. Overall, this allows us to do principled multi-turn RL using only single-turn RLHF methods without an interactive environment or user simulator inside the training loop. We demonstrate the effectiveness of Iterative GRPO on six multi-turn negotiation environments. --- ### Aligning LLMs Toward Multi-Turn Conversational Outcomes Using Iterative PPO Authors: Daniel R. Jiang, Jalaj Bhandari, Yukai Yang, Rémi Munos, Tyler Lu Published: 2025-11-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.21638v1 Optimizing large language models (LLMs) for multi-turn conversational outcomes remains a significant challenge, especially in goal-oriented settings like AI marketing or sales agents who facilitate transactions via messaging platforms. The difficulty stems from sparse, long-horizon rewards and the discrepancy between response-level planning and token-level generation. In this technical note, we propose a formal reduction of the multi-turn RL problem into a sequence of single-turn RLHF-style problems. This is achieved by setting a learned multi-turn Q-function as the reward model for the single-turn problem. We demonstrate and prove a key insight: solving this single-turn RL problem with standard token-level PPO is equivalent to a policy improvement step within the multi-turn problem. This insight naturally leads to Iterative PPO, a batch online policy iteration algorithm that alternates between fitting Q-functions from logged conversation trajectories and improving the policy. A major practical advantage is that Iterative PPO directly leverages stable, off-the-shelf single-turn RLHF tools, making it straightforward to implement. Our method occupies a middle ground between fully online and fully offline approaches, retaining the adaptability of online updates while gaining the stability benefits of offline training. --- ### Bridging the Unavoidable A Priori: A Framework for Comparative Causal Modeling Authors: Peter S. Hovmand, Kari O'Donnell, Callie Ogland-Hand, Brian Biroscak, Douglas D. Gunzler Published: 2025-11-26 Categories: cs.AI, stat.AP, stat.CO, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2511.21636v1 AI/ML models have rapidly gained prominence as innovations for solving previously unsolved problems and their unintended consequences from amplifying human biases. Advocates for responsible AI/ML have sought ways to draw on the richer causal models of system dynamics to better inform the development of responsible AI/ML. However, a major barrier to advancing this work is the difficulty of bringing together methods rooted in different underlying assumptions (i.e., Dana Meadow's "the unavoidable a priori"). This paper brings system dynamics and structural equation modeling together into a common mathematical framework that can be used to generate systems from distributions, develop methods, and compare results to inform the underlying epistemology of system dynamics for data science and AI/ML applications. --- ### Mechanisms of Non-Monotonic Scaling in Vision Transformers Authors: Anantha Padmanaban Krishna Kumar Published: 2025-11-26 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.21635v1 Deeper Vision Transformers often perform worse than shallower ones, which challenges common scaling assumptions. Through a systematic empirical analysis of ViT-S, ViT-B, and ViT-L on ImageNet, we identify a consistent three-phase Cliff-Plateau-Climb pattern that governs how representations evolve with depth. We observe that better performance is associated with progressive marginalization of the (CLS) token, originally designed as a global aggregation hub, in favor of distributed consensus among patch tokens. We quantify patterns of information mixing with an Information Scrambling Index, and show that in ViT-L the information-task tradeoff emerges roughly 10 layers later than in ViT-B, and that these additional layers correlate with increased information diffusion rather than improved task performance. Taken together, these results suggest that transformer architectures in this regime may benefit more from carefully calibrated depth that executes clean phase transitions than from simply increasing parameter count. The Information Scrambling Index provides a useful diagnostic for existing models and suggests a potential design target for future architectures. All code is available at: https://github.com/AnanthaPadmanaban-KrishnaKumar/Cliff-Plateau-Climb. --- ### Qwen3-VL Technical Report Authors: Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, Xionghui Chen, Zesen Cheng, Lianghao Deng, Wei Ding, Chang Gao, Chunjiang Ge, Wenbin Ge, Zhifang Guo et al. Published: 2025-11-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.21631v2 We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively supports interleaved contexts of up to 256K tokens, seamlessly integrating text, images, and video. The model family includes both dense (2B/4B/8B/32B) and mixture-of-experts (30B-A3B/235B-A22B) variants to accommodate diverse latency-quality trade-offs. Qwen3-VL delivers three core pillars: (i) markedly stronger pure-text understanding, surpassing comparable text-only backbones in several cases; (ii) robust long-context comprehension with a native 256K-token window for both text and interleaved multimodal inputs, enabling faithful retention, retrieval, and cross-referencing across long documents and videos; and (iii) advanced multimodal reasoning across single-image, multi-image, and video tasks, demonstrating leading performance on comprehensive evaluations such as MMMU and visual-math benchmarks (e.g., MathVista and MathVision). Architecturally, we introduce three key upgrades: (i) an enhanced interleaved-MRoPE for stronger spatial-temporal modeling across images and video; (ii) DeepStack integration, which effectively leverages multi-level ViT features to tighten vision-language alignment; and (iii) text-based time alignment for video, evolving from T-RoPE to explicit textual timestamp alignment for more precise temporal grounding. Under comparable token budgets and latency constraints, Qwen3-VL achieves superior performance in both dense and Mixture-of-Experts (MoE) architectures. We envision Qwen3-VL serving as a foundational engine for image-grounded reasoning, agentic decision-making, and multimodal code intelligence in real-world workflows. --- ### Qwen3-VL Technical Report Authors: Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, Xionghui Chen, Zesen Cheng, Lianghao Deng, Wei Ding, Chang Gao, Chunjiang Ge, Wenbin Ge, Zhifang Guo et al. Published: 2025-11-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.21631v1 We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively supports interleaved contexts of up to 256K tokens, seamlessly integrating text, images, and video. The model family includes both dense (2B/4B/8B/32B) and mixture-of-experts (30B-A3B/235B-A22B) variants to accommodate diverse latency-quality trade-offs. Qwen3-VL delivers three core pillars: (i) markedly stronger pure-text understanding, surpassing comparable text-only backbones in several cases; (ii) robust long-context comprehension with a native 256K-token window for both text and interleaved multimodal inputs, enabling faithful retention, retrieval, and cross-referencing across long documents and videos; and (iii) advanced multimodal reasoning across single-image, multi-image, and video tasks, demonstrating leading performance on comprehensive evaluations such as MMMU and visual-math benchmarks (e.g., MathVista and MathVision). Architecturally, we introduce three key upgrades: (i) an enhanced interleaved-MRoPE for stronger spatial-temporal modeling across images and video; (ii) DeepStack integration, which effectively leverages multi-level ViT features to tighten vision-language alignment; and (iii) text-based time alignment for video, evolving from T-RoPE to explicit textual timestamp alignment for more precise temporal grounding. Under comparable token budgets and latency constraints, Qwen3-VL achieves superior performance in both dense and Mixture-of-Experts (MoE) architectures. We envision Qwen3-VL serving as a foundational engine for image-grounded reasoning, agentic decision-making, and multimodal code intelligence in real-world workflows. --- ### The author is dead, but what if they never lived? A reception experiment on Czech AI- and human-authored poetry Authors: Anna Marklová, Ondřej Vinš, Martina Vokáčová, Jiří Milička Published: 2025-11-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.21629v1 Large language models are increasingly capable of producing creative texts, yet most studies on AI-generated poetry focus on English -- a language that dominates training data. In this paper, we examine the perception of AI- and human-written Czech poetry. We ask if Czech native speakers are able to identify it and how they aesthetically judge it. Participants performed at chance level when guessing authorship (45.8\% correct on average), indicating that Czech AI-generated poems were largely indistinguishable from human-written ones. Aesthetic evaluations revealed a strong authorship bias: when participants believed a poem was AI-generated, they rated it as less favorably, even though AI poems were in fact rated equally or more favorably than human ones on average. The logistic regression model uncovered that the more the people liked a poem, the less probable was that they accurately assign the authorship. Familiarity with poetry or literary background had no effect on recognition accuracy. Our findings show that AI can convincingly produce poetry even in a morphologically complex, low-resource (with respect of the training data of AI models) Slavic language such as Czech. The results suggest that readers' beliefs about authorship and the aesthetic evaluation of the poem are interconnected. --- ### Scale-Agnostic Kolmogorov-Arnold Geometry in Neural Networks Authors: Mathew Vanherreweghe, Michael H. Freedman, Keith M. Adams Published: 2025-11-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.21626v3 Recent work by Freedman and Mulligan demonstrated that shallow multilayer perceptrons spontaneously develop Kolmogorov-Arnold geometric (KAG) structure during training on synthetic three-dimensional tasks. However, it remained unclear whether this phenomenon persists in realistic high-dimensional settings and what spatial properties this geometry exhibits. We extend KAG analysis to MNIST digit classification (784 dimensions) using 2-layer MLPs with systematic spatial analysis at multiple scales. We find that KAG emerges during training and appears consistently across spatial scales, from local 7-pixel neighborhoods to the full 28x28 image. This scale-agnostic property holds across different training procedures: both standard training and training with spatial augmentation produce the same qualitative pattern. These findings reveal that neural networks spontaneously develop organized, scale-invariant geometric structure during learning on realistic high-dimensional data. --- ### Scale-Agnostic Kolmogorov-Arnold Geometry in Neural Networks Authors: Mathew Vanherreweghe, Michael H. Freedman, Keith M. Adams Published: 2025-11-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.21626v1 Recent work by Freedman and Mulligan demonstrated that shallow multilayer perceptrons spontaneously develop Kolmogorov-Arnold geometric (KAG) structure during training on synthetic three-dimensional tasks. However, it remained unclear whether this phenomenon persists in realistic high-dimensional settings and what spatial properties this geometry exhibits. We extend KAG analysis to MNIST digit classification (784 dimensions) using 2-layer MLPs with systematic spatial analysis at multiple scales. We find that KAG emerges during training and appears consistently across spatial scales, from local 7-pixel neighborhoods to the full 28x28 image. This scale-agnostic property holds across different training procedures: both standard training and training with spatial augmentation produce the same qualitative pattern. These findings reveal that neural networks spontaneously develop organized, scale-invariant geometric structure during learning on realistic high-dimensional data. --- ### Active Learning for GCN-based Action Recognition Authors: Hichem Sahbi Published: 2025-11-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.21625v1 Despite the notable success of graph convolutional networks (GCNs) in skeleton-based action recognition, their performance often depends on large volumes of labeled data, which are frequently scarce in practical settings. To address this limitation, we propose a novel label-efficient GCN model. Our work makes two primary contributions. First, we develop a novel acquisition function that employs an adversarial strategy to identify a compact set of informative exemplars for labeling. This selection process balances representativeness, diversity, and uncertainty. Second, we introduce bidirectional and stable GCN architectures. These enhanced networks facilitate a more effective mapping between the ambient and latent data spaces, enabling a better understanding of the learned exemplar distribution. Extensive evaluations on two challenging skeleton-based action recognition benchmarks reveal significant improvements achieved by our label-efficient GCNs compared to prior work. --- ### TAGFN: A Text-Attributed Graph Dataset for Fake News Detection in the Age of LLMs Authors: Kay Liu, Yuwei Han, Haoyan Xu, Henry Peng Zou, Yue Zhao, Philip S. Yu Published: 2025-11-26 Categories: cs.SI, cs.CL arXiv: https://arxiv.org/abs/2511.21624v1 Large Language Models (LLMs) have recently revolutionized machine learning on text-attributed graphs, but the application of LLMs to graph outlier detection, particularly in the context of fake news detection, remains significantly underexplored. One of the key challenges is the scarcity of large-scale, realistic, and well-annotated datasets that can serve as reliable benchmarks for outlier detection. To bridge this gap, we introduce TAGFN, a large-scale, real-world text-attributed graph dataset for outlier detection, specifically fake news detection. TAGFN enables rigorous evaluation of both traditional and LLM-based graph outlier detection methods. Furthermore, it facilitates the development of misinformation detection capabilities in LLMs through fine-tuning. We anticipate that TAGFN will be a valuable resource for the community, fostering progress in robust graph-based outlier detection and trustworthy AI. The dataset is publicly available at https://huggingface.co/datasets/kayzliu/TAGFN and our code is available at https://github.com/kayzliu/tagfn. ---