# Research Papers — 2026-04 · bundle page 62 of 233

> Full-text markdown of papers #3051–3100 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-04/page/62
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/61.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/63.md)

### Calibrating conditional risk

Authors: Andrey Vasilyev, Yikai Wang, Xiaocheng Li, Guanting Chen
Published: 2026-04-22
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2604.20409v1

We introduce and study the problem of calibrating conditional risk, which involves estimating the expected loss of a prediction model conditional on input features. We analyze this problem in both classification and regression settings and show that it is fundamentally equivalent to a standard regression task. For classification settings, we further establish a connection between conditional risk calibration and individual/conditional probability calibration, and develop theoretical insights for the performance metric. This reveals that while conditional risk calibration is related to existing uncertainty quantification problems, it remains a distinct and standalone machine learning problem. Empirically, we validate our theoretical findings and demonstrate the practical implications of conditional risk calibration in the learning to defer (L2D) framework. Our systematic experiments provide both qualitative and quantitative assessments, offering guidance for future research in uncertainty-aware decision-making.

---

### Robustness of Spatio-temporal Graph Neural Networks for Fault Location in Partially Observable Distribution Grids

Authors: Burak Karabulut, Carlo Manna, Chris Develder
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.20403v2

Fault location in distribution grids is critical for reliability and minimizing outage durations. Yet, it remains challenging due to partial observability, given sparse measurement infrastructure. Recent works show promising results by combining Recurrent Neural Networks (RNNs) and Graph Neural Networks (GNNs) for spatio-temporal learning. Still, many modern GNN architectures remain untested for this grid application, while existing GNN solutions have not explored GNN topology definitions beyond simply adopting the full grid topology to construct the GNN graph. We address these gaps by (i) systematically comparing a newly proposed graph-forming strategy (measured-only) to the traditional full-topology approach, and (ii) introducing STGNN (Spatio-temporal GNN) models based on GraphSAGE and an improved Graph Attention (GATv2), for distribution grid fault location; (iii) benchmarking them against state-of-the-art STGNN and RNN baselines on the IEEE 123-bus feeder. In our experiments, all evaluated STGNN variants achieve high performance and consistently outperform a pure RNN baseline, with improvements up to 11 percentage points F1. Among STGNN models, the newly explored RGATv2 and RGSAGE achieve only marginally higher F1 scores. Still, STGNNs demonstrate superior stability, with tight confidence intervals (within +/- 1.4%) compared to the RNN baseline (up to +/- 7.5%) across different experiment runs. Finally, our proposed reduced GNN topology (measured-only) shows clear benefits in both (i) model training time (6-fold reduction) and (ii) model performance (up to 11 points F1). This suggests that measured-only graphs offer a more practical, efficient, and robust framework for partially observable distribution grids.

---

### Onyx: Cost-Efficient Disk-Oblivious ANN Search

Authors: Deevashwer Rathee, Jean-Luc Watson, Zirui Neil Zhao, G. Edward Suh, Raluca Ada Popa
Published: 2026-04-22
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2604.20401v1

Approximate nearest neighbor (ANN) search in AI systems increasingly handles sensitive data on third-party infrastructure. Trusted execution environments (TEEs) offer protection, but cost-efficient deployments must rely on external SSDs, which leaks user queries through disk access patterns to the host. Oblivious RAM (ORAM) can hide these access patterns but at a high cost; when paired with existing disk-based ANN search techniques, it makes poor use of SSD resources, yielding high latency and poor cost-efficiency. The core challenge for efficient oblivious ANN search over SSDs is balancing both bandwidth and access count. The state-of-the-art ORAM-ANN design minimizes access count at the ANN level and bandwidth at the ORAM level, each trading-off the other, leaving the combined system with both resources overutilized. We propose inverting this design, minimizing bandwidth consumption in the ANN layer and access count in the ORAM layer, since each component is better suited for its new role: ANN's inherent approximation allows for more bandwidth efficiency, while ORAM has no fundamental lower bounds on access count (as opposed to bandwidth). To this end, we propose a cost-efficient approach, Onyx, with two new co-designed components: Onyx-ANNS introduces a compact intermediate representation that proactively prunes the majority of bandwidth-intensive accesses without hurting recall, and Onyx-ORAM proposes a locality-aware shallow tree design that reduces access count while remaining compatible with bandwidth-efficient ORAM techniques. Compared to the state-of-the-art oblivious ANN search system, Onyx achieves $1.7-9.9\times$ lower cost and $2.3-12.3\times$ lower latency.

---

### WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning

Authors: Juyong Jiang, Chenglin Cai, Chansung Park, Jiasi Shen, Sunghun Kim, Jianguo Li, Yue Wang
Published: 2026-04-22
Categories: cs.CL, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2604.20398v1

While Large Language Models (LLMs) excel at function-level code generation, project-level tasks such as generating functional and visually aesthetic multi-page websites remain highly challenging. Existing works are often limited to single-page static websites, while agentic frameworks typically rely on multi-turn execution with proprietary models, leading to substantial token costs, high latency, and brittle integration. Training a small LLM end-to-end with reinforcement learning (RL) is a promising alternative, yet it faces a critical bottleneck in designing reliable and computationally feasible rewards for website generation. Unlike single-file coding tasks that can be verified by unit tests, website generation requires evaluating inherently subjective aesthetics, cross-page interactions, and functional correctness. To this end, we propose WebGen-R1, an end-to-end RL framework tailored for project-level website generation. We first introduce a scaffold-driven structured generation paradigm that constrains the large open-ended action space and preserves architectural integrity. We then design a novel cascaded multimodal reward that seamlessly couples structural guarantees with execution-grounded functional feedback and vision-based aesthetic supervision. Extensive experiments demonstrate that our WebGen-R1 substantially transforms a 7B base model from generating nearly nonfunctional websites into producing deployable, aesthetically aligned multi-page websites. Remarkably, our WebGen-R1 not only consistently outperforms heavily scaled open-source models (up to 72B), but also rivals the state-of-the-art DeepSeek-R1 (671B) in functional success, while substantially exceeding it in valid rendering and aesthetic alignment. These results position WebGen-R1 as a viable path for scaling small open models from function-level code generation to project-level web application generation.

---

### SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation

Authors: Chris Choy, Junha Lee, Chunghyun Park, Minsu Cho, Jan Kautz
Published: 2026-04-22
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2604.20395v2

Open-vocabulary 3D instance segmentation is a core capability for robotics and AR/VR, but prior methods trade one bottleneck for another: multi-stage 2D+3D pipelines aggregate foundation-model outputs at hundreds of seconds per scene, while pseudo-labeled end-to-end approaches rely on fragmented masks and external region proposals. We present SpaCeFormer, a proposal-free space-curve transformer that runs in 0.12--0.30 seconds per scene across standard benchmarks, 2--3 orders of magnitude faster than multi-stage 2D+3D pipelines. We pair it with SpaCeFormer-3M, the largest open-vocabulary 3D instance segmentation dataset (3.0M multi-view-consistent captions over 604K instances from 7.4K scenes) built through multi-view mask clustering and multi-view VLM captioning; it reaches 21$\times$ higher mask recall than prior single-view pipelines (54.3% vs 2.5% at IoU$>$0.5). SpaCeFormer combines spatial window attention with Morton-curve serialization for spatially coherent features, and uses a RoPE-enhanced decoder to predict instance masks directly from learned queries without external proposals. On ScanNet200 we achieve 11.1 zero-shot mAP, a 2.8$\times$ improvement over the prior best proposal-free method; on ScanNet++ and Replica, we reach 22.9 and 24.1 mAP, surpassing all prior methods including those using multi-view 2D inputs.

---

### MLG-Stereo: ViT Based Stereo Matching with Multi-Stage Local-Global Enhancement

Authors: Haoyu Zhang, Jingyi Zhou, Peng Ye, Jiakang Yuan, Lin Zhang, Feng Xu, Tao Chen
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20393v1

With the development of deep learning, ViT-based stereo matching methods have made significant progress due to their remarkable robustness and zero-shot ability. However, due to the limitations of ViTs in handling resolution sensitivity and their relative neglect of local information, the ability of ViT-based methods to predict details and handle arbitrary-resolution images is still weaker than that of CNN-based methods. To address these shortcomings, we propose MLG-Stereo, a systematic pipeline-level design that extends global modeling beyond the encoder stage. First, we propose a Multi-Granularity Feature Network to effectively balance global context and local geometric information, enabling comprehensive feature extraction from images of arbitrary resolution and bridging the gap between training and inference scales. Then, a Local-Global Cost Volume is constructed to capture both locally-correlated and global-aware matching information. Finally, a Local-Global Guided Recurrent Unit is introduced to iteratively optimize the disparity locally under the guidance of global information. Extensive experiments are conducted on multiple benchmark datasets, demonstrating that our MLG-Stereo exhibits highly competitive performance on the Middlebury and KITTI-2015 benchmarks compared to contemporaneous leading methods, and achieves outstanding results in the KITTI-2012 dataset.

---

### Self-supervised pretraining for an iterative image size agnostic vision transformer

Authors: Nedyalko Prisadnikov, Danda Pani Paudel, Yuqian Fu, Luc Van Gool
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20392v1

Vision Transformers (ViTs) dominate self-supervised learning (SSL). While they have proven highly effective for large-scale pretraining, they are computationally inefficient and scale poorly with image size. Consequently, foundational models like DINO are constrained to low-resolution processing. A recent foveal-inspired transformer achieves resolution agnosticism by iteratively processing a fixed-size context of multi-zoom patches. This model demonstrated promising results via supervised learning, utilizing a sequential, recurrent-like process without backpropagation through time. To unlock its potential as a foundational backbone, we introduce a novel sequential-to-global SSL framework based on DINO's self-distillation objective. Supported by an efficient integral-image patch extraction method, our approach enables large-scale pretraining for image-size agnostic vision encoders. We achieve competitive performance on ImageNet-1K and downstream classification tasks, maintaining a constant computational budget regardless of input resolution.

---

### CyberCertBench: Evaluating LLMs in Cybersecurity Certification Knowledge

Authors: Gustav Keppler, Ghada Elbez, Veit Hagenmeyer
Published: 2026-04-22
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2604.20389v1

The rapid evolution and use of Large Language Models (LLMs) in professional workflows require an evaluation of their domain-specific knowledge against industry standards. We introduceCyberCertBench, a new suite of Multiple Choice Question Answering (MCQA) benchmarks derived from industry recognized certifications. CyberCertBench evaluates LLM domain knowledgeagainst the professional standards of Information Technology cybersecurity and more specializedareas such as Operational Technology and related cybersecurity standards. Concurrently, we propose and validate a novel Proposer-Verifier framework, a methodology to generate interpretable,natural language explanations for model performance. Our evaluation shows that frontier modelsachieve human expert level in general networking and IT security knowledge. However, theiraccuracy declines in questions that require vendor-specific nuances or knowledge in formalstandards, like, e.g., IEC 62443. Analysis of model scaling trend and release date demonstratesremarkable gains in parameter efficiency, while recent larger models show diminishing returns.Code and evaluation scripts are available at: https://github.com/GKeppler/CyberCertBench.

---

### Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs

Authors: Aishik Mandal, Hiba Arnaout, Clarissa W. Ong, Juliet Bockhorst, Kate Sheehan, Rachael Moldow, Tanmoy Chakraborty, Iryna Gurevych
Published: 2026-04-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.20382v2

Rising demand for mental health support has increased interest in using Large Language Models (LLMs) for counseling, but adapting them to this safety-critical domain is hindered by limited real-world data due to privacy constraints. Synthetic datasets provide a promising alternative, but existing approaches often rely on unstructured or semi-structured text inputs and overlook structural dependencies between a client's cognitive, emotional, and behavioral states, leading to psychologically inconsistent and less realistic interactions. We introduce Graph2Counsel, a framework for generating synthetic counseling sessions grounded in Client Psychological Graphs (CPGs) that encode relationships among clients' thoughts, emotions, and behaviors. Graph2Counsel uses a structured prompting pipeline guided by counselor strategies and CPG, and explores prompting strategies including CoT and Multi-Agent Feedback. It produces 760 sessions from 76 CPGs across diverse client profiles. In expert evaluation, our dataset outperforms prior datasets on specificity, counselor competence, authenticity, conversational flow, and safety (Krippendorff's $α$ = 0.70). Fine-tuning an open-source model on this dataset improves performance on several metrics on CounselingBench and CounselBench, while matching baselines on others. We further introduce Therapy-Eval, a multi-turn evaluation framework, and demonstrate the effectiveness of our fine-tuned model in realistic therapeutic conversations. We make our code, data and fine-tuned model public.

---

### Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs

Authors: Aishik Mandal, Hiba Arnaout, Clarissa W. Ong, Juliet Bockhorst, Kate Sheehan, Rachael Moldow, Tanmoy Chakraborty, Iryna Gurevych
Published: 2026-04-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.20382v1

Rising demand for mental health support has increased interest in using Large Language Models (LLMs) for counseling. However, adapting LLMs to this high-risk safety-critical domain is hindered by the scarcity of real-world counseling data due to privacy constraints. Synthetic datasets provide a promising alternative, but existing approaches often rely on unstructured or semi-structured text inputs and overlook structural dependencies between a client's cognitive, emotional, and behavioral states, often producing psychologically inconsistent interactions and reducing data realism and quality. We introduce Graph2Counsel, a framework for generating synthetic counseling sessions grounded in Client Psychological Graphs (CPGs) that encode relationships among clients' thoughts, emotions, and behaviors. Graph2Counsel employs a structured prompting pipeline guided by counselor strategies and CPG, and explores prompting strategies including CoT (Wei et al., 2022) and Multi-Agent Feedback (Li et al., 2025a). Graph2Counsel produces 760 sessions from 76 CPGs across diverse client profiles. In expert evaluation, our dataset outperforms prior datasets on specificity, counselor competence, authenticity, conversational flow, and safety, with substantial inter-annotator agreement (Krippendorff's $α$ = 0.70). Fine-tuning an open-source model on this dataset improves performance on CounselingBench (Nguyen et al., 2025) and CounselBench (Li et al., 2025b), showing downstream utility. We also make our code and data public.

---

### Distributional Value Estimation Without Target Networks for Robust Quality-Diversity

Authors: Behrad Koohy, Jamie Bayne
Published: 2026-04-22
Categories: cs.LG, cs.NE, cs.RO
arXiv: https://arxiv.org/abs/2604.20381v1

Quality-Diversity (QD) algorithms excel at discovering diverse repertoires of skills, but are hindered by poor sample efficiency and often require tens of millions of environment steps to solve complex locomotion tasks. Recent advances in Reinforcement Learning (RL) have shown that high Update-to-Data (UTD) ratios accelerate Actor-Critic learning. While effective, standard high-UTD algorithms typically utilise target networks to stabilise training. This requirement introduces a significant computational bottleneck, rendering them impractical for resource-intensive Quality-Diversity (QD) tasks where sample efficiency and rapid population adaptation are critical. In this paper, we introduce QDHUAC, a sample-efficient, target-free and distributional QD-RL algorithm that provides dense and low-variance gradient signals, which enables high-UTD training for Dominated Novelty Search whilst requiring an order of magnitude fewer environment steps. We demonstrate that our method enables stable training at high UTD ratios, achieving competitive coverage and fitness on high-dimensional Brax environments with an order of magnitude fewer samples than baselines. Our results suggest that combining target-free distributional critics with dominance-based selection is a key enabler for the next generation of sample-efficient evolutionary RL algorithms.

---

### Towards Event-Aware Forecasting in DeFi: Insights from On-chain Automated Market Maker Protocols

Authors: Huaiyu Jia, Jiehshun You, Yizhi Luo, Jingyu Liu, Shuo Sun
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.20374v1

Automated Market Makers (AMMs), as a core infrastructure of decentralized finance (DeFi), uniquely drive on-chain asset pricing through a deterministic reserve ratio mechanism. Unlike traditional markets, AMM price dynamics is triggered largely by on-chain events (e.g., swap) that change the reserve ratio, rather than by continuous responses to off-chain information. This makes event-level analysis crucial for understanding price formation mechanisms in AMMs. However, existing research generally neglects the micro-structural dynamics at the AMMs level, lacking both a comprehensive dataset covering multiple protocols with fine-grained event classification and an effective framework for event-aware modeling. To fill this gap, we construct a dataset containing 8.9 million on-chain event records from four representative AMMs protocols: Pendle, Uniswap v3, Aave and Morpho, with precise annotations of transaction type and block height timestamps. Furthermore, we propose an Uncertainty Weighted Mean Squared Error (UWM) loss function, which incorporates the block interval regression term into the traditional Time-Point Process (TPP) objective function by weighting the uncertainty with homoscedasticity. Extensive experiments on eight advanced TPP architectures demonstrate that this loss function reduces the time prediction error by an average of 56.41\% while maintaining the accuracy of event type prediction, establishing a robust benchmark for event-aware prediction in the AMMs ecosystem. This work provides the necessary data foundation and methodological framework for modeling the discreteness and event-driven characteristics of on-chain price discovery. All datasets and source code are publicly available. https://github.com/yosen-king/Deep-AMM-Events

---

### Neuro-evolutionary stochastic architectures in gauge-covariant neural fields

Authors: Rodrigo Carmo Terin
Published: 2026-04-22
Categories: cs.NE, hep-th, nlin.AO
arXiv: https://arxiv.org/abs/2604.20373v1

We extend our gauge-covariant stochastic neural-field framework by promoting architecture-level parameters to slow stochastic variables evolving in function space. Our effective theory is formulated in terms of classical commuting fields and provides symmetry-constrained diagnostics of marginality and finite-width effects through the maximal Lyapunov exponent, the amplification factor, and dressed spectral kernels. On top of this dynamics, we introduce a Markovian evolutionary scheme compatible with the local $U(1)$ structure of the effective model. By using a minimal implementation, the genotype is reduced to the weight-variance parameter $σ_w^2$, and the fitness functional combines spectral agreement, marginal stability, and a symmetry-constrained critical anchor. Comparing three evolutionary models, we find that only the fully symmetry-constrained Ginibre $U(1)$ version robustly approaches a narrow near-marginal regime and reproduces the predicted low-frequency finite-width spectral behavior. These results support the use of symmetry-guided effective stability diagnostics as practical principles for stochastic architecture search in controlled settings.

---

### AI models of unstable flow exhibit hallucination

Authors: Ramdhan Wibawa, Birendra Jha
Published: 2026-04-22
Categories: physics.flu-dyn, cs.AI, cs.LG, nlin.PS
arXiv: https://arxiv.org/abs/2604.20372v1

We report the first systematic evidence of hallucination in AI models of fluid dynamics, demonstrated in the canonical problem of hydrodynamically unstable transport known as viscous fingering. AI-based modeling of flow with instabilities remains challenging because rapidly evolving, multiscale fingering patterns are difficult to resolve accurately. We identify solutions that appear visually realistic yet are physically implausible, analogous to hallucinations in large language models. These hallucinations manifest as spurious fluid interfaces and reverse diffusion that violate conservation laws. We show that their origin lies in the spectral bias of AI models, which becomes dominant at high flow rates and viscosity contrasts. Guided by this insight, we introduce DeepFingers, a new framework for AI-driven fluid dynamics that enforces balanced learning across the full spectrum of spatial modes by combining the Fourier Neural Operator with a Deep Operator Network to predict the spatiotemporal evolution of viscous fingers. By conditioning on both time and viscosity contrast, DeepFingers learns mappings between successive concentration fields across regimes. The framework accurately captures tip splitting, finger merging, and channel formation while preserving global metrics of mixing. The results open a new research direction to investigate fundamental limitations in AI models of physical systems.

---

### Cold-Start Forecasting of New Product Life-Cycles via Conditional Diffusion Models

Authors: Ruihan Zhou, Zishi Zhang, Jinhui Han, Yijie Peng, Xiaowei Zhang
Published: 2026-04-22
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2604.20370v1

Forecasting the life-cycle trajectory of a newly launched product is important for launch planning, resource allocation, and early risk assessment. This task is especially difficult in the pre-launch and early post-launch phases, when product-specific outcome history is limited or unavailable, creating a cold-start problem. In these phases, firms must make decisions before demand patterns become reliably observable, while early signals are often sparse, noisy, and unstable We propose the Conditional Diffusion Life-cycle Forecaster (CDLF), a conditional generative framework for forecasting new-product life-cycle trajectories under cold start. CDLF combines three sources of information: static descriptors, reference trajectories from similar products, and newly arriving observations when available. Here, static descriptors refer to structured pre-launch characteristics of the product, such as category, price tier, brand or organization identity, scale, and access conditions. This structure allows the model to condition forecasts on relevant product context and to update them adaptively over time without retraining, yielding flexible multi-modal predictive distributions under extreme data scarcity. The method satisfies consistency with a horizon-uniform distributional error bound for recursive generation. Across studies on Intel microprocessor stock keeping unit (SKU) life cycles and the platform-mediated adoption of open large language model repositories, CDLF delivers more accurate point forecasts and higher-quality probabilistic forecasts than classical diffusion models, Bayesian updating approaches, and other state-of-the-art machine-learning baselines.

---

### LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel

Authors: Zhe Feng, Sen Lian, Changwei Wang, Muyang Zhang, Tianlong Tan, Rongtao Xu, Weiliang Meng, Xiaopeng Zhang
Published: 2026-04-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.20368v1

The quadratic complexity of softmax attention presents a major obstacle for scaling Transformers to high-resolution vision tasks. Existing linear attention variants often replace the softmax with Gaussian kernels to reduce complexity, but such approximations lack theoretical grounding and tend to oversuppress mid-range token interactions. We propose LaplacianFormer, a Transformer variant that employs a Laplacian kernel as a principled alternative to softmax, motivated by empirical observations and theoretical analysis. To address expressiveness degradation under low-rank approximations, we introduce a provably injective feature map that retains fine-grained token information. For efficient computation, we adopt a Nyström approximation of the kernel matrix and solve the resulting system using Newton--Schulz iteration, avoiding costly matrix inversion and SVD. We further develop custom CUDA implementations for both the kernel and solver, enabling high-throughput forward and backward passes suitable for edge deployment. Experiments on ImageNet show that LaplacianFormer achieves strong performance-efficiency trade-offs while improving attention expressiveness.

---

### Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation

Authors: Xingyu Zhu, Junfeng Fang, Shuo Wang, Beier Zhu, Zhicai Wang, Yonghui Yang, Xiangnan He
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20366v1

Large Vision-Language Models (LVLMs) exhibit powerful generative capabilities but frequently produce hallucinations that compromise output reliability. Fine-tuning on annotated data devoid of hallucinations offers the most direct solution, while its high computational cost motivates recent representation-based methods, which focus on mitigating hallucinatory components within hidden representations. Though efficient, we empirically observe that these methods degrade general generation capacity due to incomplete extraction of hallucination components and non-selective parameter updates. To address these limitations, we propose MPD, a dual-stage framework for mitigating hallucinations without performance degradation. Specifically, our MPD relies on two essential factors: (1) semantic-aware component disentanglement to extract pure hallucination components, and (2) interpretable parameter updates that selectively modify parameters most relevant to hallucination. Extensive experiments demonstrate that MPD achieves state-of-the-art performance, reducing hallucinations by 23.4\% while maintaining 97.4\% of general generative capability as evaluated on LLaVA-Bench and MME, with no additional computational cost.

---

### Benefits of Low-Cost Bio-Inspiration in the Age of Overparametrization

Authors: Kevin Godin-Dubois, Anil Yaman, Anna V. Kononova
Published: 2026-04-22
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2604.20365v2

While Central Pattern Generators (CPGs) and Multi-Layer Perceptrons (MLP) are widely used paradigms in robot control, few systematic studies have been performed on the relative merits of large parameter spaces in highly constrained settings. As opposed to traditional Machine Learning contexts, our input and output spaces are small and performance is bounded thus having more parameters may actively hinder the learning process instead of empowering it. To empirically measure this, we submit a given robot morphology, with limited proprioceptive capabilities, to controller optimisation under two bio-inspired paradigms (CPGs and MLPs) with evolutionary- and reinforcement- trainer protocols. By varying parameter spaces across multiple reward functions, we demonstrate that shallow MLPs and densely connected CPGs result in better performance when compared to deeper MLPs or Actor-Critic architectures. To account for the relationship between said performance and the number of parameters, we introduce a Parameter Impact metric which showcases diminishing returns for MLPs but not for CPGs. Taken together these results demonstrate, on a fixed quadrupedal morphology, the benefits of integrating prior bias when considering locomotion tasks with simple hinge actuators.

---

### Benefits of Low-Cost Bio-Inspiration in the Age of Overparametrization

Authors: Kevin Godin-Dubois, Anil Yaman, Anna V. Kononova
Published: 2026-04-22
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2604.20365v1

While Central Pattern Generators (CPGs) and Multi-Layer Perceptrons (MLP) are widely used paradigms in robot control, few systematic studies have been performed on the relative merits of large parameter spaces. In contexts where input and output spaces are small and performance is bounded, having more parameters to optimize may actively hinder the learning process instead of empowering it. To empirically measure this, we submit a given robot morphology, with limited proprioceptive capabilities, to controller optimization under two bio-inspired paradigms (CPGs and MLPs) with evolutionary- and reinforcement- trainer protocols. By varying parameter spaces across multiple reward functions, we observe that shallow MLPs and densely connected CPGs result in better performance when compared to deeper MLPs or Actor-Critic architectures. To account for the relationship between said performance and the number of parameters, we introduce a Parameter Impact metric which demonstrates that the additional parameters required by the reinforcement technique do not translate into better performance, thus favouring evolutionary strategies.

---

### Object Referring-Guided Scanpath Prediction with Perception-Enhanced Vision-Language Models

Authors: Rong Quan, Yantao Lai, Dong Liang, Jie Qin
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20361v1

Object Referring-guided Scanpath Prediction (ORSP) aims to predict the human attention scanpath when they search for a specific target object in a visual scene according to a linguistic description describing the object. Multimodal information fusion is a key point of ORSP. Therefore, we propose a novel model, ScanVLA, to first exploit a Vision-Language Model (VLM) to extract and fuse inherently aligned visual and linguistic feature representations from the input image and referring expression. Next, to enhance the ScanVLA's perception of fine-grained positional information, we not only propose a novel History Enhanced Scanpath Decoder (HESD) that directly takes historical fixations' position information as input to help predict a more reasonable position for the current fixation, but also adopt a frozen Segmentation LoRA as an auxiliary component to help localize the referred object more precisely, which improves the scanpath prediction task without incurring additional large computational and time costs. Extensive experimental results demonstrate that ScanVLA can significantly outperform existing scanpath prediction methods under object referring.

---

### ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval

Authors: Zixu Li, Yupeng Hu, Zhiwei Chen, Mingyu Zhang, Zhiheng Fu, Liqiang Nie
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20358v1

The Composed Image Retrieval (CIR) task provides a flexible retrieval paradigm via a reference image and modification text, but it heavily relies on expensive and error-prone triplet annotations. This paper systematically investigates the Noisy Triplet Correspondence (NTC) problem introduced by annotations. We find that NTC noise, particularly ``hard noise'' (i.e., the reference and target images are highly similar but the modification text is incorrect), poses a unique challenge to existing Noise Correspondence Learning (NCL) methods because it breaks the traditional ``small loss hypothesis''. We identify and elucidate three key, yet overlooked, challenges in the NTC task, namely (C1) Modality Suppression, (C2) Negative Anchor Deficiency, and (C3) Unlearning Backlash. To address these challenges, we propose a Cone-based robuSt noisE-unlearning comPositional network (ConeSep). Specifically, we first propose Geometric Fidelity Quantization, theoretically establishing and practically estimating a noise boundary to precisely locate noisy correspondence. Next, we introduce Negative Boundary Learning, which learns a ``diagonal negative combination'' for each query as its explicit semantic opposite-anchor in the embedding space. Finally, we design Boundary-based Targeted Unlearning, which models the noisy correction process as an optimal transport problem, elegantly avoiding Unlearning Backlash. Extensive experiments on benchmark datasets (FashionIQ and CIRR) demonstrate that ConeSep significantly outperforms current state-of-the-art methods, which fully demonstrates the effectiveness and robustness of our method.

---

### SignDATA: Data Pipeline for Sign Language Translation

Authors: Kuanwei Chen, Tingyi Lin
Published: 2026-04-22
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2604.20357v1

Sign-language datasets are difficult to preprocess consistently because they vary in annotation schema, clip timing, signer framing, and privacy constraints. Existing work usually reports downstream models, while the preprocessing pipeline that converts raw video into training-ready pose or video artifacts remains fragmented, backend-specific, and weakly documented. We present SignDATA, a config-driven preprocessing toolkit that standardizes heterogeneous sign-language corpora into comparable outputs for learning. The system supports two end-to-end recipes: a pose recipe that performs acquisition, manifesting, person localization, clipping, cropping, landmark extraction, normalization, and WebDataset export, and a video recipe that replaces pose extraction with signer-cropped video packaging. SignDATA exposes interchangeable MediaPipe and MMPose backends behind a common interface, typed job schemas, experiment-level overrides, and per-stage checkpointing with config- and manifest-aware hashes. We validate the toolkit through a research-oriented evaluation design centered on backend comparison, preprocessing ablations, and privacy-aware video generation on datasets. Our contribution is a reproducible preprocessing layer for sign-language research that makes extractor choice, normalization policy, and privacy tradeoffs explicit, configurable, and empirically comparable.Code is available at https://github.com/balaboom123/signdata-slt.

---

### Hallucination Early Detection in Diffusion Models

Authors: Federico Betti, Lorenzo Baraldi, Lorenzo Baraldi, Rita Cucchiara, Nicu Sebe
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20354v1

Text-to-Image generation has seen significant advancements in output realism with the advent of diffusion models. However, diffusion models encounter difficulties when tasked with generating multiple objects, frequently resulting in hallucinations where certain entities are omitted. While existing solutions typically focus on optimizing latent representations within diffusion models, the relevance of the initial generation seed is typically underestimated. While using various seeds in multiple iterations can improve results, this method also significantly increases time and energy costs. To address this challenge, we introduce HEaD+ (Hallucination Early Detection +), a novel approach designed to identify incorrect generations early in the diffusion process. The HEaD+ framework integrates cross-attention maps and textual information with a novel input, the Predicted Final Image. The objective is to assess whether to proceed with the current generation or restart it with a different seed, thereby exploring multiple-generation seeds while conserving time. HEaD+ is trained on the newly created InsideGen dataset of 45,000 generated images, each containing prompts with up to seven objects. Our findings demonstrate a 6-8% increase in the likelihood of achieving a complete generation (i.e., an image accurately representing all specified subjects) with four objects when applying HEaD+ alongside existing models. Additionally, HEaD+ reduces generation times by up to 32% when aiming for a complete image, enhancing the efficiency of generating complete and accurate object representations relative to leading models. Moreover, we propose an integrated localization module that predicts object centroid positions and verifies pairwise spatial relations (if requested by the users) at an intermediate timestep, gating generation together with object presence to further improve relation-consistent outcomes.

---

### X-PCR: A Benchmark for Cross-modality Progressive Clinical Reasoning in Ophthalmic Diagnosis

Authors: Gui Wang, Zehao Zhong, YongSong Zhou, Yudong Li, Ende Wu, Wooi Ping Cheah, Rong Qu, Jianfeng Ren, Linlin Shen
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20350v1

Despite significant progress in Multi-modal Large Language Models (MLLMs), their clinical reasoning capacity for multi-modal diagnosis remains largely unexamined. Current benchmarks, mostly single-modality data, can't evaluate progressive reasoning and cross-modal integration essential for clinical practice. We introduce the Cross-Modality Progressive Clinical Reasoning (X-PCR) benchmark, the first comprehensive evaluation of MLLMs through a complete ophthalmology diagnostic workflow, with two reasoning tasks: 1) a six-stage progressive reasoning chain spanning image quality assessment to clinical decision-making, and 2) a cross-modality reasoning task integrating six imaging modalities. The benchmark comprises 26,415 images and 177,868 expert-verified VQA pairs curated from 51 public datasets, covering 52 ophthalmic diseases. Evaluation of 21 MLLMs reveals critical gaps in progressive reasoning and cross-modal integration. Dataset and code: https://github.com/CVI-SZU/X-PCR.

---

### Bimanual Robot Manipulation via Multi-Agent In-Context Learning

Authors: Alessio Palma, Indro Spinelli, Vignesh Prasad, Luca Scofano, Yufeng Jin, Georgia Chalvatzaki, Fabio Galasso
Published: 2026-04-22
Categories: cs.RO, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2604.20348v2

Language Models (LLMs) have emerged as powerful reasoning engines for embodied control. In particular, In-Context Learning (ICL) enables off-the-shelf, text-only LLMs to predict robot actions without any task-specific training while preserving their generalization capabilities. Applying ICL to bimanual manipulation remains challenging as the high-dimensional joint action space and tight inter-arm coordination constraints rapidly overwhelm standard context windows. To address this, we introduce BiCICLe (Bimanual Coordinated In-Context Learning), the first framework that enables standard LLMs to perform few-shot bimanual manipulation without fine-tuning. BiCICLe frames bimanual control as a multi-agent leader-follower problem, decoupling the action space into sequential, conditioned single-arm predictions. Evaluated on 13 tasks from the TWIN benchmark, BiCICLe achieves 70.5% average success rate, outperforming the best training-free baseline by 6.1 percentage points and surpassing most supervised methods. We also demonstrate superior real-world performance on 3 tasks without hardware-specific retraining.

---

### A Vision-Language-Action Model for Adaptive Ultrasound-Guided Needle Insertion and Needle Tracking

Authors: Yuelin Zhang, Qingpeng Ding, Longxiang Tang, Chengyu Fang, Shing Shin Cheng
Published: 2026-04-22
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2604.20347v1

Ultrasound (US)-guided needle insertion is a critical yet challenging procedure due to dynamic imaging conditions and difficulties in needle visualization. Many methods have been proposed for automated needle insertion, but they often rely on hand-crafted pipelines with modular controllers, whose performance degrades in challenging cases. In this paper, a Vision-Language-Action (VLA) model is proposed for adaptive and automated US-guided needle insertion and tracking on a robotic ultrasound (RUS) system. This framework provides a unified approach to needle tracking and needle insertion control, enabling real-time, dynamically adaptive adjustment of insertion based on the obtained needle position and environment awareness. To achieve real-time and end-to-end tracking, a Cross-Depth Fusion (CDF) tracking head is proposed, integrating shallow positional and deep semantic features from the large-scale vision backbone. To adapt the pretrained vision backbone for tracking tasks, a Tracking-Conditioning (TraCon) register is introduced for parameter-efficient feature conditioning. After needle tracking, an uncertainty-aware control policy and an asynchronous VLA pipeline are presented for adaptive needle insertion control, ensuring timely decision-making for improved safety and outcomes. Extensive experiments on both needle tracking and insertion show that our method consistently outperforms state-of-the-art trackers and manual operation, achieving higher tracking accuracy, improved insertion success rates, and reduced procedure time, highlighting promising directions for RUS-based intelligent intervention.

---

### Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulation

Authors: Jiahao Xu, Xiaohan Yuan, Xingchen Wu, Chongyang Xu, Kun Li, Buzhen Huang
Published: 2026-04-22
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2604.20336v1

Co-manipulation requires multiple humans to synchronize their motions with a shared object while ensuring reasonable interactions, maintaining natural poses, and preserving stable states. However, most existing motion generation approaches are designed for single-character scenarios or fail to account for payload-induced dynamics. In this work, we propose a flow-matching framework that ensures the generated co-manipulation motions align with the intended goals while maintaining naturalness and effectiveness. Specifically, we first introduce a generative model that derives explicit manipulation strategies from the object's affordance and spatial configuration, which guide the motion flow toward successful manipulation. To improve motion quality, we then design an adversarial interaction prior that promotes natural individual poses and realistic inter-person interactions during co-manipulation. In addition, we also incorporate a stability-driven simulation into the flow matching process, which refines unstable interaction states through sampling-based optimization and directly adjusts the vector field regression to promote more effective manipulation. The experimental results demonstrate that our method achieves higher contact accuracy, lower penetration, and better distributional fidelity compared to state-of-the-art human-object interaction baselines. The code is available at https://github.com/boycehbz/StaCOM.

---

### Quantization robustness from dense representations of sparse functions in high-capacity kernel associative memory

Authors: Akira Tamamori
Published: 2026-04-22
Categories: cs.NE
arXiv: https://arxiv.org/abs/2604.20333v4

High-capacity associative memories based on Kernel Logistic Regression (KLR) achieve strong retrieval performance but typically require substantial computational resources. This paper investigates the compressibility of KLR Hopfield networks to clarify the geometric principles underlying their robust representations. We present a geometric interpretation based on spontaneous symmetry breaking and Walsh analysis, and examine it through compression experiments involving quantization and pruning. The experiments reveal a clear asymmetry: the network remains robust under low-precision quantization while exhibiting strong sensitivity to pruning. We interpret this behavior through a "sparse function, dense representation" principle, in which a sparse input mapping is implemented through a dense bimodal parameterization. These findings suggest a practical route toward hardware-efficient kernel associative memories and provide insight into the geometric principles underlying robust representation in neural systems.

---

### Quantization robustness from dense representations of sparse functions in high-capacity kernel associative memory

Authors: Akira Tamamori
Published: 2026-04-22
Categories: cs.NE
arXiv: https://arxiv.org/abs/2604.20333v3

High-capacity associative memories based on Kernel Logistic Regression (KLR) achieve strong retrieval performance but typically require substantial computational resources. This paper investigates the compressibility of KLR Hopfield networks to clarify the geometric principles underlying their robust representations. We present a geometric interpretation based on spontaneous symmetry breaking and Walsh analysis, and examine it through compression experiments involving quantization and pruning. The experiments reveal a clear asymmetry: the network remains robust under low-precision quantization while exhibiting strong sensitivity to pruning. We interpret this behavior through a "sparse function, dense representation" principle, in which a sparse input mapping is implemented through a dense bimodal parameterization. These findings suggest a practical route toward hardware-efficient kernel associative memories and provide insight into the geometric principles underlying robust representation in neural systems.

---

### Surrogate modeling for interpreting black-box LLMs in medical predictions

Authors: Changho Han, Songsoo Kim, Dong Won Kim, Leo Anthony Celi, Jaewoong Kim, SungA Bae, Dukyong Yoon
Published: 2026-04-22
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.20331v2

Large language models (LLMs), trained on vast datasets, encode extensive real-world knowledge within their parameters, yet their black-box nature obscures the mechanisms and extent of this encoding. Surrogate modeling, which uses simplified models to approximate complex systems, can offer a path toward better interpretability of black-box models. We propose a surrogate modeling framework that quantitatively explains LLM-encoded knowledge. For a specific hypothesis derived from domain knowledge, this framework approximates the latent LLM knowledge space using observable elements (input-output pairs) through extensive prompting across a comprehensive range of simulated scenarios. Through proof-of-concept experiments in medical predictions, we demonstrate our framework's effectiveness in revealing the extent to which LLMs "perceive" each input variable in relation to the output. Particularly, given concerns that LLMs may perpetuate inaccuracies and societal biases embedded in their training data, our experiments using this framework quantitatively revealed both associations that contradict established medical knowledge and the persistence of scientifically refuted racial assumptions within LLM-encoded knowledge. By disclosing these issues, our framework can act as a red-flag indicator to support the safe and reliable application of these models.

---

### Image Generators are Generalist Vision Learners

Authors: Valentin Gabeur, Shangbang Long, Songyou Peng, Paul Voigtlaender, Shuyang Sun, Yanan Bao, Karen Truong, Zhicheng Wang, Wenlei Zhou, Jonathan T. Barron, Kyle Genova, Nithish Kannen et al.
Published: 2026-04-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.20329v3

Recent works show that image and video generators exhibit zero-shot visual understanding behaviors, in a way reminiscent of how LLMs develop emergent capabilities of language understanding and reasoning from generative pretraining. While it has long been conjectured that the ability to create visual content implies an ability to understand it, there has been limited evidence that generative vision models have developed strong understanding capabilities. In this work, we demonstrate that image generation training serves a role similar to LLM pretraining, and lets models learn powerful and general visual representations that enable SOTA performance on various vision tasks. We introduce Vision Banana, a generalist model built by instruction-tuning Nano Banana Pro (NBP) on a mixture of its original training data alongside a small amount of vision task data. By parameterizing the output space of vision tasks as RGB images, we seamlessly reframe perception as image generation. Our generalist model, Vision Banana, achieves SOTA results on a variety of vision tasks involving both 2D and 3D understanding, beating or rivaling zero-shot domain-specialists, including Segment Anything Model 3 on segmentation tasks, and the Depth Anything series on metric depth estimation. We show that these results can be achieved with lightweight instruction-tuning without sacrificing the base model's image generation capabilities. The superior results suggest that image generation pretraining is a generalist vision learner. It also shows that image generation serves as a unified and universal interface for vision tasks, similar to text generation's role in language understanding and reasoning. We could be witnessing a major paradigm shift for computer vision, where generative vision pretraining takes a central role in building Foundational Vision Models for both generation and understanding.

---

### HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization

Authors: Tao Cheng, Shi-Zhe Chen, Hao Zhang, Yixin Qin, Jinwen Luo, Zheng Wei
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20328v2

Chain-of-Thought (CoT) reasoning significantly elevates the complex problem-solving capabilities of multimodal large language models (MLLMs). However, adapting CoT to vision typically discretizes signals to fit LLM inputs, causing early semantic collapse and discarding fine-grained details. While external tools can mitigate this, they introduce a rigid bottleneck, confining reasoning to predefined operations. Although recent latent reasoning paradigms internalize visual states to overcome these limitations, optimizing the resulting hybrid discrete-continuous action space remains challenging. In this work, we propose HyLaR (Hybrid Latent Reasoning), a framework that seamlessly interleaves discrete text generation with continuous visual latent representations. Specifically, following an initial cold-start supervised fine-tuning (SFT), we introduce DePO (Decoupled Policy Optimization) to enable effective reinforcement learning within this hybrid space. DePO decomposes the policy gradient objective, applying independent trust-region constraints to the textual and latent components, alongside an exact closed-form von Mises-Fisher (vMF) KL regularizer. Extensive experiments demonstrate that HyLaR outperforms standard MLLMs and state-of-the-art latent reasoning approaches across fine-grained perception and general multimodal understanding benchmarks. Code is available at https://github.com/EthenCheng/HyLaR.

---

### SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark

Authors: Gui Wang, YongSong Zhou, Kaijun Deng, Wooi Ping Cheah, Rong Qu, Jianfeng Ren, Linlin Shen
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20319v1

Fine-grained spatiotemporal reasoning on surgical videos is critical, yet the capabilities of Multi-modal Large Language Models (MLLMs) in this domain remain largely unexplored. To bridge this gap, we introduce SurgCoT, a unified benchmark for evaluating chain-of-thought (CoT) reasoning in MLLMs across 7 surgical specialties and 35 diverse procedures. SurgCoT assesses five core reasoning dimensions: Causal Action Ordering, Cue-Action Alignment, Affordance Mapping, Micro-Transition Localization, and Anomaly Onset Tracking, through a structured CoT framework with an intensive annotation protocol (Question-Option-Knowledge-Clue-Answer), where the Knowledge field provides essential background context and Clue provides definitive spatiotemporal evidence. Evaluation of 10 leading MLLMs shows: 1) commercial models outperform open-source and medical-specialized variants; 2) significant gaps exist in surgical CoT reasoning; 3) SurgCoT enables effective evaluation and enhances progressive spatiotemporal reasoning. SurgCoT provides a reproducible testbed to narrow the gap between MLLM capabilities and clinical reasoning demands. Code: https://github.com/CVI-SZU/SurgCoT.

---

### UniCVR: From Alignment to Reranking for Unified Zero-Shot Composed Visual Retrieval

Authors: Haokun Wen, Xuemeng Song, Haoyu Zhang, Weili Guan, Xiangyu Zhao, Liqiang Nie
Published: 2026-04-22
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2604.20318v2

Composed image retrieval, multi-turn composed image retrieval, and composed video retrieval all share a common paradigm: composing the reference visual with modification text to retrieve the desired target. Despite this shared structure, the three tasks have been studied in isolation, with no prior work proposing a unified framework, let alone a zero-shot solution. In this paper, we propose UniCVR, the first unified zero-shot composed visual retrieval framework that jointly addresses all three tasks without any task-specific human-annotated data. UniCVR strategically combines two complementary strengths: Multimodal Large Language Models (MLLMs) for compositional query understanding and Vision-Language Pre-trained (VLP) models for structured visual retrieval. Concretely, UniCVR operates in two stages. In Stage~I, we train the MLLM as a compositional query embedder via contrastive learning on a curated multi-source dataset of approximately 3.5M samples, bridging the heterogeneous embedding spaces between the MLLM and the frozen VLP gallery encoder. A cluster-based hard negative sampling strategy is proposed to strengthen contrastive supervision. In Stage~II, we introduce an MLLM-guided dual-level reranking mechanism that applies adaptive budgeted subset scoring to a small number of top-ranked candidates, and then exploits the resulting relevance signals through a dual-level re-scoring scheme, producing more accurate final rankings with minimal computational overhead. Extensive experiments across five benchmarks covering all three tasks demonstrate that UniCVR achieves cutting-edge performance, validating its effectiveness and generalizability.

---

### MD-Face: MoE-Enhanced Label-Free Disentangled Representation for Interactive Facial Attribute Editing

Authors: Xuan Cui, Yunfei Zhao, Bo Liu, Wei Duan, Xingrong Fan
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20317v1

GAN-based facial attribute editing is widely used in virtual avatars and social media but often suffers from attribute entanglement, where modifying one face attribute unintentionally alters others. While supervised disentangled representation learning can address this, it relies heavily on labeled data, incurring high annotation costs. To address these challenges, we propose MD-Face, a label-free disentangled representation learning framework based on Mixture of Experts (MoE). MD-Face utilizes a MoE backbone with a gating mechanism that dynamically allocates experts, enabling the model to learn semantic vectors with greater independence. To further enhance attribute entanglement, we introduce a geometry-aware loss, which aligns each semantic vector with its corresponding Semantic Boundary Vector (SBV) through a Jacobian-based pushforward method. Experiments with ProGAN and StyleGAN show that MD-Face outperforms unsupervised baselines and competes with supervised ones. Compared to diffusion-based methods, it offers better image quality and lower inference latency, making it ideal for interactive editing.

---

### R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling

Authors: Aijia Cheng, Kailong Wang, Ling Shi, Yongxin Zhao
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.20316v2

Function calling empowers large language models (LLMs) to interface with external tools, yet existing RL-based approaches suffer from misalignment between reasoning processes and tool-call decisions. We propose R2IF, a reasoning-aware RL framework for interpretable function calling, adopting a composite reward integrating format/correctness constraints, Chain-of-Thought Effectiveness Reward (CER), and Specification-Modification-Value (SMV) reward, optimized via GRPO. Experiments on BFCL/ACEBench show R2IF outperforms baselines by up to 34.62% (Llama3.2-3B on BFCL) with positive Average CoT Effectiveness (0.05 for Llama3.2-3B), enhancing both function-calling accuracy and interpretability for reliable tool-augmented LLM deployment.

---

### Formalising the Logit Shift Induced by LoRA: A Technical Note

Authors: Xiang Shi, Shuaizhi Cheng, Mingwei Li
Published: 2026-04-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.20313v1

This technical note provides a first-order formalisation of the logit shift and fact-margin change induced by Low-Rank Adaptation (LoRA). Using a first-order Fréchet approximation around the base model trajectory, we show that the multi-layer LoRA effect can be decomposed into a linear summation of layerwise contributions and a higher-order remainder term representing inter-layer coupling.

---

### Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction

Authors: Dali Wang, Yunyao Zhang, Junqing Yu, Yi-Ping Phoebe Chen, Chen Xu, Zikai Song
Published: 2026-04-22
Categories: cs.MM, cs.AI
arXiv: https://arxiv.org/abs/2604.20311v2

Micro-video popularity prediction (MVPP) aims to forecast the future popularity of videos on online media, which is essential for applications such as content recommendation and traffic allocation. In real-world scenarios, it is critical for MVPP approaches to understand both the temporal dynamics of a given video (temporal) and its historical relevance to other videos (spatial). However, existing approaches sufer from limitations in both dimensions: temporally, they rely on sparse short-range sampling that restricts content perception; spatially, they depend on flat retrieval memory with limited capacity and low efficiency, hindering scalable knowledge utilization. To overcome these limitations, we propose a unified framework that achieves joint spatio-temporal enlargement, enabling precise perception of extremely long video sequences while supporting a scalable memory bank that can infinitely expand to incorporate all relevant historical videos. Technically, we employ a Temporal Enlargement driven by a frame scoring module that extracts highlight cues from video frames through two complementary pathways: sparse sampling and dense perception. Their outputs are adaptively fused to enable robust long-sequence content understanding. For Spatial Enlargement, we construct a Topology-Aware Memory Bank that hierarchically clusters historically relevant content based on topological relationships. Instead of directly expanding memory capacity, we update the encoder features of the corresponding clusters when incorporating new videos, enabling unbounded historical association without unbounded storage growth. Extensive experiments on three widely used MVPP benchmarks demonstrate that our method consistently outperforms 11 strong baselines across mainstream metrics, achieving robust improvements in both prediction accuracy and ranking consistency.

---

### Sheaf Neural Networks on SPD Manifolds: Second-Order Geometric Representation Learning

Authors: Yuhan Peng, Junwen Dong, Yuzhi Zeng, Hao Li, Ce Ju, Huitao Feng, Diaaeldin Taha, Anna Wienhard, Kelin Xia
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.20308v2

Graph neural networks face two fundamental challenges rooted in the linear structure of Euclidean vector spaces: (1) Current architectures represent geometry through vectors (directions, gradients), yet many tasks require matrix-valued representations that capture relationships between directions-such as how atomic orientations covary in a molecule. These second-order representations are naturally captured by points on the symmetric positive definite matrices (SPD) manifold; (2) Standard message passing applies shared transformations across edges. Sheaf neural networks address this via edge-specific transformations, but existing formulations remain confined to vector spaces and therefore cannot propagate matrix-valued features. We address both challenges by developing the first sheaf neural network operates natively on the SPD manifold. Our key insight is that the SPD manifold admits a Lie group structure, enabling well-posed analogs of sheaf operators without projecting to Euclidean space. Theoretically, we prove that SPD-valued sheaves are strictly more expressive than Euclidean sheaves: they admit consistent configurations (global sections) that vector-valued sheaves cannot represent, directly translating to richer learned representations. Empirically, our sheaf convolution transforms effectively rank-1 directional inputs into full-rank matrices encoding local geometric structure. Our dual-stream architecture achieves SOTA on 6/7 MoleculeNet benchmarks, with the sheaf framework providing consistent depth robustness.

---

### Improving Facial Emotion Recognition through Dataset Merging and Balanced Training Strategies

Authors: Serap Kırbız
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20307v1

In this paper, a deep learning framework is proposed for automatic facial emotion based on deep convolutional networks. In order to increase the generalization ability and the robustness of the method, the dataset size is increased by merging three publicly available facial emotion datasets: CK+, FER+ and KDEF. Despite the increase in dataset size, the minority classes still suffer from insufficient number of training samples, leading to data imbalance. The data imbalance problem is minimized by online and offline augmentation techniques and random weighted sampling. Experimental results demonstrate that the proposed method can recognize the seven basic emotions with 82% accuracy. The results demonstrate the effectiveness of the proposed approach in tackling the challenges of data imbalance and improving classification performance in facial emotion recognition.

---

### Dual Causal Inference: Integrating Backdoor Adjustment and Instrumental Variable Learning for Medical VQA

Authors: Zibo Xu, Qiang Li, Ke Lu, Jin Wang, Weizhi Nie, Yuting Su
Published: 2026-04-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.20306v1

Medical Visual Question Answering (MedVQA) aims to generate clinically reliable answers conditioned on complex medical images and questions. However, existing methods often overfit to superficial cross-modal correlations, neglecting the intrinsic biases embedded in multimodal medical data. Consequently, models become vulnerable to cross-modal confounding effects, severely hindering their ability to provide trustworthy diagnostic reasoning. To address this limitation, we propose a novel Dual Causal Inference (DCI) framework for MedVQA. To the best of our knowledge, DCI is the first unified architecture that integrates Backdoor Adjustment (BDA) and Instrumental Variable (IV) learning to jointly tackle both observable and unobserved confounders. Specifically, we formulate a Structural Causal Model (SCM) where observable cross-modal biases (e.g., frequent visual and textual co-occurrences) are mitigated via BDA, while unobserved confounders are compensated using an IV learned from a shared latent space. To guarantee the validity of the IV, we design mutual information constraints that maximize its dependence on the fused multimodal representations while minimizing its associations with the unobserved confounders and target answers. Through this dual mechanism, DCI extracts deconfounded representations that capture genuine causal relationships. Extensive experiments on four benchmark datasets, SLAKE, SLAKE-CP, VQA-RAD, and PathVQA, demonstrate that our method consistently outperforms existing approaches, particularly in out-of-distribution (OOD) generalization. Furthermore, qualitative analyses confirm that DCI significantly enhances the interpretability and robustness of cross-modal reasoning by explicitly disentangling true causal effects from spurious cross-modal shortcuts.

---

### LLM-guided phase diagram construction through high-throughput experimentation

Authors: Ryo Tamura, Haruhiko Morito, Yuna Oikawa, Guillaume Deffrennes, Shoichi Matsuda, Naruki Yoshikawa, Tomoaki Takayama, Taichi Abe, Koji Tsuda, Kei Terayama
Published: 2026-04-22
Categories: cond-mat.mtrl-sci, cs.AI
arXiv: https://arxiv.org/abs/2604.20304v1

Constructing phase diagrams for multicomponent alloys requires extensive experimental measurements and is a time-consuming task. Here we investigate whether large language models (LLMs) can guide experimental planning for phase diagram construction. In our framework, a general-purpose LLM serves as the experimental planner, suggesting compositions for measurement at each cycle in a closed loop with high-throughput synthesis and X-ray diffraction phase identification. Using this framework, we experimentally constructed the ternary phase diagram of the Co-Al-Ge system at 900 degree C through iterative synthesis and characterization. We compared two strategies that differ in how the initial compositions are selected: one uses predictions from a domain-specific LLM trained on phase diagram data (aLLoyM), while the other relies solely on the general-purpose LLM. The two strategies exhibited complementary strengths. aLLoyM directed the initial measurements toward compositionally complex regions in the interior of the ternary diagram, enabling the earliest discovery of all three novel phases that form only in the ternary system. In contrast, the general-purpose LLM adopted a textbook-like approach which efficiently identified a larger number of phases in fewer cycles. In addition, a simulated benchmark comparing the LLM against conventional machine learning confirmed that the LLM achieves more efficient exploration. The results demonstrate that LLMs have high potential as experimental planners for phase diagram construction.

---

### Properties and limitations of geometric tempering for gradient flow dynamics

Authors: Francesca Romana Crucinio, Sahani Pathiraja
Published: 2026-04-22
Categories: stat.ML, cs.LG, stat.CO, stat.ME
arXiv: https://arxiv.org/abs/2604.20301v1

We consider the problem of sampling from a probability distribution $π$. It is well known that this can be written as an optimisation problem over the space of probability distributions in which we aim to minimise the Kullback--Leibler divergence from $π$. We consider the effect of replacing $π$ with a sequence of moving targets $(π_t)_{t\ge0}$ defined via geometric tempering on the Wasserstein and Fisher--Rao gradient flows. We show that convergence occurs exponentially in continuous time, providing novel bounds in both cases. We also consider popular time discretisations and explore their convergence properties. We show that in the Fisher--Rao case, replacing the target distribution with a geometric mixture of initial and target distribution never leads to a convergence speed up both in continuous time and in discrete time. Finally, we explore the gradient flow structure of tempered dynamics and derive novel adaptive tempering schedules.

---

### FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory

Authors: Yingjie Gu, Wenjian Xiong, Liqiang Wang, Pengcheng Ren, Chao Li, Xiaojing Zhang, Yijuan Guo, Qi Sun, Jingyao Ma, Shidang Shi
Published: 2026-04-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.20300v2

For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--inspired by human cognitive processes (hippocampal indexing/consolidation theory and Ebbinghaus forgetting curve)--remains underexplored. We argue that in resource-constrained environments, a well-designed forgetting mechanism is as crucial as remembering, delivering benefits across three dimensions: (1) efficiency via intelligent memory pruning, (2) quality by dynamically updating outdated preferences and context, and (3) security through active forgetting of malicious inputs, sensitive data, and privacy-compromising content. Our framework establishes a taxonomy of forgetting mechanisms: passive decay-based, active deletion-based, safety-triggered, and adaptive reinforcement-based. Building on advances in LLM agent architectures and vector databases, we present detailed specifications, implementation strategies, and empirical validation from controlled experiments. Results show significant improvements: access efficiency (+8.49%), content quality (+29.2% signal-to-noise ratio), and security performance (100% elimination of security risks). Our work bridges cognitive neuroscience and AI systems, offering practical solutions for real-world deployment while addressing ethical and regulatory compliance. The paper concludes with challenges and future directions, establishing selective forgetting as a fundamental capability for next-generation LLM agents operating in real-world, resource-constrained scenarios. Our contributions align with AI-native memory systems and responsible AI development.

---

### Online Survival Analysis: A Bandit Approach under Cox PH Model

Authors: Yang Xu, Wenbin Lu, Rui Song
Published: 2026-04-22
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2604.20296v1

Survival analysis is a widely used statistical framework for modeling time-to-event data under censoring. Classical methods, such as the Cox proportional hazards (Cox PH) model, offer a semiparametric approach to estimating the effects of covariates on the hazard function. Despite its importance, survival analysis has been largely unexplored in online settings, particularly within the bandit framework, where decisions must be made sequentially to optimize treatments as new data arrive over time. In this work, we take an initial step toward integrating survival analysis into a purely online learning setting under the Cox PH model, addressing key challenges including staggered entry, delayed feedback, and right censoring. We adapt three canonical bandit algorithms to balance exploration and exploitation, with theoretical guarantees of sublinear regret bounds. Extensive simulations and semi-real experiments using SEER cancer data demonstrate that our approach enables rapid and effective learning of near-optimal treatment policies.

---

### Synthetic Flight Data Generation Using Generative Models

Authors: Karim Aly, Alexei Sharpanskykh
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.20293v1

The increasing adoption of synthetic data in aviation research offers a promising solution to data scarcity and confidentiality challenges. This study investigates the potential of generative models to produce realistic synthetic flight data and evaluates their quality through a comprehensive four-stage assessment framework. The need for synthetic flight data arises from their potential to serve as an alternative to confidential real-world records and to augment rare events in historical datasets. These enhanced datasets can then be used to train machine learning models that predict critical events, such as flight delays, cancellations, diversions, and turnaround times. Two generative models, Tabular Variational Autoencoder (TVAE) and Gaussian Copula (GC), are adapted to generate synthetic flight information and compared based on their ability to preserve statistical similarity, fidelity, diversity, and predictive utility. Results indicate that while GC achieves higher statistical similarity and fidelity, its computational cost hinders its applicability to large datasets. In contrast, TVAE efficiently handles large datasets and enables scalable synthetic data generation. The findings demonstrate that synthetic data can support flight delay prediction models with accuracy comparable to those trained on real data. These results pave the way for leveraging synthetic flight data to enhance predictive modeling in air transportation.

---

### Efficient INT8 Single-Image Super-Resolution via Deployment-Aware Quantization and Teacher-Guided Training

Authors: Pham Phuong Nam Nguyen, Nam Tien Le, Thi Kim Trang Vo, Nhu Tinh Anh Nguyen
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20291v1

Efficient single-image super-resolution (SISR) requires balancing reconstruction fidelity, model compactness, and robustness under low-bit deployment, which is especially challenging for x3 SR. We present a deployment-oriented quantized SISR framework based on an extract-refine-upsample design. The student performs most computation in the low-resolution space and uses a lightweight re-parameterizable backbone with PixelShuffle reconstruction, yielding a compact inference graph. To improve quality without significantly increasing complexity, we adopt a three-stage training pipeline: Stage 1 learns a basic reconstruction mapping with spatial supervision; Stage 2 refines fidelity using Charbonnier loss, DCT-domain supervision, and confidence-weighted output-level distillation from a Mamba-based teacher; and Stage 3 applies quantization-aware training directly on the fused deploy graph. We further use weight clipping and BatchNorm recalibration to improve quantization stability. On the MAI 2026 Quantized 4K Image Super-Resolution Challenge test set, our final AIO MAI submission achieves 29.79 dB PSNR and 0.8634 SSIM, obtaining a final score of 1.8 under the target mobile INT8 deployment setting. Ablation on Stage 3 optimization shows that teacher-guided supervision improves the dynamic INT8 TFLite reconstruction from 29.91 dB/0.853 to 30.0003 dB/0.856, while the fixed-shape deployable INT8 TFLite artifact attains 30.006 dB/0.857.

---

### X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference

Authors: Yixiao Zeng, Jianlei Zheng, Chaoda Zheng, Shijia Chen, Mingdian Liu, Tongping Liu, Tengwei Luo, Yu Zhang, Boyang Wang, Linkun Xu, Siyuan Lu, Bo Tian et al.
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20289v2

Real-time world simulation is becoming a key infrastructure for scalable evaluation and online reinforcement learning of autonomous driving systems. Recent driving world models built on autoregressive video diffusion achieve high-fidelity, controllable multi-camera generation, but their inference cost remains a bottleneck for interactive deployment. However, existing diffusion caching methods are designed for offline video generation with multiple denoising steps, and do not transfer to this scenario. Few-step distilled models have no inter-step redundancy left for these methods to reuse, and sequence-level parallelization techniques require future conditioning that closed-loop interactive generation does not provide. We present X-Cache, a training-free acceleration method that caches along a different axis: across consecutive generation chunks rather than across denoising steps. X-Cache maintains per-block residual caches that persist across chunks, and applies a dual-metric gating mechanism over a structure- and action-aware block-input fingerprint to independently decide whether each block should recompute or reuse its cached residual. To prevent approximation errors from permanently contaminating the autoregressive KV cache, X-Cache identifies KV update chunks (the forward passes that write clean keys and values into the persistent cache) and unconditionally forces full computation on these chunks, cutting off error propagation. We implement X-Cache on X-world, a production multi-camera action-conditioned driving world model built on multi-block causal DiT with few-step denoising and rolling KV cache. X-Cache achieves 71% block skip rate with 2.6x wall-clock speedup while maintaining minimum degradation.

---

### Generative Augmentation of Imbalanced Flight Records for Flight Diversion Prediction: A Multi-objective Optimisation Framework

Authors: Karim Aly, Alexei Sharpanskykh, Jacco Hoekstra
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.20288v2

Flight diversions are rare but high-impact events in aviation, making their reliable prediction vital for both safety and operational efficiency. However, their scarcity in historical records impedes the training of machine learning models used to predict them. This study addresses this challenge by proposing a generative augmentation framework for imbalanced aviation tabular records. The principal contribution lies in the design of a composite optimisation objective specifically tailored to flight data, which integrates four complementary quality dimensions into a single score used to guide automated hyperparameter search via the Tree-structured Parzen Estimator (TPE) algorithm: realism, statistical similarity, fidelity, and predictive utility. These dimensions were selected and defined to reflect the operational and statistical requirements specific to aviation records, and were complemented by two descriptive evaluation dimensions, diversity and operational validity, forming a six-stage assessment framework. The composite objective was then used to tune three deep generative models, namely Tabular Variational Autoencoder (TVAE), Conditional Tabular Generative Adversarial Network (CTGAN), and CopulaGAN, with Gaussian Copula (GC) serving as a statistical baseline. Results show that optimised models substantially outperform their default counterparts across all six assessment dimensions, and that augmentation with the resulting synthetic data improves diversion prediction compared to training on real data alone. These findings demonstrate that domain-adapted multi-objective optimisation is an effective strategy for generative augmentation of rare events in aviation, with applicability to other imbalanced tabular prediction tasks.

---

### MambaLiteUNet: Cross-Gated Adaptive Feature Fusion for Robust Skin Lesion Segmentation

Authors: Md Maklachur Rahman, Soon Ki Jung, Tracy Hammond
Published: 2026-04-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.20286v1

Recent segmentation models have demonstrated promising efficiency by aggressively reducing parameter counts and computational complexity. However, these models often struggle to accurately delineate fine lesion boundaries and texture patterns essential for early skin cancer diagnosis and treatment planning. In this paper, we propose MambaLiteUNet, a compact yet robust segmentation framework that integrates Mamba state space modeling into a U-Net architecture, along with three key modules: Adaptive Multi-Branch Mamba Feature Fusion (AMF), Local-Global Feature Mixing (LGFM), and Cross-Gated Attention (CGA). These modules are designed to enhance local-global feature interaction, preserve spatial details, and improve the quality of skip connections. MambaLiteUNet achieves an average IoU of 87.12% and average Dice score of 93.09% across ISIC2017, ISIC2018, HAM10000, and PH2 benchmarks, outperforming state-of-the-art models. Compared to U-Net, our model improves average IoU and Dice by 7.72 and 4.61 points, respectively, while reducing parameters by 93.6% and GFLOPs by 97.6%. Additionally, in domain generalization with six unseen lesion categories, MambaLiteUNet achieves 77.61% IoU and 87.23% Dice, performing best among all evaluated models. Our extensive experiments demonstrate that MambaLiteUNet achieves a strong balance between accuracy and efficiency, making it a competitive and practical solution for dermatological image segmentation. Our code is publicly available at: https://github.com/maklachur/MambaLiteUNet.

---