# Research Papers — 2026-03 · bundle page 11 of 243 > Full-text markdown of papers #501–550 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/11 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/10.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/12.md) ### Embedding-Only Uplink for Onboard Retrieval Under Shift in Remote Sensing Authors: Sangcheol Sim Published: 2026-03-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.03301v1 Downlink bottlenecks motivate onboard systems that prioritize hazards without transmitting raw pixels. We study a strict setting where a ground station uplinks only compact embeddings plus metadata, and an onboard system performs vector search to triage new captures. We ask whether this embedding-only pipeline remains useful under explicit remote-sensing shift: cross-time (pre/post-event), cross-event/location (different disasters), cross-site cloud (15 geographic sites), and cross-city AOI holdout (buildings). Using OlmoEarth embeddings on a scaled public multi-task benchmark (27 Sentinel-2 L2A scenes, 15 cloud sites, 5 SpaceNet-2 AOIs; 10 seeds), we find that all effective methods rely on the same uplinked embeddings, but the optimal decision head is task-dependent: kNN retrieval is significantly superior for cloud classification (0.92 vs. centroid 0.91; p<0.01, Wilcoxon), while class centroids dominate temporal change detection (0.85 vs. retrieval 0.48; p<0.01). These results show that embedding-only uplink is the key enabler--once embeddings are onboard, the system can select the best head per task at no additional uplink cost, with all telemetry under 1 KB per query. --- ### A Survey on AI for 6G: Challenges and Opportunities Authors: Constantina Chatzieleftheriou, Eirini Liotou Published: 2026-03-30 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2604.02370v1 As wireless communication evolves, each generation of networks brings new technologies that change how we connect and interact. Artificial Intelligence (AI) is becoming crucial in shaping the future of sixth-generation (6G) networks. By combining AI and Machine Learning (ML), 6G aims to offer high data rates, low latency, and extensive connectivity for applications including smart cities, autonomous systems, holographic telepresence, and the tactile internet. This paper provides a detailed overview of the role of AI in supporting 6G networks. It focuses on key technologies like deep learning, reinforcement learning, federated learning, and explainable AI. It also looks at how AI integrates with essential network functions and discusses challenges related to scalability, security, and energy efficiency, along with new solutions. Additionally, this work highlights perspectives that connect AI-driven analytics to 6G service domains like Ultra-Reliable Low-Latency Communication (URLLC), Enhanced Mobile Broadband (eMBB), Massive Machine-Type Communication (mMTC), and Integrated Sensing and Communication (ISAC). It addresses concerns about standardization, ethics, and sustainability. By summarizing recent research trends and identifying future directions, this survey offers a valuable reference for researchers and practitioners at the intersection of AI and next-generation wireless communication. --- ### Beyond Message Passing: A Semantic View of Agent Communication Protocols Authors: Dun Yuan, Fuyuan Lyu, Ye Yuan, Weixu Zhang, Bowei He, Jiayi Geng, Linfeng Du, Zipeng Sun, Yankai Chen, Changjiang Han, Jikun Kang, Xi Chen et al. Published: 2026-03-30 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2604.02369v3 Agent communication protocols are becoming critical infrastructure for large language model (LLM) systems that must use tools, coordinate with other agents, and operate across heterogeneous environments. This work presents a human-inspired perspective on this emerging landscape by organizing agent communication into three layers: communication, syntactic, and semantic. Under this framework, we systematically analyze 18 representative protocols and compare how they support reliable transport, structured interaction, and meaning-level coordination. Our analysis shows a clear imbalance in current protocol design. Most protocols provide increasingly mature support for transport, streaming, schema definition, and lifecycle management, but offer limited protocol-level mechanisms for clarification, context alignment, and verification. As a result, semantic responsibilities are often pushed into prompts, wrappers, or application-specific orchestration logic, creating hidden interoperability and maintenance costs. To make this gap actionable, we further identify major forms of technical debt in today's protocol ecosystem and distill practical guidance for selecting protocols under different deployment settings. We conclude by outlining a research agenda for interoperable, secure, and semantically robust agent ecosystems that move beyond message passing toward shared understanding. --- ### A Learning-Based Cooperative Coevolution Framework for Heterogeneous Large-Scale Global Optimization Authors: Wenjie Qiu, Zixin Wang, Hongyu Fang, Zeyuan Ma, Yue-Jiao Gong Published: 2026-03-30 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.01241v1 Cooperative Coevolution (CC) effectively addresses Large-Scale Global Optimization (LSGO) via decomposition but struggles with the emerging class of Heterogeneous LSGO (H-LSGO) problems arising from real-world applications, where subproblems exhibit diverse dimensions and distinct landscapes. The prevailing CC paradigm, relying on a fixed low-dimensional optimizer, often fails to navigate this heterogeneity. To address this limitation, we propose the Learning-Based Heterogeneous Cooperative Coevolution Framework (LH-CC). By formulating the optimization process as a Markov Decision Process, LH-CC employs a meta-agent to adaptively select the most suitable optimizer for each subproblem. We also introduce a flexible benchmark suite to generate diverse H-LSGO problem instances. Extensive experiments on 3000-dimensional problems with complex coupling relationships demonstrate that LH-CC achieves superior solution quality and computational efficiency compared to state-of-the-art baselines. Furthermore, the framework exhibits robust generalization across varying problem instances, optimization horizons, and optimizers. Our findings reveal that dynamic optimizer selection is a pivotal strategy for solving complex H-LSGO problems. --- ### Task-Centric Personalized Federated Fine-Tuning of Language Models Authors: Gabriel U. Talasso, Meghdad Kurmanji, Allan M. de Souza, Nicholas D. Lane, Leandro A. Villas Published: 2026-03-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.00050v2 Federated Learning (FL) has emerged as a promising technique for training language models on distributed and private datasets of diverse tasks. However, aggregating models trained on heterogeneous tasks often degrades the overall performance of individual clients. To address this issue, Personalized FL (pFL) aims to create models tailored for each client's data distribution. Although these approaches improve local performance, they usually lack robustness in two aspects: (i) generalization: when clients must make predictions on unseen tasks, or face changes in their data distributions, and (ii) intra-client tasks interference: when a single client's data contains multiple distributions that may interfere with each other during local training. To tackle these two challenges, we propose FedRouter, a clustering-based pFL that builds specialized models for each task rather than for each client. FedRouter uses adapters to personalize models by employing two clustering mechanisms to associate adapters with specific tasks. A local clustering that associate adapters with task data samples and a global one that associates similar adapters from different clients to construct task-centric personalized models. Additionally, we propose an evaluation router mechanism that routes test samples to the best adapter based on the created clusters. Experiments comparing our method with existing approaches across a multitask dataset, FedRouter demonstrate strong resilience in these challenging scenarios performing up to 6.1% relatively better under tasks interference and up to 136% relative improvement under generalization evaluation. --- ### Whittaker-Henderson smoother for long satellite image time series interpolation Authors: Mathieu Fauvel Published: 2026-03-30 Categories: eess.IV, cs.AI arXiv: https://arxiv.org/abs/2604.00048v1 Whittaker smoother is a widely adopted solution to pre-process satellite image time series. Yet, two key limitations remain: the smoothing parameter must be tuned individually for each pixel, and the standard formulation assumes homoscedastic noise, imposing uniform smoothing across the temporal dimension. This paper addresses both limitations by casting the Whittaker smoother as a differentiable neural layer, in which the smoothing parameter is inferred by a neural network. The framework is further extended to handle heteroscedastic noise through a time-varying regularization, allowing the degree of smoothing to adapt locally along the time series. To enable large-scale processing, a sparse, memory-efficient, and fully differentiable implementation is proposed, exploiting the symmetric banded structure of the underlying linear system via Cholesky factorization. Benchmarks on GPU demonstrate that this implementation substantially outperforms standard dense linear solvers, both in speed and memory consumption. The approach is validated on SITS acquired over the French metropolitan territory between 2016 and 2024. Results confirm the feasibility of large-scale heteroscedastic Whittaker smoothing, though reconstruction differences with the homoscedastic baseline remain limited, suggesting that the transformer architecture used for smoothing parameter estimation may lack the temporal acuity needed to capture abrupt noise variations such as singleday cloud contamination. --- ### Realistic Market Impact Modeling for Reinforcement Learning Trading Environments Authors: Lucas Riera Abbade, Anna Helena Reali Costa Published: 2026-03-30 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2603.29086v2 Reinforcement learning (RL) has shown promise for trading, yet most open-source backtesting environments assume negligible or fixed transaction costs, causing agents to learn trading behaviors that fail under realistic execution. We introduce three Gymnasium-compatible trading environments -- MACE (Market-Adjusted Cost Execution) stock trading, margin trading, and portfolio optimization -- that integrate nonlinear market impact models grounded in the Almgren-Chriss framework and the empirically validated square-root impact law. Each environment provides pluggable cost models, permanent impact tracking with exponential decay, and comprehensive trade-level logging. We evaluate five DRL algorithms (A2C, PPO, DDPG, SAC, TD3) on the NASDAQ-100, comparing a fixed 10 bps baseline against the AC model with Optuna-tuned hyperparameters. Our results show that (i) the cost model materially changes both absolute performance and the relative ranking of algorithms across all three environments; (ii) the AC model produces dramatically different trading behavior, e.g., daily costs dropping from $200k to $8k with turnover falling from 19% to 1%; (iii) hyperparameter optimization is essential for constraining pathological trading, with costs dropping up to 82%; and (iv) algorithm-cost model interactions are strongly environment-specific, e.g., DDPG's OOS Sharpe jumps from -2.1 to 0.3 under AC in margin trading while SAC's drops from -0.5 to -1.2. We release the full suite as an open-source extension to FinRL-Meta. --- ### PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering Authors: Xingyu Li, Rongguang Wang, Yuying Wang, Mengqing Guo, Chenyang Li, Tao Sheng, Sujith Ravi, Dan Roth Published: 2026-03-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.29085v1 Large language models (LLMs) remain brittle on multi-hop question answering (MHQA), where answering requires combining evidence across documents through retrieval and reasoning. Iterative retrieval systems can fail by locking onto an early low-recall trajectory and amplifying downstream errors, while planning-only approaches may produce static query sets that cannot adapt when intermediate evidence changes. We propose \textbf{Planned Active Retrieval and Reasoning RAG (PAR$^2$-RAG)}, a two-stage framework that separates \emph{coverage} from \emph{commitment}. PAR$^2$-RAG first performs breadth-first anchoring to build a high-recall evidence frontier, then applies depth-first refinement with evidence sufficiency control in an iterative loop. Across four MHQA benchmarks, PAR$^2$-RAG consistently outperforms existing state-of-the-art baselines, compared with IRCoT, PAR$^2$-RAG achieves up to \textbf{23.5\%} higher accuracy, with retrieval gains of up to \textbf{10.5\%} in NDCG. --- ### Is the Modality Gap a Bug or a Feature? A Robustness Perspective Authors: Rhea Chowers, Oshri Naparstek, Udi Barzelay, Yair Weiss Published: 2026-03-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.29080v2 Many modern multi-modal models (e.g. CLIP) seek an embedding space in which the two modalities are aligned. Somewhat surprisingly, almost all existing models show a strong modality gap: the distribution of images is well-separated from the distribution of texts in the shared embedding space. Despite a series of recent papers on this topic, it is still not clear why this gap exists nor whether closing the gap in post-processing will lead to better performance on downstream tasks. In this paper we show that under certain conditions, minimizing the contrastive loss yields a representation in which the two modalities are separated by a global gap vector that is orthogonal to their embeddings. We also show that under these conditions the modality gap is monotonically related to robustness: decreasing the gap does not change the clean accuracy of the models but makes it less likely that a model will change its output when the embeddings are perturbed. Our experiments show that for many real-world VLMs we can significantly increase robustness by a simple post-processing step that moves one modality towards the mean of the other modality, without any loss of clean accuracy. --- ### PolarQuant: Optimal Gaussian Weight Quantization via Hadamard Rotation for LLM Compression Authors: Caio Vicentino Published: 2026-03-30 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.29078v2 We present PolarQuant, a post-training weight quantization method for large language models (LLMs) that exploits the distributional structure of neural network weights to achieve near-lossless compression. PolarQuant operates in three stages: (1) block-wise normalization to the unit hypersphere, (2) Walsh-Hadamard rotation to transform coordinates into approximately Gaussian random variables, and (3) quantization with centroids matched to the Gaussian distribution. Our ablation reveals that Hadamard rotation alone accounts for 98% of the quality improvement, reducing Qwen3.5-9B perplexity from 6.90 (absmax Q5) to 6.40 (Delta = +0.03 from FP16), making it practically lossless without any calibration data. Furthermore, PolarQuant functions as an effective preprocessing step for downstream INT4 quantizers: PolarQuant Q5 dequantized and re-quantized by torchao INT4 achieves perplexity 6.56 versus 6.68 for direct absmax INT4, while maintaining 43.1 tok/s throughput at 6.5 GB VRAM. Code and models are publicly available. --- ### Dual Perspectives in Emotion Attribution: A Generator-Interpreter Framework for Cross-Cultural Analysis of Emotion in LLMs Authors: Aizirek Turdubaeva, Uichin Lee Published: 2026-03-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.29077v1 Large language models (LLMs) are increasingly used in cross-cultural systems to understand and adapt to human emotions, which are shaped by cultural norms of expression and interpretation. However, prior work on emotion attribution has focused mainly on interpretation, overlooking the cultural background of emotion generators. This assumption of universality neglects variation in how emotions are expressed and perceived across nations. To address this gap, we propose a Generator-Interpreter framework that captures dual perspectives of emotion attribution by considering both expression and interpretation. We systematically evaluate six LLMs on an emotion attribution task using data from 15 countries. Our analysis reveals that performance variations depend on the emotion type and cultural context. Generator-interpreter alignment effects are present; the generator's country of origin has a stronger impact on performance. We call for culturally sensitive emotion modeling in LLM-based systems to improve robustness and fairness in emotion understanding across diverse cultural contexts. --- ### The Future of AI is Many, Not One Authors: Daniel J. Singer, Luca Garzino Demo Published: 2026-03-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.29075v1 The way we're thinking about generative AI right now is fundamentally individual. We see this not just in how users interact with models but also in how models are built, how they're benchmarked, and how commercial and research strategies using AI are defined. We argue that we should abandon this approach if we're hoping for AI to support groundbreaking innovation and scientific discovery. Drawing on research and formal results in complex systems, organizational behavior, and philosophy of science, we show why we should expect deep intellectual breakthroughs to come from epistemically diverse groups of AI agents working together rather than singular superintelligent agents. Having a diverse team broadens the search for solutions, delays premature consensus, and allows for the pursuit of unconventional approaches. Developing diverse AI teams also addresses AI critics' concerns that current models are constrained by past data and lack the creative insight required for innovation. The upshot, we argue, is that the future of transformative transformer-based AI is fundamentally many, not one. --- ### How much of persistent homology is topology? A quantitative decomposition for spin model phase transitions Authors: Matthew Loftus Published: 2026-03-30 Categories: cond-mat.stat-mech, cs.LG, math.AT arXiv: https://arxiv.org/abs/2603.29072v1 Point-cloud persistent homology (PH) -- computing alpha or Rips complexes on spin-position point clouds -- has been widely applied to detect phase transitions in classical spin models since Donato et al. (2016), with subsequent studies attributing the detection to the topological content of the persistence diagram. We ask a simple question that has not been posed: what fraction of the PH signal is genuinely topological? We introduce f_topo, a quantitative decomposition that separates the density-driven and topological contributions to any PH statistic by comparing real spin configurations against density-matched shuffled null models. Across the 2D Ising model (system sizes L = 16-128, ten temperatures) and Potts models (q = 3, 5), we find that H_0 statistics -- total persistence, persistence entropy, feature count -- are 94-100% density-driven (f_topo < 0.07). The density-matched shuffled null detects T_c at the identical location and with comparable peak height as real configurations, showing that density alone is sufficient for phase transition detection. However, H_1 statistics are partially topological: the topological fraction grows with system size as delta(TP_{H_1}) ~ L^{0.53} and follows a finite-size scaling collapse delta(T, L) = L^{0.53} g(tL^{1/nu}) with collapse quality CV = 0.27. The longest persistence bar is strongly topological (f_topo > 1) and scales with the correlation length. A scale-resolved analysis reveals that the topological excess shifts from large-scale to small-scale features as L increases. We propose that the TDA-for-phase-transitions community adopt shuffled null models as standard practice, and that H_1 rather than H_0 statistics be used when genuine topological information is sought. --- ### On the Mirage of Long-Range Dependency, with an Application to Integer Multiplication Authors: Zichao Wei Published: 2026-03-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.29069v2 Integer multiplication has long been considered a hard problem for neural networks, with the difficulty widely attributed to the O(n) long-range dependency induced by carry chains. We argue that this diagnosis is wrong: long-range dependency is not an intrinsic property of multiplication, but a mirage produced by the choice of computational spacetime. We formalize the notion of mirage and provide a constructive proof: when two n-bit binary integers are laid out as a 2D outer-product grid, every step of long multiplication collapses into a $3 \times 3$ local neighborhood operation. Under this representation, a neural cellular automaton with only 321 learnable parameters achieves perfect length generalization up to $683\times$ the training range. Five alternative architectures -- including Transformer (6,625 params), Transformer+RoPE, and Mamba -- all fail under the same representation. We further analyze how partial successes locked the community into an incorrect diagnosis, and argue that any task diagnosed as requiring long-range dependency should first be examined for whether the dependency is intrinsic to the task or induced by the computational spacetime. --- ### ARCS: Autoregressive Circuit Synthesis with Topology-Aware Graph Attention and Spec Conditioning Authors: Tushar Dhananjay Pathak Published: 2026-03-30 Categories: cs.LG, cs.AR arXiv: https://arxiv.org/abs/2603.29068v3 This paper presents ARCS (Autoregressive Circuit Synthesis), a system for amortized analog circuit generation. ARCS produces complete, SPICE-simulatable designs (topology and component values) in milliseconds rather than the minutes required by search-based methods. A hybrid pipeline combines two learned generators, a graph VAE and a flow-matching model, with SPICE-based ranking. It achieves 99.9% simulation validity (reward 6.43/8.0) across 32 topologies using only 8 SPICE evaluations, 40x fewer than genetic algorithms. For single-model inference, a topology-aware Graph Transformer with Best-of-3 candidate selection reaches 85% simulation validity in 97ms, over 600x faster than random search. The key technical contribution adapts Group Relative Policy Optimization (GRPO) to multi-topology circuit reinforcement learning. GRPO resolves a critical failure mode of REINFORCE, cross-topology reward distribution mismatch, through per-topology advantage normalization. This improves simulation validity by +9.6 percentage points over REINFORCE in only 500 RL steps (10x fewer). Grammar-constrained decoding additionally guarantees 100% structural validity by construction via topology-aware token masking. --- ### CivicShield: A Cross-Domain Defense-in-Depth Framework for Securing Government-Facing AI Chatbots Against Multi-Turn Adversarial Attacks Authors: KrishnaSaiReddy Patil Published: 2026-03-30 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.29062v1 LLM-based chatbots in government services face critical security gaps. Multi-turn adversarial attacks achieve over 90% success against current defenses, and single-layer guardrails are bypassed with similar rates. We present CivicShield, a cross-domain defense-in-depth framework for government-facing AI chatbots. Drawing on network security, formal verification, biological immune systems, aviation safety, and zero-trust cryptography, CivicShield introduces seven defense layers: (1) zero-trust foundation with capability-based access control, (2) perimeter input validation, (3) semantic firewall with intent classification, (4) conversation state machine with safety invariants, (5) behavioral anomaly detection, (6) multi-model consensus verification, and (7) graduated human-in-the-loop escalation. We present a formal threat model covering 8 multi-turn attack families, map the framework to NIST SP 800-53 controls across 14 families, and evaluate using ablation analysis. Theoretical analysis shows layered defenses reduce attack probability by 1-2 orders of magnitude versus single-layer approaches. Simulation against 1,436 scenarios including HarmBench (416), JailbreakBench (200), and XSTest (450) achieves 72.9% combined detection (69.5-76.0% CI) with 2.9% effective false positive rate after graduated response, while maintaining 100% detection of multi-turn crescendo and slow-drift attacks. The honest drop on real benchmarks versus author-generated scenarios (71.2% vs 76.7% on HarmBench, 47.0% vs 70.0% on JailbreakBench) validates independent evaluation importance. CivicShield addresses an open gap at the intersection of AI safety, government compliance, and practical deployment. --- ### LA-Sign: Looped Transformers with Geometry-aware Alignment for Skeleton-based Sign Language Recognition Authors: Muxin Pu, Mei Kuan Lim, Chun Yong Chong, Chen Change Loy Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.29057v2 Skeleton-based isolated sign language recognition (ISLR) demands fine-grained understanding of articulated motion across multiple spatial scales, from subtle finger movements to global body dynamics. Existing approaches typically rely on deep feed-forward architectures, which increase model capacity but lack mechanisms for recurrent refinement and structured representation. We propose LA-Sign, a looped transformer framework with geometry-aware alignment for ISLR. Instead of stacking deeper layers, LA-Sign derives its depth from recurrence, repeatedly revisiting latent representations to progressively refine motion understanding under shared parameters. To further regularise this refinement process, we present a geometry-aware contrastive objective that projects skeletal and textual features into an adaptive hyperbolic space, encouraging multi-scale semantic organisation. We study three looping designs and multiple geometric manifolds, demonstrating that encoder-decoder looping combined with adaptive Poincare alignment yields the strongest performance. Extensive experiments on WLASL and MSASL benchmarks show that LA-Sign achieves state-of-the-art results while using fewer unique layers, highlighting the effectiveness of recurrent latent refinement and geometry-aware representation learning for sign language recognition. --- ### Data-informed lifting line theory Authors: Arjun Sharma, Jonas A. Actor, Peter A. Bosler Published: 2026-03-30 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2603.29051v1 We present a data-driven framework that extends the predictive capability of classical lifting-line theory (LLT) to a wider aerodynamic regime by incorporating higher-fidelity aerodynamic data from panel method simulations. A neural network architecture with a convolutional layer followed by fully connected layers is developed, comprising two parallel subnetworks to separately process spanwise collocation points and global geometric/aerodynamic inputs such as angle of attack, chord, twist, airfoil distribution, and sweep. Among several configurations tested, this architecture is most effective in learning corrections to LLT outputs. The trained model captures higher-order three-dimensional effects in spanwise lift and drag distributions in regimes where LLT is inaccurate, such as low aspect ratios and high sweep, and generalizes well to wing configurations outside both the LLT regime and the training data range. The method retains LLT's computational efficiency, enabling integration into aerodynamic optimization loops and early-stage aircraft design studies. This approach offers a practical path for embedding high-fidelity corrections into low-order methods and may be extended to other aerodynamic prediction tasks, such as propeller performance. --- ### Let the Abyss Stare Back Adaptive Falsification for Autonomous Scientific Discovery Authors: Peiran Li, Fangzhou Lin, Shuo Xing, Jiashuo Sun, Dylan Zhang, Siyuan Yang, Chaoqun Ni, Zhengzhong Tu Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.29045v1 Autonomous scientific discovery is entering a more dangerous regime: once the evaluator is frozen, a sufficiently strong search process can learn to win the exam without learning the mechanism the task was meant to reveal. This is the idea behind our title. To let the abyss stare back is to make evaluation actively push against the candidate through adaptive falsification, rather than passively certify it through static validation. We introduce DASES, a falsification-driven framework in which an Innovator, an Abyss Falsifier, and a Mechanistic Causal Extractor co-evolve executable scientific artifacts and scientifically admissible counterexample environments under a fixed scientific contract. In a controlled loss-discovery problem with a single editable locus, DASES rejects artifacts that static validation would have accepted, identifies the first candidate that survives the admissible falsification frontier, and discovers FNG-CE, a loss that transfers beyond the synthetic discovery environment and consistently outperforms CE and CE+L2 under controlled comparisons across standard benchmarks, including ImageNet. --- ### An Empirical Recipe for Universal Phone Recognition Authors: Shikhar Bharadwaj, Chin-Jou Li, Kwanghee Choi, Eunjung Yeo, William Chen, Shinji Watanabe, David R. Mortensen Published: 2026-03-30 Categories: cs.CL, cs.LG, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2603.29042v2 Phone recognition (PR) is a key enabler of multilingual and low-resource speech processing tasks, yet robust performance remains elusive. Highly performant English-focused models do not generalize across languages, while multilingual models underutilize pretrained representations. It also remains unclear how data scale, architecture, and training objective contribute to multilingual PR. We present PhoneticXEUS -- trained on large-scale multilingual data and achieving state-of-the-art performance on both multilingual (17.7% PFER) and accented English speech (10.6% PFER). Through controlled ablations with evaluations across 100+ languages under a unified scheme, we empirically establish our training recipe and quantify the impact of SSL representations, data scale, and loss objectives. In addition, we analyze error patterns across language families, accented speech, and articulatory features. All data and code are released openly at https://github.com/changelinglab/PhoneticXeus --- ### A Latent Risk-Aware Machine Learning Approach for Predicting Operational Success in Clinical Trials based on TrialsBank Authors: Iness Halimi, Emmanuel Piffo, Oumnia Boudersa, Yvan Marcel Carre Vilmorin, Melissa Ait-ikhlef, Karima Kone, Andy Tan, Augustin Medina, Juliette Hernando, Sheila Ernest, Vatche Bartekian, Karine Lalonde et al. Published: 2026-03-30 Categories: cs.LG, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2603.29041v1 Clinical trials are characterized by high costs, extended timelines, and substantial operational risk, yet reliable prospective methods for predicting trial success before initiation remain limited. Existing artificial intelligence approaches often focus on isolated metrics or specific development stages and frequently rely on variables unavailable at the trial design phase, limiting real-world applicability. We present a hierarchical latent risk-aware machine learning framework for prospective prediction of clinical trial operational success using a curated subset of TrialsBank, a proprietary AI-ready database developed by Sorintellis, comprising 13,700 trials. Operational success was defined as the ability to initiate, conduct, and complete a clinical trial according to planned timelines, recruitment targets, and protocol specifications through database lock. This approach decomposes operational success prediction into two modeling stages. First, intermediate latent operational risk factors are predicted using more than 180 drug- and trial-level features available before trial initiation. These predicted latent risks are then integrated into a downstream model to estimate the probability of operational success. A staged data-splitting strategy was employed to prevent information leakage, and models were benchmarked using XGBoost, CatBoost, and Explainable Boosting Machines. Across Phase I-III, the framework achieves strong out-of-sample performance, with F1-scores of 0.93, 0.92, and 0.91, respectively. Incorporating latent risk drivers improves discrimination of operational failures, and performance remains robust under independent inference evaluation. These results demonstrate that clinical trial operational success can be prospectively forecasted using a latent risk-aware AI framework, enabling early risk assessment and supporting data-driven clinical development decision-making. --- ### Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning Authors: Bilgehan Sel, Xuanli He, Alwin Peng, Ming Jin, Jerry Wei Published: 2026-03-30 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.29038v1 Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass safety measures through targeted fine-tuning. We introduce Trojan-Speak, an adversarial fine-tuning method that bypasses Anthropic's Constitutional Classifiers. Our approach uses curriculum learning combined with GRPO-based hybrid reinforcement learning to teach models a communication protocol that evades LLM-based content classification. Crucially, while prior adversarial fine-tuning approaches report more than 25% capability degradation on reasoning benchmarks, Trojan-Speak incurs less than 5% degradation while achieving 99+% classifier evasion for models with 14B+ parameters. We demonstrate that fine-tuned models can provide detailed responses to expert-level CBRN (Chemical, Biological, Radiological, and Nuclear) queries from Anthropic's Constitutional Classifiers bug-bounty program. Our findings reveal that LLM-based content classifiers alone are insufficient for preventing dangerous information disclosure when adversaries have fine-tuning access, and we show that activation-level probes can substantially improve robustness to such attacks. --- ### Generating Humanless Environment Walkthroughs from Egocentric Walking Tour Videos Authors: Yujin Ham, Junho Kim, Vivek Boominathan, Guha Balakrishnan Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.29036v1 Egocentric "walking tour" videos provide a rich source of image data to develop rich and diverse visual models of environments around the world. However, the significant presence of humans in frames of these videos due to crowds and eye-level camera perspectives mitigates their usefulness in environment modeling applications. We focus on addressing this challenge by developing a generative algorithm that can realistically remove (i.e., inpaint) humans and their associated shadow effects from walking tour videos. Key to our approach is the construction of a rich semi-synthetic dataset of video clip pairs to train this generative model. Each pair in the dataset consists of an environment-only background clip, and a composite clip of walking humans with simulated shadows overlaid on the background. We randomly sourced both foreground and background components from real egocentric walking tour videos around the world to maintain visual diversity. We then used this dataset to fine-tune the state-of-the-art Casper video diffusion model for object and effects inpainting, and demonstrate that the resulting model performs far better than Casper both qualitatively and quantitatively at removing humans from walking tour clips with significant human presence and complex backgrounds. Finally, we show that the resulting generated clips can be used to build successful 3D/4D models of urban locations. --- ### The Surprising Effectiveness of Noise Pretraining for Implicit Neural Representations Authors: Kushal Vyas, Alper Kayabasi, Daniel Kim, Vishwanath Saragadam, Ashok Veeraraghavan, Guha Balakrishnan Published: 2026-03-30 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2603.29034v1 The approximation and convergence properties of implicit neural representations (INRs) are known to be highly sensitive to parameter initialization strategies. While several data-driven initialization methods demonstrate significant improvements over standard random sampling, the reasons for their success -- specifically, whether they encode classical statistical signal priors or more complex features -- remain poorly understood. In this study, we explore this phenomenon through a series of experimental analyses leveraging noise pretraining. We pretrain INRs on diverse noise classes (e.g., Gaussian, Dead Leaves, Spectral) and measure their ability to both fit unseen signals and encode priors for an inverse imaging task (denoising). Our analyses on image and video data reveal a surprising finding: simply pretraining on unstructured noise (Uniform, Gaussian) dramatically improves signal fitting capacity compared to all other baselines. However, unstructured noise also yields poor deep image priors for denoising. In contrast, we also find that noise with the classic $1/|f^α|$ spectral structure of natural images achieves an excellent balance of signal fitting and inverse imaging capabilities, performing on par with the best data-driven initialization methods. This finding enables more efficient INR training in applications lacking sufficient prior domain-specific data. For more details, visit project page at https://kushalvyas.github.io/noisepretraining.html --- ### From Astronomy to Astrology: Testing the Illusion of Zodiac-Based Personality Prediction with Machine Learning Authors: Abhinna Sundar Samantaray, Finnja Annika Fluhrer, Dhruv Saini, Omkar Charaple, Anish Kumar Singh, Dhruv Vansraj Rathore Published: 2026-03-30 Categories: cs.LG, physics.pop-ph arXiv: https://arxiv.org/abs/2603.29033v1 Astrology has long been used to interpret human personality, estimate compatibility, and guide social decision-making. Zodiac-based systems in particular remain culturally influential across much of the world, including in South Asian societies where astrological reasoning can shape marriage matching, naming conventions, ritual timing, and broader life planning. Despite this persistence, astrology has never established either a physically plausible mechanism or a statistically reliable predictive foundation. In this work, we examine zodiac-based personality prediction using a controlled machine-learning framework. We construct a synthetic dataset in which individuals are assigned zodiac signs and personality labels drawn from a shared pool of 100 broadly human traits. Each sign is associated with a subset of 10 common descriptors, intentionally overlapping with those assigned to other signs, thereby reproducing the ambiguity characteristic of practical astrological systems. We then train Logistic Regression, Random Forest, and neural-network classifiers to infer personality labels from zodiac-based features and nuisance covariates. Across all experiments, predictive performance remains at or near random expectation, while shuffled-label controls yield comparable accuracies. We argue that the apparent success of astrology arises not from measurable predictive structure, but from trait universality, category overlap, cognitive biases such as the Barnum effect and confirmation bias, and the interpretive flexibility of astrologers and pundits. We conclude that zodiac-based systems do not provide reliable information for predicting human behavior and instead function as culturally durable narrative frameworks. This paper is intended as a humorous academic exercise. --- ### MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation Authors: Bharath Krishnamurthy, Ajita Rattani Published: 2026-03-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.29029v1 Recent multimodal face generation models address the spatial control limitations of text-to-image diffusion models by augmenting text-based conditioning with spatial priors such as segmentation masks, sketches, or edge maps. This multimodal fusion enables controllable synthesis aligned with both high-level semantic intent and low-level structural layout. However, most existing approaches typically extend pre-trained text-to-image pipelines by appending auxiliary control modules or stitching together separate uni-modal networks. These ad hoc designs inherit architectural constraints, duplicate parameters, and often fail under conflicting modalities or mismatched latent spaces, limiting their ability to perform synergistic fusion across semantic and spatial domains. We introduce MMFace-DiT, a unified dual-stream diffusion transformer engineered for synergistic multimodal face synthesis. Its core novelty lies in a dual-stream transformer block that processes spatial (mask/sketch) and semantic (text) tokens in parallel, deeply fusing them through a shared Rotary Position-Embedded (RoPE) Attention mechanism. This design prevents modal dominance and ensures strong adherence to both text and structural priors to achieve unprecedented spatial-semantic consistency for controllable face generation. Furthermore, a novel Modality Embedder enables a single cohesive model to dynamically adapt to varying spatial conditions without retraining. MMFace-DiT achieves a 40% improvement in visual fidelity and prompt alignment over six state-of-the-art multimodal face generation models, establishing a flexible new paradigm for end-to-end controllable generative modeling. The code and dataset are available on our project page: https://vcbsl.github.io/MMFace-DiT/ --- ### On the limited utility of parallel data for learning shared multilingual representations Authors: Julius Leino, Jörg Tiedemann Published: 2026-03-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.29026v1 Shared multilingual representations are essential for cross-lingual tasks and knowledge transfer across languages. This study looks at the impact of parallel data, i.e. translated sentences, in pretraining as a signal to trigger representations that are aligned across languages. We train reference models with different proportions of parallel data and show that parallel data seem to have only a minimal effect on the cross-lingual alignment. Based on multiple evaluation methods, we find that the effect is limited to potentially accelerating the representation sharing in the early phases of pretraining, and to decreasing the amount of language-specific neurons in the model. Cross-lingual alignment seems to emerge on similar levels even without the explicit signal from parallel data. --- ### The Model Says Walk: Measuring whether LLMs Condition on Hidden Constraints Authors: Yubo Li, Lu Zhang, Tianchong Jiang, Ramayya Krishnan, Rema Padman Published: 2026-03-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.29025v4 Asked whether to walk or drive to a car wash 50 m away, most language models say walk, forgetting that the car has to be there. Such failures are usually measured by accuracy on questions where the hidden constraint applies. We show that this is misleading: a model can answer these questions correctly without reasoning about the constraint at all, simply by favoring the cautious option. We instead ask whether a model's decision changes when the constraint is removed. We test this at three levels of control: log-probability sweeps on open-weight models, a 500-prompt stress test, and CORE, a new human-validated benchmark of minimal constraint-present/constraint-absent pairs. The picture is consistent. The constraint nudges decisions rather than governing them. Models still miss presence constraints like the car wash, yet elsewhere they apply constraints that are not there. As a result, standard accuracy flatters all ten models we evaluate and reorders their ranking, and prompting fixes that look effective largely vanish under paired scoring. Claims about hidden-constraint reasoning need paired evidence. --- ### The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning Authors: Yubo Li, Lu Zhang, Tianchong Jiang, Ramayya Krishnan, Rema Padman Published: 2026-03-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.29025v3 Large language models fail when a salient surface cue conflicts with an unstated feasibility constraint. We introduce the Heuristic Override Benchmark (HOB): 500 instances spanning 4 heuristic families and 5 constraint families, with minimal pairs and explicitness gradients. We pair HOB with a falsifiable behavioral characterization following a diagnose-measure-bridge-treat arc. Causal-behavioral analysis of the car wash problem across six models reveals context-independent sigmoid heuristics: the distance cue has 8.7 to 38 times more influence than the goal, and attribution better matches keyword association than compositional inference. Across 14 models, strict 10/10 evaluation shows that no model exceeds 75%, and presence constraints are hardest at 44%. A minimal hint improves performance by 15 pp, suggesting a constraint-inference failure rather than missing knowledge. However, 12 of 14 models perform worse when the constraint is removed, by up to 39 pp, revealing conservative bias. A thinking-mode ablation on Gemini 3.1 Pro drops performance from 74.6% with thinking on to 58.4% with thinking off, while explicit goal decomposition recovers it to 71.2%. Thus, internal deliberation does useful work, and explicit prompting can partially substitute for it. Reasoning models do not categorically outperform non-reasoning peers: after controlling for capability rank, the residual reasoning-mode effect is 1.8 pp and is not significant. Parametric probes show that the sigmoid pattern generalizes to cost, efficiency, and semantic-similarity heuristics. Goal-decomposition prompting improves performance by 5.0 pp, compared with 3.1 pp for generic chain-of-thought, isolating constraint enumeration as the active ingredient. Overall, heuristic override is a systematic reasoning vulnerability with a quantified locus in inference order, not knowledge, and a tested intervention. --- ### Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction Authors: Diego C. Lerma-Torres Published: 2026-03-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.29023v1 Large language models lack persistent, structured memory for long-term interaction and context-sensitive retrieval. Expanding context windows does not solve this: recent evidence shows that context length alone degrades reasoning by up to 85% - even with perfect retrieval. We propose a bio-inspired memory framework grounded in complementary learning systems theory, cognitive behavioral therapy's belief hierarchy, dual-process cognition, and fuzzy-trace theory, organized around three principles: (1) Memory has valence, not just content - pre-computed emotional-associative summaries (valence vectors) organized in an emergent belief hierarchy inspired by Beck's cognitive model enable instant orientation before deliberation; (2) Retrieval defaults to System 1 with System 2 escalation - automatic spreading activation and passive priming as default, with deliberate retrieval only when needed, and graded epistemic states that address hallucination structurally; and (3) Encoding is active, present, and feedback-dependent - a thalamic gateway tags and routes information between stores, while the executive forms gists through curiosity-driven investigation, not passive exposure. Seven functional properties specify what any implementation must satisfy. Over time, the system converges toward System 1 processing - the computational analog of clinical expertise - producing interactions that become cheaper, not more expensive, with experience. --- ### UltraG-Ray: Physics-Based Gaussian Ray Casting for Novel Ultrasound View Synthesis Authors: Felix Duelmer, Jakob Klaushofer, Magdalena Wysocki, Nassir Navab, Mohammad Farid Azampour Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.29022v1 Novel view synthesis (NVS) in ultrasound has gained attention as a technique for generating anatomically plausible views beyond the acquired frames, offering new capabilities for training clinicians or data augmentation. However, current methods struggle with complex tissue and view-dependent acoustic effects. Physics-based NVS aims to address these limitations by including the ultrasound image formation process into the simulation. Recent approaches combine a learnable implicit scene representation with an ultrasound-specific rendering module, yet a substantial gap between simulation and reality remains. In this work, we introduce UltraG-Ray, a novel ultrasound scene representation based on a learnable 3D Gaussian field, coupled to an efficient physics-based module for B-mode synthesis. We explicitly encode ultrasound-specific parameters, such as attenuation and reflection, into a Gaussian-based spatial representation and realize image synthesis within a novel ray casting scheme. In contrast to previous methods, this approach naturally captures view-dependent attenuation effects, thereby enabling the generation of physically informed B-mode images with increased realism. We compare our method to state-of-the-art and observe consistent gains in image quality metrics (up to 15% increase on MS-SSIM), demonstrating clear improvement in terms of realism of the synthesized ultrasound images. --- ### Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wild Authors: Deepak Akkil, Mowafak Allaham, Amal Raj, Tamer Abuelsaad, Ravi Kokku Published: 2026-03-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.29020v1 Reliable evaluation of AI agents operating in complex, real-world environments requires methodologies that are robust, transparent, and contextually aligned with the tasks agents are intended to perform. This study identifies persistent shortcomings in existing AI agent evaluation practices that are particularly acute in web agent evaluation, as exemplified by our audit of WebVoyager, including task-framing ambiguity and operational variability that hinder meaningful and reproducible performance comparisons. To address these challenges, we introduce Emergence WebVoyager, an enhanced version of the WebVoyager benchmark that standardizes evaluation methodology through clear guidelines for task instantiation, failure handling, annotation, and reporting. Emergence WebVoyager achieves an inter-annotator agreement of 95.9\%, indicating improved clarity and reliability in both task formulation and evaluation. Applying this framework to evaluate OpenAI Operator reveals substantial performance variation across domains and task types, with an overall success rate of 68.6\%, substantially lower than the 87\% previously reported by OpenAI, demonstrating the utility of our approach for more rigorous and comparable web agent evaluation. --- ### Improving Efficiency of GPU Kernel Optimization Agents using a Domain-Specific Language and Speed-of-Light Guidance Authors: Siva Kumar Sastry Hari, Vignesh Balaji, Sana Damani, Qijing Huang, Christos Kozyrakis Published: 2026-03-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.29010v1 Optimizing GPU kernels with LLM agents is an iterative process over a large design space. Every candidate must be generated, compiled, validated, and profiled, so fewer trials will save both runtime and cost. We make two key observations. First, the abstraction level that agents operate at is important. If it is too low, the LLM wastes reasoning on low-impact details. If it is too high, it may miss important optimization choices. Second, agents cannot easily tell when they reach the point of diminishing returns, wasting resources as they continue searching. These observations motivate two design principles to improve efficiency: (1) a compact domain-specific language (DSL) that can be learned in context and lets the model reason at a higher level while preserving important optimization levers, and (2) Speed-of-Light (SOL) guidance that uses first-principles performance bounds to steer and budget search. We implement these principles in $μ$CUTLASS, a DSL with a compiler for CUTLASS-backed GPU kernels that covers kernel configuration, epilogue fusion, and multi-stage pipelines. We use SOL guidance to estimate headroom and guide optimization trials, deprioritize problems that are near SOL, and flag kernels that game the benchmark. On 59 KernelBench problems with the same iteration budgets, switching from generating low-level code to DSL code using GPT-5-mini turns a 0.40x geomean regression into a 1.27x speedup over PyTorch. Adding SOL-guided steering raises this to 1.56x. Across model tiers, $μ$CUTLASS + SOL-guidance lets weaker models outperform stronger baseline agents at lower token cost. SOL-guided budgeting saves 19-43% of tokens while retaining at least 95% of geomean speedup, with the best policy reaching a 1.68x efficiency gain. Lastly, SOL analysis helps detect benchmark-gaming cases, where kernels may appear fast while failing to perform the intended computation. --- ### MEDiC: Multi-objective Exploration of Distillation from CLIP Authors: Konstantinos Georgiou, Maofeng Tang, Hairong Qi Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.29009v1 Masked image modeling (MIM) methods typically operate in either raw pixel space (reconstructing masked patches) or latent feature space (aligning with a pre-trained teacher). We present MEDiC (Multi-objective Exploration of Distillation from CLIP), a framework that combines both spaces in a single pipeline through three complementary objectives: patch-level token distillation from a frozen CLIP encoder, global CLS alignment, and pixel reconstruction via a lightweight decoder. We conduct a systematic investigation of the design space surrounding this multi-objective framework. First, we show that all three objectives provide complementary information, with the full combination reaching 73.9% kNN accuracy on ImageNet-1K. Second, we introduce hierarchical clustering with relative position bias for evolved masking and find that, despite producing more semantically coherent masks than prior methods, evolved masking does not outperform simple block masking in the teacher-guided distillation setting, a finding we attribute to the teacher's inherent semantic awareness. Third, we reveal that optimal scalar loss weights are extremely fragile, with small perturbations causing drops of up to 17 percentage points in kNN accuracy. Our framework achieves 73.9% kNN and 85.1% fine-tuning accuracy with ViT-Base at 300 epochs. --- ### Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference Authors: Zifan He, Rui Ma, Yizhou Sun, Jason Cong Published: 2026-03-30 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2603.29002v3 Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex reasoning. We show that these optimizations can be unified into a four-step memory processing pipeline: Prepare Memory, Compute Relevancy, Retrieval, and Apply to Inference. Through systematic profiling, we identify a 22%-97% memory processing overhead in LLM inference and strong heterogeneity in its computational characteristics. Motivated by this insight, we argue that \textbf{heterogeneous systems} are well-suited to accelerate memory processing and thus end-to-end inference. We demonstrate this approach on a GPU-FPGA system by offloading sparse, irregular, and memory-bounded operations to FPGAs while retaining compute-intensive operations on GPUs. Evaluated on an AMD MI210 GPU and an Alveo U55C FPGA, our system is up to $2.2\times$ faster and achieves up to $4.7\times$ less energy across multiple LLM inference optimizations than the GPU baseline (similar results hold on NVIDIA A100). These results establish heterogeneous systems as a practical direction for efficient LLM memory processing and inform future heterogeneous hardware design. --- ### Transfer Learning in Bayesian Optimization for Aircraft Design Authors: Ali Tfaily, Youssef Diouane, Nathalie Bartoli, Michael Kokkolaras Published: 2026-03-30 Categories: math.OC, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.28999v1 The use of transfer learning within Bayesian optimization addresses the disadvantages of the so-called \textit{cold start} problem by using source data to aid in the optimization of a target problem. We present a method that leverages an ensemble of surrogate models using transfer learning and integrates it in a constrained Bayesian optimization framework. We identify challenges particular to aircraft design optimization related to heterogeneous design variables and constraints. We propose the use of a partial-least-squares dimension reduction algorithm to address design space heterogeneity, and a \textit{meta} data surrogate selection method to address constraint heterogeneity. Numerical benchmark problems and an aircraft conceptual design optimization problem are used to demonstrate the proposed methods. Results show significant improvement in convergence in early optimization iterations compared to standard Bayesian optimization, with improved prediction accuracy for both objective and constraint surrogate models. --- ### Design Principles for the Construction of a Benchmark Evaluating Security Operation Capabilities of Multi-agent AI Systems Authors: Yicheng Cai, Mitchell John DeStefano, Guodong Dong, Pulkit Handa, Peng Liu, Tejas Singhal, Peiyu Tseng, Winston Jen White Published: 2026-03-30 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.28998v1 As Large Language Models (LLMs) and multi-agent AI systems are demonstrating increasing potential in cybersecurity operations, organizations, policymakers, model providers, and researchers in the AI and cybersecurity communities are interested in quantifying the capabilities of such AI systems to achieve more autonomous SOCs (security operation centers) and reduce manual effort. In particular, the AI and cybersecurity communities have recently developed several benchmarks for evaluating the red team capabilities of multi-agent AI systems. However, because the operations in SOCs are dominated by blue team operations, the capabilities of AI systems & agents to achieve more autonomous SOCs cannot be evaluated without a benchmark focused on blue team operations. To our best knowledge, no systematic benchmark for evaluating coordinated multi-task blue team AI has been proposed in the literature. Existing blue team benchmarks focus on a particular task. The goal of this work is to develop a set of design principles for the construction of a benchmark, which is denoted as SOC-bench, to evaluate the blue team capabilities of AI. Following these design principles, we have developed a conceptual design of SOC-bench, which consists of a family of five blue team tasks in the context of large-scale ransomware attack incident response. --- ### GenFusion: Feed-forward Human Performance Capture via Progressive Canonical Space Updates Authors: Youngjoong Kwon, Yao He, Heejung Choi, Chen Geng, Zhengmao Liu, Jiajun Wu, Ehsan Adeli Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28997v1 We present a feed-forward human performance capture method that renders novel views of a performer from a monocular RGB stream. A key challenge in this setting is the lack of sufficient observations, especially for unseen regions. Assuming the subject moves continuously over time, we take advantage of the fact that more body parts become observable by maintaining a canonical space that is progressively updated with each incoming frame. This canonical space accumulates appearance information over time and serves as a context bank when direct observations are missing in the current live frame. To effectively utilize this context while respecting the deformation of the live state, we formulate the rendering process as probabilistic regression. This resolves conflicts between past and current observations, producing sharper reconstructions than deterministic regression approaches. Furthermore, it enables plausible synthesis even in regions with no prior observations. Experiments on in-domain (4D-Dress) and out-of-distribution (MVHumanNet) datasets demonstrate the effectiveness of our approach. --- ### Hybrid Quantum-Classical AI for Industrial Defect Classification in Welding Images Authors: Akshaya Srinivasan, Xiaoyin Cheng, Jianming Yi, Alexander Geng, Desislava Ivanova, Andreas Weinmann, Ali Moghiseh Published: 2026-03-30 Categories: cs.CV, eess.IV, quant-ph arXiv: https://arxiv.org/abs/2603.28995v1 Hybrid quantum-classical machine learning offers a promising direction for advancing automated quality control in industrial settings. In this study, we investigate two hybrid quantum-classical approaches for classifying defects in aluminium TIG welding images and benchmarking their performance against a conventional deep learning model. A convolutional neural network is used to extract compact and informative feature vectors from weld images, effectively reducing the higher-dimensional pixel space to a lower-dimensional feature space. Our first quantum approach encodes these features into quantum states using a parameterized quantum feature map composed of rotation and entangling gates. We compute a quantum kernel matrix from the inner products of these states, defining a linear system in a higher-dimensional Hilbert space corresponding to the support vector machine (SVM) optimization problem and solving it using a Variational Quantum Linear Solver (VQLS). We also examine the effect of the quantum kernel condition number on classification performance. In our second method, we apply angle encoding to the extracted features in a variational quantum circuit and use a classical optimizer for model training. Both quantum models are tested on binary and multiclass classification tasks and the performance is compared with the classical CNN model. Our results show that while the CNN model demonstrates robust performance, hybrid quantum-classical models perform competitively. This highlights the potential of hybrid quantum-classical approaches for near-term real-world applications in industrial defect detection and quality assurance. --- ### An Explicit Surrogate for Gaussian Mixture Flow Matching with Wasserstein Gap Bounds Authors: Elham Rostami, Taous-Meriem Laleg-Kirati, Hamidou Tembine Published: 2026-03-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.28992v1 We study training-free flow matching between two Gaussian mixture models (GMMs) using explicit velocity fields that transport one mixture into the other over time. Our baseline approach constructs component-wise Gaussian paths with affine velocity fields satisfying the continuity equation, which yields to a closed-form surrogate for the pairwise kinetic transport cost. In contrast to the exact Gaussian Wasserstein cost, which relies on matrix square-root computations, the surrogate admits a simple analytic expression derived from the kinetic energy of the induced flow. We then analyze how closely this surrogate approximates the exact cost. We prove second-order agreement in a local commuting regime and derive an explicit cubic error bound in the local commuting regime. To handle nonlocal regimes, we introduce a path-splitting strategy that localizes the covariance evolution and enables piecewise application of the bound. We finally compare the surrogate with an exact construction based on the Gaussian Wasserstein geodesic and summarize the results in a practical regime map showing when the surrogate is accurate and the exact method is preferable. --- ### Drop the Hierarchy and Roles: How Self-Organizing LLM Agents Outperform Designed Structures Authors: Victoria Dochkina Published: 2026-03-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.28990v1 How much autonomy can multi-agent LLM systems sustain -- and what enables it? We present a 25,000-task computational experiment spanning 8 models, 4--256 agents, and 8 coordination protocols ranging from externally imposed hierarchy to emergent self-organization. We observe that autonomous behavior already emerges in current LLM agents: given minimal structural scaffolding (fixed ordering), agents spontaneously invent specialized roles, voluntarily abstain from tasks outside their competence, and form shallow hierarchies -- without any pre-assigned roles or external design. A hybrid protocol (Sequential) that enables this autonomy outperforms centralized coordination by 14% (p<0.001), with a 44% quality spread between protocols (Cohen's d=1.86, p<0.0001). The degree of emergent autonomy scales with model capability: strong models self-organize effectively, while models below a capability threshold still benefit from rigid structure -- suggesting that as foundation models improve, the scope for autonomous coordination will expand. The system scales sub-linearly to 256 agents without quality degradation (p=0.61), producing 5,006 unique roles from just 8 agents. Results replicate across closed- and open-source models, with open-source achieving 95% of closed-source quality at 24x lower cost. The practical implication: give agents a mission, a protocol, and a capable model -- not a pre-assigned role. --- ### Multi-fidelity approaches for general constrained Bayesian optimization with application to aircraft design Authors: Oihan Cordelier, Youssef Diouane, Nathalie Bartoli, Eric Laurendeau Published: 2026-03-30 Categories: math.OC, cs.CE, stat.ML arXiv: https://arxiv.org/abs/2603.28987v1 Aircraft design relies heavily on solving challenging and computationally expensive Multidisciplinary Design Optimization problems. In this context, there has been growing interest in multi-fidelity models for Bayesian optimization to improve the MDO process by balancing computational cost and accuracy through the combination of high- and low-fidelity simulation models, enabling efficient exploration of the design process at a minimal computational effort. In the existing literature, fidelity selection focuses only on the objective function to decide how to integrate multiple fidelity levels, balancing precision and computational cost using variance reduction criteria. In this work, we propose novel multi-fidelity selection strategies. Specifically, we demonstrate how incorporating information from both the objective and the constraints can further reduce computational costs without compromising the optimality of the solution. We validate the proposed multi-fidelity optimization strategy by applying it to four analytical test cases, showcasing its effectiveness. The proposed method is used to efficiently solve a challenging aircraft wing aero-structural design problem. The proposed setting uses a linear vortex lattice method and a finite element method for the aerodynamic and structural analysis respectively. We show that employing our proposed multi-fidelity approach leads to $86\%$ to $200\%$ more constraint compliant solutions given a limited budget compared to the state-of-the-art approach. --- ### Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research Authors: Martin Legrand, Tao Jiang, Matthieu Feraud, Benjamin Navet, Yousouf Taghzouti, Fabien Gandon, Elise Dumont, Louis-Félix Nothias Published: 2026-03-30 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2603.28986v1 Current Autonomous Scientific Research (ASR) systems, despite leveraging large language models (LLMs) and agentic architectures, remain constrained by fixed workflows and toolsets that prevent adaptation to evolving tasks and environments. We introduce Mimosa, an evolving multi-agent framework that automatically synthesizes task-specific multi-agent workflows and iteratively refines them through experimental feedback. Mimosa leverages the Model Context Protocol (MCP) for dynamic tool discovery, generates workflow topologies via a meta-orchestrator, executes subtasks through code-generating agents that invoke available tools and scientific software libraries, and scores executions with an LLM-based judge whose feedback drives workflow refinement. On ScienceAgentBench, Mimosa achieves a success rate of 43.1% with DeepSeek-V3.2, surpassing both single-agent baselines and static multi-agent configurations. Our results further reveal that models respond heterogeneously to multi-agent decomposition and iterative learning, indicating that the benefits of workflow evolution depend on the capabilities of the underlying execution model. Beyond these benchmarks, Mimosa modular architecture and tool-agnostic design make it readily extensible, and its fully logged execution traces and archived workflows support auditability by preserving every analytical step for inspection and potential replication. Combined with domain-expert guidance, the framework has the potential to automate a broad range of computationally accessible scientific tasks across disciplines. Released as a fully open-source platform, Mimosa aims to provide an open foundation for community-driven ASR. --- ### Stepper: Stepwise Immersive Scene Generation with Multiview Panoramas Authors: Felix Wimbauer, Fabian Manhardt, Michael Oechsle, Nikolai Kalischek, Christian Rupprecht, Daniel Cremers, Federico Tombari Published: 2026-03-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.28980v2 The synthesis of immersive 3D scenes from text is rapidly maturing, driven by novel video generative models and feed-forward 3D reconstruction, with vast potential in AR/VR and world modeling. While panoramic images have proven effective for scene initialization, existing approaches suffer from a trade-off between visual fidelity and explorability: autoregressive expansion suffers from context drift, while panoramic video generation is limited to low resolution. We present Stepper, a unified framework for text-driven immersive 3D scene synthesis that circumvents these limitations via stepwise panoramic scene expansion. Stepper leverages a novel multi-view 360° diffusion model that enables consistent, high-resolution expansion, coupled with a geometry reconstruction pipeline that enforces geometric coherence. Trained on a new large-scale, multi-view panorama dataset, Stepper achieves state-of-the-art fidelity and structural consistency, outperforming prior approaches, thereby setting a new standard for immersive scene generation. --- ### Privacy Guard & Token Parsimony by Prompt and Context Handling and LLM Routing Authors: Alessio Langiu Published: 2026-03-30 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.28972v1 The large-scale adoption of Large Language Models (LLMs) forces a trade-off between operational cost (OpEx) and data privacy. Current routing frameworks reduce costs but ignore prompt sensitivity, exposing users and institutions to leakage risks towards third-party cloud providers. We formalise the "Inseparability Paradigm": advanced context management intrinsically coincides with privacy management. We propose a local "Privacy Guard" -- a holistic contextual observer powered by an on-premise Small Language Model (SLM) -- that performs abstractive summarisation and Automatic Prompt Optimisation (APO) to decompose prompts into focused sub-tasks, re-routing high-risk queries to Zero-Trust or NDA-covered models. This dual mechanism simultaneously eliminates sensitive inference vectors (Zero Leakage) and reduces cloud token payloads (OpEx Reduction). A LIFO-based context compacting mechanism further bounds working memory, limiting the emergent leakage surface. We validate the framework through a 2x2 benchmark (Lazy vs. Expert users; Personal vs. Institutional secrets) on a 1,000-sample dataset, achieving a 45% blended OpEx reduction, 100% redaction success on personal secrets, and -- via LLM-as-a-Judge evaluation -- an 85% preference rate for APO-compressed responses over raw baselines. Our results demonstrate that Token Parsimony and Zero Leakage are mathematically dual projections of the same contextual compression operator. --- ### A Pontryagin Method of Model-based Reinforcement Learning via Hamiltonian Actor-Critic Authors: Chengyang Gu, Yuxin Pan, Hui Xiong, Yize Chen Published: 2026-03-30 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2603.28971v1 Model-based reinforcement learning (MBRL) improves sample efficiency by leveraging learned dynamics models for policy optimization. However, the effectiveness of methods such as actor-critic is often limited by compounding model errors, which degrade long-horizon value estimation. Existing approaches, such as Model-Based Value Expansion (MVE), partially mitigate this issue through multi-step rollouts, but remain sensitive to rollout horizon selection and residual model bias. Motivated by the Pontryagin Maximum Principle (PMP), we propose Hamiltonian Actor-Critic (HAC), a model-based approach that eliminates explicit value function learning by directly optimizing a Hamiltonian defined over the learned dynamics and reward for deterministic systems. By avoiding value approximation, HAC reduces sensitivity to model errors while admitting convergence guarantees. Extensive experiments on continuous control benchmarks, in both online and offline RL settings, demonstrate that HAC outperforms model-free and MVE-based baselines in control performance, convergence speed, and robustness to distributional shift, including out-of-distribution (OOD) scenarios. In offline settings with limited data, HAC matches or exceeds state-of-the-art methods, highlighting its strong sample efficiency. --- ### Spectral Edge Dynamics: An Analytical-Empirical Study of Phase Transitions in Neural Network Training Authors: Yongzhong Xu Published: 2026-03-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.28964v3 We develop the spectral edge analysis: phase transitions in neural network training -- grokking, capability gains, loss plateaus -- are controlled by the spectral gap of the rolling-window Gram matrix of parameter updates. In the extreme aspect ratio regime (parameters $P \sim 10^8$, window $W \sim 10$), the classical BBP detection threshold is vacuous; the operative structure is the intra-signal gap separating dominant from subdominant modes at position $k^* = \mathrm{argmax}\, σ_j/σ_{j+1}$. From three assumptions we derive: (i) gap dynamics governed by a Dyson-type ODE with curvature asymmetry, damping, and gradient driving; (ii) a spectral loss decomposition linking each mode's learning contribution to its Davis--Kahan stability coefficient; (iii) the Gap Maximality Principle, showing that $k^*$ is the unique dynamically privileged position -- its collapse is the only one that disrupts learning, and it sustains itself through an $α$-feedback loop requiring no assumption on the optimizer. The adiabatic parameter $\mathcal{A} = \|ΔG\|_F / (η\, g^2)$ controls circuit stability: $\mathcal{A} \ll 1$ (plateau), $\mathcal{A} \sim 1$ (phase transition), $\mathcal{A} \gg 1$ (forgetting). Tested across six model families (150K--124M parameters): gap dynamics precede every grokking event (24/24 with weight decay, 1/24 without), the gap position is optimizer-dependent (Muon: $k^*=1$, AdamW: $k^*=2$ on the same model), and 19/20 quantitative predictions are confirmed. The framework is consistent with the edge of stability, Tensor Programs, Dyson Brownian motion, the Lottery Ticket Hypothesis, and neural scaling laws. --- ### AutoWorld: Learning Multi-Agent Traffic Simulation with Self-Supervised World Models Authors: Mozhgan Pourkeshavarz, Tianran Liu, Nicholas Rhinehart Published: 2026-03-30 Categories: cs.RO, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.28963v2 Simulation with realistic traffic agents is essential for validating autonomous driving systems. Existing data-driven simulators learn agent behavior from higher-level abstractions such as 3D bounding boxes and polylines, inferred by upstream perception pipelines. These lossy abstractions discard sensory context that directly shapes agent behavior, limiting the distributional realism that simulation aims to reproduce. To address this limitation, we propose AutoWorld, a traffic simulation framework that grounds agent behavior in raw sensor observations through a self-supervised world model trained on LiDAR occupancy data. Given world model samples, AutoWorld constructs a coarse-to-fine predictive scene context as input to a multi-agent motion generation model. Furthermore, we designed a motion-aware latent supervision objective that enriches AutoWorld's latent representation of scene dynamics. To better exploit this latent space during inference, AutoWorld employs a cascaded Determinantal Point Process framework to guide diversity-aware sampling across both the world model and motion model. Experiments on the Waymo Sim Agents Challenge (WOSAC) demonstrate that AutoWorld achieves competitive performance, with larger gains in partially-observed scenarios where trajectory abstractions are most limited. We further show that grounding simulation in raw LiDAR through AutoWorld scales better with additional data than trajectory-only and LiDAR-conditioning baselines. Ablations confirm the contribution of each component. --- ### Multi-Agent LLMs for Adaptive Acquisition in Bayesian Optimization Authors: Andrea Carbonati, Mohammadsina Almasi, Hadis Anahideh Published: 2026-03-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.28959v1 The exploration-exploitation trade-off is central to sequential decision-making and black-box optimization, yet how Large Language Models (LLMs) reason about and manage this trade-off remains poorly understood. Unlike Bayesian Optimization, where exploration and exploitation are explicitly encoded through acquisition functions, LLM-based optimization relies on implicit, prompt-based reasoning over historical evaluations, making search behavior difficult to analyze or control. In this work, we present a metric-level study of LLM-mediated search policy learning, studying how LLMs construct and adapt exploration-exploitation strategies under multiple operational definitions of exploration, including informativeness, diversity, and representativeness. We show that single-agent LLM approaches, which jointly perform strategy selection and candidate generation within a single prompt, suffer from cognitive overload, leading to unstable search dynamics and premature convergence. To address this limitation, we propose a multi-agent framework that decomposes exploration-exploitation control into strategic policy mediation and tactical candidate generation. A strategy agent assigns interpretable weights to multiple search criteria, while a generation agent produces candidates conditioned on the resulting search policy defined as weights. This decomposition renders exploration-exploitation decisions explicit, observable, and adjustable. Empirical results across various continuous optimization benchmarks indicate that separating strategic control from candidate generation substantially improves the effectiveness of LLM-mediated search. --- ### Minimum Norm Interpolation via the Local Theory of Banach Spaces: The Role of $2$-Uniform Convexity Authors: Gil Kur, Pierre Bizeul Published: 2026-03-30 Categories: math.FA, cs.LG, math.MG, math.PR, math.ST arXiv: https://arxiv.org/abs/2603.28956v2 The minimum-norm interpolator (MNI) framework has recently attracted considerable attention as a tool for understanding generalization in overparameterized models, such as neural networks. In this work, we study the MNI under a $2$-uniform convexity assumption, which is weaker than requiring the norm to be induced by an inner product; in this setting, the MNI typically does not admit a closed-form solution. At a high level, we show that this condition yields an upper bound on the MNI bias in both linear and nonlinear models. We further show that this bound is sharp for overparameterized linear regression when the norm's unit ball is in isotropic or John's position and the covariates are i.i.d.\ sub-Gaussian, for example, when each covariate vector has i.i.d. Rademacher entries. Finally, under the same assumption on the covariates, we prove sharp generalization bounds for the $\ell_p$-MNI when $p \in \bigl(1 + C/\log d, 2\bigr)$. To the best of our knowledge, this is the \emph{first} work to establish sharp bounds for non-Gaussian covariates in linear models when the norm is not induced by an inner product. This work is deeply inspired by classical work on $K$-convexity and recent work on the geometry of $2$-uniformly convex and isotropic convex bodies. ---