# Research Papers — 2026-03 · bundle page 195 of 243 > Full-text markdown of papers #9701–9750 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/195 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/194.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/196.md) ### ColonSplat: Reconstruction of Peristaltic Motion in Colonoscopy with Dynamic Gaussian Splatting Authors: Weronika Smolak-Dyżewska, Joanna Kaleta, Diego Dall'Alba, Przemysław Spurek Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06860v1 Accurate 3D reconstruction of colonoscopy data, accounting for complex peristaltic movements, is crucial for advanced surgical navigation and retrospective diagnostics. While recent novel view synthesis and 3D reconstruction methods have demonstrated remarkable success in general endoscopic scenarios, they struggle in the highly constrained environment of the colon. Due to the limited field of view of a camera moving through an actively deforming tubular structure, existing endoscopic methods reconstruct the colon appearance only for initial camera trajectory. However, the underlying anatomy remains largely static; instead of updating Gaussians' spatial coordinates (xyz), these methods encode deformation through either rotation, scale or opacity adjustments. In this paper, we first present a benchmark analysis of state-of-the-art dynamic endoscopic methods for realistic colonoscopic scenes, showing that they fail to model true anatomical motion. To enable rigorous evaluation of global reconstruction quality, we introduce DynamicColon, a synthetic dataset with ground-truth point clouds at every timestep. Building on these insights, we propose ColonSplat, a dynamic Gaussian Splatting framework that captures peristaltic-like motion while preserving global geometric consistency, achieving superior geometric fidelity on C3VDv2 and DynamicColon datasets. Project page: https://wmito.github.io/ColonSplat --- ### The Trace Is the State: Exact Credit Assignment for LLM Agent Teams Authors: Yanjun Chen, Yirong Sun, Hanlin Wang, Jinghan Wang, Xinming Zhang, Xiaoyu Shen, Wenjie Li, Wei Zhang Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06859v3 Credit assignment for a team of LLM agents, what each message was worth, has mostly been treated as prediction: a learned critic, a trajectory-level score, or an agent ablation stands in for the counterfactual that defines credit, which is rarely run. Teams that communicate through a shared context are different: when everything a downstream agent reads is written into the trace, the trace is the state, and that counterfactual can be executed. A credit signal can then be judged as any estimator is: by bias, variance, and agreement with an independent reference. C3, credit assignment by counterfactual continuation, substitutes one message at a decision point and continues the run to the terminal reward, so its credit is unbiased, exact up to Monte Carlo error. Given the sampled alternatives, that error's variance follows a derived law with no term for the number of agents, and the observed noise follows the law on 6 workflows of 2 to 10 decision points. On the 2-agent chain, from 4 continuations, C3 ranks alternatives at 0.69 rank correlation against a 16-continuation reference, near the 0.73 at which 2 such references agree; a critic trained on the same rollouts reaches 0.29. Used as the advantage in training a 2-agent team, C3 beats MAGRPO, the stronger baseline in our comparison, and spends 37% fewer training tokens than MAPPO, since only the messages downstream of a decision point are regenerated. When the trace is the state, credit need not be predicted; it can be exact. --- ### Exact Is Easier: Credit Assignment for Cooperative LLM Agents Authors: Yanjun Chen, Yirong Sun, Hanlin Wang, Jinghan Wang, Xinming Zhang, Xiaoyu Shen, Wenjie Li, Wei Zhang Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06859v2 Removing an agent from a cooperative team to measure its contribution seems natural, yet in multi-agent LLM systems this evaluation distorts the result it claims to measure. This failure is not isolated: learned critics, trajectory-level baselines, and agent-removal counterfactuals all inherit from standard multi-agent reinforcement learning a premise that exact counterfactual evaluation requires privileged environment access, and therefore approximate. In cooperative LLM systems, this premise is false. Interaction histories are deterministic functions of observable text with no hidden state, so any decision point can be restored exactly, making direct causal measurement possible without parametric approximation. C3 exploits this property by fixing the complete history at each decision point, sampling alternative actions under a frozen behavior policy, and computing unbiased per-decision advantages through a parameter-free leave-one-out baseline. Across six benchmarks spanning math reasoning and code generation, two model families, and two multi-agent topologies, C3 consistently outperforms all baselines; a controlled decomposition confirms gains originate from credit quality, not architecture, while checkpoint restoration reduces training token consumption. The exact solution proves simpler, cheaper, and more effective than all approximate alternatives. The same structural property that enables exact credit also enables exact verification: three independently computable diagnostics, credit fidelity, within-group variance, and inter-agent influence, constitute the first method-agnostic auditing tool for multi-agent LLM credit assignment. Our code is available at https://github.com/EIT-EAST-Lab/C3 --- ### Are Audio-Language Models Listening? Audio-Specialist Heads for Adaptive Audio Steering Authors: Neta Glazer, Lenny Aharon, Ethan Fetaya Published: 2026-03-06 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2603.06854v1 Multimodal large language models can exhibit text dominance, over-relying on linguistic priors instead of grounding predictions in non-text inputs. One example is large audio-language models (LALMs) where decisive audio evidence can be under-utilized even when it contains important information. To address this issue we use mechanistic interpretability to identify a small set of audio-specialist attention heads whose audio attention yields a ``listening'' signal. We show that this signal increases when audio evidence affects the model's output, providing an indicator of audio engagement under standard prompting. Leveraging this localization, we construct an audio--silence steering direction and apply an inference-time activation intervention to the final representation, amplifying the model's audio effect. To demonstrate the utility of this intervention, we show on MMAU that this improves accuracy by up to +8.0 percentage points on two Qwen-based LALMs, without any parameter updates. --- ### An Extended Topological Model For High-Contrast Optical Flow Authors: Brad Turow, Jose A. Perea Published: 2026-03-06 Categories: cs.CV, math.AT arXiv: https://arxiv.org/abs/2603.06853v1 In this paper, we identify low-dimensional models for dense core subsets in the space of $3\times 3$ high-contrast optical flow patches sampled from the Sintel dataset. In particular, we leverage the theory of approximate and discrete circle bundles to identify a 3-manifold whose boundary is a previously proposed optical flow torus, together with disjoint circles corresponding to pairs of binary step-edge range image patches. The 3-manifold model we introduce provides an explanation for why the previously-proposed torus model could not be verified with direct methods (e.g., a straightforward persistent homology computation). We also demonstrate that nearly all optical flow patches in the top 1 percent by contrast norm are found near the family of binary step-edge circles described above, rather than the optical flow torus, and that these frequently occurring patches are concentrated near motion boundaries (which are of particular importance for computer vision tasks such as object segmentation and tracking). Our findings offer insights on the subtle interplay between topology and geometry in inference for visual data. --- ### Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstruction Authors: Yulun Wu, Ruyi Zha, Wei Cao, Yingying Li, Yuanhao Cai, Yaoyao Liu Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06852v2 Sparse-view computed tomography (CT) is critical for reducing radiation exposure to patients. Recent advances in radiative 3D Gaussian Splatting (3DGS) have enabled fast and accurate sparse-view CT reconstruction. Despite these algorithmic advancements, practical reconstruction fidelity remains fundamentally bounded by the quality of the captured data, raising the crucial yet underexplored problem of X-ray active view selection. Existing active view selection methods are primarily designed for natural-light scenes and fail to capture the unique geometric ambiguities and physical attenuation properties inherent in X-ray imaging. In this paper, we present Perturbed Gaussian Ensemble, an active view selection framework that integrates uncertainty modeling with sequential decision-making, tailored for X-ray Gaussian Splatting. Specifically, we identify low-density Gaussian primitives that are likely to be uncertain and apply stochastic density scaling to construct an ensemble of plausible Gaussian density fields. For each candidate projection, we measure the structural variance of the ensemble predictions and select the one with the highest variance as the next best view. Extensive experimental results on arbitrary-trajectory CT benchmarks demonstrate that our density-guided perturbation strategy effectively eliminates geometric artifacts and consistently outperforms existing baselines in progressive tomographic reconstruction under unified view selection protocols. --- ### Bilateral Trade Under Heavy-Tailed Valuations: Minimax Regret without a Variance Bound Authors: Hangyi Zhao Published: 2026-03-06 Categories: stat.ML, cs.GT, cs.LG arXiv: https://arxiv.org/abs/2603.06851v4 In contextual bilateral trade under full feedback, the posted price does not affect which valuations are observed. We show that in this model such action-independent feedback removes the polynomial adaptation penalty familiar from heavy-tailed bandits: fully parameter-free algorithms attain the oracle minimax $T$-exponents up to logarithmic factors, with no knowledge of the moment order $p \in (1,2)$ or its scale $σ_p$, and -- in the nonparametric case -- none of the effective Hölder smoothness $β\in (0,1)$. The statistic that makes model selection possible is a paired squared-loss difference, whose noise-square term cancels exactly, leaving noise damped by the candidate gap. The resulting bilateral-trade regret rates are new. Trader valuations have bounded conditional densities and heavy tails -- finite $p$-th moments for some $p \in (1,2)$, with possibly infinite variance. An epoch-based algorithm with truncated means achieves regret $\widetilde{O}(T^{(2-p)/p})$ in the parametric model and $\widetilde{O}(T^{1-2β(p-1)/(βp + d(p-1))})$ when the market value function is $β$-Hölder, with matching $Ω(\cdot)$ lower bounds -- under a mild nondegeneracy condition -- via Assouad's method and a fixed-support mixture construction -- characterizing the minimax rate in $T$ up to logarithmic factors over the effective smoothness range $β\in (0,1)$, interpolating between the classical nonparametric rate at $p{=}2$ and the trivial linear rate as $p \to 1^+$. The enabling structural step extends the self-bounding property of Bachoc et al. (ICML 2025) from bounded to real-valued valuations: within our conditionally independent, conditionally centered noise model, bounded conditional densities and finite first moments suffice for the expected regret of any price $π$ to satisfy $\mathbb{E}(g(m,V,W) - g(π,V,W)) \le L|m-π|^2$ -- no second moment is needed. --- ### Bilateral Trade Under Heavy-Tailed Valuations: Minimax Regret with Infinite Variance Authors: Hangyi Zhao Published: 2026-03-06 Categories: stat.ML, cs.GT, cs.LG arXiv: https://arxiv.org/abs/2603.06851v3 We study contextual bilateral trade under full feedback when, conditionally on the context, trader valuations have bounded density but infinite variance. We first extend the self-bounding property of Bachoc et al. (ICML 2025) from bounded to real-valued valuations, showing that the expected regret of any price $π$ satisfies $E(g(m,V,W) - g(π,V,W)) \le L|m-π|^2$ under bounded density and finite first moments alone. Combining this with truncated-mean estimation, we prove that an epoch-based algorithm achieves regret $\widetilde{O}(T^{1-2β(p-1)/(βp + d(p-1))})$ when the noise has finite $p$-th moment for $p \in (1,2)$ and the market value function is $β$-Hölder, and we establish a matching $Ω(\cdot)$ lower bound via Assouad's method with a fixed-support mixture construction. Our results characterize the minimax rate in $T$ for this problem up to logarithmic factors, interpolating between the classical nonparametric rate at $p=2$ and the trivial linear rate as $p \to 1^+$. Finally, we show these rates are achievable by fully parameter-free algorithms: median-of-means pricing attains the parametric oracle rate with no knowledge of $(p, σ_p)$ or the parameter norm, and a cell-width tournament extends this jointly to the tail and smoothness parameters when $β\le d$ -- under full feedback, tail-adaptivity is free. --- ### Twitch: Learning Abstractions for Equational Theorem Proving Authors: Guy Axelrod, Moa Johansson, Nicholas Smallbone Published: 2026-03-06 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2603.06849v1 Several successful strategies in automated reasoning rely on human-supplied guidance about which term or clause shapes are interesting. In this paper we aim to discover interesting term shapes automatically. Specifically, we discover abstractions : term patterns that occur over and over again in relevant proofs. We present our tool Twitch which discovers abstractions with the help of Stitch, a tool originally developed for discovering reusable library functions in program synthesis tasks. Twitch can produce abstractions in two ways: (1) from a partial, failed proof of a conjecture; (2) from successful proofs of other theorems in the same domain. We have also extended Twee, an equational theorem prover, to use these abstractions. We evaluate Twitch on a set of unit equality (UEQ) problems from TPTP, and show that it can prove 12 rating-1 problems as well as yielding significant speed-ups on many other problems. --- ### MotionBits: Video Segmentation through Motion-Level Analysis of Rigid Bodies Authors: Howard H. Qian, Kejia Ren, Yu Xiang, Vicente Ordonez, Kaiyu Hang Published: 2026-03-06 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.06846v1 Rigid bodies constitute the smallest manipulable elements in the real world, and understanding how they physically interact is fundamental to embodied reasoning and robotic manipulation. Thus, accurate detection, segmentation, and tracking of moving rigid bodies is essential for enabling reasoning modules to interpret and act in diverse environments. However, current segmentation models trained on semantic grouping are limited in their ability to provide meaningful interaction-level cues for completing embodied tasks. To address this gap, we introduce MotionBit, a novel concept that, unlike prior formulations, defines the smallest unit in motion-based segmentation through kinematic spatial twist equivalence, independent of semantics. In this paper, we contribute (1) the MotionBit concept and definition, (2) a hand-labeled benchmark, called MoRiBo, for evaluating moving rigid-body segmentation across robotic manipulation and human-in-the-wild videos, and (3) a learning-free graph-based MotionBits segmentation method that outperforms state-of-the-art embodied perception methods by 37.3\% in macro-averaged mIoU on the MoRiBo benchmark. Finally, we demonstrate the effectiveness of MotionBits segmentation for downstream embodied reasoning and manipulation tasks, highlighting its importance as a fundamental primitive for understanding physical interactions. --- ### Validation of a Small Language Model for DSM-5 Substance Category Classification in Child Welfare Records Authors: Brian E. Perron, Dragan Stoll, Bryan G. Victor, Zia Qia, Andreas Jud, Joseph P. Ryan Published: 2026-03-06 Categories: cs.CL, cs.GL arXiv: https://arxiv.org/abs/2603.06836v1 Background: Recent studies have demonstrated that large language models (LLMs) can perform binary classification tasks on child welfare narratives, detecting the presence or absence of constructs such as substance-related problems, domestic violence, and firearms involvement. Whether smaller, locally deployable models can move beyond binary detection to classify specific substance types from these narratives remains untested. Objective: To validate a locally hosted LLM classifier for identifying specific substance types aligned with DSM-5 categories in child welfare investigation narratives. Methods: A locally hosted 20-billion-parameter LLM classified child maltreatment investigation narratives from a Midwestern U.S. state. Records previously identified as containing substance-related problems were passed to a second classification stage targeting seven DSM-5 substance categories. Expert human review of 900 stratified cases assessed classification precision, recall, and inter-method reliability (Cohen's kappa). Test-retest stability was evaluated using approximately 15,000 independently classified records. Results: Five substance categories achieved almost perfect inter-method agreement (kappa = 0.94-1.00): alcohol, cannabis, opioid, stimulant, and sedative/hypnotic/anxiolytic. Classification precision ranged from 92% to 100% for these categories. Two low-prevalence categories (hallucinogen, inhalant) performed poorly. Test-retest agreement ranged from 92.1% to 99.1% across the seven categories. Conclusions: A small, locally hosted LLM can reliably classify substance types from child welfare administrative text, extending prior work on binary classification to multi-label substance identification. --- ### Joint 3D Gravity and Magnetic Inversion via Rectified Flow and Ginzburg-Landau Guidance Authors: Dhruman Gupta, Yashas Shende, Aritra Das, Chanda Grover Kamra, Debayan Gupta Published: 2026-03-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.06829v2 Subsurface ore detection is of paramount importance given the rising depletion of shallow mineral resources in recent years. It is crucial to explore approaches that go beyond the limitations of traditional geological exploration methods. Due to readily available surface readings, joint magnetic and gravitational inversion is a promising new method - given magnetic and gravitational data on a surface, jointly reconstructing the underlying densities that generate them. However, this is ill-posed and has non-unique solutions. Deterministic methods often require handcrafted priors and converge to a single solution and do not capture the distribution, which is often of interest. We introduce a novel framework that reframes 3D gravity and magnetic joint inversion as a rectified flow on the Noddyverse dataset, the largest physics-based dataset for inversion. We introduce a Ginzburg-Landau (GL) regularizer, a generalized version of the Ising model that aids in ore identification, enabling physics-aware training. We also propose a guidance methodology based on GL theory that can be used as a plug-and-play module with existing unconditional denoisers. Lastly, we also train and release a VAE for the 3D densities, which facilitates downstream work in the field. --- ### Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models Authors: Md Ashikur Rahman, Md Arifur Rahman, Niamul Hassan Samin, Abdullah Ibne Hanif Arean, Juena Ahmed Noshin Published: 2026-03-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.06828v2 We uncover a behavioral law of long-horizon vision-language models: models that maintain temporally grounded beliefs generalize better. Standard benchmarks measure only final-answer accuracy, which obscures how models use visual information; a model can guess correctly while its step-by-step reasoning is entirely unanchored to the visual input. We formalize this as behavioral faithfulness over long horizons, an empirically measurable property that quantifies whether a model's intermediate reasoning remains consistent with the evolving visual state. Across eight models on three long-horizon benchmarks, we demonstrate that temporal grounding quality is a leading indicator of robustness: the Step Grounding Rate (SGR) predicts out-of-distribution retention with $r = 0.83$ (permutation test $p = 0.003$), a relationship that holds within capacity-matched models and cannot be explained by scale or in-distribution accuracy. Critically, grounding quality varies by up to 10.8 percentage points within parameter-matched 7B models despite similar accuracy, revealing it as an independent axis of model capability. Multiple robustness checks confirm the signal reflects genuine visual reliance: counterfactual traces drop SGR by 26--41 percentage points, cross-architecture verifiers agree at $ρ= 0.96$, random reasoning scores near chance ($\sim 18\%$), and the predictor remains strong even without explicit reasoning disclosure ($r = 0.78$). --- ### CREDO: Epistemic-Aware Conformalized Credal Envelopes for Regression Authors: Luben M. C. Cabezas, Sabina J. Sloman, Bruno M. Resende, Fanyi Wu, Michele Caprio, Rafael Izbicki Published: 2026-03-06 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2603.06826v1 Conformal prediction delivers prediction intervals with distribution-free coverage, but its intervals can look overconfident in regions where the model is extrapolating, because standard conformal scores do not explicitly represent epistemic uncertainty. Credal methods, by contrast, make epistemic effects visible by working with sets of plausible predictive distributions, but they are typically model-based and lack calibration guarantees. We introduce CREDO, a simple "credal-then-conformalize" recipe that combines both strengths. CREDO first builds an interpretable credal envelope that widens when local evidence is weak, then applies split conformal calibration on top of this envelope to guarantee marginal coverage without further assumptions. This separation of roles yields prediction intervals that are interpretable: their width can be decomposed into aleatoric noise, epistemic inflation, and a distribution-free calibration slack. We provide a fast implementation based on trimming extreme posterior predictive endpoints, prove validity, and show on benchmark regressions that CREDO maintains target coverage while improving sparsity adaptivity at competitive efficiency. --- ### "Dark Triad" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior Authors: Roshni Lulla, Fiona Collins, Sanaya Parekh, Thilo Hagendorff, Jonas Kaplan Published: 2026-03-06 Categories: cs.CL, cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2603.06816v1 The alignment problem refers to concerns regarding powerful intelligences, ensuring compatibility with human preferences and values as capabilities increase. Current large language models (LLMs) show misaligned behaviors, such as strategic deception, manipulation, and reward-seeking, that can arise despite safety training. Gaining a mechanistic understanding of these failures requires empirical approaches that can isolate behavioral patterns in controlled settings. We propose that biological misalignment precedes artificial misalignment, and leverage the Dark Triad of personality (narcissism, psychopathy, and Machiavellianism) as a psychologically grounded framework for constructing model organisms of misalignment. In Study 1, we establish comprehensive behavioral profiles of Dark Triad traits in a human population (N = 318), identifying affective dissonance as a central empathic deficit connecting the traits, as well as trait-specific patterns in moral reasoning and deceptive behavior. In Study 2, we demonstrate that dark personas can be reliably induced in frontier LLMs through minimal fine-tuning on validated psychometric instruments. Narrow training datasets as small as 36 psychometric items resulted in significant shifts across behavioral measures that closely mirrored human antisocial profiles. Critically, models generalized beyond training items, demonstrating out-of-context reasoning rather than memorization. These findings reveal latent persona structures within LLMs that can be readily activated through narrow interventions, positioning the Dark Triad as a validated framework for inducing, detecting, and understanding misalignment across both biological and artificial intelligence. --- ### AI-Assisted Curation of Conference Scholarship: Compiling, Structuring, and Analyzing Two Decades of Presentations at the Society for Social Work and Research Authors: Brian Perron, Bryan Victor, Zia Qi Published: 2026-03-06 Categories: cs.DL, cs.AI arXiv: https://arxiv.org/abs/2603.06814v1 Purpose: This study developed a comprehensive database of presentation abstracts from the Society for Social Work and Research (SSWR) Annual Conference and examined patterns in research methodology, authorship, collaboration, and institutional participation over two decades. Method: Abstract metadata was compiled from the SSWR Confex conference management system for presentations from 2005 to 2026 using web scraping. A small language model (gpt-oss:20b) performed classification and extraction tasks on abstracts, including categorization of methodologies and parsing of author affiliations, with human review at each major stage to ensure accuracy. Results: The database contains 23,793 presentations with 69,924 author records representing 20,779 unique researchers from 4,049 institutions across 93 countries. Annual conference presentations increased from 423 in 2005 to 1,935 in 2026, representing a compound annual growth rate of 7.5%. Quantitative methods predominated (61.1%), followed by qualitative approaches (23.4%), mixed methods (9.1%), and reviews (5.4%). The mean number of authors per presentation increased from 2.22 in 2005 to 3.31 in 2026. International participation grew from 4.5% to 13.5% of author affiliations over the observation period. Discussion: Findings indicate substantial growth in SSWR conference participation, alongside increased collaboration and international engagement. The methodological distribution reveals continued quantitative predominance with growing qualitative representation. This database provides research infrastructure for systematic hypothesis testing about research priorities and disciplinary development over time, enabling analyses that inform both scholarship and conference planning. --- ### Reinforcing the World's Edge: A Continual Learning Problem in the Multi-Agent-World Boundary Authors: Dane Malenfant Published: 2026-03-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.06813v3 Ordinary decentralized multi-agent reinforcement learning presents each focal agent with a continual learning problem: peer updates change its induced rewards and dynamics even when the joint Markov game is stationary. We connect the lifetime of success-conditioned reusable structure to peer learning and policy reuse. An invariant core represents maximal abstract patterns shared by a high fraction of successful trajectories; survival refers to a fixed pattern's coverage, not an unchanged maximal frontier. An established sharp conditioning bound limits coverage loss to $\frac{\varepsilon}{p_0}$, where $\varepsilon$ is trajectory-law drift, $p_0$ is reference success mass, and drift is smaller than the initial compatible-success mass. Combining this bound with peer-policy movement certifies $Ω(\frac{1}η)$ survival under bounded peer updates of size $η$ and positive coverage margin. An effective-conflict condition yields a matching $Θ(\frac{1}η)$ first-exit law and holds in an analytic exact-policy-gradient class. With success-mass and performance calibration, structural survival also yields policy-value and finite-library transfer guarantees. An exactly solvable corridor tests the structural predictions. Two registered 64-stream studies in continual control and cue-MNIST show that coverage erosion predicts impending failure and enables near-oracle intervention. An exploratory reanalysis of eight learned-partner Level-Based Foraging pairings suggests the same erosion--failure link under peer learning. --- ### Reinforcing the World's Edge: A Continual Learning Problem in the Multi-Agent-World Boundary Authors: Dane Malenfant Published: 2026-03-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.06813v1 Reusable decision structure survives across episodes in reinforcement learning, but this depends on how the agent--world boundary is drawn. In stationary, finite-horizon MDPs, an invariant core: the (not-necessarily contiguous) subsequences of state--action pairs shared by all successful trajectories (optionally under a simple abstraction) can be constructed. Under mild goal-conditioned assumptions, it's existence can be proven and explained by how the core captures prototypes that transfer across episodes. When the same task is embedded in a decentralized Markov game and the peer agent is folded into the world, each peer-policy update induces a new MDP; the per-episode invariant core can shrink or vanish, even with small changes to the induced world dynamics, sometimes leaving only the individual task core or just nothing. This policy-induced non-stationarity can be quantified with a variation budget over the induced kernels and rewards, linking boundary drift to loss of invariants. The view that a continual RL problem arises from instability of the agent--world boundary (rather than exogenous task switches) in decentralized MARL suggests future work on preserving, predicting, or otherwise managing boundary drift. --- ### Making AI Evaluation Deployment Relevant Through Context Specification Authors: Matthew Holmes, Thiago Lacerda, Reva Schwartz Published: 2026-03-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.06811v3 With many organizations struggling to gain value from AI deployments, pressure to evaluate AI in an informed manner has intensified. Status quo AI evaluation approaches often mask the operational realities that ultimately determine deployment success, making it difficult for organizational decision makers to know whether and how AI tools will deliver durable value. We introduce and describe context specification as a process to support and inform this decision making process. Context specification turns diffuse stakeholder perspectives about what matters in a given setting into clear, named constructs: explicit definitions of the properties, behaviors, and outcomes that evaluations aim to capture, so they can be observed and measured in context. The process serves as a foundational roadmap for evaluating what AI systems are likely to do in the deployment contexts that organizations actually manage. --- ### Multi-Agent Reinforcement Learning with Submodular Reward Authors: Wenjing Chen, Chengyuan Qian, Shuo Xing, Yi Zhou, Victoria Crawford Published: 2026-03-06 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2603.06810v1 In this paper, we study cooperative multi-agent reinforcement learning (MARL) where the joint reward exhibits submodularity, which is a natural property capturing diminishing marginal returns when adding agents to a team. Unlike standard MARL with additive rewards, submodular rewards model realistic scenarios where agent contributions overlap (e.g., multi-drone surveillance, collaborative exploration). We provide the first formal framework for this setting and develop algorithms with provable guarantees on sample efficiency and regret bound. For known dynamics, our greedy policy optimization achieves a $1/2$-approximation with polynomial complexity in the number of agents $K$, overcoming the exponential curse of dimensionality inherent in joint policy optimization. For unknown dynamics, we propose a UCB-based learning algorithm achieving a $1/2$-regret of $O(H^2KS\sqrt{AT})$ over $T$ episodes. --- ### A Hybrid Machine Learning Model for Cerebral Palsy Detection Authors: Karan Kumar Singh, Nikita Gajbhiye, Gouri Sankar Mishra Published: 2026-03-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.06803v1 The development of effective treatments for Cerebral Palsy (CP) can begin with the early identification of affected children while they are still in the early stages of the disorder. Pathological issues in the brain can be better diagnosed with the use of one of many medical imaging techniques. Magnetic Resonance Imaging (MRI) has revolutionized medical imaging with its unparalleled image resolution. A unique Machine Learning (ML) model that was built to identify CP disorder is presented in this paper. The model is intended to assist in the early diagnosis of CP in newborns. In this study, the brain MRI images dataset was first collected, and then the preprocessing techniques were applied to this dataset to make it ready for use in the proposed model. Following this, the proposed model was constructed by combining three CNN models, specifically VGG 19, Efficient-Net, and the ResNet50 model, to extract features from the image. Following this, a Bi-LSTM was utilized as a classifier to determine whether or not CP was present, and finally, the proposed model was employed for training and testing. The results show that the proposed model achieved an accuracy of 98.83%, which is higher than VGG-19 (96.79%), Efficient-Net (97.29%), and VGG-16 (97.50%).. When the suggested model is compared to other models that have been pre-trained in the past, the accuracy scores seem to be much higher. --- ### Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy Authors: Yuhan Liu, Juntian Zhang, Yichen Wu, Martin Takac, Salem Lahlou, Xiuying Chen, Nils Lukas Published: 2026-03-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.06801v1 Multi-Agent Debate (MAD) has emerged as a promising paradigm for enhancing large language model reasoning. However, recent work reveals a limitation:standard MAD cannot improve belief correctness beyond majority voting; we refer to this as the Martingale Curse. This curse arises because correlated errors cause agents to converge toward erroneous consensus, where debate merely reinforces collective mistakes rather than filtering noise. We propose AceMAD, a framework that breaks the Martingale Curse by harnessing asymmetric cognitive potential energy to transform MAD from a random walk into a directed convergence process with positive drift. Through a peer-prediction mechanism, agents predict their peers' belief distributions, revealing asymmetric cognitive potential: truth-holders not only know the correct answer but also anticipate the crowd's misconceptions, while the hallucinating majority remains blind to their collective error. This asymmetry creates a potential energy gap that we quantify via strictly proper scoring rules. We prove this cognitive potential manifests as information-theoretic superiority and, under nonlinear aggregation, converts into submartingale drift toward truth, directly breaking the Martingale Curse. Experiments on challenging subsets across six benchmarks show AceMAD recovers sparse truth signals even when initial majorities are incorrect, substantially outperforming baseline methods. --- ### NEST: Network- and Memory-Aware Device Placement For Distributed Deep Learning Authors: Irene Wang, Vishnu Varma Venkata, Arvind Krishnamurthy, Divya Mahajan Published: 2026-03-06 Categories: cs.LG, cs.DC, stat.ML arXiv: https://arxiv.org/abs/2603.06798v2 The growing scale of deep learning demands distributed training frameworks that jointly reason about parallelism, memory, and network topology. Prior works often rely on heuristic or topology-agnostic search, handling communication and memory separately. Without per-device memory awareness, these methods typically ensure feasibility post hoc by sharding parameters and activations across many devices, increasing synchronization, inflating communication, and underutilizing compute-limiting scalability and efficiency on real datacenter networks. We present NEST, a network-, compute-, and memory-aware device placement framework that unifies model parallelism, topology modeling, and memory feasibility via structured dynamic programming. NEST's DP operates on operator graphs with tensor and expert parallel configurations, explicit allreduce latencies across hierarchical or arbitrary networks, and memory/compute profiles. By factoring parallelism across tensor, pipeline, data, and expert dimensions, NEST defines a principled search space for hybrid strategies while jointly optimizing co-location, network latency, and memory feasibility. Evaluations across diverse hardware and networks show NEST achieves up to 2.43 times higher throughput, better memory efficiency, and improved scalability over state-of-the-art baselines, providing a foundation for co-designing parallelization strategies and datacenter interconnects for next-generation AI infrastructure. The source code of NEST is available at: https://github.com/scai-tech/Nest --- ### Best-of-Tails: Bridging Optimism and Pessimism in Inference-Time Alignment Authors: Hsiang Hsu, Eric Lei, Chun-Fu Chen Published: 2026-03-06 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.06797v1 Inference-time alignment effectively steers large language models (LLMs) by generating multiple candidates from a reference model and selecting among them with an imperfect reward model. However, current strategies face a fundamental dilemma: ``optimistic'' approaches like Best-of-$N$ suffer from reward hacking, while ``pessimistic'' regularized methods often stifle the exploration needed to discover high-quality responses. In this work, we formalize this trade-off through the lens of regret minimization, demonstrating that the optimal strategy depends critically on the tail behavior of the reward distribution. We show theoretically that light-tailed regimes favor optimism to unearth high-quality outliers, whereas heavy-tailed regimes require pessimism to guard against reward mis-calibration in the extremes. Guided by this insight, we introduce Best-of-Tails (BoT), an adaptive inference-time alignment framework that uses Tsallis divergence as a tunable regularizer to provide a finer granularity of interpolation between these extremes. BoT uses the Hill estimator to characterize reward-tail heaviness on a per-prompt basis and dynamically adjusts its selection rule to balance exploration gains against alignment error. Across math, multiple-choice reasoning, and human-preference evaluations, BoT improves alignment performance across a range of reference and reward model configurations relative to fixed-strategy baselines. --- ### Optimistic Policy Regularization Authors: Mai Pham, Vikrant Vaze, Peter Chin Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06793v1 Deep reinforcement learning agents frequently suffer from premature convergence, where early entropy collapse causes the policy to discard exploratory behaviors before discovering globally optimal strategies. We introduce Optimistic Policy Regularization (OPR), a lightweight mechanism designed to preserve and reinforce historically successful trajectories during policy optimization. OPR maintains a dynamic buffer of high-performing episodes and biases learning toward these behaviors through directional log-ratio reward shaping and an auxiliary behavioral cloning objective. When instantiated on Proximal Policy Optimization (PPO), OPR substantially improves sample efficiency on the Arcade Learning Environment. Across 49 Atari games evaluated at the 10-million step benchmark, OPR achieves the highest score in 22 environments despite baseline methods being reported at the standard 50-million step horizon. Beyond arcade benchmarks, OPR also generalizes to the CAGE Challenge 2 cyber-defense environment, surpassing the competition-winning Cardiff agent while using the same PPO architecture. These results demonstrate that anchoring policy updates to empirically successful trajectories can improve both sample efficiency and final performance. --- ### Physics-Informed Diffusion Model for Generating Synthetic Extreme Rare Weather Events Data Authors: Marawan Yakout, Tannistha Maiti, Monira Majhabeen, Tarry Singh Published: 2026-03-06 Categories: cs.LG, cs.AI, physics.ao-ph, physics.geo-ph arXiv: https://arxiv.org/abs/2603.06782v1 Data scarcity is a primary obstacle in developing robust Machine Learning (ML) models for detecting rapidly intensifying tropical cyclones. Traditional data augmentation techniques (rotation, flipping, brightness adjustment) fail to preserve the physical consistency and high-intensity gradients characteristic of rare Category 4-equivalent events, which constitute only 0.14\% of our dataset (202 of 140,514 samples). We propose a physics-informed diffusion model based on the Context-UNet architecture to generate synthetic, multi-spectral satellite imagery of extreme weather events. Our model is conditioned on critical atmospheric parameters such as average wind speed, type of Ocean and stage of development (early, mature, late etc) -- the known drivers of rapid intensification. Using a controlled pre-generated noise sampling strategy and mixed-precision training, we generated $16\times16$ wind-field samples that are cropped from multi-spectral satellite imagery which preserve realistic spatial autocorrelation and physical consistency. Results demonstrate that our model successfully learns discriminative features across ten distinct context classes, effectively mitigating the data bottleneck. Specifically, we address the extreme class imbalance in our dataset, where Class 4 (Ocean 2, early stage with average wind speed 50kn hurricane) contains only 202 samples compared to 79,768 samples in Class 0. This generative framework provides a scalable solution for augmenting training datasets for operational weather detection algorithms. The average Results yield an average Log-Spectral Distance (LSD) of 4.5dB, demonstrating a scalable framework for enhancing operational weather detection algorithms. --- ### xaitimesynth: A Python Package for Evaluating Attribution Methods for Time Series with Synthetic Ground Truth Authors: Gregor Baer Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06781v1 Evaluating time series attribution methods is difficult because real-world datasets rarely provide ground truth for which time points drive a prediction. A common workaround is to generate synthetic data where class-discriminating features are placed at known locations, but each study currently reimplements this from scratch. We introduce xaitimesynth, a Python package that provides reusable infrastructure for this evaluation approach. The package generates synthetic time series following an additive model where each sample is a sum of background signal and a localized, class-discriminating feature, with the feature window automatically tracked as a ground truth mask. A fluent data generation API and YAML configuration format allow flexible and reproducible dataset definitions for both univariate and multivariate time series. The package also provides standard localization metrics, including AUC-PR, AUC-ROC, Relevance Mass Accuracy, and Relevance Rank Accuracy. xaitimesynth is open source and available at https://github.com/gregorbaer/xaitimesynth. --- ### SpatialMAGIC: A Hybrid Framework Integrating Graph Diffusion and Spatial Attention for Spatial Transcriptomics Imputation Authors: Sayeem Bin Zaman, Fahim Hafiz, Riasat Azim Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06780v1 Spatial transcriptomics (ST) enables mapping gene expression with spatial context but is severely affected by high sparsity and technical noise, which conceals true biological signals and hinders downstream analyses. To address these challenges, SpatialMagic was proposed, which is a hybrid imputation model combining MAGIC-based graph diffusion with transformer-based spatial self-attention. The long-range dependencies in the gene expression are captured by graph diffusion, and local neighborhood structure is captured by spatial attention models, which allow for recovering the missing expression values, retaining spatial consistency. Across multiple platforms, SpatialMagic consistently outperforms existing baselines, including MAGIC and attention-based models, achieving peak Adjusted Rand Index (ARI) scores in clustering accuracy of 0.3301 on high-resolution Stereo-Seq data, 0.3074 on Slide-Seq, and 0.4216 on the Sci-Space dataset. Beyond quantitative improvements, SpatialMagic substantially enhances downstream biological analyses by improving the detection of both up- and down-regulated genes while maintaining regulatory consistency across datasets. The pathway enrichment analysis of the recovered genes indicates that they are involved in consistent processes across key metabolic, transport, and neural signaling pathways, suggesting that the framework improves data quality while preserving biological interpretability. Overall, SpatialMagic's hybrid diffusion attention strategy and refinement module outperform state-of-the-art baselines on quantitative metrics and provide a better understanding of the imputed data by preserving tissue architecture and uncovering biologically relevant genes. The source code and datasets are provided in the following link: https://github.com/sayeemzzaman/SpatialMAGIC --- ### HGT-Scheduler: Deep Reinforcement Learning for the Job Shop Scheduling Problem via Heterogeneous Graph Transformers Authors: Bulent Soykan Published: 2026-03-06 Categories: cs.LG, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2603.06777v1 The Job Shop Scheduling Problem (JSSP) is commonly formulated as a disjunctive graph in which nodes represent operations and edges encode technological precedence constraints as well as machine-sharing conflicts. Most existing reinforcement learning approaches model this graph as homogeneous, merging job-precedence and machine-contention edges into a single relation type. Such a simplification overlooks the intrinsic heterogeneity of the problem structure and may lead to the loss of critical relational information. To address this limitation, we propose the Heterogeneous Graph Transformer (HGT)-Scheduler, a reinforcement learning framework that models the JSSP as a heterogeneous graph. The proposed architecture leverages a Heterogeneous Graph Transformer to capture type-specific relational patterns through edge-type-dependent attention mechanisms applied to precedence and contention relations. The scheduling policy is trained using Proximal Policy Optimization. The effectiveness of the proposed method is evaluated on the Fisher--Thompson benchmark instances. On the FT06 instance, the HGT-Scheduler achieves an optimality gap of 8.4\%, statistically outperforming both an identical architecture that ignores edge types ($p = 0.011$) and a standard Graph Isomorphism Network baseline. On the larger FT10 instance, the approach demonstrates favorable scalability. However, under a 50,000-step training limit, the performance of heterogeneous and homogeneous graph models is comparable, suggesting that edge-type awareness requires longer training horizons for larger problem instances. Ablation analyses further indicate that a three-layer attention architecture provides the best performance. Overall, the results confirm that explicitly modeling distinct edge semantics improves the learning of effective scheduling policies. --- ### Gauge Freedom and Metric Dependence in Neural Representation Spaces Authors: Jericho Cain Published: 2026-03-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.06774v1 Neural network representations are often analyzed as vectors in a fixed Euclidean space. However, their coordinates are not uniquely defined. If a hidden representation is transformed by an invertible linear map, the network function can be preserved by applying the inverse transformation to downstream weights. Representations are therefore defined only up to invertible linear transformations. We study neural representation spaces from this geometric viewpoint and treat them as vector spaces with a gauge freedom under the general linear group. Within this framework, commonly used similarity measures such as cosine similarity become metric-dependent quantities whose values can change under coordinate transformations that leave the model function unchanged. This provides a common interpretation for several observations in the literature, including cosine-similarity instability, anisotropy in embedding spaces, and the appeal of representation comparison methods such as SVCCA and CKA. Experiments on multilayer perceptrons and convolutional networks confirm that inserting invertible transformations into trained models can substantially distort cosine similarity and nearest-neighbor structure while leaving predictions unchanged. These results indicate that analysis of neural representations should focus either on quantities that are invariant under this gauge freedom or on explicitly chosen canonical coordinates. --- ### Failure Detection in Chemical Processes Using Symbolic Machine Learning: A Case Study on Ethylene Oxidation Authors: Julien Amblard, Niklas Groll, Matthew Tait, Mark Law, Gürkan Sin, Alessandra Russo Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06767v3 Over the past decade, Artificial Intelligence has significantly advanced, mostly driven by large-scale neural approaches. However, in the chemical process industry, where safety is critical, these methods are often unsuitable due to their brittleness, and lack of explainability and interpretability. Furthermore, open-source real-world datasets containing historical failures are scarce in this domain. In this paper, we investigate an approach for predicting failures in chemical processes using symbolic machine learning and conduct a feasibility study in the context of an ethylene oxidation process. Our method builds on a state-of-the-art symbolic machine learning system capable of learning predictive models in the form of probabilistic rules from context-dependent noisy examples. This system is a general-purpose symbolic learner, which makes our approach independent of any specific chemical process. To address the lack of real-world failure data, we conduct our feasibility study leveraging data generated from a chemical process simulator. Experimental results show that symbolic machine learning can outperform baseline methods such as random forest and multilayer perceptron, while preserving interpretability through the generation of compact, rule-based predictive models. Finally, we explain how such learned rule-based models could be integrated into agents to assist chemical plant operators in decision-making during potential failures. --- ### HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compression Authors: Haoxuan Xiong, Yuanyuan Xu, Kun Zhu, Yiming Wang, Baoliu Ye Published: 2026-03-06 Categories: eess.IV, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2603.06766v1 Learned image compression (LIC) has achieved remarkable coding efficiency, where entropy modeling plays a pivotal role in minimizing bitrate through informative priors. Existing methods predominantly exploit internal contexts within the input image, yet the rich external priors embedded in large-scale training data remain largely underutilized. Recent advances in dictionary-based entropy models have demonstrated that incorporating external priors can substantially enhance compression performance. However, current approaches organize heterogeneous external priors within a single-level dictionary, resulting in imbalanced utilization and limited representational capacity. Moreover, effective entropy modeling requires not only expressive priors but also a parameter estimation network capable of interpreting them. To address these challenges, we propose HiDE, a Hierarchical Dictionary-based Entropy modeling framework for learned image compression. HiDE decomposes external priors into global structural and local detail dictionaries with cascaded retrieval, enabling structured and efficient utilization of external information. Moreover, a context-aware parameter estimator with parallel multi-receptive-field design is introduced to adaptively exploit heterogeneous contexts for accurate conditional probability estimation. Experimental results show that HiDE achieves 18.5%, 21.99%, and 24.01% BD-rate savings over VTM-12.1 on the Kodak, CLIC, and Tecnick datasets, respectively. --- ### Metalearning traffic assignment for network disruptions with graph convolutional neural networks Authors: Serio Agriesti, Guido Cantelmo, Francisco Camara Pereira Published: 2026-03-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.06763v1 Building machine-learning models for estimating traffic flows from OD matrices requires an appropriate design of the training process and a training dataset spanning over multiple regimes and dynamics. As machine-learning models rely heavily on historical data, their predictions are typically accurate only when future traffic patterns resemble those observed during training. However, their performance often degrades when there is a significant statistical discrepancy between historical and future conditions. This issue is particularly relevant in traffic forecasting when predictions are required for modified versions of the network, where the underlying graph structure changes due to events such as maintenance, public demonstrations, flooding, or other extreme disruptions. Ironically, these are precisely the situations in which reliable traffic predictions are most needed. In the presented work, we combine a machine-learning model (graph convolutional neural network) with a meta-learning architecture to train the former to quickly adapt to new graph structures and demand patterns, so that it may easily be applied to scenarios in which changes in the road network (the graph) and the demand (the node features) happen simultaneously. Our results show that the use of meta-learning allows the graph neural network to quickly adapt to unseen graphs (network closures) and OD matrixes while easing the burden of designing a training dataset that covers all relevant patterns for the practitioners. The proposed architecture achieves a R^2 of around 0.85 over unseen closures and OD matrixes. --- ### Prediction of Steady-State Flow through Porous Media Using Machine Learning Models Authors: Jinhong Wang, Matei C. Ignuta-Ciuncanu, Ricardo F. Martinez-Botas, Teng Cao Published: 2026-03-06 Categories: physics.flu-dyn, cs.CE, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2603.06762v1 Solving flow through porous media is a crucial step in the topology optimisation of cold plates, a key component in modern thermal management. Traditional computational fluid dynamics (CFD) methods, while accurate, are often prohibitively expensive for large and complex geometries. In contrast, data-driven surrogate models provide a computationally efficient alternative, enabling rapid and reliable predictions. In this study, we develop a machine-learning framework for predicting steady-state flow through porous media governed by the Navier-Stokes-Brinkman equations. We implement and compare three model architectures-convolutional autoencoder (AE), U-Net, and Fourier Neural Operator (FNO)-evaluating their predictive performance. To enhance physics consistency, we incorporate physics-informed loss functions. Our results demonstrate that FNO outperforms AE and U-Net, achieving a mean squared error (MSE) as low as 0.0017 while providing speedups of up to 1000 times compared to CFD. Additionally, the mesh-invariant property of FNO emphasizes its suitability for topology optimisation tasks, where varying mesh resolutions are required. This study highlights the potential of machine learning to accelerate fluid flow predictions in porous media, offering a scalable alternative to traditional numerical methods. --- ### Diversity-Aware Adaptive Collocation for Physics-Informed Neural Networks via Sparse QUBO Optimization and Hybrid Coresets Authors: Hadi Salloum, Maximilian Mifsud Bonici, Sinan Ibrahim, Pavel Osinenko, Alexei Kornaev Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06761v1 Physics-Informed Neural Networks (PINNs) enforce governing equations by penalizing PDE residuals at interior collocation points, but standard collocation strategies - uniform sampling and residual-based adaptive refinement - can oversample smooth regions, produce highly correlated point sets, and incur unnecessary training cost. We reinterpret collocation selection as a coreset construction problem: from a large candidate pool, select a fixed-size subset that is simultaneously informative (high expected impact on reducing PDE error) and diverse (low redundancy under a space-time similarity notion). We formulate this as a QUBO/BQM objective with linear terms encoding residual-based importance and quadratic terms discouraging redundant selections. To avoid the scalability issues of dense k-hot QUBOs, we propose a sparse graph-based BQM built on a kNN similarity graph and an efficient repair procedure that enforces an exact collocation budget. We further introduce hybrid coverage anchors to guarantee global PDE enforcement. We evaluate the method on the 1D time-dependent viscous Burgers equation with shock formation and report both accuracy and end-to-end time-to-accuracy, including a timing breakdown of selection overhead. Results demonstrate that sparse and hybrid formulations reduce selection overhead relative to dense QUBOs while matching or improving accuracy at fixed collocation budgets. --- ### Gradient-based Nested Co-Design of Aerodynamic Shape and Control for Winged Robots Authors: Daniele Affinita, Mingda Xu, Benoît Valentin Gherardi, Pascal Fua Published: 2026-03-06 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.06760v1 Designing aerial robots for specialized tasks, from perching to payload delivery, requires tailoring their aerodynamic shape to specific mission requirements. For tasks involving wide flight envelopes, the usual sequential process of first determining the shape and then the motion planner is likely to be suboptimal due to the inherent nonlinear interactions between them. This limitation has been motivating co-design research, which involves jointly optimizing the aerodynamic shape and the motion planner. In this paper, we present a general-purpose, gradient-based, nested co-design framework where the motion planner solves an optimal control problem and the aerodynamic forces used in the dynamics model are determined by a neural surrogate model. This enables us to model complex subsonic flow conditions encountered in aerial robotics and to overcome the limited applicability of existing co-design methods. These limitations stem from the simplifying assumptions they require for computational tractability to either the planner or the aerodynamics. We validate our method on two complex dynamic tasks for fixed-wing gliders: perching and a short landing. Our optimized designs improve task performance compared to an evolutionary baseline in a fraction of the computation time. --- ### Enhancing SHAP Explainability for Diagnostic and Prognostic ML Models in Alzheimer Disease Authors: Pablo Guillén, Enrique Frias-Martinez Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06758v1 Alzheimer disease (AD) diagnosis and prognosis increasingly rely on machine learning (ML) models. Although these models provide good results, clinical adoption is limited by the need for technical expertise and the lack of trustworthy and consistent model explanations. SHAP (SHapley Additive exPlanations) is com-monly used to interpret AD models, but existing studies tend to focus on explanations for isolated tasks, providing little evidence about their robustness across disease stages, model architectures, or prediction objectives. This paper proposes a multi-level explainability framework that measures the coherence, stabil-ity and consistency of explanations by integrating: (1) within-model coherence metrics between feature importance and SHAP, (2) SHAP stability across AD boundaries, and (3) SHAP cross-task consistency be-tween diagnosis and prognosis. Using AutoML to optimize classifiers on the NACC dataset, we trained four diagnostic and four prognostic models covering the standard AD progression stages. Stability was then evaluated using correlation metrics, top-k feature overlap, SHAP sign consistency, and domain-level contribution ratios. Results show that cognitive and functional markers dominate SHAP explanations in both diagnosis and prognosis. SHAP-SHAP consistency between diagnostic and prognostic models was high across all classifiers, with 100% sign stability and minimal shifts in explanatory magnitude. Domain-level contributions also remained stable, with only minimal increases in genetic features for prognosis. These results demonstrate that SHAP explanations can be quantitatively vali-dated for robustness and transferability, providing clinicians with more reliable interpretations of ML pre-dictions. --- ### Learning Unbiased Cluster Descriptors for Interpretable Imbalanced Concept Drift Detection Authors: Yiqun Zhang, Zhanpei Huang, Mingjie Zhao, Chuyao Zhang, Yang Lu, Yuzhu Ji, Fangqing Gu, An Zeng Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06757v1 Unlabeled streaming data are usually collected to describe dynamic systems, where concept drift detection is a vital prerequisite to understanding the evolution of systems. However, the drifting concepts are usually imbalanced in most real cases, which brings great challenges to drift detection. That is, the dominant statistics of large clusters can easily mask the drifting of small cluster distributions (also called small concepts), which is known as the `masking effect'. Considering that most existing approaches only detect the overall existence of drift under the assumption of balanced concepts, two critical problems arise: 1) where the small concept is, and 2) how to detect its drift. To address the challenging concept drift detection for imbalanced data, we propose Imbalanced Cluster Descriptor-based Drift Detection (ICD3) approach that is unbiased to the imbalanced concepts. This approach first detects imbalanced concepts by employing a newly designed multi-distribution-granular search, which ensures that the distribution of both small and large concepts is effectively captured. Subsequently, it trains a One-Cluster Classifier (OCC) for each identified concept to carefully monitor their potential drifts in the upcoming data chunks. Since the detection is independently performed for each concept, the dominance of large clusters is thus circumvented. ICD3 demonstrates highly interpretability by specifically locating the drifted concepts, and is robust to the changing of the imbalance ratio of concepts. Comprehensive experiments with multi-aspect ablation studies conducted on various benchmark datasets demonstrate the superiority of ICD3 against the state-of-the-art counterparts. --- ### Implementation of Quantum Implicit Neural Representation in Deterministic and Probabilistic Autoencoders for Image Reconstruction/Generation Tasks Authors: Saadet Müzehher Eren Published: 2026-03-06 Categories: cs.LG, quant-ph arXiv: https://arxiv.org/abs/2603.06755v3 We propose a quantum implicit neural representation (QINR)-based autoencoder (AE) and variational autoencoder (VAE) for image reconstruction and generation tasks. Our purpose is to demonstrate that the QINR in VAEs and AEs can transform information from the latent space into highly rich, periodic, and high-frequency features. Additionally, we aim to show that the QINR-VAE can be more stable than various quantum generative adversarial network (QGAN) models in image generation because it can address the low diversity problem. Our quantum-classical hybrid models consist of a classical convolutional neural network (CNN) encoder and a quantum-based QINR decoder. We train the QINR-AE/VAE with binary cross-entropy with logits (BCEWithLogits) as the reconstruction loss. For the QINR-VAE, we additionally employ Kullback-Leibler divergence for latent regularization with beta/capacity scheduling to prevent posterior collapse. We introduce learnable angle-scaling in data reuploading to address optimization challenges. We test our models on the MNIST, E-MNIST, and Fashion MNIST datasets to reconstruct and generate images. Our results demonstrate that the QINR structure in VAE can produce a wider variety of images with a small amount of data than various generative models that have been studied. We observe that the generated/reconstructed images from the QINR-VAE/AE are clear with sharp boundaries and details. Overall, we find that the addition of QINR-based quantum layers into the AE/VAE frameworks shows improved performance of reconstruction/generation under the constrained experimental setting relative to the specific baselines. --- ### Implementation of Quantum Implicit Neural Representation in Deterministic and Probabilistic Autoencoders for Image Reconstruction/Generation Tasks Authors: Saadet Müzehher Eren Published: 2026-03-06 Categories: cs.LG, quant-ph arXiv: https://arxiv.org/abs/2603.06755v2 We propose a quantum implicit neural representation (QINR)-based autoencoder (AE) and variational autoencoder (VAE) for image reconstruction and generation tasks. Our purpose is to demonstrate that the QINR in VAEs and AEs can transform information from the latent space into highly rich, periodic, and high-frequency features. Additionally, we aim to show that the QINR-VAE can be more stable than various quantum generative adversarial network (QGAN) models in image generation because it can address the low diversity problem. Our quantum-classical hybrid models consist of a classical convolutional neural network (CNN) encoder and a quantum-based QINR decoder. We train the QINR-AE/VAE with binary cross-entropy with logits (BCEWithLogits) as the reconstruction loss. For the QINR-VAE, we additionally employ Kullback-Leibler divergence for latent regularization with beta/capacity scheduling to prevent posterior collapse. We introduce learnable angle-scaling in data reuploading to address optimization challenges. We test our models on the MNIST, E-MNIST, and Fashion-MNIST datasets to reconstruct and generate images. Our results demonstrate that the QINR structure in VAE can produce a wider variety of images with a small amount of data than various generative models that have been studied. We observe that the generated and reconstructed images from the QINR-VAE/AE are clear with sharp boundaries and details. Overall, we find that the addition of QINR-based quantum layers into the AE/VAE frameworks enhances the performance of reconstruction and generation with a constrained set of parameters. --- ### EarthBridge: A Solution for 4th Multi-modal Aerial View Image Challenge Translation Track Authors: Zhenyuan Chen, Guanyuan Shen, Feng Zhang Published: 2026-03-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.06753v2 Cross-modal image-to-image translation among Electro-Optical (EO), Infrared (IR), and Synthetic Aperture Radar (SAR) sensors is essential for comprehensive multi-modal aerial-view analysis. However, translating between these modalities is notoriously difficult due to their distinct electromagnetic signatures and geometric characteristics. This paper presents \textbf{EarthBridge}, a high-fidelity translation framework developed for the 4th Multi-modal Aerial View Image Challenge -- Translation (MAVIC-T). We explore two distinct methodologies: \textbf{Diffusion Bridge Implicit Models (DBIM)}, which we generalize using non-Markovian bridge processes for high-quality deterministic sampling, and \textbf{Contrastive Unpaired Translation (CUT)}, which utilizes contrastive learning for structural consistency. Our EarthBridge framework employs a channel-concatenated UNet denoiser trained with Karras-weighted bridge scalings and a specialized "booting noise" initialization to handle the inherent ambiguity in cross-modal mappings. We evaluate these methods across all four challenge tasks (SAR$\rightarrow$EO, SAR$\rightarrow$RGB, SAR$\rightarrow$IR, RGB$\rightarrow$IR), achieving superior spatial detail and spectral accuracy. Our solution achieved a composite score of 0.38, securing the second position on the MAVIC-T leaderboard. Code is available at https://github.com/Bili-Sakura/EarthBridge-Preview. --- ### Latent Autoencoder Ensemble Kalman Filter for Nonlinear Data assimilation Authors: Xin T. Tong, Yanyan Wang, Liang Yan Published: 2026-03-06 Categories: cs.LG, math.NA, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2603.06752v2 The ensemble Kalman filter (EnKF) is widely used for data assimilation in high-dimensional systems, but its performance often deteriorates for strongly nonlinear dynamics due to the structural mismatch between the Kalman update and the underlying system behavior. In this work, we propose a latent autoencoder ensemble Kalman filter (LAE-EnKF) that addresses this limitation by reformulating the assimilation problem in a learned latent space with linear and stable dynamics. The proposed method learns a nonlinear encoder--decoder together with a stable linear latent evolution operator and a consistent latent observation mapping, yielding a closed linear state-space model in the latent coordinates. This construction restores compatibility with the Kalman filtering framework and allows both forecast and analysis steps to be carried out entirely in the latent space. Compared with existing autoencoder-based and latent assimilation approaches that rely on unconstrained nonlinear latent dynamics, the proposed formulation emphasizes structural consistency, stability, and interpretability. We provide a theoretical analysis of learning linear dynamics on low-dimensional manifolds and establish generalization error bounds for the proposed latent model. Numerical experiments on representative nonlinear and chaotic systems demonstrate that the LAE-EnKF yields more accurate and stable assimilation than the standard EnKF and related latent-space methods, while maintaining comparable computational cost and data-driven. --- ### XMACNet: An Explainable Lightweight Attention based CNN with Multi Modal Fusion for Chili Disease Classification Authors: Tapon Kumer Ray, Rajkumar Y, Shalini R, Srigayathri K, Jayashree S, Lokeswari P Published: 2026-03-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.06750v1 Plant disease classification via imaging is a critical task in precision agriculture. We propose XMACNet, a novel light-weight Convolutional Neural Network (CNN) that integrates self-attention and multi-modal fusion of visible imagery and vegetation indices for chili disease detection. XMACNet uses an EfficientNetV2S backbone enhanced by a self-attention module and a fusion branch that processes both RGB images and computed vegetation index maps (NDVI, NPCI, MCARI). We curated a new dataset of 12,000 chili leaf images across six classes (five disease types plus healthy), augmented synthetically via StyleGAN to mitigate data scarcity. Trained on this dataset, XMACNet achieves high accuracy, F1-score, and AUC, outperforming baseline models such as ResNet-50, MobileNetV2, and a Swin Transformer variant. Crucially, XMACNet is explainable: we use Grad-CAM++ and SHAP to visualize and quantify the models focus on disease features. The models compact size and fast inference make it suitable for edge deployment in real-world farming scenarios. --- ### Robotic Foundation Models for Industrial Control: A Comprehensive Survey and Readiness Assessment Framework Authors: David Kube, Simon Hadwiger, Tobias Meisen Published: 2026-03-06 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.06749v1 Robotic foundation models (RFMs) are emerging as a promising route towards flexible, instruction- and demonstration-driven robot control, however, a critical investigation of their industrial applicability is still lacking. This survey gives an extensive overview over the RFM-landscape and analyses, driven by concrete implications, how industrial domains and use cases shape the requirements of RFMs, with particular focus on collaborative robot platforms, heterogeneous sensing and actuation, edge-computing constraints, and safety-critical operation. We synthesise industrial deployment perspectives into eleven interdependent implications and operationalise them into an assessment framework comprising a catalogue of 149 concrete criteria, spanning both model capabilities and ecosystem requirements. Using this framework, we evaluate 324 manipulation-capable RFMs via 48,276 criterion-level decisions obtained via a conservative LLM-assisted evaluation pipeline, validated against expert judgements. The results indicate that industrial maturity is limited and uneven: even the highest-rated models satisfy only a fraction of criteria and typically exhibit narrow implication-specific peaks rather than integrated coverage. We conclude that progress towards industry-grade RFMs depends less on isolated benchmark successes than on systematic incorporation of safety, real-time feasibility, robust perception, interaction, and cost-effective system integration into auditable deployment stacks. --- ### Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment Authors: Xiaoyang Hou, Junqi Liu, Chence Shi, Xin Liu, Zhi Yang, Jian Tang Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06748v2 Protein sequence design must balance designability, defined as the ability to recover a target backbone, with multiple, often competing, developability properties such as solubility, thermostability, and expression. Existing approaches address these properties through post hoc mutation, inference-time biasing, or retraining on property-specific subsets, yet they are target dependent and demand substantial domain expertise or careful hyperparameter tuning. In this paper, we introduce ProtAlign, a multi-objective preference alignment framework that fine-tunes pretrained inverse folding models to satisfy diverse developability objectives while preserving structural fidelity. ProtAlign employs a semi-online Direct Preference Optimization strategy with a flexible preference margin to mitigate conflicts among competing objectives and constructs preference pairs using in silico property predictors. Applied to the widely used ProteinMPNN backbone, the resulting model MoMPNN enhances developability without compromising designability across tasks including sequence design for CATH 4.3 crystal structures, de novo generated backbones, and real-world binder design scenarios, making it an appealing framework for practical protein sequence design. --- ### ButterflyViT: 354$\times$ Expert Compression for Edge Vision Transformers Authors: Aryan Karmore Published: 2026-03-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.06746v1 Deploying sparse Mixture of Experts(MoE) Vision Transformers remains a challenge due to linear expert memory scaling. Linear memory scaling stores $N$ independent expert weight matrices requiring $\mathcal{O}(N_E \cdot d^2)$ memory, which exceeds edge devices memory budget. Current compression methods like quantization, pruning and low-rank factorization reduce constant factors but leave the scaling bottleneck unresolved. We introduce ButterflyViT, a method that treats experts not as independent weight matrices but as geometric reorientations of a unified shared quantized substrate. Diversity among experts arises from viewing different angles of shared capacity, not from redundant storage. By applying learned rotations to a shared ternary prototype, each expert yields $\mathcal{O}(d_{\text{model}} \cdot d_{\text{ff}} + N_E \cdot n_\ell \cdot d)$ memory which is sub-linear in the number of experts. To address the unique challenges of vision, a spatial smoothness regulariser is introduced that penalises routing irregularities between adjacent patch tokens, turning patch correlation into a training signal. Across image classification tasks on CIFAR-100, ButterflyViT achieves 354$\times$ memory reduction at 64 experts with negligible accuracy loss. ButterflyViT allows multiple experts to fit on edge-constrained devices showing that geometric parameterization breaks linear scaling. --- ### Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection Authors: Minjae Kang, Jaehyung Kim Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06745v1 Large Language Models (LLMs), despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim to mitigate this by manipulating model internals, but have a potential risk of oversteering, where excessive emphasis on the instruction degrades task accuracy and overall text quality. To address this, we introduce DIRECTER (Dynamic rejection steering), a novel steering method that dynamically modulates steering strength by scaling the KV cache without extra dataset. DIRECTER couples steering with a plausibility-guided decoding loop, which adaptively adjusts steering strength at each step by comparing the steered output distribution to the original. If the steered output is deemed implausible, steering strength is progressively weakened. This strength modulation is guided by a lightweight, one-time attention sensitivity analysis that ranks layers by their influence on model representations. Extensive evaluations show that DIRECTER significantly enhances instruction-following capabilities across diverse benchmarks, improving accuracy by up to 6.5% over baselines without the common trade-offs in generation quality or task fidelity. The proposed dynamic, plausibility-guided control during activation steering further demonstrates its potential as a general mechanism for mitigating oversteering that is compatible with existing baselines. --- ### Stabilizing Reinforcement Learning for Diffusion Language Models Authors: Jianyuan Zhong, Kaibo Wang, Ding Ding, Zijin Feng, Haoli Bai, Yang Xiang, Jiacheng Sun, Qiang Xu Published: 2026-03-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06743v1 Group Relative Policy Optimization (GRPO) is highly effective for post-training autoregressive (AR) language models, yet its direct application to diffusion large language models (dLLMs) often triggers reward collapse. We identify two sources of incompatibility. First, GRPO relies on importance ratios defined by sequence probabilities, which are intractable in dLLMs and must be estimated (e.g., via ELBO-based or mean-field likelihood proxies), yielding inherently noisy ratios. Second, standard GRPO's formulation is not designed for estimated ratios: its conditional clipping can be anomalously bypassed by model-agnostic estimation noise, producing gradient spikes, while its fixed group-size normalization amplifies gradient-magnitude fluctuations under high-variance ratio estimates. We show these effects form a self-reinforcing instability loop that drives policy drift and further increases ratio variance. To break this loop, we propose StableDRL, a reformulation of GRPO tailored for dLLMs that uses (i) unconditional clipping to suppress outlier-induced spikes and (ii) self-normalization to constrain updates within the convex hull of per-sample gradients. We further extend StableDRL to block-wise diffusion models via a staircase attention mechanism. --- ### Improved Constrained Generation by Bridging Pretrained Generative Models Authors: Xiaoxuan Liang, Saeid Naderiparizi, Yunpeng Liu, Berend Zwartsenberg, Frank Wood Published: 2026-03-06 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2603.06742v1 Constrained generative modeling is fundamental to applications such as robotic control and autonomous driving, where models must respect physical laws and safety-critical constraints. In real-world settings, these constraints rarely take the form of simple linear inequalities, but instead complex feasible regions that resemble road maps or other structured spatial domains. We propose a constrained generation framework that generates samples directly within such feasible regions while preserving realism. Our method fine-tunes a pretrained generative model to enforce constraints while maintaining generative fidelity. Experimentally, our method exhibits characteristics distinct from existing fine-tuning and training-free constrained baselines, revealing a new compromise between constraint satisfaction and sampling quality. --- ### Heterogeneous Decentralized Diffusion Models Authors: Zhiying Jiang, Raihan Seraj, Marcos Villagra, Bidhan Roy Published: 2026-03-06 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.06741v3 Training frontier-scale diffusion models often requires substantial computational resources concentrated in tightly-coupled clusters, limiting participation to well-resourced institutions. While Decentralized Diffusion Models (DDM) enable training multiple experts in isolation, existing approaches require 1176 GPU-days and homogeneous training objectives across all experts. We present an efficient framework that dramatically reduces resource requirements while supporting heterogeneous training objectives. Our approach combines three key contributions: (1) a heterogeneous decentralized training paradigm that allows experts to use different objectives (DDPM and Flow Matching), unified at inference time without any retraining; (2) pretrained checkpoint conversion from ImageNet-DDPM to Flow Matching objectives, accelerating convergence and enabling initialization without objective-specific pretraining; and (3) PixArt-$α$'s efficient AdaLN-Single architecture, reducing parameters while maintaining quality. Experiments on LAION-Aesthetics show that, relative to the training scale reported for prior DDM work, our approach reduces the compute by 16$\times$ and data by 14$\times$. Under aligned inference settings, our heterogeneous configuration achieves better FID and higher intra-prompt diversity than the homogeneous baseline. By eliminating synchronization requirements and enabling mixed DDPM/FM objectives, our framework makes decentralized generative model training accessible to contributors with single GPUs requiring only 24--48GB VRAM. ---