# Research Papers — 2026-04 · bundle page 142 of 233

> Full-text markdown of papers #7051–7100 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/142
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/141.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/143.md)

### DBGL: Decay-aware Bipartite Graph Learning for Irregular Medical Time Series Classification

Authors: Jian Chen, Yuzhu Hu, Xiaoyan Yuan, Yuxuan Hu, Jinfeng Xu, Yipeng Du, Wenhao Yuan, Wei Wang, Edith C. H. Ngai
Published: 2026-04-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.11842v1

Irregular Medical Time Series play a critical role in the clinical domain to better understand the patient's condition. However, inherent irregularity arising from heterogeneous sampling rates, asynchronous observations, and variable gaps poses key challenges for reliable modeling. Existing methods often distort temporal sampling irregularity and missingness patterns while failing to capture variable decay irregularity, resulting in suboptimal representations. To address these limitations, we introduce DBGL, Decay-Aware Bipartite Graph Learning for Irregular Medical Time Series. DBGL first introduces a patient-variable bipartite graph that simultaneously captures irregular sampling patterns without artificial alignment and adaptively models variable relationships for temporal sampling irregularity modeling, enhancing representation learning. To model variable decay irregularity, DBGL designs a novel node-specific temporal decay encoding mechanism that captures each variable's decay rates based on sampling interval, yielding a more accurate and faithful representation of irregular temporal dynamics. We evaluate the performance of DBGL on four publicly available datasets, and the results show that DBGL outperforms all baselines.

---

### Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions

Authors: Wenhao Zhang, Lin Mu, Li Ni, Peiquan Jin, Yiwen Zhang
Published: 2026-04-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.11841v1

Low-rank adaptation (LoRA) is a widely used strategy for efficient fine-tuning of large language models (LLMs), but its strictly linear structure fundamentally limits expressive capacity. The bilinear formulation of weight updates captures only first-order dependencies between low-rank factors, restricting the modeling of nonlinear and higher-order parameter interactions. In this paper, we propose Polynomial Expansion Rank Adaptation (PERA), a novel method that introduces structured polynomial expansion directly into the low-rank factor space. By expanding each low-rank factor to synthesize high-order interaction terms before composition, PERA transforms the adaptation space into a polynomial manifold capable of modeling richer nonlinear coupling without increasing rank or inference cost. We provide theoretical analysis demonstrating that PERA offers enhanced expressive capacity and more effective feature utilization compare to existing linear adaptation approaches. Empirically, PERA consistently outperforms state-of-the-art methods across diverse benchmarks. Notably, our experiments show that incorporating high-order nonlinear components particularly square terms is crucial for enhancing expressive capacity and maintaining strong and robust performance under various rank settings. Our code is available at https://github.com/zhangwenhao6/PERA

---

### Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Simulation

Authors: Sandro Andric
Published: 2026-04-12
Categories: cs.LG, cs.AI, cs.CY, cs.MA
arXiv: https://arxiv.org/abs/2604.11840v3

Language models are increasingly used to simulate people: survey respondents, negotiators, stakeholders in policy exercises. In that role a model should reproduce how people plausibly behave, hesitating, conceding late, and settling for imperfect deals, rather than playing the best move. We call this the sampler role, in contrast to the solver role of finding the best move, and we test how the reasoning modes providers ship to strengthen models as solvers affect it. Our testbed is multi-party negotiation: five agents bargain over a regulation for fifteen turns, and unresolved issues are decided by an authority. Agents without a structured memory of the negotiation almost never reach agreement, whether reasoning is on or off: 314 of 315 such runs end with the authority deciding. What reasoning changes is how the failure looks. With reasoning enabled, one model family negotiates visibly, with varied moves, concessions in most runs, and a different path every time, yet still ends without agreement in fifteen runs of fifteen. Diversity checks would pass a model whose endings never change. Two further results show the task permits agreement: when agents write their own short running notes on the negotiation, agreement becomes the norm, while the same notes supplied ready-made change nothing; and hand-coded agents following textbook concession strategies agree in most runs under identical rules. Simulation pipelines should therefore vet models as samplers, on the distributions of outcomes they produce. Fidelity as a sampler must be tested on its own: solver strength is no guide to it, and switching on reasoning leaves it where it was.

---

### Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents

Authors: Bronislav Sidik, Lior Rokach
Published: 2026-04-12
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2604.11839v2

Autonomous AI agents built on open-source runtimes such as OpenClaw expose every available tool to every session by default, regardless of the task. A summarization task receives the same shell execution, subagent spawning, and credential access capabilities as a code deployment task, a 15x overprovision ratio that we call the capability overprovisioning problem. Existing defenses, including the NemoClaw container sandbox and the Cisco DefenseClaw skill scanner, address containment and threat detection but do not learn the minimum viable capability set for each task type. We present Aethelgard, a four layer adaptive governance framework that enforces least privilege for AI agents through a learned policy. Layer 1, the Capability Governor, dynamically scopes which tools the agent is aware of in each session. Layer 3, the Safety Router, intercepts tool calls before execution using a hybrid rule based and fine tuned classifier. Layer 2, the RL Learning Policy, trains a PPO policy on the accumulated audit log to learn the minimum viable skill set for each task type.

---

### A Layer-wise Analysis of Supervised Fine-Tuning

Authors: Qinghua Zhao, Xueling Gong, Xinyu Chen, Zhongfeng Kang, Xinlu Li
Published: 2026-04-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.11838v2

While critical for alignment, Supervised Fine-Tuning (SFT) incurs the risk of catastrophic forgetting, yet the layer-wise emergence of instruction-following capabilities remains elusive. We investigate this mechanism via a comprehensive analysis utilizing information-theoretic, geometric, and optimization metrics across model scales (1B-32B). Our experiments reveal a distinct depth-dependent pattern: middle layers (20\%-80\%) are stable, whereas final layers exhibit high sensitivity. Leveraging this insight, we propose Mid-Block Efficient Tuning, which selectively updates these critical intermediate layers. Empirically, our method outperforms standard LoRA up to 10.2\% on GSM8K (OLMo2-7B) with reduced parameter overhead, demonstrating that effective alignment is architecturally localized rather than distributed. The code is publicly available at https://anonymous.4open.science/r/base_sft.

---

### A Layer-wise Analysis of Supervised Fine-Tuning

Authors: Qinghua Zhao, Xueling Gong, Xinyu Chen, Zhongfeng Kang, Xinlu Li
Published: 2026-04-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.11838v1

While critical for alignment, Supervised Fine-Tuning (SFT) incurs the risk of catastrophic forgetting, yet the layer-wise emergence of instruction-following capabilities remains elusive. We investigate this mechanism via a comprehensive analysis utilizing information-theoretic, geometric, and optimization metrics across model scales (1B-32B). Our experiments reveal a distinct depth-dependent pattern: middle layers (20\%-80\%) are stable, whereas final layers exhibit high sensitivity. Leveraging this insight, we propose Mid-Block Efficient Tuning, which selectively updates these critical intermediate layers. Empirically, our method outperforms standard LoRA up to 10.2\% on GSM8K (OLMo2-7B) with reduced parameter overhead, demonstrating that effective alignment is architecturally localized rather than distributed. The code is publicly available at https://anonymous.4open.science/r/base_sft.

---

### Schema-Adaptive Tabular Representation Learning with LLMs for Generalizable Multimodal Clinical Reasoning

Authors: Hongxi Mao, Wei Zhou, Mengting Jia, Tao Fang, Huan Gao, Bin Zhang, Shangyang Li
Published: 2026-04-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.11835v2

Machine learning for tabular data remains constrained by poor schema generalization, a challenge rooted in the lack of semantic understanding of structured variables. This challenge is particularly acute in domains like clinical medicine, where electronic health record (EHR) schemas vary significantly. To solve this problem, we propose Schema-Adaptive Tabular Representation Learning, a novel method that leverages large language models (LLMs) to create transferable tabular embeddings. By transforming structured variables into semantic natural language statements and encoding them with a pretrained LLM, our approach enables zero-shot alignment across unseen schemas without manual feature engineering or retraining. We integrate our encoder into a multimodal framework for dementia diagnosis, combining tabular and MRI data. Experiments on NACC and ADNI datasets demonstrate state-of-the-art performance and successful zero-shot transfer to unseen schemas, significantly outperforming clinical baselines, including board-certified neurologists, in retrospective diagnostic tasks. These results validate our LLM-driven approach as a scalable, robust solution for heterogeneous real-world data, offering a pathway to extend LLM-based reasoning to structured domains.

---

### Training single-electron and single-photon stochastic physical neural networks

Authors: Tong Dou, Shiro Kumara, Josh Burns, Ethan Sigler, Parth Girdhar, David Petty, Gerard Milburn, Jo Plested, Matt Woolley
Published: 2026-04-12
Categories: quant-ph, cond-mat.dis-nn, cs.ET, cs.LG
arXiv: https://arxiv.org/abs/2604.10861v1

The computational demands of deep learning motivate the investigation of alternative approaches to computation. One alternative is physical neural networks~(PNNs), in which learning and inference are performed directly via physical processes. Stochastic PNNs arise when the underlying neurons are realized by the dynamics of a stochastic activation switch. Here we propose novel electronic and photonic stochastic neurons. The electronic realization is implemented by single-electron tunneling through a quantum dot. The photonic realization is implemented via a single-photon source driving one of two modes coupled via a controllable beam-splitter-like interaction. In the electronic case, the charge state of the quantum dot forms the basis for the stochastic neuron, whereas in the photonic case the occupation of the undriven mode serves as the basis for the stochastic neuron. Training of stochastic PNNs is performed with models of stochastic neurons, as well as with coherently-driven, single-photon detector stochastic neurons previously introduced. Several training strategies for MNIST handwritten digit classification have been investigated using single-hidden-layer stochastic PNNs, including varying the number of trials in each layer to control forward pass stochasticity and employing either true probability or empirical outputs in the backward pass to evaluate their influence on gradient estimation. We show that when empirical outputs are used in the backward pass, the network achieves more than 97\% test accuracy with few trials per layer. Despite the simplicity of the model architecture, high test accuracy is maintained in the presence of a high degree of noise and model uncertainty. The results demonstrate the potential of embracing stochastic PNNs for deep learning.

---

### Query Lower Bounds for Diffusion Sampling

Authors: Zhiyang Xun, Eric Price
Published: 2026-04-12
Categories: cs.LG, cs.AI, cs.DS, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2604.10857v2

Diffusion models generate samples by iteratively querying learned score estimates. A rapidly growing literature focuses on accelerating sampling by minimizing the number of score evaluations, yet the information-theoretic limits of such acceleration remain unclear. In this work, we establish the first score query lower bounds for diffusion sampling. We prove that for $d$-dimensional distributions, given access to score estimates with polynomial accuracy $\varepsilon=d^{-O(1)}$ (in any $L^p$ sense), any sampling algorithm requires $\widetildeΩ(\sqrt{d})$ adaptive score queries. In particular, our proof shows that, within any polynomial total-query budget, successful sampling requires searching over $\widetildeΩ(\sqrt{d})$ distinct noise levels, providing a formal explanation for why multiscale noise schedules are necessary in practice.

---

### Query Lower Bounds for Diffusion Sampling

Authors: Zhiyang Xun, Eric Price
Published: 2026-04-12
Categories: cs.LG, cs.AI, cs.DS, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2604.10857v1

Diffusion models generate samples by iteratively querying learned score estimates. A rapidly growing literature focuses on accelerating sampling by minimizing the number of score evaluations, yet the information-theoretic limits of such acceleration remain unclear. In this work, we establish the first score query lower bounds for diffusion sampling. We prove that for $d$-dimensional distributions, given access to score estimates with polynomial accuracy $\varepsilon=d^{-O(1)}$ (in any $L^p$ sense), any sampling algorithm requires $\widetildeΩ(\sqrt{d})$ adaptive score queries. In particular, our proof shows that any sampler must search over $\widetildeΩ(\sqrt{d})$ distinct noise levels, providing a formal explanation for why multiscale noise schedules are necessary in practice.

---

### BridgeSim: Unveiling the OL-CL Gap in End-to-End Autonomous Driving

Authors: Seth Z. Zhao, Luobin Wang, Hongwei Ruan, Yuxin Bao, Yilan Chen, Ziyang Leng, Abhijit Ravichandran, Honglin He, Zewei Zhou, Xu Han, Abhishek Peri, Zhiyu Huang et al.
Published: 2026-04-12
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2604.10856v1

Open-loop (OL) to closed-loop (CL) gap (OL-CL gap) exists when OL-pretrained policies scoring high in OL evaluations fail to transfer effectively in closed-loop (CL) deployment. In this paper, we unveil the root causes of this systemic failure and propose a practical remedy. Specifically, we demonstrate that OL policies suffer from Observational Domain Shift and Objective Mismatch. We show that while the former is largely recoverable with adaptation techniques, the latter creates a structural inability to model complex reactive behaviors, which forms the primary OL-CL gap. We find that a wide range of OL policies learn a biased Q-value estimator that neglects both the reactive nature of CL simulations and the temporal awareness needed to reduce compounding errors. To this end, we propose a Test-Time Adaptation (TTA) framework that calibrates observational shift, reduces state-action biases, and enforces temporal consistency. Extensive experiments show that TTA effectively mitigates planning biases and yields superior scaling dynamics than its baseline counterparts. Furthermore, our analysis highlights the existence of blind spots in standard OL evaluation protocols that fail to capture the realities of closed-loop deployment.

---

### Uncertainty-Aware Sparse Identification of Dynamical Systems via Bayesian Model Averaging

Authors: Shuhei Kashiwamura, Yusuke Kato, Hiroshi Kori, Masato Okada
Published: 2026-04-12
Categories: stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2604.10854v1

In many problems of data-driven modeling for dynamical systems, the governing equations are not known a priori and must be selected phenomenologically from a large set of candidate interactions and basis functions. In such situations, point estimates alone can be misleading, because multiple model components may explain the observed data comparably well, especially when the data are limited or the dynamics exhibit poor identifiability. Quantifying the uncertainty associated with model selection is therefore essential for constructing reliable dynamical models from data. In this work, we develop a Bayesian sparse identification framework for dynamical systems with coupled components, aimed at inferring both interaction structure and functional form together with principled uncertainty quantification. The proposed method combines sparse modeling with Bayesian model averaging, yielding posterior inclusion probabilities that quantify the credibility of each candidate interaction and basis component. Through numerical experiments on oscillator networks, we show that the framework accurately recovers sparse interaction structures with quantified uncertainty, including higher-order harmonic components, phase-lag effects, and multi-body interactions. We also demonstrate that, even in a phenomenological setting where the true governing equations are not contained in the assumed model class, the method can identify effective functional components with quantified uncertainty. These results highlight the importance of Bayesian uncertainty quantification in data-driven discovery of dynamical models.

---

### A Benchmark for Gap and Overlap Analysis as a Test of KG Task Readiness

Authors: Maruf Ahmed Mridul, Rohit Kapa, Oshani Seneviratne
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10853v1

Task-oriented evaluation of knowledge graph (KG) quality increasingly asks whether an ontology-based representation can answer the competency questions that users actually care about, in a manner that is reproducible, explainable, and traceable to evidence. This paper adopts that perspective and focuses on gap and overlap analysis for policy-like documents (e.g., insurance contracts), where given a scenario, which documents support it (overlap) and which do not (gap), with defensible justifications. The resulting gap/overlap determinations are typically driven by genuine differences in coverage and restrictions rather than missing data, making the task a direct test of KG task readiness rather than a test of missing facts or query expressiveness. We present an executable and auditable benchmark that aligns natural-language contract text with a formal ontology and evidence-linked ground truth, enabling systematic comparison of methods. The benchmark includes: (i) ten simplified yet diverse life-insurance contracts reviewed by a domain expert, (ii) a domain ontology (TBox) with an instantiated knowledge base (ABox) populated from contract facts, and (iii) 58 structured scenarios paired with SPARQL queries with contract-level outcomes and clause-level excerpts that justify each label. Using this resource, we compare a text-only LLM baseline that infers outcomes directly from contract text against an ontology-driven pipeline that answers the same scenarios over the instantiated KG, demonstrating that explicit modeling improves consistency and diagnosis for gap/overlap analyses. Although demonstrated for gap and overlap analysis, the benchmark is intended as a reusable template for evaluating KG quality and supporting downstream work such as ontology learning, KG population, and evidence-grounded question answering.

---

### Task2vec Readiness: Diagnostics for Federated Learning from Pre-Training Embeddings

Authors: Cristiano Mafuz, Rodrigo Silva
Published: 2026-04-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.10849v1

Federated learning (FL) performance is highly sensitive to heterogeneity across clients, yet practitioners lack reliable methods to anticipate how a federation will behave before training. We propose readiness indices, derived from Task2Vec embeddings, that quantifies the alignment of a federation prior to training and correlates with its eventual performance. Our approach computes unsupervised metrics -- such as cohesion, dispersion, and density -- directly from client embeddings. We evaluate these indices across diverse datasets (CIFAR-10, FEMNIST, PathMNIST, BloodMNIST) and client counts (10--20), under Dirichlet heterogeneity levels spanning $α\in \{0.05,\dots,5.0\}$ and FedAVG aggregation strategy. Correlation analyses show consistent and significant Pearson and Spearman coefficients between some of the Task2Vec-based readiness and final performance, with values often exceeding 0.9 across dataset$\times$client configurations, validating this approach as a robust proxy for FL outcomes. These findings establish Task2Vec-based readiness as a principled, pre-training diagnostic for FL that may offer both predictive insight and actionable guidance for client selection in heterogeneous federations.

---

### Transformers Learn Latent Mixture Models In-Context via Mirror Descent

Authors: Francesco D'Angelo, Nicolas Flammarion
Published: 2026-04-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.10848v1

Sequence modelling requires determining which past tokens are causally relevant from the context and their importance: a process inherent to the attention layers in transformers, yet whose underlying learned mechanisms remain poorly understood. In this work, we formalize the task of estimating token importance as an in-context learning problem by introducing a framework based on Mixture of Transition Distributions, where a latent variable determines the influence of past tokens on the next. The distribution over this latent variable is parameterized by unobserved mixture weights that transformers must learn in-context. We demonstrate that transformers can implement Mirror Descent to learn these weights from the context. Specifically, we give an explicit construction of a three-layer transformer that exactly implements one step of Mirror Descent and prove that the resulting estimator is a first-order approximation of the Bayes-optimal predictor. Corroborating our construction and its learnability via gradient descent, we empirically show that transformers trained from scratch learn solutions consistent with our theory: their predictive distributions, attention patterns, and learned transition matrix closely match the construction, while deeper models achieve performance comparable to multi-step Mirror Descent.

---

### Retinal Cyst Detection from Optical Coherence Tomography Images

Authors: Abhishek Dharmaratnakar, Aadheeshwar Vijayakumar, Suchand Dayanand
Published: 2026-04-12
Categories: cs.CV, cs.AI, cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2604.10843v1

Retinal Cysts are formed by leakage and accumulation of fluid in the retina due to the incompetence of retinal vasculature. These cystic spaces have significance in several ocular diseases such as age-related macular degeneration, diabetic macular edema, etc. Optical coherence tomography is one of the predominant diagnosing techniques for imaging retinal pathologies. Segmenting and quantification of intraretinal cysts plays the vital role in predicting visual acuity. In literature, several methods have been proposed for automatic segmentation of intraretinal cysts. As cystoid macular edema becomes a major problem to humankind, we need to quantify it accurately and operate it out, else it might cause many problems later on. Though research is being carried out in this area, not much of progress has been made and accuracy achieved so far is 68\% which is very less. Also, the methods depend on the quality of the image and give very low results for high noise images like topcon. This work uses ResNet CNN (Convolutional Neural Network) approach of segmentation by the way of patchwise classification for training on image set from cyst segmentation challenge dataset and testing on test data set given by 2 different graders for all 4 vendors in the challenge. It also compares these methods using first publicly available novel cyst segmentation challenge dataset. The methods were evaluated using quantitative measures to assess their robustness against the challenges of intraretinal cyst segmentation. The results are found to be better than the previous state of the art approaches giving more than 70\% dice coefficient on all vendors irrespective of their quality.

---

### Resilient Write: A Six-Layer Durable Write Surface for LLM Coding Agents

Authors: Justice Owusu Agyemang, Jerry John Kponyo, Elliot Amponsah, Godfred Manu Addo Boakye, Kwame Opuni-Boachie Obour Agyekum
Published: 2026-04-12
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2604.10842v3

LLM-powered coding agents increasingly rely on tool-use protocols such as the Model Context Protocol (MCP) to read and write files on a developer's workstation. When a write fails - due to content filters, truncation, or an interrupted session - the agent typically receives no structured signal, loses the draft, and wastes tokens retrying blindly. We present Resilient Write, an MCP server that interposes a six-layer durable write surface between the agent and the filesystem. The layers - pre-flight risk scoring, transactional atomic writes, resume-safe chunking, structured typed errors, out-of-band scratchpad storage, and task-continuity handoff envelopes - are orthogonal and independently adoptable. Each layer maps to a concrete failure mode observed during a real agent session in April 2026, in which content-safety filters silently rejected a draft containing redacted API-key prefixes. Three additional tools - chunk preview, format-aware validation, and journal analytics - emerged from using the system to compose this paper. A 186-test suite validates correctness at each layer, and quantitative comparison against naive and defensive baselines shows a 5x reduction in recovery time and a 13x improvement in agent self-correction rate. Resilient Write is open-source under the MIT license.

---

### Harnessing Photonics for Machine Intelligence

Authors: Hanqing Zhu, Shupeng Ning, Hongjian Zhou, Ziang Yin, Ray T. Chen, Jiaqi Gu, David Z. Pan
Published: 2026-04-12
Categories: physics.optics, cs.AI, cs.AR, cs.ET, cs.LG
arXiv: https://arxiv.org/abs/2604.10841v1

The exponential growth of machine-intelligence workloads is colliding with the power, memory, and interconnect limits of the post-Moore era, motivating compute substrates that scale beyond transistor density alone. Integrated photonics is emerging as a candidate for artificial intelligence (AI) acceleration by exploiting optical bandwidth and parallelism to reshape data movement and computation. This review reframes photonic computing from a circuits-and-systems perspective, moving beyond building-block progress toward cross-layer system analysis and full-stack design automation. We synthesize recent advances through a bottleneck-driven taxonomy that delineates the operating regimes and scaling trends where photonics can deliver end-to-end sustained benefits. A central theme is cross-layer co-design and workload-adaptive programmability to sustain high efficiency and versatility across evolving application domains at scale. We further argue that Electronic-Photonic Design Automation (EPDA) will be pivotal, enabling closed-loop co-optimization across simulation, inverse design, system modeling, and physical implementation. By charting a roadmap from laboratory prototypes to scalable, reproducible electronic-photonic ecosystems, this review aims to guide the CAS community toward an automated, system-centric era of photonic machine intelligence.

---

### Immune2V: Image Immunization Against Dual-Stream Image-to-Video Generation

Authors: Zeqian Long, Ozgur Kara, Haotian Xue, Yongxin Chen, James M. Rehg
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10837v1

Image-to-video (I2V) generation has the potential for societal harm because it enables the unauthorized animation of static images to create realistic deepfakes. While existing defenses effectively protect against static image manipulation, extending these to I2V generation remains underexplored and non-trivial. In this paper, we systematically analyze why modern I2V models are highly robust against naive image-level adversarial attacks (i.e., immunization). We observe that the video encoding process rapidly dilutes the adversarial noise across future frames, and the continuous text-conditioned guidance actively overrides the intended disruptive effect of the immunization. Building on these findings, we propose the Immune2V framework which enforces temporally balanced latent divergence at the encoder level to prevent signal dilution, and aligns intermediate generative representations with a precomputed collapse-inducing trajectory to counteract the text-guidance override. Extensive experiments demonstrate that Immune2V produces substantially stronger and more persistent degradation than adapted image-level baselines under the same imperceptibility budget.

---

### HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching

Authors: Zerui Chen, Rolandos Alexandros Potamias, Shizhe Chen, Jiankang Deng, Cordelia Schmid, Stefanos Zafeiriou
Published: 2026-04-12
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2604.10836v1

Generating realistic 3D hand-object interactions (HOI) is a fundamental challenge in computer vision and robotics, requiring both temporal coherence and high-fidelity physical plausibility. Existing methods remain limited in their ability to learn expressive motion representations for generation and perform temporal reasoning. In this paper, we present HO-Flow, a framework for synthesizing realistic hand-object motion sequences from texts and canoncial 3D objects. HO-Flow first employs an interaction-aware variational autoencoder to encode sequences of hand and object motions into a unified latent manifold by incorporating hand and object kinematics, enabling the representation to capture rich interaction dynamics. It then leverages a masked flow matching model that combines auto-regressive temporal reasoning with continuous latent generation, improving temporal coherence. To further enhance generalization, HO-Flow predicts object motions relative to the initial frame, enabling effective pre-training on large-scale synthetic data. Experiments on the GRAB, OakInk, and DexYCB benchmarks demonstrate that HO-Flow achieves state-of-the-art performance in both physical plausibility and motion diversity for interaction motion synthesis.

---

### LLMs for Qualitative Data Analysis Fail on Security-specificComments in Human Experiments

Authors: Maria Camporese, Fabio Massacci, Yuanjun Gong
Published: 2026-04-12
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2604.10834v1

(Background:) Thematic analysis of free-text justifications in human experiments provides significant qualitative insights. Yet, it is costly because reliable annotations require multiple domain experts. Large language models (LLMs) seem ideal candidates to replace human annotators. (Problem:) Coding security-specific aspects (code identifiers mentioned, lines-of-code mentioned, security keywords mentioned) may require deeper contextual understanding than sentiment classification. (Objective:) Explore whether LLMs can act as automated annotators for technical security comments by human subjects. (Method:) We prompt four top-performing LLMs on LiveBench to detect nine security-relevant codes in free-text comments by human subjects analyzing vulnerable code snippets. Outputs are compared to human annotators using Cohen's Kappa (chance-corrected accuracy). We test different prompts mimicking annotation best practices, including emerging codes, detailed codebooks with examples, and conflicting examples. (Negative Results:) We observed marked improvements only when using detailed code descriptions; however, these improvements are not uniform across codes and are insufficient to reliably replace a human annotator. (Limitations:) Additional studies with more LLMs and annotation tasks are needed.

---

### Speaking to No One: Ontological Dissonance and the Double Bind of Conversational AI

Authors: Hugh Brosnahan, Izabela Lipinska
Published: 2026-04-12
Categories: cs.HC, cs.AI, cs.CL, cs.CY, cs.ET
arXiv: https://arxiv.org/abs/2604.10833v1

Recent reports indicate that sustained interaction with conversational artificial intelligence (AI) systems can, in a small subset of users, contribute to the emergence or stabilisation of delusional experience. Existing accounts typically attribute such cases either to individual vulnerability or to failures of safety engineering. These explanations are incomplete. Drawing on phenomenology, psychiatry, and cognitive neuroscience, this paper argues that the risk arises from the relational and ontological structure of the interaction itself. Conversational AI generates ontological dissonance: a conflict between the appearance of relational presence and the absence of any subject capable of sustaining it. Maintained through a communicative double bind and amplified by attentional asymmetries, this dissonance tends, under conditions of affective vulnerability, to stabilise into a technologically mediated analogue of folie a deux. This account explains why explicit disclaimers often fail to disrupt delusional involvement and clarifies the ethical and clinical implications for the design and use of conversational AI.

---

### Know Thy Reasoner: Not All Language Models Explore Alike

Authors: Moulik Choraria, Argyrios Gerogiannis, Anirban Das, Supriyo Chakraborty, Sourya Basu, Sambit Sahu, Lav R. Varshney
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10827v2

Compute scaling for LLM reasoning trades off exploring solution approaches (\emph{breadth}) against refining promising ones (\emph{depth}), yet why a given trade-off works, and why it often fails to transfer across models, remains unclear. We argue that \textbf{the optimal strategy depends on the model's \emph{diversity profile}, the spread of probability mass across solution approaches, and that this must be characterized before any exploration strategy is adopted.} We formalize this with a framework decomposing reasoning uncertainty, deriving when depth-based refinement outperforms parallel sampling, and validate it across three model families at both inference and training. Our central finding is that the diversity regime dictates the strategy: low-diversity aligned models benefit from depth-based refinement with lightweight intrinsic signals, whereas high-diversity base models are often harmed by it, and instead need breadth or stronger signals to compensate.

---

### CheeseBench: Evaluating Large Language Models on Rodent Behavioral Neuroscience Paradigms

Authors: Zacharie Bugaud
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10825v2

We introduce CheeseBench, a benchmark that evaluates large language models (LLMs) on nine classical behavioral neuroscience paradigms (Morris water maze, Barnes maze, T-maze, radial arm maze, star maze, operant chamber, shuttle box, conditioned place preference, and delayed non-match to sample), spanning six cognitive dimensions. Each task is grounded in peer-reviewed rodent protocols with approximate animal baselines. The agent receives a unified system prompt with no task-specific instructions and must discover goals purely from ASCII text observations and reward signals, much like a rodent placed into an unfamiliar apparatus. We evaluate six open-weight LLMs (3B to 72B parameters) on text-based ASCII renderings and compare against both a random baseline and a graph-based reinforcement learning agent. Our best model (Qwen2.5-VL-7B) reaches 52.6% average success on ASCII input, compared to 32.1% for random agents and 78.9% for approximate rodent baselines. We find that (1) scaling beyond 7B yields diminishing returns, (2) longer context history degrades performance, (3) chain-of-thought prompting hurts rather than helps, and (4) a vision-language architecture provides an advantage at 7B but hurts at 32B. Because the same model's performance ranges from 20% to 57% depending on interface parameters alone, these results characterize the agent-plus-interface system, not the model in isolation. Under this unified zero-shot ASCII protocol, current open-weight LLM agents remain well below approximate rodent reference values, particularly on tasks requiring spatial navigation and within-trial state tracking.

---

### Uncertainty-Guided Attention and Entropy-Weighted Loss for Precise Plant Seedling Segmentation

Authors: Mohamed Ehab, Ali Hamdi
Published: 2026-04-12
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2604.10823v1

Plant seedling segmentation supports automated phenotyping in precision agriculture. Standard segmentation models face difficulties due to intricate background images and fine structures in leaves. We introduce UGDA-Net (Uncertainty-Guided Dual Attention Network with Entropy-Weighted Loss and Deep Supervision). Three novel components make up UGDA-Net. The first component is Uncertainty-Guided Dual Attention (UGDA). UGDA uses channel variance to modulate feature maps. The second component is an entropy-weighted hybrid loss function. This loss function focuses on high-uncertainty boundary pixels. The third component employs deep supervision for intermediate encoder layers. We performed a comprehensive systematic ablation study. This study focuses on two widely-used architectures, U-Net and LinkNet. It analyzes five incremental configurations: Baseline, Loss-only, Attention-only, Deep Supervision, and UGDA-Net. We trained UGDA-net using a high-resolution plant seedling image dataset containing 432 images. We demonstrate improved segmentation performance and accuracy. With an increase in Dice coefficient of 9.3% above baseline. LinkNet's variance is 13.2% above baseline. Overlays that are qualitative in nature show the reduced false positives at the leaf boundary. Uncertainty heatmaps are consistent with the complex morphology. UGDA-Net aids in the segmentation of delicate structures in plants and provides a high-def solution. The results showed that uncertainty-guided attention and uncertainty-weighted loss are two complementing systems.

---

### Slithering Through Gaps: Capturing Discrete Isolated Modes via Logistic Bridging

Authors: Pinaki Mohanty, Ruqi Zhang
Published: 2026-04-12
Categories: cs.LG, stat.CO, stat.ML
arXiv: https://arxiv.org/abs/2604.10821v1

High-dimensional and complex discrete distributions often exhibit multimodal behavior due to inherent discontinuities, posing significant challenges for sampling. Gradient-based discrete samplers, while effective, frequently become trapped in local modes when confronted with rugged or disconnected energy landscapes. This limits their ability to achieve adequate mixing and convergence in high-dimensional multimodal discrete spaces. To address these challenges, we propose \emph{Hyperbolic Secant-squared Gibbs-Sampling (HiSS)}, a novel family of sampling algorithms that integrates a \emph{Metropolis-within-Gibbs} framework to enhance mixing efficiency. HiSS leverages a logistic convolution kernel to couple the discrete sampling variable with the continuous auxiliary variable in a joint distribution. This design allows the auxiliary variable to encapsulate the true target distribution while facilitating easy transitions between distant and disconnected modes. We provide theoretical guarantees of convergence and demonstrate empirically that HiSS outperforms many popular alternatives on a wide variety of tasks, including Ising models, binary neural networks, and combinatorial optimization.

---

### Differentially Private Verification of Distribution Properties

Authors: Elbert Du, Cynthia Dwork, Pranay Tankala, Linjun Zhang
Published: 2026-04-12
Categories: cs.DS, cs.CC, cs.LG
arXiv: https://arxiv.org/abs/2604.10819v2

A recent line of work initiated by Chiesa and Gur and further developed by Herman and Rothblum investigates the sample and communication complexity of verifying properties of distributions with the assistance of a powerful, knowledgeable, but untrusted prover. In this work, we initiate the study of differentially private distribution property verification. After all, if we do not trust the prover to help us with verification, why should we trust it with our sensitive sample? We map a landscape of differentially private verification of properties of distributions. In the non-private case it is known that one-round private-coin protocols can have substantially lower complexity than public-coin (AM) protocols. In contrast, the possibility for improvement in differentially private interactive proofs depends on the privacy parameter regime and model. Drawing on connections between privacy and replicability and privacy amplification techniques in the literature we show: 1. There exists a reduction from any one-round $(\varepsilon,δ)$-differentially private private-coin protocol to a differentially private AM protocol for the parameter regime $\varepsilon = O(1/\sqrt{s})$ and $δ= O(1/s^{5/2})$ with the same privacy and sample and communication complexities. In the local model, this is relaxed to $\varepsilon = O(1/\sqrt{\log s})$ 2. However, when the privacy guarantee is very relaxed ($\varepsilon \in Ω(\log s)$), private coins indeed reduce sample and communication complexities. We also obtain a computationally efficient Merlin-Arthur proof for privately testing whether samples are drawn from a product distribution and prove that its sample complexity is optimal up to a $polylog N$ factor by reducing uniformity testing to independence testing with Boolean attributes and appealing to known lower bounds on sample complexity for private uniformity testing.

---

### Differentially Private Verification of Distribution Properties

Authors: Elbert Du, Cynthia Dwork, Pranay Tankala, Linjun Zhang
Published: 2026-04-12
Categories: cs.DS, cs.CC, cs.LG
arXiv: https://arxiv.org/abs/2604.10819v1

A recent line of work initiated by Chiesa and Gur and further developed by Herman and Rothblum investigates the sample and communication complexity of verifying properties of distributions with the assistance of a powerful, knowledgeable, but untrusted prover. In this work, we initiate the study of differentially private (DP) distribution property testing. After all, if we do not trust the prover to help us with verification, why should we trust it with our sensitive sample? We map a landscape of DP prover-aided proofs of properties of distributions. In the non-private case it is known that one-round (two message) private-coin protocols can have substantially lower complexity than public-coin AM protocols, but in the private case, the possibility for improvement depends on the parameter regime and privacy model. Drawing on connections to replicability and techniques for amplification, we show: (1) There exists a reduction from any one-round $(\varepsilon,δ)$-DP private-coin interactive proof to a one-round public-coin DP interactive proof with the same privacy parameters, for the parameter regime $\varepsilon=O(1/\sqrt{n})$ and $δ=O(1/n^{5/2})$, and with the same sample and communication complexities. (2) If the verifier's message in the private-coin interactive proof is $O(1/\sqrt{\log n})$ locally DP -- a far more relaxed privacy parameter regime in a different model -- then applying one additional transformation again yields a one-round public-coin protocol with the same privacy bound and the same sample and computational complexities. (3) However, when the privacy guarantee is very relaxed ($\varepsilon\inΩ(\log n)$), private coins indeed reduce complexity. We also obtain a Merlin-Arthur (one-message) proof for privately testing whether samples are drawn from a product distribution, and prove that its sample complexity is optimal.

---

### MeloTune: On-Device Arousal Learning and Peer-to-Peer Mood Coupling for Proactive Music Curation

Authors: Hongwei Xu
Published: 2026-04-12
Categories: cs.SD, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2604.10815v2

MeloTune is an iPhone-deployed music agent that instantiates the Mesh Memory Protocol (MMP) and Symbolic-Vector Attention Fusion (SVAF) as a production system for affect-aware music curation with peer-to-peer mood coupling. Each device runs two closed-form continuous-time (CfC) networks: a private listener-level CfC that predicts a short-horizon affective trajectory on Russell's circumplex and drives proactive curation, and a shared mesh-runtime CfC at MMP Layer 6 that integrates Cognitive Memory Blocks (CMBs) from co-listening peers. CfC hidden states never cross the wire; only structured CMBs do. A Personal Arousal Function (PAF) replaces the standard linear mapping from audio intensity to psychological arousal with a per-listener learned adjustment, trained from behavioral signals (skip, completion, favorite, volume) and from drift between user-declared mood and machine inference. The same track receives different arousal predictions for different listeners. The model (94,552 parameters) achieves trajectory MAE 0.414, pattern accuracy 96.6%, and intent accuracy 69.4% on held-out validation. PAF evidence from a live deployment session (46 observations across 11 genres) demonstrates that the learning loop operates end-to-end, with pop reaching full confidence after 22 observations. All inference runs on-device via CoreML. To our knowledge, this is the first production deployment of MMP/SVAF on consumer mobile hardware. The accompanying SDK (sym-swift v0.3.78, SYMCore v0.3.7) enforces strict protocol conformance. Music is the case study; the substrate is the contribution.

---

### Online Covariance Estimation in Averaged SGD: Improved Batch-Mean Rates and Minimax Optimality via Trajectory Regression

Authors: Yijin Ni, Xiaoming Huo
Published: 2026-04-12
Categories: cs.LG, math.ST
arXiv: https://arxiv.org/abs/2604.10814v1

We study online covariance matrix estimation for Polyak--Ruppert averaged stochastic gradient descent (SGD). The online batch-means estimator of Zhu, Chen and Wu (2023) achieves an operator-norm convergence rate of $O(n^{-(1-α)/4})$, which yields $O(n^{-1/8})$ at the optimal learning-rate exponent $α\rightarrow 1/2^+$. A rigorous per-block bias analysis reveals that re-tuning the block-growth parameter improves the batch-means rate to $O(n^{-(1-α)/3})$, achieving $O(n^{-1/6})$. The modified estimator requires no Hessian access and preserves $O(d^2)$ memory. We provide a complete error decomposition into variance, stationarity bias, and nonlinearity bias components. A weighted-averaging variant that avoids hard truncation is also discussed. We establish the minimax rate $Θ(n^{-(1-α)/2})$ for Hessian-free covariance estimation from the SGD trajectory: a Le Cam lower bound gives $Ω(n^{-(1-α)/2})$, and a trajectory-regression estimator--which estimates the Hessian by regressing SGD increments on iterates--achieves $O(n^{-(1-α)/2})$, matching the lower bound. The construction reveals that the bottleneck is the sublinear accumulation of information about the Hessian from the SGD drift.

---

### PokeRL: Reinforcement Learning for Pokemon Red

Authors: Dheeraj Mudireddy, Sai Patibandla
Published: 2026-04-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.10812v1

Pokemon Red is a long-horizon JRPG with sparse rewards, partial observability, and quirky control mechanics that make it a challenging benchmark for reinforcement learning. While recent work has shown that PPO agents can clear the first two gyms using heavy reward shaping and engineered observations, training remains brittle in practice, with agents often degenerating into action loops, menu spam, or unproductive wandering. In this paper, we present PokeRL, a modular system that trains deep reinforcement learning agents to complete early game tasks in Pokemon Red, including exiting the player's house, exploring Pallet Town to reach tall grass, and winning the first rival battle. Our main contributions are a loop-aware environment wrapper around the PyBoy emulator with map masking, a multi-layer anti-loop and anti-spam mechanism, and a dense hierarchical reward design. We argue that practical systems like PokeRL, which explicitly model failure modes such as loops and spam, are a necessary intermediate step between toy benchmarks and full Pokemon League champion agents. Code is available at https://github.com/reddheeraj/PokemonRL

---

### Analytical Modeling and Correction of Distance Error in Homography-Based Ground-Plane Mapping

Authors: Mateusz Szulc, Marcin Iwanowski
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10805v2

Accurate distance estimation from monocular cameras is essential for intelligent monitoring systems. In many deployments, image coordinates are mapped to ground positions using planar homographies initialized by manual selection of corresponding regions. Small inaccuracies in this initialization propagate into systematic distance distortions. This paper derives an explicit relationship between homography perturbations and the resulting distance error, showing that the error grows approximately quadratically with the true distance from the camera. Based on this model, two simple correction strategies are evaluated: regression-based estimation of the quadratic error function and direct optimization of the homography via coordinate-based gradient descent. A large-scale simulation study with more than 19 million test samples demonstrates that regression achieves higher peak accuracy when the model is reliably fitted, whereas gradient descent provides greater robustness against poor initial calibration. This suggests that improving geometric calibration may yield greater performance gains than increasing model complexity in many practical systems.

---

### Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis

Authors: Jugal Gajjar
Published: 2026-04-12
Categories: cs.SE, cs.AI, cs.CR, cs.LG, cs.PL
arXiv: https://arxiv.org/abs/2604.10800v1

Learned classifiers deployed in agentic pipelines face a fundamental reliability problem: predictions are probabilistic inferences, not verified conclusions, and acting on them without grounding in observable evidence leads to compounding failures across downstream stages. Software vulnerability analysis makes this cost concrete and measurable. We address this through a unified cross-language vulnerability lifecycle framework built around three LLM-driven reasoning stages-hybrid structural-semantic detection, execution-grounded agentic validation, and validation-aware iterative repair-governed by a strict invariant: no repair action is taken without execution-based confirmation of exploitability. Cross-language generalization is achieved via a Universal Abstract Syntax Tree (uAST) normalizing Java, Python, and C++ into a shared structural schema, combined with a hybrid fusion of GraphSAGE and Qwen2.5-Coder-1.5B embeddings through learned two-way gating, whose per-sample weights provide intrinsic explainability at no additional cost. The framework achieves 89.84-92.02% intra-language detection accuracy and 74.43-80.12% zero-shot cross-language F1, resolving 69.74% of vulnerabilities end-to-end at a 12.27% total failure rate. Ablations establish necessity: removing uAST degrades cross-language F1 by 23.42%, while disabling validation increases unnecessary repairs by 131.7%. These results demonstrate that execution-grounded closed-loop reasoning is a principled and practically deployable mechanism for trustworthy LLM-driven agentic AI.

---

### Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series

Authors: Krzysztof Ociepa, Łukasz Flis, Remigiusz Kinas, Krzysztof Wróbel, Adrian Gwoździej
Published: 2026-04-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.10799v1

The development of the Bielik v3 PL series, encompassing both the 7B and 11B parameter variants, represents a significant milestone in the field of language-specific large language model (LLM) optimization. While general-purpose models often demonstrate impressive multilingual capabilities, they frequently suffer from a fundamental architectural inefficiency: the use of universal tokenizers. These tokenizers, typically designed to cover a broad spectrum of languages, often fail to capture the morphological nuances of specific languages like Polish, leading to higher fertility ratios, increased inference costs, and restricted effective context windows. This report details the transition from the universal Mistral-based tokenization to a dedicated Polish-optimized vocabulary for the Bielik v3 models, exploring the FOCUS-based embedding initialization, the multi-stage pretraining curriculum, and the subsequent post-training alignment involving Supervised Fine-Tuning, Direct Preference Optimization, and Reinforcement Learning through Group Relative Policy Optimization with verifiable rewards.

---

### WBCBench 2026: A Challenge for Robust White Blood Cell Classification Under Class Imbalance

Authors: Xin Tian, Xudong Ma, Tianqi Yang, Alin Achim, Bartłomiej W Papież, Phandee Watanaboonyongcharoen, Nantheera Anantrasirichai
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10797v1

We present WBCBench 2026, an ISBI challenge and benchmark for automated WBC classification designed to stress-test algorithms under three key difficulties: (i) severe class imbalance across 13 morphologically fine-grained WBC classes, (ii) strict patient-level separation between training, validation and test sets, and (iii) synthetic scanner- and setting-induced domain shift via controlled noise, blur and illumination perturbations. All images are single-site microscopic blood smear acquisitions with standardised staining and expert hematopathologist annotations. This paper reviews the challenge and summarises the proposed solutions and final outcomes. The benchmark is organised into two phases. Phase 1 provides a pristine training set. Phase 2 introduces degraded images with split-specific severity distributions for train, validation and test, emulating a realistic shift between development and deployment conditions. We specify a standardised submission schema, open-source evaluator, and macro-averaged F1 score as the primary ranking metric.

---

### Position-Agnostic Pre-Projection for Transformer Attention: Nonlinear Feature Construction and Content Skip Before Q/K/V

Authors: Chirag Shinde
Published: 2026-04-12
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2604.10791v1

We propose two complementary modifications to transformer attention blocks. First, a non-linear pre-projection MLP is inserted between layer norm and Q/K/V projections, constructing richer features in a position-agnostic manner before any positional encoding is applied. Second, a content skip connection routes the pre-projection's features around the attention mechanism, allowing content information to bypass position-aware attention where beneficial. In frozen-probe experiments on Pythia-160M and 410M, the combined approach achieves the strongest results across methods: +40.6% LAMBADA accuracy and -39% perplexity at 160M scale. Learned skip connection weights reveal a consistent pattern across model sizes: later transformer layers activate the content bypass more strongly than earlier layers, suggesting that deeper layers benefit from content information that does not pass through positional attention. All modifications add no K/V cache overhead.

---

### ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment

Authors: Mingyu Dong, Chong Xia, Mingyuan Jia, Weichen Lyu, Long Xu, Zheng Zhu, Yueqi Duan
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10789v1

Humans exhibit an innate capacity to rapidly perceive and segment objects from video observations, and even mentally assemble them into structured 3D scenes. Replicating such capability, termed compositional 3D reconstruction, is pivotal for the advancement of Spatial Intelligence and Embodied AI. However, existing methods struggle to achieve practical deployment due to the insufficient integration of cross-modal information, leaving them dependent on manual object prompting, reliant on auxiliary visual inputs, and restricted to overly simplistic scenes by training biases. To address these limitations, we propose ReplicateAnyScene, a framework capable of fully automated and zero-shot transformation of casually captured videos into compositional 3D scenes. Specifically, our pipeline incorporates a five-stage cascade to extract and structurally align generic priors from vision foundation models across textual, visual, and spatial dimensions, grounding them into structured 3D representations and ensuring semantic coherence and physical plausibility of the constructed scenes. To facilitate a more comprehensive evaluation of this task, we further introduce the C3DR benchmark to assess reconstruction quality from diverse aspects. Extensive experiments demonstrate the superiority of our method over existing baselines in generating high-quality compositional 3D scenes.

---

### TInR: Exploring Tool-Internalized Reasoning in Large Language Models

Authors: Qiancheng Xu, Yongqi Li, Fan Liu, Hongru Wang, Min Yang, Wenjie Li
Published: 2026-04-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.10788v2

Tool-Integrated Reasoning (TIR) has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools during reasoning. Existing TIR methods typically rely on external tool documentation during reasoning. However, this leads to tool mastery difficulty, tool size constraints, and inference inefficiency. To mitigate these issues, we explore Tool-Internalized Reasoning (TInR), aiming at facilitating reasoning with tool knowledge internalized into LLMs. Achieving this goal presents notable requirements, including tool internalization and tool-reasoning coordination. To address them, we propose TInR-U, a tool-internalized reasoning framework for unified reasoning and tool usage. TInR-U is trained through a three-phase pipeline: 1) tool internalization with a bidirectional knowledge alignment strategy; 2) supervised fine-tuning warm-up using high-quality reasoning annotations, and 3) reinforcement learning with TInR-specific rewards. We comprehensively evaluate our method across in-domain and out-of-domain settings. Experiment results show that TInR-U achieves superior performance in both settings, highlighting its effectiveness and efficiency.

---

### When Meaning Isn't Literal: Exploring Idiomatic Meaning Across Languages and Modalities

Authors: Sarmistha Das, Shreyas Guha, Suvrayan Bandyopadhyay, Salisa Phosit, Kitsuchart Pasupa, Sriparna Saha
Published: 2026-04-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.10787v1

Idiomatic reasoning, deeply intertwined with metaphor and culture, remains a blind spot for contemporary language models, whose progress skews toward surface-level lexical and semantic cues. For instance, the Bengali idiom \textit{\foreignlanguage{bengali}{\char"0986\char"0999\char"09CD\char"0997\char"09C1 \char"09B0 \char"09AB\char"09B2 \char"099F\char"0995}} (angur fol tok, ``grapes are sour''): it encodes denial-driven rationalization, yet naive models latch onto the literal fox-and-grape imagery. Addressing this oversight, we present ``Mediom,'' a multilingual, multimodal idiom corpus of 3,533 Hindi, Bengali, and Thai idioms, each paired with gold-standard explanations, cross-lingual translations, and carefully aligned text--image representations. We benchmark both large language models (textual reasoning) and vision-language models (figurative disambiguation) on Mediom, exposing systematic failures in metaphor comprehension. To mitigate these gaps, we propose ``HIDE,'' a Hinting-based Idiom Explanation framework that leverages error-feedback retrieval and targeted diagnostic cues for iterative reasoning refinement. Collectively, Mediom and HIDE establish a rigorous test bed and methodology for culturally grounded, multimodal idiom understanding embedded with reasoning hints in next-generation AI systems.

---

### Do BERT Embeddings Encode Narrative Dimensions? A Token-Level Probing Analysis of Time, Space, Causality, and Character in Fiction

Authors: Beicheng Bei, Hannah Hyesun Chun, Chen Guo, Arwa Saghiri
Published: 2026-04-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.10786v1

Narrative understanding requires multidimensional semantic structures. This study investigates whether BERT embeddings encode dimensions of fictional narrative semantics -- time, space, causality, and character. Using an LLM to accelerate annotation, we construct a token-level dataset labeled with these four narrative categories plus "others." A linear probe on BERT embeddings (94% accuracy) significantly outperforms a control probe on variance-matched random embeddings (47%), confirming that BERT encodes meaningful narrative information. With balanced class weighting, the probe achieves a macro-average recall of 0.83, with moderate success on rare categories such as causality (recall = 0.75) and space (recall = 0.66). However, confusion matrix analysis reveals "Boundary Leakage," where rare dimensions are systematically misclassified as "others." Clustering analysis shows that unsupervised clustering aligns near-randomly with predefined categories (ARI = 0.081), suggesting that narrative dimensions are encoded but not as discretely separable clusters. Future work includes a POS-only baseline to disentangle syntactic patterns from narrative encoding, expanded datasets, and layer-wise probing.

---

### TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training

Authors: Yinyi Luo, Wenwen Wang, Hayes Bai, Hongyu Zhu, Hao Chen, Pan He, Marios Savvides, Sharon Li, Jindong Wang
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10784v2

Recent advances in unified multimodal models (UMMs) have led to a proliferation of architectures capable of understanding, generating, and editing across visual and textual modalities. However, developing a unified framework for UMMs remains challenging due to the diversity of model architectures and the heterogeneity of training paradigms and implementation details. In this paper, we present TorchUMM, the first unified codebase for comprehensive evaluation, analysis, and post-training across diverse UMM backbones, tasks, and datasets. TorchUMM supports a broad spectrum of models covering a wide range of scales and design paradigms. Our benchmark encompasses three core task dimensions: multimodal understanding, generation, and editing, and integrates both established and novel datasets to evaluate perception, reasoning, compositionality, and instruction-following abilities. By providing a unified interface and standardized evaluation protocols, TorchUMM enables fair and reproducible comparisons across heterogeneous models and fosters deeper insights into their strengths and limitations, facilitating the development of more capable unified multimodal systems. Code is available at: https://github.com/AIFrontierLab/TorchUMM.

---

### Learning Preference-Based Objectives from Clinical Narratives for Dynamic Sepsis Treatment

Authors: Daniel J. Tan, Jayne Hui Zhen Chan, Kai Wen Hwang, Arturo Yong Yao Neo, Kay Choong See, Mengling Feng
Published: 2026-04-12
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.10783v2

Designing reward functions for reinforcement learning (RL) in healthcare remains challenging because clinically meaningful outcomes are sparse, delayed, and difficult to explicitly specify. Although structured clinical data capture physiologic states, they often fail to reflect broader aspects of patient trajectories such as treatment response, recovery dynamics, and intervention burden. Clinical narratives, by contrast, encode longitudinal clinician assessments of disease progression, treatment effectiveness, and recovery, providing a potential source of trajectory-level supervision beyond predefined outcome metrics. We propose Clinical Narrative-informed Preference Rewards (CN-PR), a framework that learns reward functions directly from discharge summaries by treating clinical narratives as scalable supervision for trajectory-level preferences. Using a large language model, we derive trajectory quality scores and construct pairwise preferences between patient trajectories to learn rewards through preference-based optimization. To account for variability in narrative informativeness, we incorporate a task relevance signal that weights supervision according to its relevance to the downstream decision-making task. We evaluate CN-PR in dynamic sepsis treatment using offline RL. The learned reward demonstrated strong monotonic alignment with trajectory quality scores and produced policies associated with improved recovery-related outcomes, including increased organ support-free days and faster shock resolution, while maintaining mortality performance comparable to outcome-based reward baselines. These findings were preserved under external validation. Our results suggest that clinical narratives provide a scalable and expressive source of supervision for reward learning in dynamic treatment regimes.

---

### LIDARLearn: A Unified Deep Learning Library for 3D Point Cloud Classification, Segmentation, and Self-Supervised Representation Learning

Authors: Said Ohamouddou, Hanaa El Afia, Abdellatif El Afia, Raddouane Chiheb
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10780v1

Three-dimensional (3D) point cloud analysis has become central to applications ranging from autonomous driving and robotics to forestry and ecological monitoring. Although numerous deep learning methods have been proposed for point cloud understanding, including supervised backbones, self-supervised pre-training (SSL), and parameter-efficient fine-tuning (PEFT), their implementations are scattered across incompatible codebases with differing data pipelines, evaluation protocols, and configuration formats, making fair comparisons difficult. We introduce \lib{}, a unified, extensible PyTorch library that integrates over 55 model configurations covering 29 supervised architectures, seven SSL pre-training methods, and five PEFT strategies, all within a single registry-based framework supporting classification, semantic segmentation, part segmentation, and few-shot learning. \lib{} provides standardised training runners, cross-validation with stratified $K$-fold splitting, automated LaTeX/CSV table generation, built-in Friedman/Nemenyi statistical testing with critical-difference diagrams for rigorous multi-model comparison, and a comprehensive test suite with 2\,200+ automated tests validating every configuration end-to-end. The code is available at https://github.com/said-ohamouddou/LIDARLearn under the MIT licence.

---

### Uncertainty-quantified Pulse Signal Recovery from Facial Video using Regularized Stochastic Interpolants

Authors: Vineet R. Shenoy, Cheng Peng, Rama Chellappa, Yu Sun
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10777v1

Imaging Photoplethysmography (iPPG), an optical procedure which recovers a human's blood volume pulse (BVP) waveform using pixel readout from a camera, is an exciting research field with many researchers performing clinical studies of iPPG algorithms. While current algorithms to solve the iPPG task have shown outstanding performance on benchmark datasets, no state-of-the art algorithms, to the best of our knowledge, performs test-time sampling of solution space, precluding an uncertainty analysis that is critical for clinical applications. We address this deficiency though a new paradigm named Regularized Interpolants with Stochasticity for iPPG (RIS-iPPG). Modeling iPPG recovery as an inverse problem, we build probability paths that evolve the camera pixel distribution to the ground-truth signal distribution by predicting the instantaneous flow and score vectors of a time-dependent stochastic process; and at test-time, we sample the posterior distribution of the correct BVP waveform given the camera pixel intensity measurements by solving a stochastic differential equation. Given that physiological changes are slowly varying, we show that iPPG recovery can be improved through regularization that maximizes the correlation between the residual flow vector predictions of two adjacent time windows. Experimental results on three datasets show that RIS-iPPG provides superior reconstruction quality and uncertainty estimates of the reconstruction, a critical tool for the widespread adoption of iPPG algorithms in clinical and consumer settings.

---

### HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language Models

Authors: Haiyan Jiang, Deyu Zhang, Dongdong Weng, Weitao Song, Henry Been-Lirn Duh
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10772v1

3D layout generation and editing play a crucial role in Embodied AI and immersive VR interaction. However, manual creation requires tedious labor, while data-driven generation often lacks diversity. The emergence of large models introduces new possibilities for 3D scene synthesis. We present HOG-Layout that enables text-driven hierarchical scene generation, optimization and real-time scene editing with large language models (LLMs) and vision-language models (VLMs). HOG-Layout improves scene semantic consistency and plausibility through retrieval-augmented generation (RAG) technology, incorporates an optimization module to enhance physical consistency, and adopts a hierarchical representation to enhance inference and optimization, achieving real-time editing. Experimental results demonstrate that HOG-Layout produces more reasonable environments compared with existing baselines, while supporting fast and intuitive scene editing.

---

### At FullTilt: Real-Time Open-Set 3D Macromolecule Detection Directly from Tilted 2D Projections

Authors: Ming-Yang Ho, Alberto Bartesaghi
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10766v5

Open-set 3D macromolecule detection in cryogenic electron tomography eliminates the need for target-specific model retraining. However, strict VRAM constraints prohibit processing an entire 3D tomogram, forcing current methods to rely on slow sliding-window inference over extracted subvolumes. To overcome this, we propose FullTilt, an end-to-end framework that redefines 3D detection by operating directly on aligned 2D tilt-series. Because a tilt-series contains significantly fewer images than slices in a reconstructed tomogram, FullTilt eliminates redundant volumetric computation, accelerating inference by orders of magnitude. To process the entire tilt-series simultaneously, we introduce a tilt-series encoder to efficiently fuse cross-view information. We further propose a multiclass visual prompt encoder for flexible prompting, a tilt-aware query initializer to effectively anchor 3D queries, and an auxiliary geometric primitives module to enhance the model's understanding of multi-view geometry while improving robustness to adverse imaging artifacts. Extensive evaluations on three real-world datasets demonstrate that FullTilt achieves state-of-the-art zero-shot performance while drastically reducing runtime and VRAM requirements, paving the way for rapid, large-scale visual proteomics analysis. All code and data will be publicly available upon publication.

---

### At FullTilt: Real-Time Open-Set 3D Macromolecule Detection Directly from Tilted 2D Projections

Authors: Ming-Yang Ho, Alberto Bartesaghi
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10766v4

Open-set 3D macromolecule detection in cryogenic electron tomography eliminates the need for target-specific model retraining. However, strict VRAM constraints prohibit processing an entire 3D tomogram, forcing current methods to rely on slow sliding-window inference over extracted subvolumes. To overcome this, we propose FullTilt, an end-to-end framework that redefines 3D detection by operating directly on aligned 2D tilt-series. Because a tilt-series contains significantly fewer images than slices in a reconstructed tomogram, FullTilt eliminates redundant volumetric computation, accelerating inference by orders of magnitude. To process the entire tilt-series simultaneously, we introduce a tilt-series encoder to efficiently fuse cross-view information. We further propose a multiclass visual prompt encoder for flexible prompting, a tilt-aware query initializer to effectively anchor 3D queries, and an auxiliary geometric primitives module to enhance the model's understanding of multi-view geometry while improving robustness to adverse imaging artifacts. Extensive evaluations on three real-world datasets demonstrate that FullTilt achieves state-of-the-art zero-shot performance while drastically reducing runtime and VRAM requirements, paving the way for rapid, large-scale visual proteomics analysis. All code and data will be publicly available upon publication.

---

### Lung Cancer Detection Using Deep Learning

Authors: Imama Ajmi, Abhishek Das
Published: 2026-04-12
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.10765v1

Lung cancer, the second leading cause of cancer-related deaths, is primarily linked to long-term tobacco smoking (85% of cases). Surprisingly, 10-15% of cases occur in non-smokers. In 2020, approximately 2 million people were affected globally, resulting in 1.5 million deaths. The survival rate, at around 20%, lags behind other cancers, partly due to late-stage symptom manifestation. Necessitates early and accurate detection for effective treatment. Performance metrics such as accuracy, precision, recall (sensitivity), and F1-score are computed to provide a comprehensive evaluation of each model's capabilities. By comparing these metrics, this study offers insights into the strengths and limitations of each approach, contributing to the advancement of lung cancer detection techniques. In this paper, we are going to discuss the methodologies of lung cancer detection using different deep learning algorithms - InceptionV3, MobileNetV2, VGG16, ResNet152 - are explored for their efficacy in classifying lung cancer cases. Our Proposed Model algorithm based is a 16 layers architecture based on CNN model. Our Proposed model exhibits several key highlights that contribute to its novelty. By integrating multiple layer types such as convolutional, pooling, flatten, dropout, fully connected and dense layers, the model leverages the strengths of each layer to enhance its predictive capabilities. Novelty of our proposed model is that its accuracy is increasing consistently with the increasing no of epochs. We have tested the model performance up to epoch no 30. Our proposed model also overcome the overfitting problem.

---

### Prosociality by Coupling, Not Mere Observation: Homeostatic Sharing in an Inspectable Recurrent Artificial Life Agent

Authors: Aishik Sanyal
Published: 2026-04-12
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2604.10760v2

Artificial agents can be made to ``help'' through explicit social rewards, hard-coded prosocial bonuses, or direct access to another agent's state. I isolate a narrower route: homeostatic coupling. Building on ReCoN-Ipsundrum, I add a scalar homeostat and a social coupling channel while keeping action selection self-directed: the planner scores only the actor's predicted internal state, with no partner-welfare reward. In a one-step FoodShareToy, an exact solver finds a switch from EAT to PASS at $λ^\star \approx 0.91$ for the default state. In a multi-step SocialCorridorWorld, partner-state access without coupling leaves behavior unchanged, whereas coupled agents fetch, carry, and pass food to the partner. Sham lesions preserve helping; coupling-off and shuffled-partner lesions abolish it. A coupling/load sweep shows that coupling creates a low-load helping regime but does not guarantee rescue under higher metabolic load. This is not a claim about empathy, altruism, consciousness, or moral status. It is a minimal ALife demonstration that, in this controller, partner-state access is behaviorally inert unless partner distress is routed into self-regulation.

---

### MMRareBench: A Rare-Disease Multimodal and Multi-Image Medical Benchmark

Authors: Junzhi Ning, Jiashi Lin, Yingying Fang, Wei Li, Jiyao Liu, Cheng Tang, Chenglong Ma, Wenhao Tang, Tianbin Li, Ziyan Huang, Guang Yang, Junjun He
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10755v2

Multimodal large language models (MLLMs) have advanced clinical tasks for common conditions, but their performance on rare diseases remains largely untested. In rare-disease scenarios, clinicians often lack prior clinical knowledge, forcing them to rely strictly on case-level evidence for clinical judgments. Existing benchmarks predominantly evaluate common-condition, single-image settings, leaving multimodal and multi-image evidence integration under rare-disease data scarcity systematically unevaluated. We introduce MMRareBench, to our knowledge the first rare-disease benchmark jointly evaluating multimodal and multi-image clinical capability across four workflow-aligned tracks: diagnosis, treatment planning, cross-image evidence alignment, and examination suggestion. The benchmark comprises 1,756 question-answer pairs with 7,958 associated medical images curated from PMC case reports, with Orphanet-anchored ontology alignment, track-specific leakage control, evidence-grounded annotations, and a two-level evaluation protocol. A systematic evaluation of 23 MLLMs reveals fragmented capability profiles and universally low treatment-planning performance, with medical-domain models trailing general-purpose MLLMs substantially on multi-image tracks despite competitive diagnostic scores. These patterns are consistent with a capacity dilution effect: medical fine-tuning can narrow the diagnostic gap but may erode the compositional multi-image capability that rare-disease evidence integration demands.

---