# Research Papers — 2026-03 · bundle page 147 of 243

> Full-text markdown of papers #7301–7350 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/147
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/146.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/148.md)

### Hallucination as output-boundary misclassification: a composite abstention architecture for language models

Authors: Angelina Hintsanen
Published: 2026-03-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.06195v1

Large language models often produce unsupported claims. We frame this as a misclassification error at the output boundary, where internally generated completions are emitted as if they were grounded in evidence. This motivates a composite intervention that combines instruction-based refusal with a structural abstention gate. The gate computes a support deficit score, St, from three black-box signals: self-consistency (At), paraphrase stability (Pt), and citation coverage (Ct), and blocks output when St exceeds a threshold. In a controlled evaluation across 50 items, five epistemic regimes, and three models, neither mechanism alone was sufficient. Instruction-only prompting reduced hallucination sharply, but still showed over-cautious abstention on answerable items and residual hallucination for GPT-3.5-turbo. The structural gate preserved answerable accuracy across models but missed confident confabulation on conflicting-evidence items. The composite architecture achieved high overall accuracy with low hallucination, while also inheriting some over-abstention from the instruction component. A supplementary 100-item no-context stress test derived from TruthfulQA showed that structural gating provides a capability-independent abstention floor. Overall, instruction-based refusal and structural gating show complementary failure modes, which suggests that effective hallucination control benefits from combining both mechanisms.

---

### SafeScreen: A Safety-First Screening Framework for Personalized Video Retrieval for Vulnerable Users

Authors: Wenzheng Zhao, Madhava Kalyan Gadiputi, Fengpei Yuan
Published: 2026-03-12
Categories: cs.CV, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2604.03264v1

Open-domain video platforms offer rich, personalized content that could support health, caregiving, and educational applications, but their engagement-optimized recommendation algorithms can expose vulnerable users to inappropriate or harmful material. These risks are especially acute in child-directed and care settings (e.g., dementia care), where content must satisfy individualized safety constraints before being shown. We introduce SafeScreen, a safety-first video screening framework that retrieves and presents personalized video while enforcing individualized safety constraints. Rather than ranking videos by relevance or popularity, SafeScreen treats safety as a prerequisite and performs sequential approval or rejection of candidate videos through an automated pipeline. SafeScreen integrates three key components: (i) profile-driven extraction of individualized safety criteria, (ii) evidence-grounded assessments via adaptive question generation and multimodal VideoRAG analysis, and (iii) LLM-based decision-making that verifies safety, appropriateness, and relevance before content exposure. This design enables explainable, real-time screening of uncurated video repositories without relying on precomputed safety labels. We evaluate SafeScreen in a dementia-care reminiscence case study using 30 synthetic patient profiles and 90 test queries. Results demonstrate that SafeScreen prioritizes safety over engagement, diverging from YouTube's engagement-optimized rankings in 80-93% of cases, while maintaining high levels of safety coverage, sensibleness, and groundedness, as validated by both LLM-based evaluation and domain experts.

---

### LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling

Authors: Keqin Xie
Published: 2026-03-12
Categories: cs.CL, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2604.03263v1

Most current long-context language models still rely on attention to handle both local interaction and long-range state, which leaves relatively little room to test alternative decompositions of sequence modeling. We propose LPC-SM, a hybrid autoregressive architecture that separates local attention, persistent memory, predictive correction, and run-time control within the same block, and we use Orthogonal Novelty Transport (ONT) to govern slow-memory writes. We evaluate a 158M-parameter model in three stages spanning base language modeling, mathematical continuation, and 4096-token continuation. Removing mHC raises the Stage-A final LM loss from 12.630 to 15.127, while adaptive sparse control improves the Stage-B final LM loss from 12.137 to 10.787 relative to a matched fixed-ratio continuation. The full route remains stable at sequence length 4096, where Stage C ends with final LM loss 11.582 and improves the delayed-identifier diagnostic from 14.396 to 12.031 in key cross-entropy. Taken together, these results show that long-context autoregressive modeling can be organized around a broader division of labor than attention alone.

---

### AI Governance Control Stack for Operational Stability: Achieving Hardened Governance in AI Systems

Authors: Horatio Morgan
Published: 2026-03-12
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2604.03262v1

Artificial intelligence systems are increasingly embedded in high-stakes decision environments, yet many governance approaches focus primarily on policy guidance rather than operational stability mechanisms. As AI deployments scale, organizations require governance architectures capable of maintaining reliable, auditable, and accountable behavior over time. This paper introduces the AI Governance Control Stack for Operational Stability, a layered governance architecture designed to ensure traceable and resilient AI system behavior. The proposed control stack integrates six complementary governance layers: system-of-record version governance, evidence-based verification, decision-time explainability logging, telemetry monitoring, model drift detection, and governance escalation. Together, these layers provide a structured mechanism for preserving governance integrity across the AI lifecycle while enabling organizations to detect instability, respond to emerging risks, and maintain regulatory accountability. The architecture aligns operational governance practices with emerging regulatory and standards frameworks, including the EU AI Act, ISO/IEC 42001 Artificial Intelligence Management Systems, and the NIST AI Risk Management Framework. By combining explainability infrastructure with continuous monitoring and human oversight mechanisms, the governance control stack provides a practical blueprint for achieving hardened AI governance in complex enterprise environments. The paper contributes a conceptual governance architecture and a framework alignment analysis demonstrating how operational stability mechanisms can strengthen responsible AI implementation. The findings suggest that organizations must move beyond static policy frameworks toward integrated governance control systems capable of sustaining trustworthy AI operation in dynamic environments.

---

### VIGIL: An Extensible System for Real-Time Detection and Mitigation of Cognitive Bias Triggers

Authors: Bo Kang, Sander Noels, Tijl De Bie
Published: 2026-03-12
Categories: cs.CL, cs.CY, cs.HC
arXiv: https://arxiv.org/abs/2604.03261v2

The rise of generative AI is posing increasing risks to online information integrity and civic discourse. Most concretely, such risks can materialise in the form of mis- and disinformation. As a mitigation, media-literacy and transparency tools have been developed to address factuality of information and the reliability and ideological leaning of information sources. However, a subtler but possibly no less harmful threat to civic discourse is to use of persuasion or manipulation by exploiting human cognitive biases and related cognitive limitations. To the best of our knowledge, no tools exist to directly detect and mitigate the presence of triggers of such cognitive biases in online information. We present VIGIL (VIrtual GuardIan angeL), the first browser extension for real-time cognitive bias trigger detection and mitigation, providing in-situ scroll-synced detection, LLM-powered reformulation with full reversibility, and privacy-tiered inference from fully offline to cloud. VIGIL is built to be extensible with third-party plugins, with several plugins that are rigorously validated against NLP benchmarks are already included. It is open-sourced at https://github.com/aida-ugent/vigil.

---

### Why Attend to Everything? Focus is the Key

Authors: Hengshuai Yao, Xing Chen, Ahmed Murtadha, Jin Li, Yasin Abbasi Yadkori, Shuai Shao, Changling Liu, Guan Wang, Mingli Yuan, William Chen, Sen Song
Published: 2026-03-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.03260v2

Standard attention scales quadratically with sequence length. Efficient attention methods reduce this O(n^2) cost, but when retrofitted into pretrained models, they often degrade perplexity, downstream accuracy, or both. We introduce Focus, a method that learns which token pairs matter. Focus adds a small set of learnable centroids--as few as 148K parameters per layer--that act as gates: only token pairs belonging to the same centroid group attend to each other over long ranges. Focus is composable: it can be added to any pretrained model by training only the centroids while keeping all original weights frozen. Experiments show that composing Focus onto pretrained models yields zero degradation on downstream benchmarks across model sizes from 124M to 70B parameters and five attention architectures. Surprisingly, sparse Focus attention outperforms full attention at 124M scale (30.3 vs. 31.4 perplexity) and matches full attention when trained from scratch at 7B scale (13.82 vs. 13.89). Focus is also fast: top-k group membership gives a 2x speedup with better quality than the original pretrained model. Using our FlashAttention decomposition, Focus achieves an 8.6x speedup at 1M tokens without custom kernels.

---

### SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression

Authors: Xinhao Huang, You-Liang Huang, Zeyi Wen
Published: 2026-03-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.03258v1

Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but the billion-scale parameters pose deployment challenges. Although existing methods attempt to reduce the scale of LLMs, they require either special hardware support or expensive post-training to maintain model quality. To facilitate efficient and affordable model slimming, we propose a novel training-free compression method for LLMs, named "SoLA", which leverages \textbf{So}ft activation sparsity and \textbf{L}ow-r\textbf{A}nk decomposition. SoLA can identify and retain a minority of components significantly contributing to inference, while compressing the majority through low-rank decomposition, based on our analysis of the activation pattern in the feed-forward network (FFN) of modern LLMs. To alleviate the decomposition loss, SoLA is equipped with an adaptive component-wise low-rank allocation strategy to assign appropriate truncation positions for different weight matrices. We conduct extensive experiments on LLaMA-2-7B/13B/70B and Mistral-7B models across a variety of benchmarks. SoLA exhibits remarkable improvement in both language modeling and downstream task accuracy without post-training. For example, with a 30\% compression rate on the LLaMA-2-70B model, SoLA surpasses the state-of-the-art method by reducing perplexity from 6.95 to 4.44 and enhancing downstream task accuracy by 10\%.

---

### From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation

Authors: Han Song, Yucheng Zhou, Jianbing Shen, Yu Cheng
Published: 2026-03-12
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2604.02355v1

Combining Chain-of-Thought (CoT) with Reinforcement Learning (RL) improves text-to-image (T2I) generation, yet the underlying interaction between CoT's exploration and RL's optimization remains unclear. We present a systematic entropy-based analysis that yields three key insights: (1) CoT expands the generative exploration space, while RL contracts it toward high-reward regions; (2) final reward is strongly negatively correlated with both the mean and variance of image-token entropy, highlighting the need to reduce uncertainty and instability; and (3) the entropy of the textual CoT directly governs downstream image quality, with lower-entropy CoTs leading to better generations. Motivated by these findings, we propose Entropy-Guided Group Relative Policy Optimization (EG-GRPO), a fine-tuning strategy that reallocates optimization budget by uncertainty: low-entropy tokens are excluded from reward-driven updates to preserve stability, while high-entropy tokens receive an entropy bonus that encourages structured exploration without collapse. Experiments on standard T2I benchmarks demonstrate that EG-GRPO achieves state-of-the-art performance.

---

### DOne: Decoupling Structure and Rendering for High-Fidelity Design-to-Code Generation

Authors: Xinhao Huang, Jinke Yu, Wenhao Xu, Zeyi Wen, Ying Zhou, Junzhuo Liu, Junhao Ji, Zulong Chen
Published: 2026-03-12
Categories: cs.CV, cs.SE
arXiv: https://arxiv.org/abs/2604.01226v1

While Vision Language Models (VLMs) have shown promise in Design-to-Code generation, they suffer from a "holistic bottleneck-failing to reconcile high-level structural hierarchy with fine-grained visual details, often resulting in layout distortions or generic placeholders. To bridge this gap, we propose DOne, an end-to-end framework that decouples structure understanding from element rendering. DOne introduces (1) a learned layout segmentation module to decompose complex designs, avoiding the limitations of heuristic cropping; (2) a specialized hybrid element retriever to handle the extreme aspect ratios and densities of UI components; and (3) a schema-guided generation paradigm that bridges layout and code. To rigorously assess performance, we introduce HiFi2Code, a benchmark featuring significantly higher layout complexity than existing datasets. Extensive evaluations on the HiFi2Code demonstrate that DOne outperforms exiting methods in both high-level visual similarity (e.g., over 10% in GPT Score) and fine-grained element alignment. Human evaluations confirm a 3 times productivity gain with higher visual fidelity.

---

### GENIE: Gram-Eigenmode INR Editing with Closed-Form Geometry Updates

Authors: Samundra Karki, Adarsh Krishnamurthy, Baskar Ganapathysubramanian
Published: 2026-03-12
Categories: cs.GR, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.29860v1

Implicit Neural Representations (INRs) provide compact models of geometry, but it is unclear when their learned shapes can be edited without retraining. We show that the Gram operator induced by the INR's penultimate features admits deformation eigenmodes that parameterize a family of realizable edits of the SDF zero level set. A key finding is that these modes are not intrinsic to the geometry alone: they are reliably recoverable only when the Gram operator is estimated from sufficiently rich sampling distributions. We derive a single closed-form update that performs geometric edits to the INR without optimization by leveraging the deformation modes. We characterize theoretically the precise set of deformations that are feasible under this one-shot update, and show that editing is well-posed exactly within the span of these deformation modes.

---

### Contextual Graph Representations for Task-Driven 3D Perception and Planning

Authors: Christopher Agia
Published: 2026-03-12
Categories: cs.RO, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.26685v1

Recent advances in computer vision facilitate fully automatic extraction of object-centric relational representations from visual-inertial data. These state representations, dubbed 3D scene graphs, are a hierarchical decomposition of real-world scenes with a dense multiplex graph structure. While 3D scene graphs claim to promote efficient task planning for robot systems, they contain numerous objects and relations when only small subsets are required for a given task. This magnifies the state space that task planners must operate over and prohibits deployment in resource constrained settings. This thesis tests the suitability of existing embodied AI environments for research at the intersection of robot task planning and 3D scene graphs and constructs a benchmark for empirical comparison of state-of-the-art classical planners. Furthermore, we explore the use of graph neural networks to harness invariances in the relational structure of planning domains and learn representations that afford faster planning.

---

### PLDR-LLMs Reason At Self-Organized Criticality

Authors: Burc Gokden
Published: 2026-03-12
Categories: cs.AI, cs.CL, cs.LG, nlin.AO
arXiv: https://arxiv.org/abs/2603.23539v1

We show that PLDR-LLMs pretrained at self-organized criticality exhibit reasoning at inference time. The characteristics of PLDR-LLM deductive outputs at criticality is similar to second-order phase transitions. At criticality, the correlation length diverges, and the deductive outputs attain a metastable steady state. The steady state behaviour suggests that deductive outputs learn representations equivalent to scaling functions, universality classes and renormalization groups from the training dataset, leading to generalization and reasoning capabilities in the process. We can then define an order parameter from the global statistics of the model's deductive output parameters at inference. The reasoning capabilities of a PLDR-LLM is better when its order parameter is close to zero at criticality. This observation is supported by the benchmark scores of the models trained at near-criticality and sub-criticality. Our results provide a self-contained explanation on how reasoning manifests in large language models, and the ability to reason can be quantified solely from global model parameter values of the deductive outputs at steady state, without any need for evaluation of curated benchmark datasets through inductive output for reasoning and comprehension.

---

### ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics

Authors: Xinkui Zhao, Sai Liu, Yifan Zhang, Qingyu Ma, Guanjie Cheng, Naibo Wang, Chang Liu
Published: 2026-03-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.20260v1

The integration of Large Language Models into Multi-Agent Systems (MAS) has enabled the so-lution of complex, long-horizon tasks through collaborative reasoning. However, this collec-tive intelligence is inherently fragile, as a single logical fallacy can rapidly propagate and lead to system-wide failure. Most current research re-lies on post-hoc failure analysis, thereby hinder-ing real-time intervention. To address this, we propose PROMAS, a proactive framework utiliz-ing Markov transitions for predictive error anal-ysis. PROMAS extracts Causal Delta Features to capture semantic displacement, mapping them to a quantized Vector Markov Space to model reasoning as probabilistic transitions. By inte-grating a Proactive Prediction Head with Jump Detection, the method localizes errors via risk acceleration rather than static thresholds. On the Who&When benchmark, PROMAS achieves 22.97% step-level accuracy while processing only 27% of reasoning logs. This performance rivals reactive monitors like MASC while reducing data overhead by 73%. Although this strategy entails an accuracy trade-off compared to post-hoc meth-ods, it significantly improves intervention latency, balancing diagnostic precision with the real-time demands of autonomous reasoning.

---

### Agreement Between Large Language Models, Human Reviewers, and Authors in Evaluating STROBE Checklists for Observational Studies in Rheumatology

Authors: Emre Bilgin, Ebru Ozturk, Meera Shah, Lisa Traboco, Rebecca Everitt, Ai Lyn Tan, Marwan Bukhari, Vincenzo Venerito, Latika Gupta
Published: 2026-03-12
Categories: cs.DL, cs.AI
arXiv: https://arxiv.org/abs/2603.19303v1

Introduction: Evaluating compliance with the Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement can be time-consuming and subjective. This study compares STROBE assessments from large language models (LLMs), a human reviewer panel, and the original manuscript authors in observational rheumatology research. Methods: Guided by the GRRAS and DEAL Pathway B frameworks, 17 rheumatology articles were independently assessed. Evaluations used the 22-item STROBE checklist, completed by the authors, a five-person human panel (ranging from junior to senior professionals), and two LLMs (ChatGPT-5.2, Gemini-3Pro). Items were grouped into Methodological Rigor and Presentation and Context domains. Inter-rater reliability was calculated using Gwet's Agreement Coefficient (AC1). Results: Overall agreement across all reviewers was 85.0% (AC1=0.826). Domain stratification showed almost perfect agreement for Presentation and Context (AC1=0.841) and substantial agreement for Methodological Rigor (AC1=0.803). Although LLMs achieved complete agreement (AC1=1.000) with all human reviewers on standard formatting elements, their agreement with human reviewers and authors declined on complex items. For example, regarding the item on loss to follow-up, the agreement between Gemini 3 Pro and the senior reviewer was AC1=-0.252, while the agreement with the authors was only fair. Additionally, ChatGPT-5.2 generally demonstrated higher agreement with human reviewers than Gemini-3Pro on specific methodological items. Conclusion: While LLMs show potential for basic STROBE screening, their lower agreement with human experts on complex methodological items likely reflects a reliance on surface-level information. Currently, these models appear more reliable for standardizing straightforward checks than for replacing expert human judgment in evaluating observational research.

---

### Adapting Methods for Domain-Specific Japanese Small LMs: Scale, Architecture, and Quantization

Authors: Takato Yasuno
Published: 2026-03-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.18037v1

This paper presents a systematic methodology for building domain-specific Japanese small language models using QLoRA fine-tuning. We address three core questions: optimal training scale, base-model selection, and architecture-aware quantization. Stage 1 (Training scale): Scale-learning experiments (1k--5k samples) identify n=4,000 as optimal, where test-set NLL reaches minimum (1.127) before overfitting at 5k samples. Stage 2 (Compare finetuned SLMs): Comparing four Japanese LLMs shows that Llama-3 models with Japanese continual pre-training (Swallow-8B, ELYZA-JP-8B) outperform multilingual models (Qwen2.5-7B). Stage 3 (Quantization): Llama-3 architectures improve under Q4_K_M quantization, while GQA architectures degrade severely (Qwen2.5: -0.280 points). Production recommendation: Swallow-8B Q4_K_M achieves 2.830/3 score, 8.9 s/question, 4.9 GB size. The methodology generalizes to low-resource technical domains and provides actionable guidance for compact Japanese specialist LMs on consumer hardware.

---

### MST-Direct: Matching via Sinkhorn Transport for Multivariate Geostatistical Simulation with Complex Non-Linear Dependencies

Authors: Tchalies Bachmann Schmitz
Published: 2026-03-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.18036v1

Multivariate geostatistical simulation requires the faithful reproduction of complex non-linear dependencies among geological variables, including bimodal distributions, step functions, and heteroscedastic relationships. Traditional methods such as the Gaussian Copula and LU Decomposition assume linear correlation structures and often fail to preserve these complex joint distribution patterns. We propose MST-Direct (Matching via Sinkhorn Transport), a novel algorithm based on Optimal Transport theory that uses the Sinkhorn algorithm to directly match multivariate distributions while preserving spatial correlation structures. The method processes all variables simultaneously as a single multidimensional vector, enabling relational matching across the full joint space rather than relying on pairwise linear dependencies.

---

### Gaussian Process Regression-based Knowledge Distillation Framework for Simultaneous Prediction of Physical and Mechanical Properties of Epoxy Polymers

Authors: Sindu B. S., Jan Hamaekers
Published: 2026-03-12
Categories: cond-mat.soft, cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2603.16925v1

Epoxy polymers are widely used due to their multifunctional properties, but machine learning (ML) applications remain limited owing to their complex 3D molecular structure, multi-component nature, and lack of curated datasets. Existing ML studies are largely restricted to simulation data, specific properties, or narrow constituent ranges. To address these limitations, we developed an informed Gaussian Process Regression-based Knowledge Distillation (GPR-KD) framework for predicting multiple physical (glass transition temperature, density) and mechanical properties (elastic modulus, tensile strength, compressive strength, flexural strength, fracture energy, adhesive strength) of thermoset epoxy polymers. The model was trained on experimental literature data covering diverse monomer classes (9 resins, 40 hardeners). Individual GPR models serve as teacher models capturing nonlinear feature-property relationships, while a unified neural network student model learns distilled knowledge across all properties simultaneously. By encoding the target property as an input feature, the student model leverages cross-property correlations. Molecular-level descriptors extracted from SMILES representations using RDKit create a physics-informed model. The framework combines GPR interpretability and robustness with deep learning scalability and generalization. Comparative analysis demonstrates superior prediction accuracy over conventional ML models. Simultaneous multi-property prediction further improves accuracy through information sharing across correlated properties. The proposed framework enables accelerated design of novel epoxy polymers with tailored properties.

---

### Quantum-Secure-By-Construction (QSC): A Paradigm Shift For Post-Quantum Agentic Intelligence

Authors: Arit Kumar Bishwas, Mousumi Sen, Albert Nieto-Morales, Joel Jacob Varghese
Published: 2026-03-12
Categories: cs.AI, cs.CR, quant-ph
arXiv: https://arxiv.org/abs/2603.15668v1

As agentic artificial intelligence systems scale across globally distributed and long lived infrastructures, secure and policy compliant communication becomes a fundamental systems challenge. This challenge grows more serious in the quantum era, where the cryptographic assumptions built into today's AI deployments may not remain valid over their operational lifetime. Here, we introduce quantum secure by construction, or QSC, as a design paradigm that treats quantum secure communication as a core architectural property of agentic AI systems rather than an upgrade added later. We realize QSC through a runtime adaptive security model that combines post quantum cryptography, quantum random number generation, and quantum key distribution to secure interactions among autonomous agents operating across heterogeneous cloud, edge, and inter organizational environments. The approach is cryptographically pluggable and guided by policy, allowing the system to adjust its security posture according to infrastructure availability, regulatory constraints, and performance needs. QSC contributes a governance aware orchestration layer that selects and combines link specific cryptographic protections across the full agent lifecycle, including session bootstrap, inter agent coordination, tool invocation, and memory access. Through system level analysis and empirical evaluation, we examine the trade offs between classical and quantum secure mechanisms and show that QSC can reduce the operational complexity and cost of introducing quantum security into deployed agentic AI systems. These results position QSC as a foundational paradigm for post quantum agentic intelligence and establish a principled pathway for designing globally interoperable, resilient, and future ready intelligent systems.

---

### A Dynamic Survey of Fuzzy, Intuitionistic Fuzzy, Neutrosophic, Plithogenic, and Extensional Sets

Authors: Takaaki Fujita, Florentin Smarandache
Published: 2026-03-12
Categories: cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2603.15667v1

Real-world phenomena often exhibit vagueness, partial truth, and incomplete information. To model such uncertainty in a mathematically rigorous way, many generalized set-theoretic frameworks have been introduced, including Fuzzy Sets (1), Intuitionistic Fuzzy Sets (2), Neutrosophic Sets (3,4), Vague Sets (5), Hesitant Fuzzy Sets (6), Picture Fuzzy Sets (7), Quadripartitioned Neutrosophic Sets (8), Penta-Partitioned Neutrosophic Sets (9), Plithogenic Sets (10), HyperFuzzy Sets (11), and HyperNeutrosophic Sets (12). Within these frameworks, a wide range of notions has been proposed and studied, particularly in the settings of fuzzy, intuitionistic fuzzy, neutrosophic, and plithogenic set theories. This extensive literature underscores both the significance of these theories and the breadth of their application areas. As a result, many ideas, constructions, and structural patterns recur across these four major families of uncertainty-oriented models. In this book, we provide a comprehensive, large-scale survey of Fuzzy, Intuitionistic Fuzzy, Neutrosophic, and Plithogenic Sets. Our goal is to give readers a systematic overview of existing developments and, through a unified exposition, to stimulate new insights, further conceptual extensions, and additional applications across a wide range of disciplines.

---

### Compiled Memory: Not More Information, but More Precise Instructions for Language Agents

Authors: James Rhodes, George Kang
Published: 2026-03-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.15666v1

Existing memory systems for language agents address memory management: how to retrieve and page more information within a context budget. We address a complementary problem -- memory utility: what experience is worth keeping, and how it should change agent behavior. We present Atlas, a memory kernel that compiles accumulated task experience into an agent's instruction structure -- without fine-tuning, RAG, or human intervention. Memory is distillation, not storage; delivery is instruction rewriting, not context injection. Facts extracted from agent failures and successes are verified through a three-step promotion gate and delivered by rewriting the agent's system prompt with learned sub-bullets. On CUAD contract analysis, the evolved prompt improves GPT-4o token-level F1 by $+8.7$pp and precision by $+12.5$pp. On HotpotQA multi-hop QA, joint F1 improves $+3.16$pp. An ablation isolates the mechanism's defining property -- the training signal constraint: the evolved prompt learns exactly what it is taught, and nothing more. Applied to Claude Sonnet~4.5 using the same evolved prompt -- compiled from GPT-4o errors, unchanged -- joint F1 improves $+2.31$pp, with gains concentrating where Claude's stronger baseline leaves the most room -- confirming that the compiled knowledge is task-shaped, not model-shaped.

---

### Projection Guided Personalized Federated Learning for Low Dose CT Denoising

Authors: Anas Zafar, Muhammad Waqas, Amgad Muneer, Rukhmini Bandyopadhyay, Jia Wu
Published: 2026-03-12
Categories: eess.IV, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.13422v1

Low-dose CT (LDCT) reduces radiation exposure but introduces protocol-dependent noise and artifacts that vary across institutions. While federated learning enables collaborative training without centralizing patient data, existing methods personalize in image space, making it difficult to separate scanner noise from patient anatomy. We propose ProFed (Projection Guided Personalized Federated Learning), a framework that complements the image space approach by performing dual-level personalization in the projection space, where noise originates during CT measurements before reconstruction combines protocol and anatomy effects. ProFed introduces: (i) anatomy-aware and protocol-aware networks that personalize CT reconstruction to patient and scanner-specific features, (ii) multi-constraint projection losses that enforce consistency with CT measurements, and (iii) uncertainty-guided selective aggregation that weights clients by prediction confidence. Extensive experiments on the Mayo Clinic 2016 dataset demonstrate that ProFed achieves 42.56 dB PSNR with CNN backbones and 44.83 dB with Transformers, outperforming 11 federated learning baselines, including the physics-informed SCAN-PhysFed by +1.42 dB.

---

### Generalization and Memorization in Rectified Flow

Authors: Mingxing Rao, Daniel Moyer
Published: 2026-03-12
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2603.13421v3

Generative models based on the Flow Matching objective, particularly Rectified Flow, have emerged as a dominant paradigm for efficient, high-fidelity image synthesis. However, while existing research heavily prioritizes generation quality and architectural scaling, the underlying dynamics of how RF models memorize training data remain largely underexplored. In this paper, we systematically investigate the memorization behaviors of RF through the test statistics of Membership Inference Attacks (MIA). We progressively formulate three test statistics, culminating in a complexity-calibrated metric that successfully decouples intrinsic image spatial complexity from genuine memorization signals. This calibration yields a significant performance surge -- boosting attack AUC by up to 15% and the privacy-critical TPR@1%FPR metric by up to 45% -- establishing the first non-trivial MIA specifically tailored for RF. Leveraging these refined metrics, we uncover a distinct temporal pattern: under standard uniform temporal training, a model's susceptibility to MIA strictly peaks at the integration midpoint, a phenomenon we justify via the network's forced deviation from linear approximations. Finally, we demonstrate that substituting uniform timestep sampling with a Symmetric Exponential (U-shaped) distribution effectively minimizes exposure to vulnerable intermediate timesteps. Extensive evaluations across three datasets confirm that this temporal regularization suppresses memorization while preserving generative fidelity.

---

### Generalization and Memorization in Rectified Flow

Authors: Mingxing Rao, Daniel Moyer
Published: 2026-03-12
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2603.13421v2

Generative models based on the Flow Matching objective, particularly Rectified Flow, have emerged as a dominant paradigm for efficient, high-fidelity image synthesis. However, while existing research heavily prioritizes generation quality and architectural scaling, the underlying dynamics of how RF models memorize training data remain largely underexplored. In this paper, we systematically investigate the memorization behaviors of RF through the test statistics of Membership Inference Attacks (MIA). We progressively formulate three test statistics, culminating in a complexity-calibrated metric that successfully decouples intrinsic image spatial complexity from genuine memorization signals. This calibration yields a significant performance surge -- boosting attack AUC by up to 15% and the privacy-critical TPR@1%FPR metric by up to 45% -- establishing the first non-trivial MIA specifically tailored for RF. Leveraging these refined metrics, we uncover a distinct temporal pattern: under standard uniform temporal training, a model's susceptibility to MIA strictly peaks at the integration midpoint, a phenomenon we justify via the network's forced deviation from linear approximations. Finally, we demonstrate that substituting uniform timestep sampling with a Symmetric Exponential (U-shaped) distribution effectively minimizes exposure to vulnerable intermediate timesteps. Extensive evaluations across three datasets confirm that this temporal regularization suppresses memorization while preserving generative fidelity.

---

### Accelerating Suffix Jailbreak attacks with Prefix-Shared KV-cache

Authors: Xinhai Wang, Shaopeng Fu, Shu Yang, Liangyu Wang, Tianhang Zheng, Di Wang
Published: 2026-03-12
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2603.13420v2

Suffix jailbreak attacks serve as a systematic method for red-teaming Large Language Models (LLMs) but suffer from prohibitive computational costs, as a large number of candidate suffixes need to be evaluated before identifying a jailbreak suffix. This paper presents Prefix-Shared KV Cache (PSKV), a plug-and-play inference optimization technique tailored for jailbreak suffix generation. Our method is motivated by a key observation that when performing suffix jailbreaking, while a large number of candidate prompts need to be evaluated, they share the same targeted harmful instruction as the prefix. Therefore, instead of performing redundant inference on the duplicated prefix, PSKV maintains a single KV cache for this prefix and shares it with every candidate prompt, enabling the parallel inference of diverse suffixes with minimal memory overhead. This design enables more aggressive batching strategies that would otherwise be limited by memory constraints. Extensive experiments on six widely used suffix attacks across five widely deployed LLMs demonstrate that PSKV reduces inference time by 40\% and peak memory usage by 50\%, while maintaining the original Attack Success Rate (ASR). The code has been submitted and will be released publicly.

---

### Diffusion Models Memorize in Training -- and Generalize in Inference

Authors: Tim Kaiser, Markus Kollmann
Published: 2026-03-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.13419v2

Diffusion models generalize well in practice. However, an optimal diffusion model fully memorizes the training data and therefore fails to generalize, raising the question of what induces generalization in a real diffusion model. We show that, despite generalizing at the sample level, diffusion models progressively overfit the denoising training objective and thereby create a generalization gap between the performance on validation and training samples. This gap is most pronounced at intermediate noise levels. Using a fully analytic error-prone toy model, we trace the factors affecting the generalization gap. We find that the optimal denoising flow field localizes sharply around training points, but the model error suppresses the exact recall of training points, yielding a smooth, generalizing flow field. Finally, we find that the generalization gap observed in training does not translate to inference, which would result in a strong similarity between generated samples and training samples. This is because the intermediate states of sampling trajectories are sufficiently far from the distribution of noisy training samples the model is trained on. Together, these findings reveal a novel picture of how diffusion models generalize: the flow field generalizes through model error, which moves sampling trajectories outside the domain of noisy training samples and thereby naturally prevents overfitting.

---

### GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models

Authors: Xiaoyun Liu, Divya Saxena, Jiannong Cao, Yuqing Zhao, Yiying Dong, Penghui Ruan
Published: 2026-03-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.13418v2

Structured pruning is widely applied to compress large language models (LLMs), but its performance depends heavily on how neuron importance is estimated. Most existing methods rely on activation statistics from a single calibration set, which introduces calibration bias and degrades downstream cross-task generalization. We observe that neurons exhibit heterogeneous distribution sensitivity, ranging from maintaining relatively stable rankings across calibration datasets to showing substantially larger cross-dataset variation. Ignoring this heterogeneity, existing methods rank all neurons in shared spaces with a uniform scoring source, so calibration-specific neurons dominate the ranking and weakly-activated neurons are scored unreliably. To address this, we propose GPrune-LLM, a structured pruning framework that reduces calibration bias by measuring and exploiting the cross-distribution behavior of neurons for fair comparison. Specifically, we restructure the neuron ranking space into behavior-consistent local spaces, adapt the scoring source where the calibration signal is unreliable, and learn per-module sparsity allocation under a global budget. Experiments across multiple models and downstream tasks show that GPrune-LLM improves the generalization of its base pruning metrics, with gains most pronounced at high sparsity, and reduces dependence on the choice of importance metric.

---

### Bridging Protocol and Production: Design Patterns for Deploying AI Agents with Model Context Protocol

Authors: Vasundra Srinivasan
Published: 2026-03-12
Categories: cs.SE, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2603.13417v1

The Model Context Protocol (MCP) standardizes how AI agents discover and invoke external tools, with over 10,000 active servers and 97 million monthly SDK downloads as of early 2026. Yet MCP does not yet standardize how agents safely operate those tools at production scale. Three protocol-level primitives remain missing: identity propagation, adaptive tool budgeting, and structured error semantics. This paper identifies these gaps through field lessons from an enterprise deployment of an AI agent platform integrated with a major cloud provider's MCP servers (client name redacted). We propose three mechanisms to fill them: (1) the Context-Aware Broker Protocol (CABP), which extends JSON-RPC with identity-scoped request routing via a six-stage broker pipeline; (2) Adaptive Timeout Budget Allocation (ATBA), which frames sequential tool invocation as a budget allocation problem over heterogeneous latency distributions; and (3) the Structured Error Recovery Framework (SERF), which provides machine-readable failure semantics that enable deterministic agent self-correction. We organize production failure modes into five design dimensions (server contracts, user context, timeouts, errors, and observability), document concrete failure vignettes, and present a production readiness checklist. All three algorithms are formalized as testable hypotheses with reproducible experimental methodology. Field observations demonstrate that while MCP provides a solid protocol foundation, reliable agent tool integration requires infrastructure-level mechanisms that the specification does not yet address.

---

### Distance-aware Soft Prompt Guidance for Multimodal Valence-Arousal Estimation

Authors: Byeongjin Jung, Chanyeong Park, Sejoon Lim
Published: 2026-03-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.13415v2

Valence-arousal (VA) estimation is crucial for capturing the nuanced nature of human emotions in naturalistic environments. While pre-trained vision-language models such as CLIP have demonstrated remarkable semantic alignment capabilities, their application to continuous regression tasks is often limited by the discrete nature of text prompts. In this paper, we propose a novel multimodal framework for VA estimation that introduces Distance-aware Soft Prompt Guidance to bridge the gap between semantic representations and continuous affective dimensions. Specifically, we partition the VA space into multiple discrete regions, each associated with distinct textual descriptions. Rather than relying on hard categorization, we employ a Gaussian kernel to compute soft labels based on the Euclidean distance between the ground-truth coordinates and the region centers, allowing the model to learn fine-grained emotional transitions. For multimodal integration, our architecture utilizes a CLIP image encoder and an Audio Spectrogram Transformer to extract robust visual and acoustic features. These features are temporally modeled using Gated Recurrent Units and integrated through a hierarchical fusion scheme that sequentially combines cross-modal attention for alignment and gated fusion for adaptive refinement. Experimental results on the Aff-Wild2 dataset show that the proposed semantic-guided approach outperforms the official baseline and demonstrates robust performance on in-the-wild data.

---

### Neuro-Symbolic Generation and Validation of Memory-Aware Formal Function Specifications

Authors: Liao Zhang, Tong Chen, Xiwei Wu, Qi Liu, Xiyu Zhai, Xinqi Wang, Qinxiang Cao
Published: 2026-03-12
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.13414v1

Formal verification of memory-manipulating programs critically depends on precise function specifications that capture memory states written by experts. This requirement has become a major bottleneck as large language models (LLMs) increasingly generate low-level systems code whose correctness cannot be assumed. To enable scalable formal verification, we focus exclusively on function specification generation, deliberately avoiding the synthesis of complex loop invariants that are central to traditional verification pipelines. We propose a neuro-symbolic framework for automatically generating memory-aware formal function specifications for C programs from natural language problem descriptions and function signatures. The pipeline first produces candidate specifications via in-context learning, and then iteratively refines them using compiler diagnostics from symbolic provers and the verification toolchain. In particular, we validate candidate specifications by constructing a proof for the negation of the specification with concrete examples, enabling machine-checked rejection of plausible-but-incorrect specifications. To support systematic evaluation, we introduce LeetCode-C-Spec, a new benchmark of 200 C programming problems for generating memory-aware formal function specifications. Experiments show that iterative refinement substantially improves syntactic validity, while symbolic prover-based refutation significantly enhances correctness assessment by filtering false positives that LLM-only judges frequently accept. Our results demonstrate that combining neural generation with symbolic feedback provides an effective approach to formal specification synthesis for memory-safe systems software.

---

### WAT: Online Video Understanding Needs Watching Before Thinking

Authors: Zifan Han, Hongbo Sun, Jinglin Xu, Canhui Tang, Yulong Lei, Xuchong Zhang, Hongbin Sun, Zhongjiang He, Hao Sun
Published: 2026-03-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.13412v1

Multimodal Large Language Models (MLLMs) have shown strong capabilities in image understanding, motivating recent efforts to extend them to video reasoning. However, existing Video LLMs struggle in online streaming scenarios, where long temporal context must be preserved under strict memory constraints. We propose WAT (Watching Before Thinking), a two-stage framework for online video reasoning. WAT separates processing into a query-independent watching stage and a query-triggered thinking stage. The watching stage builds a hierarchical memory system with a Short-Term Memory (STM) that buffers recent frames and a fixed-capacity Long-Term Memory (LTM) that maintains a diverse summary of historical content using a redundancy-aware eviction policy. In the thinking stage, a context-aware retrieval mechanism combines the query with the current STM context to retrieve relevant historical frames from the LTM for cross-temporal reasoning. To support training for online video tasks, we introduce WAT-85K, a dataset containing streaming-style annotations emphasizing real-time perception, backward tracing, and forecasting. Experiments show that WAT achieves state-of-the-art performance on online video benchmarks, including 77.7% accuracy on StreamingBench and 55.2% on OVO-Bench, outperforming existing open-source online Video LLMs while operating at real-time frame rates.

---

### Bridging the Visual-to-Physical Gap: Physically Aligned Representations for Fall Risk Analysis

Authors: Xianqi Zhang
Published: 2026-03-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.13410v1

Vision-based fall analysis has advanced rapidly, but a key bottleneck remains: visually similarmotions can correspond to very different physical outcomes because small differences in contactmechanics and protective responses are hard to infer from appearance alone. Most existingapproaches handle this by supervised injury prediction, which depends on reliable injury labels.In practice, such labels are difficult to obtain: video evidence is often ambiguous (occlusion,viewpoint limits), and true injury events are rare and cannot be safely staged, leading to noisysupervision. We address this problem with PHARL (PHysics-aware Alignment RepresentationLearning), which learns physically meaningful fall representations without requiring clinicaloutcome labels. PHARL regularizes motion embeddings with two complementary constraints:(1) trajectory-level temporal consistency for stable representation learning, and (2) multi-classphysics alignment, where simulation-derived contact outcomes shape embedding geometry. Bypairing video windows with temporally aligned simulation descriptors, PHARL captures localimpact-relevant dynamics while keeping inference purely feed-forward. Experiments on fourpublic datasets show that PHARL consistently improves risk-aligned representation quality overvisual-only baselines while maintaining strong fall-detection performance. Notably, PHARL alsoexhibits zero-shot ordinality: an interpretable severity structure (Head > Trunk > Supported)emerges without explicit ordinal supervision.

---

### Nuanced Emotion Recognition Based on a Segment-based MLLM Framework Leveraging Qwen3-Omni for AH Detection

Authors: Liang Tang, Hongda Li, Jiayu Zhang, Long Chen, Shuxian Li, Siqi Pei, Tiaonan Duan, Yuhao Cheng
Published: 2026-03-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.13406v2

Emotion recognition in videos is a pivotal task in affective computing, where identifying subtle psychological states such as Ambivalence and Hesitancy holds significant value for behavioral intervention and digital health. Ambivalence and Hesitancy states often manifest through cross-modal inconsistencies such as discrepancies between facial expressions, vocal tones, and textual semantics, posing a substantial challenge for automated recognition. This paper proposes a recognition framework that integrates temporal segment modeling with Multimodal Large Language Models. To address computational efficiency and token constraints in long video processing, we employ a segment-based strategy, partitioning videos into short clips with a maximum duration of 5 seconds. We leverage the Qwen3-Omni-30B-A3B model, fine-tuned on the BAH dataset using LoRA and full-parameter strategies via the MS-Swift framework, enabling the model to synergistically analyze visual and auditory signals. Experimental results demonstrate that the proposed method achieves an accuracy of 85.1% on the test set, significantly outperforming existing benchmarks and validating the superior capability of Multimodal Large Language Models in capturing complex and nuanced emotional conflicts. The code is released at https://github.com/dlnn123/A-H-Detection-with-Qwen-Omni.git.

---

### Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion

Authors: Yang Yang, Tianyi Zhang, Wei Huang, Jinwei Chen, Boxi Wu, Xiaofei He, Deng Cai, Bo Li, Peng-Tao Jiang
Published: 2026-03-12
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2603.13405v1

Interactive long video generation requires prompt switching to introduce new subjects or events, while maintaining perceptual fidelity and coherent motion over extended horizons. Recent distilled streaming video diffusion models reuse a rolling KV cache for long-range generation, enabling prompt-switch interaction through re-cache at each switch. However, existing streaming methods still exhibit progressive quality degradation and weakened motion dynamics. We identify two failure modes specific to interactive streaming generation: (i) at each prompt switch, current cache maintenance cannot simultaneously retain KV-based semantic context and recent latent cues, resulting in weak boundary conditioning and reduced perceptual quality; and (ii) during distillation, unbounded time indexing induces a positional distribution shift from the pretrained backbone's bounded RoPE regime, weakening pretrained motion priors and long-horizon motion retention. To address these issues, we propose \textbf{Anchor Forcing}, a cache-centric framework with two designs. First, an anchor-guided re-cache mechanism stores KV states in anchor caches and warm-starts re-cache from these anchors at each prompt switch, reducing post-switch evidence loss and stabilizing perceptual quality. Second, a tri-region RoPE with region-specific reference origins, together with RoPE re-alignment distillation, reconciles unbounded streaming indices with the pretrained RoPE regime to better retain motion priors. Experiments on long videos show that our method improves perceptual quality and motion metrics over prior streaming baselines in interactive settings. Project page: https://github.com/vivoCameraResearch/Anchor-Forcing

---

### Schema First Tool APIs for LLM Agents: A Controlled Study of Tool Misuse, Recovery, and Budgeted Performance

Authors: Akshey Sigdel, Rista Baral
Published: 2026-03-12
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.13404v1

Tool use has become central to modern LLM agents, yet interface design is rarely isolated as an experimental variable. This paper studies whether schema based tool contracts and structured validation diagnostics improve reliability under strict interaction budgets. We evaluate three conditions that preserve identical tool semantics and information content: free form documentation, JSON Schema specifications, and JSON Schema with structured diagnostics. We implement a deterministic software engineering sandbox with logs, metrics, configurations, and repository tasks, and evaluate a fully crossed pilot with one open local model, three seeds, three interface conditions, and four budgets. We report end task success, interface misuse, execution failures, semantic misuse, recovery behavior, and overhead. In this pilot, success remains zero across conditions, while schema conditions reduce interface misuse but not semantic misuse. The evidence supports a precise interpretation that interface formalization improves contract adherence, but semantic action quality and timeout sensitive tasks remain dominant bottlenecks under constrained local inference.

---

### Diabetic Retinopathy Grading with CLIP-based Ranking-Aware Adaptation:A Comparative Study on Fundus Image

Authors: Sungjun Cho
Published: 2026-03-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.13403v1

Diabetic retinopathy (DR) is a leading cause of preventable blindness, and automated fundus image grading can play an important role in large-scale screening. In this work, we investigate three CLIP-based approaches for five-class DR severity grading: (1) a zero-shot baseline using prompt engineering, (2) a hybrid FCN-CLIP model augmented with CBAM attention, and (3) a ranking-aware prompting model that encodes the ordinal structure of DR progression. We train and evaluate on a combined dataset of APTOS 2019 and Messidor-2 (n=5,406), addressing class imbalance through resampling and class-specific optimal thresholding. Our experiments show that the ranking-aware model achieves the highest overall accuracy (93.42%, AUROC 0.9845) and strong recall on clinically critical severe cases, while the hybrid FCN-CLIP model (92.49%, AUROC 0.99) excels at detecting proliferative DR. Both substantially outperform the zero-shot baseline (55.17%, AUROC 0.75). We analyze the complementary strengths of each approach and discuss their practical implications for screening contexts.

---

### Event-Driven Video Generation

Authors: Chika Maduabuchi, Jindong Wang
Published: 2026-03-12
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.13402v3

Current text-to-video models can make individual frames look convincing while still getting simple interactions wrong: objects move before contact, an intended action is skipped, a placed object keeps drifting, or a support relation breaks. Our starting point is that standard frame-first denoising updates every latent region at every step, even when the prompt implies that only a local interaction should be active. We introduce Event-Driven Video Generation (EVD), a small DiT-compatible intervention that gives the sampler an explicit event signal. A lightweight head predicts token-level event activity; training losses tie that activity to latent state change; and event-gated sampling, with hysteresis and an early-step schedule, applies the update field mainly where an interaction is forming. On EVD-Bench, EVD improves human preference and VBench dynamics for state persistence, spatial accuracy, support relations, and contact stability, while keeping appearance quality comparable to the base model. The results suggest that a modest amount of event structure can correct several interaction failures that otherwise remain hidden behind good frame-level appearance.

---

### EB-RANSAC: Random Sample Consensus based on Energy-Based Model

Authors: Muneki Yasuda, Nao Watanabe, Kaiji Sekimoto
Published: 2026-03-12
Categories: stat.ML, cond-mat.dis-nn, cs.LG
arXiv: https://arxiv.org/abs/2603.12525v1

Random sample consensus (RANSAC), which is based on a repetitive sampling from a given dataset, is one of the most popular robust estimation methods. In this study, an energy-based model (EBM) for robust estimation that has a similar scheme to RANSAC, energy-based RANSAC (EB-RANSAC), is proposed. EB-RANSAC is applicable to a wide range of estimation problems similar to RANSAC. However, unlike RANSAC, EB-RANSAC does not require a troublesome sampling procedure and has only one hyperparameter. The effectiveness of EB-RANSAC is numerically demonstrated in two applications: a linear regression and maximum likelihood estimation.

---

### LLM BiasScope: A Real-Time Bias Analysis Platform for Comparative LLM Evaluation

Authors: Himel Ghosh, Nick Elias Werner
Published: 2026-03-12
Categories: cs.CL, cs.AI, cs.CY, cs.HC
arXiv: https://arxiv.org/abs/2603.12522v1

As large language models (LLMs) are deployed widely, detecting and understanding bias in their outputs is critical. We present LLM BiasScope, a web application for side-by-side comparison of LLM outputs with real-time bias analysis. The system supports multiple providers (Google Gemini, DeepSeek, MiniMax, Mistral, Meituan, Meta Llama) and enables researchers and practitioners to compare models on the same prompts while analyzing bias patterns. LLM BiasScope uses a two-stage bias detection pipeline: sentence-level bias detection followed by bias type classification for biased sentences. The analysis runs automatically on both user prompts and model responses, providing statistics, visualizations, and detailed breakdowns of bias types. The interface displays two models side-by-side with synchronized streaming responses, per-model bias summaries, and a comparison view highlighting differences in bias distributions. The system is built on Next.js with React, integrates Hugging Face inference endpoints for bias detection, and uses the Vercel AI SDK for multi-provider LLM access. Features include real-time streaming, export to JSON/PDF, and interactive visualizations (bar charts, radar charts) for bias analysis. LLM BiasScope is available as an open-source web application, providing a practical tool for bias evaluation and comparative analysis of LLM behaviour.

---

### When LLM Judge Scores Look Good but Best-of-N Decisions Fail

Authors: Eddie Landesberg
Published: 2026-03-12
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.12520v1

Large language models are often used as judges to score candidate responses, then validated with a single global metric such as correlation with reference labels. This can be misleading when the real deployment task is best-of-n selection within a prompt. In a 5,000-prompt best-of-4 benchmark from Chatbot Arena, a judge with moderate global correlation (r = 0.47) captures only 21.0% of the improvement that perfect selection would achieve over random choice. The gap arises because global agreement is driven largely by prompt-level baseline effects, while selection depends on within-prompt ranking: within-prompt correlation is only r_within = 0.27, and coarse pointwise scoring creates ties in 67% of pairwise comparisons. In a matched-pair best-of-2 audit, explicit pairwise judging recovers much of this lost signal, raising recovery from 21.1% to 61.2%. For judge-based selection, the relevant audit should report within-prompt signal, tie rates, and recovery/top-1 accuracy, not global agreement alone.

---

### Curriculum Sampling: A Two-Phase Curriculum for Efficient Training of Flow Matching

Authors: Pengwei Sun
Published: 2026-03-12
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2603.12517v1

Timestep sampling $p(t)$ is a central design choice in Flow Matching models, yet common practice increasingly favors static middle-biased distributions (e.g., Logit-Normal). We show that this choice induces a speed--quality trade-off: middle-biased sampling accelerates early convergence but yields worse asymptotic fidelity than Uniform sampling. By analyzing per-timestep training losses, we identify a U-shaped difficulty profile with persistent errors near the boundary regimes, implying that under-sampling the endpoints leaves fine details unresolved. Guided by this insight, we propose \textbf{Curriculum Sampling}, a two-phase schedule that begins with middle-biased sampling for rapid structure learning and then switches to Uniform sampling for boundary refinement. On CIFAR-10, Curriculum Sampling improves the best FID from $3.85$ (Uniform) to $3.22$ while reaching peak performance at $100$k rather than $150$k training steps. Our results highlight that timestep sampling should be treated as an evolving curriculum rather than a fixed hyperparameter.

---

### Learning Pore-scale Multiphase Flow from 4D Velocimetry

Authors: Chunyang Wang, Linqi Zhu, Yuxuan Gu, Robert van der Merwe, Xin Ju, Catherine Spurin, Samuel Krevor, Rex Ying, Tobias Pfaff, Martin J. Blunt, Tom Bultreys, Gege Wen
Published: 2026-03-12
Categories: cs.LG, physics.flu-dyn
arXiv: https://arxiv.org/abs/2603.12516v1

Multiphase flow in porous media underpins subsurface energy and environmental technologies, including geological CO$_2$ storage and underground hydrogen storage, yet pore-scale dynamics in realistic three-dimensional materials remain difficult to characterize and predict. Here we introduce a multimodal learning framework that infers multiphase pore-scale flow directly from time-resolved four-dimensional (4D) micro-velocimetry measurements. The model couples a graph network simulator for Lagrangian tracer-particle motion with a 3D U-Net for voxelized interface evolution. The imaged pore geometry serves as a boundary constraint to the flow velocity and the multiphase interface predictions, which are coupled and updated iteratively at each time step. Trained autoregressively on experimental sequences in capillary-dominated conditions ($Ca\approx10^{-6}$), the learned surrogate captures transient, nonlocal flow perturbations and abrupt interface rearrangements (Haines jumps) over rollouts spanning seconds of physical time, while reducing hour-to-day--scale direct numerical simulations to seconds of inference. By providing rapid, experimentally informed predictions, the framework opens a route to ''digital experiments'' to replicate pore-scale physics observed in multiphase flow experiments, offering an efficient tool for exploring injection conditions and pore-geometry effects relevant to subsurface carbon and hydrogen storage.

---

### CT-VDETR: Semi-supervised 3D Trauma Detection in Computed Tomography (CT) scans using Dense Vertex Relative Position Encoding

Authors: Shivam Chaudhary, Sheethal Bhat, Andreas Maier
Published: 2026-03-12
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.12514v2

Accurate detection and localization of traumatic injuries in abdominal CT remain challenging because voxel-level annotations are limited and expensive to obtain. We present a label-efficient framework for 3D abdominal trauma detection that combines self-supervised pretraining with semi-supervised transformer-based detection. First, we use Masked Image Modeling (MIM) on 1098 CT volumes to pretrain a 3D U-Net encoder for anatomical representation learning. Next, we adapt V-DETR to dense volumetric CT through a feature adapter that converts the encoder feature grid into a compact token sequence for transformer decoding. The pretrained encoder is then integrated with V-DETR and 3D Vertex Relative Position Encoding (3D V-RPE) to improve the localization of irregularly shaped injuries. Finally, semi-supervised teacher-student consistency regularization leverages 2,000 additional unlabeled volumes during detector training. To the best of our knowledge, this is the first application of a 3D DETR-style detector to the RSNA abdominal trauma detection task. On this benchmark, the proposed method achieves 31.33% test mAP@0.50 using only 78 labeled training volumes, corresponding to a 1.53x improvement over supervised-only training. These results show that combining medical-domain pretraining with semi-supervised learning is an effective strategy for label-scarce 3D medical detection.

---

### MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens

Authors: Youngrae Kim, Qixin Hu, C. -C. Jay Kuo, Peter A. Beerel
Published: 2026-03-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.12513v1

Autoregressive diffusion enables real-time frame streaming, yet existing sliding-window caches discard past context, causing fidelity degradation, identity drift, and motion stagnation over long horizons. Current approaches preserve a fixed set of early tokens as attention sinks, but this static anchor cannot reflect the evolving content of a growing video. We introduce MemRoPE, a training-free framework with two co-designed components. Memory Tokens continuously compress all past keys into dual long-term and short-term streams via exponential moving averages, maintaining both global identity and recent dynamics within a fixed-size cache. Online RoPE Indexing caches unrotated keys and applies positional embeddings dynamically at attention time, ensuring the aggregation is free of conflicting positional phases. These two mechanisms are mutually enabling: positional decoupling makes temporal aggregation well-defined, while aggregation makes fixed-size caching viable for unbounded generation. Extensive experiments validate that MemRoPE outperforms existing methods in temporal coherence, visual fidelity, and subject consistency across minute- to hour-scale generation.

---

### Byzantine-Robust Optimization under $(L_0, L_1)$-Smoothness

Authors: Arman Bolatov, Samuel Horváth, Martin Takáč, Eduard Gorbunov
Published: 2026-03-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.12512v1

We consider distributed optimization under Byzantine attacks in the presence of $(L_0,L_1)$-smoothness, a generalization of standard $L$-smoothness that captures functions with state-dependent gradient Lipschitz constants. We propose Byz-NSGDM, a normalized stochastic gradient descent method with momentum that achieves robustness against Byzantine workers while maintaining convergence guarantees. Our algorithm combines momentum normalization with Byzantine-robust aggregation enhanced by Nearest Neighbor Mixing (NNM) to handle both the challenges posed by $(L_0,L_1)$-smoothness and Byzantine adversaries. We prove that Byz-NSGDM achieves a convergence rate of $O(K^{-1/4})$ up to a Byzantine bias floor proportional to the robustness coefficient and gradient heterogeneity. Experimental validation on heterogeneous MNIST classification, synthetic $(L_0,L_1)$-smooth optimization, and character-level language modeling with a small GPT model demonstrates the effectiveness of our approach against various Byzantine attack strategies. An ablation study further shows that Byz-NSGDM is robust across a wide range of momentum and learning rate choices.

---

### Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies

Authors: Siddharth Srikanth, Freddie Liang, Ya-Chuan Hsu, Varun Bhatt, Shihan Zhao, Henry Chen, Bryon Tjanaka, Minjune Hwang, Akanksha Saran, Daniel Seita, Aaquib Tabrez, Stefanos Nikolaidis
Published: 2026-03-12
Categories: cs.RO, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.12510v3

Vision-Language-Action (VLA) models have significant potential to enable general-purpose robotic systems for a range of vision-language tasks. However, the performance of VLA-based robots is highly sensitive to the precise wording of language instructions, and it remains difficult to predict when such robots will fail. We propose Quality Diversity (QD) optimization as a natural framework for red-teaming embodied models, and present Q-DIG (Quality Diversity for Diverse Instruction Generation), which performs red-teaming by scalably identifying diverse, natural language task descriptions that induce failures while remaining task-relevant. Q-DIG integrates QD techniques with Vision-Language Models (VLMs) to generate a broad spectrum of adversarial instructions that expose meaningful vulnerabilities in VLA behavior. Our results across multiple simulation benchmarks show that Q-DIG finds more diverse and meaningful failure modes compared to baseline methods, and that fine-tuning VLAs on the generated instructions improves task success rates. Furthermore, results from a user study highlight that Q-DIG generates prompts judged to be more natural and human-like than those from baselines. Finally, real-world evaluations of Q-DIG prompts show results consistent with simulation, and fine-tuning VLAs on the generated prompts further success rates on unseen instructions. Together, these findings suggest that Q-DIG is a promising approach for identifying vulnerabilities and improving the robustness of VLA-based robots. Our anonymous project website is at qdigvla.github.io.

---

### ELLA: Generative AI-Powered Social Robots for Early Language Development at Home

Authors: Victor Nikhil Antony, Shiye Cao, Shuning Wang, Chien-Ming Huang
Published: 2026-03-12
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2603.12508v1

Early language development shapes children's later literacy and learning, yet many families have limited access to scalable, high-quality support at home. Recent advances in generative AI make it possible for social robots to move beyond scripted interactions and engage children in adaptive, conversational activities, but it remains unclear how to design such systems for pre-schoolers and how children engage with them over time in the home. We present ELLA (Early Language Learning Agent), an autonomous, generative AI-powered social robot that supports early language development through interactive storytelling, parent-selected language targets, and scaffolded dialogue. Using a multi-phased, human-centered process, we interviewed parents (n=7) and educators (n=5) and iteratively refined ELLA through twelve in-home design workshops. We then deployed ELLA with ten children for eight days. We report design insights from in-home workshops, characterize children's engagement and behaviors during deployment, and distill design implications for generative AI-powered social robots supporting early language learning at home.

---

### Adaptive Conditional Forest Sampling for Spectral Risk Optimisation under Decision-Dependent Uncertainty

Authors: Marcell T. Kurbucz
Published: 2026-03-12
Categories: cs.LG, math.OC, stat.CO, stat.ML
arXiv: https://arxiv.org/abs/2603.12507v2

Minimising a spectral risk objective, defined as a weighted combination of expected cost and Conditional Value-at-Risk (CVaR), is challenging when the uncertainty distribution is decision-dependent, making both surrogate modelling and simulation-based ranking sensitive to tail estimation error. We propose Adaptive Conditional Forest Sampling (ACFS), a four-phase simulation-optimisation framework that integrates Generalised Random Forests for decision-conditional distribution approximation, CEM-guided global exploration, rank-weighted focused augmentation, and surrogate-to-oracle two-stage reranking before multi-start gradient-based refinement. We evaluate ACFS on two structurally distinct data-generating processes: a Gaussian copula with decision-dependent Student-t marginals and a Gaussian copula with log-normal marginals, across three penalty-weight configurations and 100 replications per setting, under a common cap on the number of true-distribution oracle draws available to each method. ACFS achieves the lowest median oracle spectral risk on the second benchmark in every configuration, with median gaps over GP-BO ranging from 8.6% to 21.8%. On the first benchmark, ACFS and GP-BO are statistically indistinguishable in median objective, but ACFS reduces cross-replication dispersion relative to GP-BO by approximately 1.9 to 2.5 times at the higher penalty weights, with near-parity at the lowest, and by 1.7 to 2.3 times throughout on the second benchmark, indicating materially improved run-to-run reliability. ACFS also outperforms CEM-SO, SGD-CVaR, and KDE-SO in nearly all settings, while ablation and sensitivity analyses support the robustness of the design and indicate that component contributions are most pronounced on the skewed log-normal benchmark.

---

### Naïve PAINE: Lightweight Text-to-Image Generation Improvement with Prompt Evaluation

Authors: Joong Ho Kim, Nicholas Thai, Souhardya Saha Dip, Dong Lao, Keith G. Mills
Published: 2026-03-12
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.12506v2

Text-to-Image (T2I) generation is primarily driven by Diffusion Models (DM) which rely on random Gaussian noise. Thus, like playing the slots at a casino, a DM will produce different results given the same user-defined inputs. This imposes a gambler's burden: To perform multiple generation cycles to obtain a satisfactory result. However, even though DMs use stochastic sampling to seed generation, the distribution of generated content quality highly depends on the prompt and the generative ability of a DM with respect to it. To account for this, we propose Naïve PAINE for improving the generative quality of Diffusion Models by leveraging T2I preference benchmarks. We directly predict the numerical quality of an image from the initial noise and given prompt. Naïve PAINE then selects a handful of quality noises and forwards them to the DM for generation. Further, Naïve PAINE provides feedback on the DM generative quality given the prompt and is lightweight enough to seamlessly fit into existing DM pipelines. Experimental results demonstrate that Naïve PAINE outperforms existing approaches on several prompt corpus benchmarks.

---

### TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction

Authors: Qianggang Ding, Haochen Shi, Luis Castejón Lozano, Miguel Conner, Juan Abia, Luis Gallego-Ledesma, Joshua Fellowes, Gerard Conangla Planes, Adam Elwood, Bang Liu
Published: 2026-03-12
Categories: cs.CE, cs.AI
arXiv: https://arxiv.org/abs/2603.12500v1

We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction that unifies symbolic relational priors, dynamic graph exploration, and LLM-guided decision making in a single end-to-end pipeline. The approach performs rule-guided multi-hop exploration restricted to admissible relation sequences, grounds candidate reasoning chains in contemporaneous news, and aggregates fully grounded evidence into auditable \texttt{UP}/\texttt{DOWN} verdicts with human-readable paths connecting text and structure. On an S\&P~500 benchmark, the method achieves 55.1\% accuracy, 55.7\% precision, 71.5\% recall, and 60.8\% F1, surpassing strong baselines and improving recall and F1 over the best graph baseline under identical evaluation. The gains stem from (i) rule-guided exploration that focuses search on economically meaningful motifs rather than arbitrary walks, and (ii) text-grounded consolidation that selectively aggregates high-confidence, fully grounded hypotheses instead of uniformly pooling weak signals. Together, these choices yield higher sensitivity without sacrificing selectivity, delivering predictive lift with faithful, auditably interpretable explanations.

---

### Probing Length Generalization in Mamba via Image Reconstruction

Authors: Jan Rathjens, Robin Schiewer, Laurenz Wiskott, Anand Subramoney
Published: 2026-03-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.12499v1

Mamba has attracted widespread interest as a general-purpose sequence model due to its low computational complexity and competitive performance relative to transformers. However, its performance can degrade when inference sequence lengths exceed those seen during training. We study this phenomenon using a controlled vision task in which Mamba reconstructs images from sequences of image patches. By analyzing reconstructions at different stages of sequence processing, we reveal that Mamba qualitatively adapts its behavior to the distribution of sequence lengths encountered during training, resulting in strategies that fail to generalize beyond this range. To support our analysis, we introduce a length-adaptive variant of Mamba that improves performance across training sequence lengths. Our results provide an intuitive perspective on length generalization in Mamba and suggest directions for improving the architecture.

---