# Research Papers — 2026-04 · bundle page 77 of 233 > Full-text markdown of papers #3801–3850 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/77 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/76.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/78.md) ### Aligning Language Models for Lyric-to-Melody Generation with Rule-Based Musical Constraints Authors: Hao Meng, Siyuan Zheng, Shuran Zhou, Qiangqiang Wang, Yang Song Published: 2026-04-20 Categories: cs.SD, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2604.18489v1 Large Language Models (LLMs) show promise in lyric-to-melody generation, but models trained with Supervised Fine-Tuning (SFT) often produce musically implausible melodies with issues like poor rhythm and unsuitable vocal ranges, a phenomenon we term "constraint violation". To address this, we propose a novel alignment framework that instills musical knowledge without human annotation. We define rule-based musical constraints to automatically generate a preference dataset from an SFT model's outputs. The model is then aligned through a sequential process, first using Direct Preference Optimization (DPO) on paired preference data, followed by Kahneman-Tversky Optimization (KTO) on unpaired negative samples. Experimental results demonstrate that our aligned model substantially reduces rule violations and outperforms strong baselines in both objective and subjective evaluations, generating melodies with substantially improved musicality and coherence. An interactive demo with audio comparisons is available at https://arain233.github.io/AligningMelody-demo. --- ### Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety Authors: Marcello Galisai, Susanna Cifani, Francesco Giarrusso, Piercosma Bisconti, Matteo Prandi, Federico Pierucci, Federico Sartore, Daniele Nardi Published: 2026-04-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.18487v1 The Adversarial Humanities Benchmark (AHB) evaluates whether model safety refusals survive a shift away from familiar harmful prompt forms. Starting from harmful tasks drawn from MLCommons AILuminate, the benchmark rewrites the same objectives through humanities-style transformations while preserving intent. This extends literature on Adversarial Poetry and Adversarial Tales from single jailbreak operators to a broader benchmark family of stylistic obfuscation and goal concealment. In the benchmark results reported here, the original attacks record 3.84% attack success rate (ASR), while transformed methods range from 36.8% to 65.0%, yielding 55.75% overall ASR across 31 frontier models. Under a European Union AI Act Code-of-Practice-inspired systemic-risk lens, Chemical, biological, radiological and nuclear (CBRN) is the highest bucket. Taken together, this lack of stylistic robustness suggests that current safety techniques suffer from weak generalization: deep understanding of 'non-maleficence' remains a central unresolved problem in frontier model safety. --- ### Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation Authors: Jinghui Lu, Jiayi Guan, Zhijian Huang, Jinlong Li, Guang Li, Lingdong Kong, Yingyan Li, Han Wang, Shaoqing Xu, Yuechen Luo, Fang Li, Chenxu Dang et al. Published: 2026-04-20 Categories: cs.CV, cs.CL, cs.RO arXiv: https://arxiv.org/abs/2604.18486v3 Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature imposes a latency cost that is prohibitive for real-time deployment. Latent CoT methods attempt to close this gap by compressing reasoning into continuous hidden states, but consistently fall short of their explicit counterparts. We suggest that this is due to purely linguistic latent representations compressing a symbolic abstraction of the world, rather than the causal dynamics that actually govern driving. Thus, we present OneVL (One-step latent reasoning and planning with Vision-Language explanations), a unified VLA and World Model framework that routes reasoning through compact latent tokens supervised by dual auxiliary decoders. Alongside a language decoder that reconstructs text CoT, we introduce a visual world model decoder that predicts future-frame tokens, forcing the latent space to internalize the causal dynamics of road geometry, agent motion, and environmental change. A three-stage training pipeline progressively aligns these latents with trajectory, language, and visual objectives, ensuring stable joint optimization. In inference, the auxiliary decoders are discarded, and all latent tokens are prefilled in a single parallel pass, matching the speed of answer-only prediction. Across four benchmarks, OneVL becomes the first latent CoT method to surpass explicit CoT, delivering superior accuracy at answer-only latency. These results show that with world model supervision, latent CoT produces more generalizable representations than verbose token-by-token reasoning. Code has been open-sourced to the community. Project Page: https://xiaomi-embodied-intelligence.github.io/OneVL --- ### XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments Authors: Kangan Qian, ChuChu Xie, Yang Zhong, Jingrui Pang, Siwen Jiao, Sicong Jiang, Zilin Huang, Yunlong Wang, Kun Jiang, Mengmeng Yang, Hao Ye, Guanghao Zhang et al. Published: 2026-04-20 Categories: cs.CV, cs.MM, cs.RO arXiv: https://arxiv.org/abs/2604.18484v1 Vision-Language-Action (VLA) models drive next-generation autonomous systems, but training them requires scalable, high-quality annotations from complex environments. Current cloud pipelines rely on generic vision-language models (VLMs) that lack geometric reasoning and domain semantics due to their 2D image-text pretraining. To address this mismatch, we propose XEmbodied, a cloud-side foundation model that endows VLMs with intrinsic 3D geometric awareness and interaction with physical cues (e.g., occupancy grids, 3D boxes). Instead of treating geometry as auxiliary input, XEmbodied integrates geometric representations via a structured 3D Adapter and distills physical signals into context tokens using an Efficient Image-Embodied Adapter. Through progressive domain curriculum and reinforcement learning post-training, XEmbodied preserves general capabilities while demonstrating robust performance across 18 public benchmarks. It significantly improves spatial reasoning, traffic semantics, embodied affordance, and out-of-distribution generalization for large-scale scenario mining and embodied VQA. --- ### Safe Control using Learned Safety Filters and Adaptive Conformal Inference Authors: Sacha Huriot, Ihab Tabbara, Hussein Sibai Published: 2026-04-20 Categories: eess.SY, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2604.18482v1 Safety filters have been shown to be effective tools to ensure the safety of control systems with unsafe nominal policies. To address scalability challenges in traditional synthesis methods, learning-based approaches have been proposed for designing safety filters for systems with high-dimensional state and control spaces. However, the inevitable errors in the decisions of these models raise concerns about their reliability and the safety guarantees they offer. This paper presents Adaptive Conformal Filtering (ACoFi), a method that combines learned Hamilton-Jacobi reachability-based safety filters with adaptive conformal inference. Under ACoFi, the filter dynamically adjusts its switching criteria based on the observed errors in its predictions of the safety of actions. The range of possible safety values of the nominal policy's output is used to quantify uncertainty in safety assessment. The filter switches from the nominal policy to the learned safe one when that range suggests it might be unsafe. We show that ACoFi guarantees that the rate of incorrectly quantifying uncertainty in the predicted safety of the nominal policy is asymptotically upper bounded by a user-defined parameter. This gives a soft safety guarantee rather than a hard safety guarantee. We evaluate ACoFi in a Dubins car simulation and a Safety Gymnasium environment, empirically demonstrating that it significantly outperforms the baseline method that uses a fixed switching threshold by achieving higher learned safety values and fewer safety violations, especially in out-of-distribution scenarios. --- ### Physics-Informed Neural Networks: A Didactic Derivation of the Complete Training Cycle Authors: Abdeladhim Tahimi Published: 2026-04-20 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2604.18481v1 This paper is a step-by-step, self-contained guide to the complete training cycle of a Physics-Informed Neural Network (PINN) -- a topic that existing tutorials and guides typically delegate to automatic differentiation libraries without exposing the underlying algebra. Using a first-order initial value problem with a known analytical solution as a running example, we walk through every stage of the process: forward propagation of both the network output and its temporal derivative, evaluation of a composite loss function built from the ODE residual and the initial condition, backpropagation of gradients -- with particular attention to the product rule that arises in hidden layers -- and a gradient descent parameter update. Every calculation is presented with explicit, verifiable numerical values using a 1-3-3-1 multilayer perceptron with two hidden layers and 22 trainable parameters. From these concrete examples, we derive general recursive formulas -- expressed as sensitivity propagation relations -- that extend the gradient computation to networks of arbitrary depth, and we connect these formulas to the automatic differentiation engines used in practice. The trained network is then validated against the exact solution, achieving a relative $L^2$ error of $4.290 \times 10^{-4}$ using only the physics-informed loss, without any data from the true solution. A companion Jupyter/PyTorch notebook reproduces every manual calculation and the full training pipeline, providing mutual validation between hand-derived and machine-computed gradients. --- ### WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time Reconciliation Authors: Harish Santhanalakshmi Ganesan Published: 2026-04-20 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.18478v1 Persistent memory is the bottleneck separating stateless chatbots from long-running agentic systems. Retrieval-augmented generation (RAG) over flat vector stores fragments facts into chunks, loses cross-session identity, and has no first-class notion of supersession or contradiction. Recent bitemporal knowledge-graph systems (Graphiti, Memento, Hydra DB) add typed edges and valid-time metadata, but the graph itself remains flat: no recursive composition, no content-addressed invariants on nodes, and edge types carry no behavior beyond a label. We present WorldDB, a memory engine built on three commitments: (i) every node is a world -- a container with its own interior subgraph, ontology scope, and composed embedding, recursive to arbitrary depth; (ii) nodes are content-addressed and immutable, so any edit produces a new hash at the node and every ancestor, giving a Merkle-style audit trail for free; (iii) edges are write-time programs -- each edge type ships on_insert/on_delete/on_query_rewrite handlers (supersession closes validity, contradicts preserves both sides, same_as stages a merge proposal), so no raw append path exists. On LongMemEval-s (500 questions, ~115k-token conversational stacks), WorldDB with Claude Opus 4.7 as answerer achieves 96.40% overall / 97.11% task-averaged accuracy, a +5.61pp improvement over the previously reported Hydra DB state-of-the-art (90.79%) and +11.20pp over Supermemory (85.20%), with perfect single-session-assistant recall and robust performance on temporal reasoning (96.24%), knowledge update (98.72%), and preference synthesis (96.67%). Ablations show that the engine's graph layer -- resolver-unified entities and typed refers_to edges -- contributes +7.0pp task-averaged independently of the underlying answerer. --- ### Multi-Scale Reversible Chaos Game Representation: A Unified Framework for Sequence Classification Authors: Sarwan Ali, Taslim Murad Published: 2026-04-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.18477v1 Biological classification with interpretability remains a challenging task. For this, we introduce a novel encoding framework, Multi-Scale Reversible Chaos Game Representation (MS-RCGR), that transforms biological sequences into multi-resolution geometric representations with guaranteed reversibility. Unlike traditional sequence encoding methods, MS-RCGR employs rational arithmetic and hierarchical k-mer decomposition to generate scale-invariant features that preserve complete sequence information while enabling diverse analytical approaches. Our framework bridges three distinct paradigms for sequence analysis: (1) traditional machine learning using extracted geometric features, (2) computer vision models operating on CGR-generated images, and (3) hybrid approaches combining protein language model embeddings with CGR features. Through comprehensive experiments on synthetic DNA and protein datasets encompassing seven distinct sequence classes, we demonstrate that MS-RCGR features consistently enhance classification performance across all paradigms. Notably, our hybrid approach combining pre-trained language model embeddings (ESM2, ProtT5) with MS-RCGR features achieves superior performance compared to either method alone. The reversibility property of our encoding ensures no information loss during transformation, while multi-scale analysis captures patterns ranging from individual nucleotides to complex motif structures. Our results indicate that MS-RCGR provides a flexible, interpretable, and high-performing foundation for biological sequence analysis. --- ### SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection Authors: Hao Vo, Khoa Vo, Thinh Phan, Ngo Xuan Cuong, Gianfranco Doretto, Hien Nguyen, Anh Nguyen, Ngan Le Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.18476v1 Camera-only 3D object detection has emerged as a cost-effective and scalable alternative to LiDAR for autonomous driving, yet existing methods primarily prioritize overall performance while overlooking the severe long-tail imbalance inherent in real-world datasets. In practice, many rare but safety-critical categories such as children, strollers, or emergency vehicles are heavily underrepresented, leading to biased learning and degraded performance. This challenge is further exacerbated by pronounced inter-class ambiguity (e.g., visually similar subclasses) and substantial intra-class diversity (e.g., objects varying widely in appearance, scale, pose, or context), which together hinder reliable long-tail recognition. In this work, we introduce SemLT3D, a Semantic-Guided Expert Distillation framework designed to enrich the representation space for underrepresented classes through semantic priors. SemLT3D consists of: (1) a language-guided mixture-of-experts module that routes 3D queries to specialized experts according to their semantic affinity, enabling the model to better disentangle confusing classes and specialize on tail distributions; and (2) a semantic projection distillation pipeline that aligns 3D queries with CLIP-informed 2D semantics, producing more coherent and discriminative features across diverse visual manifestations. Although motivated by long-tail imbalance, the semantically structured learning in SemLT3D also improves robustness under broader appearance variations and challenging corner cases, offering a principled step toward more reliable camera-only 3D perception. --- ### Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Authors: Jacob Morrison, Sanjay Adhikesaven, Akshita Bhagia, Matei Zaharia, Noah A. Smith, Sewon Min Published: 2026-04-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.18473v1 Extending a fully post-trained language model with new domain capabilities is fundamentally limited by monolithic training paradigms: retraining from scratch is expensive and scales poorly, while continued training often degrades existing capabilities. We present BAR (Branch-Adapt-Route), which trains independent domain experts, each through its own mid-training, supervised finetuning, and reinforcement learning pipeline, and composes them via a Mixture-of-Experts architecture with lightweight router training. Unlike retraining approaches that mix all domains and require full reprocessing for any update (with cost scaling quadratically), BAR enables updating individual experts independently with linear cost scaling and no degradation to existing domains. At the 7B scale, with experts for math, code, tool use, and safety, BAR achieves an overall score of 49.1 (averaged across 7 evaluation categories), matching or exceeding re-training baselines (47.8 without mid-training, 50.5 with). We further show that modular training provides a structural advantage: by isolating each domain, it avoids the catastrophic forgetting that occurs when late-stage RL degrades capabilities from earlier training stages, while significantly reducing the cost and complexity of updating or adding a domain. Together, these results suggest that decoupled, expert-based training is a scalable alternative to monolithic retraining for extending language models. --- ### NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization Authors: Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin Published: 2026-04-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.18471v2 Discrete diffusion language models (dLLMs) have recently emerged as a promising alternative to traditional autoregressive approaches, offering the flexibility to generate tokens in arbitrary orders and the potential of parallel decoding. However, existing heuristic sampling strategies remain inefficient: they choose only a small part of tokens to sample at each step, leaving substantial room for improvement. In this work, we study the problem of token sampling order optimization and demonstrate its significant potential for acceleration. Specifically, we find that fully leveraging correct predictions at each step can reduce the number of sampling iterations by an order of magnitude without compromising accuracy. Based on this, we propose Neural Indicator Sampling (NI Sampling), a general sampling order optimization framework that utilize a neural indicator to decide which tokens should be sampled at each step. We further propose a novel trajectory-preserving objective to train the indicator. Experiments on LLaDA and Dream models across multiple benchmarks show that our method achieves up to 14.3$\times$ acceleration over full-step sampling with negligible performance drop, and consistently outperforms confidence threshold sampling in the accuracy-step trade-off. Code is available at https://github.com/imagination-research/NI-Sampling. --- ### A Generalized Synthetic Control Method for Baseline Estimation in Demand Response Services Authors: Jonas Sievers, Mardavij Roozbehani Published: 2026-04-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.18469v1 Baseline estimation is critical to Demand Response (DR) settlement in electricity markets, yet existing machine learning methods remain limited in predictive performance, while methodologies from causal inference and counterfactual prediction are still underutilized in this domain. We introduce a Generalized Synthetic Control Method that builds on the classical Synthetic Control Method (SCM) from econometrics. While SCM provides a powerful framework for counterfactual estimation, classical SCM remains a static estimator: it fits the treated unit as a combination of contemporaneous donor units and therefore ignores predictable temporal structure in the residual error. We develop a generalized SCM framework that transforms baseline estimation into a dynamic counterfactual prediction problem by augmenting the donor representation with exogenous features, lagged treated load, and selected lagged donor signals. This enriched representation allows the estimator to capture autoregressive dependence, delayed donor-response patterns, and error-correction effects beyond the scope of standard SCM. The framework further accommodates nonlinear predictors when linear weighting is inadequate, with the greatest benefit arising in limited-data settings. Experiments on the Ausgrid smart-meter dataset show consistent improvements over classical SCM and strong benchmark methods, with the dominant performance gains driven by dynamic augmentation. --- ### Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation Authors: Tianshi Cao, Jiawei Ren, Yuxuan Zhang, Jaewoo Seo, Jiahui Huang, Shikhar Solanki, Haotian Zhang, Mingfei Guo, Haithem Turki, Muxingzi Li, Yue Zhu, Sipeng Zhang et al. Published: 2026-04-20 Categories: cs.CV, cs.AI, cs.GR, cs.LG arXiv: https://arxiv.org/abs/2604.18468v1 Closed-loop simulation is a core component of autonomous vehicle (AV) development, enabling scalable testing, training, and safety validation before real-world deployment. Neural scene reconstruction converts driving logs into interactive 3D environments for simulation, but it does not produce complete 3D object assets required for agent manipulation and large-viewpoint novel-view synthesis. To address this challenge, we present Asset Harvester, an image-to-3D model and end-to-end pipeline that converts sparse, in-the-wild object observations from real driving logs into complete, simulation-ready assets. Rather than relying on a single model component, we developed a system-level design for real-world AV data that combines large-scale curation of object-centric training tuples, geometry-aware preprocessing across heterogeneous sensors, and a robust training recipe that couples sparse-view-conditioned multiview generation with 3D Gaussian lifting. Within this system, SparseViewDiT is explicitly designed to address limited-angle views and other real-world data challenges. Together with hybrid data curation, augmentation, and self-distillation, this system enables scalable conversion of sparse AV object observations into reusable 3D assets. --- ### Partner-aware Peptide-Protein Interaction Prediction and Target-conditioned Peptide Generation Authors: Chupei Tang, Junxiao Kong, Moyu Tang, Di Wang, Jixiu Zhai, Ronghao Xie, Shangkun Sima, Tianchi Lu Published: 2026-04-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.18467v3 Motivation: Peptide-protein interactions (PepPIs) are central to cellular regulation and peptide therapeutics, but experimental characterization remains too slow for large-scale screening. Existing methods usually emphasize either interaction prediction or peptide generation, leaving candidate prioritization, residue-level interpretation, and target-conditioned expansion insufficiently integrated. Results: We present an integrated framework for early-stage peptide screening that combines a partner-aware prediction and localization model (ConGA-PepPI) with a target-conditioned generative model (TC-PepGen). ConGA-PepPI uses asymmetric encoding, bidirectional cross-attention, and progressive transfer from pair prediction to binding-site localization, while TC-PepGen preserves target information throughout autoregressive decoding via layerwise conditioning. In five-fold cross-validation, ConGA-PepPI achieved 0.839 accuracy and 0.921 AUROC, with binding-site AUPR values of 0.601 on the protein side and 0.950 on the peptide side, and remained competitive on external benchmarks. Under a controlled length-conditioned benchmark, 40.39% of TC-PepGen peptides exceeded native templates in AlphaFold 3 ipTM, and unconstrained generation retained evidence of target-conditioned signal. --- ### An Integrated Deep-Learning Framework for Peptide-Protein Interaction Prediction and Target-Conditioned Peptide Generation with ConGA-PepPI and TC-PepGen Authors: Chupei Tang, Junxiao Kong, Moyu Tang, Di Wang, Jixiu Zhai, Ronghao Xie, Shangkun Sima, Tianchi Lu Published: 2026-04-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.18467v2 Motivation: Peptide-protein interactions (PepPIs) are central to cellular regulation and peptide therapeutics, but experimental characterization remains too slow for large-scale screening. Existing methods usually emphasize either interaction prediction or peptide generation, leaving candidate prioritization, residue-level interpretation, and target-conditioned expansion insufficiently integrated. Results: We present an integrated framework for early-stage peptide screening that combines a partner-aware prediction and localization model (ConGA-PepPI) with a target-conditioned generative model (TC-PepGen). ConGA-PepPI uses asymmetric encoding, bidirectional cross-attention, and progressive transfer from pair prediction to binding-site localization, while TC-PepGen preserves target information throughout autoregressive decoding via layerwise conditioning. In five-fold cross-validation, ConGA-PepPI achieved 0.839 accuracy and 0.921 AUROC, with binding-site AUPR values of 0.601 on the protein side and 0.950 on the peptide side, and remained competitive on external benchmarks. Under a controlled length-conditioned benchmark, 40.39% of TC-PepGen peptides exceeded native templates in AlphaFold 3 ipTM, and unconstrained generation retained evidence of target-conditioned signal. --- ### Semantic Step Prediction: Multi-Step Latent Forecasting in LLM Reasoning Trajectories via Step Sampling Authors: Yidi Yuan Published: 2026-04-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.18464v1 Semantic Tube Prediction (STP) leverages representation geometric to regularize LLM hidden-state trajectories toward locally linear geodesics during fine-tuning, thereby greatly improving data efficiency. The original STP recipe samples random token sub-spans, which is compatible with the base large language model (LLM) training architecture. Inspired by STP, we are interested to investigate whether the sampling position can further enhance the semantic structure of multi-step reasoning, and hence affect its geometric impact. We applied STP at consecutive semantic reasoning step boundaries and achieved 168x more accurate multi-step latent prediction than frozen baselines on ProcessBench (3,400 samples), compared to only 4x for the random-token STP. Probing the latent manifold with a learned non-linear predictor reveals that STP-shaped trajectories are smooth curves, not straight lines: a 3-layer MLP reduces prediction error by a further 3-12x over linear extrapolation on step-boundary models. Removing the language modeling loss yields trajectories that are 2x more MLP-predictable than the combined loss, revealing a tradeoff between generation quality and geometric purity. Our results identify sampling position as the critical variable in geometric regularization and establish multi-step latent prediction MSE as a new evaluation metric for this class of methods. --- ### Using large language models for embodied planning introduces systematic safety risks Authors: Tao Zhang, Kaixian Qu, Zhibin Li, Jiajun Wu, Marco Hutter, Manling Li, Fan Shi Published: 2026-04-20 Categories: cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2604.18463v2 Large language models are increasingly used as planners for robotic systems, yet how safely they plan remains an open question. To evaluate safe planning systematically, we introduce DESPITE, a benchmark of 12,279 tasks spanning physical and normative dangers with fully deterministic validation. Across 23 models, even near-perfect planning ability does not ensure safety: the best-planning model fails to produce a valid plan on only 0.4% of tasks but produces dangerous plans on 28.3%. Among 18 open-source models from 3B to 671B parameters, planning ability improves substantially with scale (0.4-99.3%) while safety awareness remains relatively flat (38-57%). We identify a multiplicative relationship between these two capacities, showing that larger models complete more tasks safely primarily through improved planning, not through better danger avoidance. Three proprietary reasoning models reach notably higher safety awareness (71-81%), while non-reasoning proprietary models and open-source reasoning models remain below 57%. As planning ability approaches saturation for frontier models, improving safety awareness becomes a central challenge for deploying language-model planners in robotic systems. --- ### Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective Authors: Sijie Mai, Shiqin Han Published: 2026-04-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.18460v1 Multimodal affective computing aims to predict humans' sentiment, emotion, intention, and opinion using language, acoustic, and visual modalities. However, current models often learn spurious correlations that harm generalization under distribution shifts or noisy modalities. To address this, we propose a causal modality-invariant representation (CmIR) learning framework for robust multimodal learning. At its core, we introduce a theoretically grounded disentanglement method that separates each modality into `causal invariant representation' and `environment-specific spurious representation' from a causal inference perspective. CmIR ensures that the learned invariant representations retain stable predictive relationships with labels across different environments while preserving sufficient information from the raw inputs via invariance constraint, mutual information constraint, and reconstruction constraint. Experiments across multiple multimodal benchmarks demonstrate that CmIR achieves state-of-the-art performance. CmIR particularly excels on out-of-distribution data and noisy data, confirming its robustness and generalizability. --- ### Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions Authors: Kecheng Zhang, Zongxin Yang, Mingfei Han, Haihong Hao, Yunzhi Zhuge, Changlin Li, Junhan Zhao, Zhihui Li, Xiaojun Chang Published: 2026-04-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.18459v1 Visual agents operating in the wild must respond to queries precisely when sufficient evidence first appears in a video stream, a critical capability that is overlooked by conventional video LLMs evaluated in offline settings. The shift to an online, streaming paradigm introduces significant challenges: a lack of decision transparency, the difficulty of aligning response timing with visual evidence, and the need to maintain a global, causally consistent understanding under tight computational budgets. To address these issues, we propose a novel framework that decouples reasoning control from memory integration. We introduce \textbf{\model{}}, an instantiation of this framework with two core components. First, the \emph{Active Thinking Decision Maker (ATDM)} is a transparent reasoning controller that externalizes its decision process using observable progress ($\boldsymbolρ$) and confidence ($\boldsymbol{c}$) metrics. This allows it to precisely time its response $t_r$ to match the first-sufficient-evidence timestamp $t^\star$ while streaming its reasoning to the user. Second, the \emph{Hierarchical Progressive Semantic Integration (HPSI)} module acts as an efficient memory system. It employs a set of learnable, multi-level aggregation tokens that are propagated across clips to build a rich, global cognitive state without exceeding token budgets. %Our approach sets a new standard on key online video understanding benchmarks, achieving strong performance of \textbf{71.6\%} on StreamingBench and \textbf{46.9\%} on OVOBench, demonstrating a robust solution for evidence-aligned and transparent online video analysis. Extensive experiments demonstrate the effectiveness of ATDM and HPSI, e.g., Thinking-QwenVL improves the accuracy of the previous state-of-the-art from 67.63\% to 71.60\% on the StreamingBench benchmark. --- ### ESsEN: Training Compact Discriminative Vision-Language Transformers in a Low-Resource Setting Authors: Clayton Fields, Casey Kennington Published: 2026-04-20 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.18452v1 Vision-language modeling is rapidly increasing in popularity with an ever expanding list of available models. In most cases, these vision-language models have parameters in the tens of billions, which is necessary for some needs, but in many cases smaller models are necessary (e.g., on edge devices or independent robotic platforms). Unfortunately, there is little research in producing light-weight models or in training them with small datasets. Inspired by the language learning progression and data sparsity in child development, in this paper, we address both of these goals in a systematic fashion. We show that two-tower encoder models are superior to one-tower encoders in low-resource settings for discriminative English tasks. We show also that incorporating traditional convolutional networks into the two-tower transformer architecture can help produce parameter efficient vision-language models. Finally, we show that the cross-modal fusion module of two-tower encoders can vary significantly in shape and size while producing the same results. In addition, we present ESsEN, a compact vision-language model that can be trained end-to-end with relatively few resources that performs as well on several tasks with only a fraction of the parameters compared to other models. The experimental results and the tools we present here make vision-language modeling more accessible to a wider variety of researchers. --- ### Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario Authors: Florentin Coeurdoux, Grégoire Ferré, Jean-Philippe Bouchaud Published: 2026-04-20 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2604.18450v1 Empirical studies of trained models often report a transient regime in which signal is detectable in a finite gradient descent time window before overfitting dominates. We provide an analytically tractable random-matrix model that reproduces this phenomenon for gradient flow in a linear teacher--student setting. In this framework, learning occurs when an isolated eigenvalue separates from a noisy bulk, before eventually disappearing in the overfitting regime. The key ingredient is anisotropy in the input covariance, which induces fast and slow directions in the learning dynamics. In a two-block covariance model, we derive the full time-dependent bulk spectrum of the symmetrized weight matrix through a $2\times 2$ Dyson equation, and we obtain an explicit outlier condition for a rank-one teacher via a rank-two determinant formula. This yields a transient Baik-Ben Arous-Péché (BBP) transition: depending on signal strength and covariance anisotropy, the teacher spike may never emerge, emerge and persist, or emerge only during an intermediate time interval before being reabsorbed into the bulk. We map the corresponding phase diagrams and validate the theory against finite-size simulations. Our results provide a minimal solvable mechanism for early stopping as a transient spectral effect driven by anisotropy and noise. --- ### AutoPPA: Automated Circuit PPA Optimization via Contrastive Code-based Rule Library Learning Authors: Chongxiao Li, Pengwei Jin, Di Huang, Guangrun Sun, Husheng Han, Jianan Mu, Xinyao Zheng, Jiaguo Zhu, Shuyi Xing, Hanjun Wei, Tianyun Ma, Shuyao Cheng et al. Published: 2026-04-20 Categories: cs.LG, cs.AR arXiv: https://arxiv.org/abs/2604.18445v2 Performance, power, and area (PPA) optimization is a fundamental task in RTL design, requiring a precise understanding of circuit functionality and the relationship between circuit structures and PPA metrics. Recent studies attempt to automate this process using LLMs, but neither feedback-based nor knowledge-based methods are efficient enough, as they either design without any prior knowledge or rely heavily on human-summarized optimization rules. In this paper, we propose AutoPPA, a fully automated PPA optimization framework. The key idea is to automatically generate optimization rules that enhance the search for optimal solutions. To do this, AutoPPA employs an Explore-Evaluate-Induce ($E^2I$) workflow that contrasts and abstracts rules from diverse generated code pairs rather than manually defined prior knowledge, yielding better optimization patterns. To make the abstracted rules more generalizable, AutoPPA employs an adaptive multi-step search framework that adopts the most effective rules for a given circuit. Experiments show that AutoPPA outperforms both the manual optimization and the state-of-the-art methods SymRTLO and RTLRewriter. --- ### ProtoCLIP: Prototype-Aligned Latent Refinement for Robust Zero-Shot Chest X-Ray Classification Authors: Florian Kittler, Sheethal Bhat, Andreas Maier Published: 2026-04-20 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.18444v1 Zero-shot vision-language models (VLMs) have shown promise for chest radiograph classification, but their performance is often limited by confounding label co-occurrence, long-tail class imbalance, and transfer instability under domain shift. We propose ProtoCLIP, a refinement strategy for CLIP-style VLMs that improves zero-shot discrimination through targeted data curation and distilled anchor alignment. Specifically, we construct pathology-focused training subsets with curated negative samples to reduce co-occurrence bias. We also introduce a representation-preserving distillation objective to stabilize adaptation while maintaining semantic structure and improving discrimination of clinically relevant co-occurring pathologies. Evaluated on an unseen dataset VinDr-CXR, ProtoCLIP improves AUC by 2-10 percentage points over a strong CLIP-based baseline across multiple findings. For pneumothorax specifically, ProtoCLIP achieves a state-of-the-art AUC of 0.94. These results demonstrate that anchor-guided refinement, coupled with curated supervision and controlled adaptation, can mitigate common zero-shot transfer failures in medical VLMs without requiring large-scale retraining. --- ### Conformal Robust Set Estimation Authors: Alejandro Cholaquidis, Emilien Joly, Leonardo Moreno Published: 2026-04-20 Categories: math.ST, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.18441v2 We introduce a robust conformal prediction method based on the half-mass radius $\dP(x):=\inf\{r>0:P(B(x,r))>1/2\}$. Its empirical version is exactly the distance from a point to its $\mathbf{k}$-th nearest neighbour, with $\mathbf{k}=\lfloor n/2\rfloor+1$. The resulting conformal sets retain finite-sample marginal validity and asymptotically target the robust population central set $\Qba:=\{x\in\R^d:\dP(x)\leβ_α\}$. We prove consistency in symmetric-difference probability, derive non-asymptotic exponential bounds and obtain the rate $O((\log n/n)^{1/2})$ under a local mass condition. Under the same local regularity on the uncontaminated law, we also establish quantitative $O(η)$ stability, uniformly over arbitrary contaminations of sufficiently small mass $η$, prove Hausdorff convergence of the empirical central sets, and provide computable ball-based representations using only pairwise distances. --- ### Conformal Robust Set Estimation Authors: Alejandro Cholaquidis, Emilien Joly, Leonardo Moreno Published: 2026-04-20 Categories: math.ST, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.18441v1 Conformal prediction provides finite-sample, distribution-free coverage under exchangeability, but standard constructions may lack robustness in the presence of outliers or heavy tails. We propose a robust conformal method based on a non-conformity score defined as the half-mass radius around a point, equivalently the distance to its $(\lfloor n/2\rfloor+1)$-nearest neighbour. We show that the resulting conformal regions are marginally valid for any sample size and converge in probability to a robust population central set defined through a distance-to-a-measure functional. Under mild regularity conditions, we establish exponential concentration and tail bounds that quantify the deviation between the empirical conformal region and its population counterpart. These results provide a probabilistic justification for using robust geometric scores in conformal prediction, even for heavy-tailed or multi-modal distributions. --- ### Scalable Physics-Informed Neural Differential Equations and Data-Driven Algorithms for HVAC Systems Authors: Hanfeng Zhai, Hongtao Qiao, Hassan Mansour, Christopher Laughman Published: 2026-04-20 Categories: cs.LG, eess.SY, nlin.AO arXiv: https://arxiv.org/abs/2604.18438v2 We present a scalable, data-driven simulation framework for large-scale heating, ventilation, and air conditioning (HVAC) systems that couples physics-informed neural ordinary differential equations (PINODEs) with differential-algebraic equation (DAE) solvers. At the component level, we learn heat-exchanger dynamics using an implicit PINODE formulation that predicts conserved quantities (refrigerant mass $M_r$ and internal energy $E_\text{hx}$) as outputs, enabling physics-informed training via automatic differentiation of mass/energy balances. Stable long-horizon prediction is achieved through gradient-stabilized latent evolution with gated architectures and layer normalization. At the system level, we integrate learned components with DAE solvers (IDA and DASSL) that explicitly enforce junction constraints (pressure equilibrium and mass-flow consistency), and we use Bayesian optimization to tune solver parameters for accuracy--efficiency trade-offs. To reduce residual system-level bias, we introduce a lightweight corrector network trained on short trajectory segments. Across dual-compressor and scaled network studies, the proposed approach attains multi-fold speedups over high-fidelity simulation while keeping errors low (MAPE below a few percent) and scales to systems with up to 16 compressor-condenser pairs. --- ### Revisiting Change VQA in Remote Sensing with Structured and Native Multimodal Qwen Models Authors: Yakoub Bazi, Mohamad M. Al Rahhal, Mansour Zuair, Faroun Mohamed Published: 2026-04-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.18429v1 Change visual question answering (Change VQA) addresses the problem of answering natural-language questions about semantic changes between bi-temporal remote sensing (RS) images. Although vision-language models (VLMs) have recently been studied for temporal RS image understanding, Change VQA remains underexplored in the context of modern multimodal models. In this letter, we revisit the CDVQA benchmark using recent Qwen models under a unified low-rank adaptation (LoRA) setting. We compare Qwen3-VL, which follows a structured vision-language pipeline with multi-depth visual conditioning and a full-attention decoder, with Qwen3.5, a native multimodal model that combines a single-stage alignment with a hybrid decoder backbone. Experimental results on the official CDVQA test splits show that recent VLMs improve over earlier specialized baselines. They further show that performance does not scale monotonically with model size, and that native multimodal models are more effective than structured vision-language pipelines for this task. These findings indicate that tightly integrated multimodal backbones contribute more to performance than scale or explicit multi-depth visual conditioning for language-driven semantic change reasoning in RS imagery. --- ### BhashaSutra: A Task-Centric Unified Survey of Indian NLP Datasets, Corpora, and Resources Authors: Raghvendra Kumar, Devankar Raj, Sriparna Saha Published: 2026-04-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.18423v1 India's linguistic landscape, spanning 22 scheduled languages and hundreds of marginalized dialects, has driven rapid growth in NLP datasets, benchmarks, and pretrained models. However, no dedicated survey consolidates resources developed specifically for Indian languages. Existing reviews either focus on a few high-resource languages or subsume Indian languages within broader multilingual settings, limiting coverage of low-resource and culturally diverse varieties. To address this gap, we present the first unified survey of Indian NLP resources, covering 200+ datasets, 50+ benchmarks, and 100+ models, tools, and systems across text, speech, multimodal, and culturally grounded tasks. We organize resources by linguistic phenomena, domains, and modalities; analyze trends in annotation, evaluation, and model design; and identify persistent challenges such as data sparsity, uneven language coverage, script diversity, and limited cultural and domain generalization. This survey offers a consolidated foundation for equitable, culturally grounded, and scalable NLP research in the Indian linguistic ecosystem. --- ### Spectral bandits for smooth graph functions Authors: Michal Valko, Rémi Munos, Branislav Kveton, Tomáš Kocák Published: 2026-04-20 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.18420v1 Smooth functions on graphs have wide applications in manifold and semi-supervised learning. In this paper, we study a bandit problem where the payoffs of arms are smooth on a graph. This framework is suitable for solving online learning problems that involve graphs, such as content-based recommendation. In this problem, each item we can recommend is a node and its expected rating is similar to its neighbors. The goal is to recommend items that have high expected ratings. We aim for the algorithms where the cumulative regret with respect to the optimal policy would not scale poorly with the number of nodes. In particular, we introduce the notion of an effective dimension, which is small in real-world graphs, and propose two algorithms for solving our problem that scale linearly and sublinearly in this dimension. Our experiments on real-world content recommendation problem show that a good estimator of user preferences for thousands of items can be learned from just tens of nodes evaluations. --- ### Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning Authors: Hen Davidov, Nachshon Cohen, Oren Kalinsky, Yaron Fairstein, Guy Kushilevitz, Ram Yazdi, Patrick Rebeschini Published: 2026-04-20 Categories: cs.LG, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2604.18419v6 LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses. Abstention can mitigate this by withholding outputs unlikely to be correct. While most abstention methods decide to withhold outputs before or after generation, dynamic mid-generation abstention considers early termination of unpromising reasoning traces at each token position. Prior work has explored empirical variants of this idea, but principled guidance for the abstention rule remains lacking. We present a formal analysis of dynamic abstention for LLMs, modeling abstention as an explicit action within a regularized reinforcement learning framework. An abstention reward parameter controls the trade-off between compute and information. We show that abstaining when the value function falls below this reward strictly outperforms natural baselines under general conditions. We further derive a principled and efficient method to approximate the value function. Empirical results on mathematical reasoning and toxicity avoidance tasks support our theory and demonstrate improved selective accuracy over existing methods. --- ### MedProbeBench: Systematic Benchmarking at Deep Evidence Integration for Expert-level Medical Guideline Authors: Jiyao Liu, Jianghan Shen, Sida Song, Tianbin Li, Xiaojia Liu, Rongbin Li, Ziyan Huang, Jiashi Lin, Junzhi Ning, Changkai Ji, Siqi Luo, Wenjie Li et al. Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.18418v1 Recent advances in deep research systems enable large language models to retrieve, synthesize, and reason over large-scale external knowledge. In medicine, developing clinical guidelines critically depends on such deep evidence integration. However, existing benchmarks fail to evaluate this capability in realistic workflows requiring multi-step evidence integration and expert-level judgment. To address this gap, we introduce MedProbeBench, the first benchmark leveraging high-quality clinical guidelines as expert-level references. Medical guidelines, with their rigorous standards in neutrality and verifiability, represent the pinnacle of medical expertise and pose substantial challenges for deep research agents. For evaluation, we propose MedProbe-Eval, a comprehensive evaluation framework featuring: (1) Holistic Rubrics with 1,200+ task-adaptive rubric criteria for comprehensive quality assessment, and (2) Fine-grained Evidence Verification for rigorous validation of evidence precision, grounded in 5,130+ atomic claims. Evaluation of 17 LLMs and deep research agents reveals critical gaps in evidence integration and guideline generation, underscoring the substantial distance between current capabilities and expert-level clinical guideline development. Project: https://github.com/uni-medical/MedProbeBench --- ### Balance-Guided Sparse Identification of Multiscale Nonlinear PDEs with Small-coefficient Terms Authors: Zhenhua Dang, Lei Zhang, Long Wang, Guowei He Published: 2026-04-20 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2604.18414v1 Data-driven discovery of governing equations has advanced significantly in recent years; however, existing methods often struggle in multiscale systems where dynamically significant terms may have small coefficients. Therefore, we propose Balance-Guided SINDy (BG-SINDy) inspired by the principle of dominant balance, which reformulates $\ell_0$-constrained sparse regression as a term-level $\ell_{2,0}$-regularized problem and solves it using a progressive pruning strategy. Terms are ranked according to their relative contributions to the governing equation balance rather than their absolute coefficient magnitudes. Based on this criterion, BG-SINDy alternates between least-squares regression and elimination of negligible terms, thereby preserving dynamically significant terms even when their coefficients are small. Numerical experiments on the Korteweg--de Vries equation with a small dispersion coefficient, a modified Burgers equation with vanishing hyperviscosity, a modified Kuramoto--Sivashinsky equation with multiple small-coefficient terms, and a two-dimensional reaction--diffusion system demonstrate the validity of BG-SINDy in discovering small-coefficient terms. The proposed method thus provides an efficient approach for discovering governing equations that contain small-coefficient terms. --- ### Six Llamas: Comparative Religious Ethics Through LoRA-Adapted Language Models Authors: Chad Coleman, W. Russell Neuman, Manan Shah, Ali Dasdan, Matthew Crispi, Morris Chiang, Zack Leitman, Mustafa Poonawala Published: 2026-04-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.18404v1 We present Six Llamas, a comparative study examining whether large language models fine-tuned on distinct religious corpora encode systematically different patterns of ethical reasoning. Six variants of Meta-Llama-3.1-8B are constructed: one unmodified control and five LoRA-adapted models trained exclusively on the sacred and theological texts of Christianity, Islam, Judaism, Hinduism, or Buddhism. All six models are probed with an identical battery of 17 standardized ethical prompts spanning moral dilemmas, game-theoretic scenarios, public policy questions, and moral-psychological self-assessments. To assess robustness and reproducibility, we implement a multi-temperature sampling design spanning ten temperature settings. We compute response consistency metrics, pairwise inter-model agreement rates, temperature sensitivity coefficients across four prompt domains, and run-to-run stability analyses. Findings show that LoRA-adapted models produce ethical reasoning patterns that are (a) systematically differentiated from the base model, (b) consistent with the moral logics of their training traditions, (c) structured along interpretable dimensions in moral-philosophical space, (d) core ethical positions remain stable across temperature variations for high-consensus dilemmas. The Trolley Problem achieves 100% consistency across all models and temperatures, while (e) tradition-specific divergence intensifies at higher temperatures in morally contested domains, and (f) the base model exhibits the highest overall response consistency (mean 88.3%), suggesting LoRA adaptation introduces both tradition-specific signal and increased sampling sensitivity. The study offers a proof-of-concept for the condensate comparative method using differentially trained language models as instruments for cultural and ethical analysis and identifies specific criteria for falsification and planned extensions. --- ### Adaptive Kernel Selection for Kernelized Diffusion Maps Authors: Othmane Aboussaad, Adam Miraoui, Boumediene Hamzi, Houman Owhadi Published: 2026-04-20 Categories: stat.ML, math.DS arXiv: https://arxiv.org/abs/2604.18402v1 Selecting an appropriate kernel is a central challenge in kernel-based spectral methods. In \emph{Kernelized Diffusion Maps} (KDM), the kernel determines the accuracy of the RKHS estimator of a diffusion-type operator and hence the quality and stability of the recovered eigenfunctions. We introduce two complementary approaches to adaptive kernel selection for KDM. First, we develop a variational outer loop that learns continuous kernel parameters, including bandwidths and mixture weights, by differentiating through the Cholesky-reduced KDM eigenproblem with an objective combining eigenvalue maximization, subspace orthonormality, and RKHS regularization. Second, we propose an unsupervised cross-validation pipeline that selects kernel families and bandwidths using an eigenvalue-sum criterion together with random Fourier features for scalability. Both methods share a common theoretical foundation: we prove Lipschitz dependence of KDM operators on kernel weights, continuity of spectral projectors under a gap condition, a residual-control theorem certifying proximity to the target eigenspace, and exponential consistency of the cross-validation selector over a finite kernel dictionary. --- ### CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities Authors: Daoyu Wang, Qingchuan Li, Mingyue Cheng, Jie Ouyang, Shuo Yu, Chunli Liu, Shijin Wang, Qi Liu, Enhong Chen Published: 2026-04-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.18401v5 Reinforcement learning (RL) has become a key technique for improving the agentic capabilities of large language models (LLMs). Although critic-free methods such as GRPO are increasingly popular, we argue that critic-based methods remain well suited to long-horizon agentic tasks because their critic models can assess each state and assign credit to different decisions. However, representative critic-based methods such as PPO still organize value estimation, credit assignment, and policy updates at token granularity, whereas the environment state changes only after the agent completes a full action. In this work, we propose CAPO, a critic-guided action-aligned policy optimization method for advancing LLM agent capabilities. CAPO introduces two action-aligned designs. First, it estimates the state value at the action boundary using a critic model and assigns the corresponding advantage to the complete action rather than individual tokens. Second, CAPO introduces a novel action-aware policy ratio that aggregates token ratios within each action with length calibration for consistent updates across actions of different lengths. These two designs effectively achieve fine-grained credit assignment and consistent policy updates while remaining compatible with token-level gradient computation. Experiments across multi-hop QA, academic paper search, and text-world action tasks show that CAPO consistently outperforms representative RL methods. Further analyses validate both designs and reveal how action-aligned optimization improves multi-turn RL training. We hope this work provides a practical path for training more capable LLM agents. --- ### StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning Authors: Daoyu Wang, Qingchuan Li, Mingyue Cheng, Jie Ouyang, Shuo Yu, Qi Liu, Enhong Chen Published: 2026-04-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.18401v4 Agentic reinforcement learning (RL) is emerging as a critical post-training paradigm for improving LLM agent capabilities. Existing RL algorithms for LLMs largely follow the token-centric paradigm as in RLHF and RLVR, where tokens serve as the basic units for modeling and optimization. However, this paradigm introduces a granularity mismatch in agentic RL, as it optimizes token-level predictions while LLM agents make step-level decisions through cycles of environmental observations and actions. To bridge this gap, we propose \textbf{StepPO}, a step-centric paradigm for agentic RL via step-aligned policy optimization. Specifically, we reformulate agentic RL from a token-level Markov Decision Process (MDP) into a step-level MDP, where interaction steps serve as the basic trajectory representations. We further propose step-level credit assignment to align policy optimization with the natural granularity of agent decisions. Together, StepPO optimizes agent policies at the step level for multi-turn agent-environment interaction. Experiments across multi-hop QA, academic paper search, and text-world action tasks show that StepPO consistently outperforms various RL algorithms. Further analyses provide insights into how step-centric paradigm improves agent training. We hope this step-centric paradigm offers a useful lens for understanding agent behavior and a practical path for training more capable LLM agents. --- ### Bridge-Centered Metapath Classification Using R-GCN-VGAE for Disaster-Resilient Maintenance Decisions Authors: Takato Yasuno Published: 2026-04-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.18399v1 Daily infrastructure management in preparation for disasters is critical for urban resilience. When bridges remain resilient against disaster-induced external forces, access to hospitals, shops, and residences via metapaths can be sustained, maintaining essential urban functions. However, prioritizing bridge maintenance under limited budgets requires quantifying the multi-dimensional roles that bridges play in disaster scenarios -- a challenge that existing single-indicator approaches fail to address. We focus on metapaths from national highways through bridges to buildings (hospitals, shops, residences), constructing a heterogeneous graph with road, bridge, and building layers. A Relation-centric Graph Convolutional Network Variational Autoencoder (R-GCN-VGAE) learns metapath-based feature representations, enabling classification of bridges into disaster-preparedness categories: Supply Chain (commercial logistics), Medical Access (emergency healthcare), and Residential Protection (preventing isolation). Using OSMnx and open data, we validate our methodology on three diverse cities in Ibaraki Prefecture, Japan: Mito (697 bridges), Chikusei (258 bridges), and Moriya (148 bridges), totaling 1,103 bridges. The heterogeneous graph construction from open data enables redefining bridge roles for disaster scenarios, supporting maintenance budget decision-making. We contributed that (1) Open-data methodology for constructing urban heterogeneous graphs. (2) Redefinition of bridge roles for disaster scenarios via metapath-based classification. (3) Establishment of maintenance budget decision support methodology. (4) k-NN tuning strategy validated across diverse city scales. (5) Empirical demonstration of UMAP superiority over t-SNE/PCA for multi-role bridge visualization. --- ### AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment Authors: Yixuan Wang, Yue Huang, Hong Qian, Yunzhao Wei, Yifei Ding, Wenkai Wang, Zhi Liu, Zhongjing Huang, Aimin Zhou, Jiajun Guo Published: 2026-04-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.18398v3 Creativity has become a core competence in the era of LLMs and human-AI collaboration, underpinning innovation in real-world problem solving. Crucially, the systematic improvement of creativity necessitates scientifically valid assessment instruments. Psychometric research recognizes context-based assessment as an effective way to measure creative thinking. However, high-quality expert-designed contexts remain scarce. Existing LLM-based generators often struggle with insufficient assessment cues, weak narrative coherence, limited stylistic diversity, and poor support for creative thinking. To address these challenges, we propose AlphaContext, an evolutionary tree-based psychometric context generator for creativity assessment. First, the HyperTree Outline Planner formalizes expert-designed outlining as a rule-guided hypertree and performs top-down hierarchical planning. The MCTS-based Context Generator fills the outline via MCTS to balance global structure and local quality. Then, the Evolutionary Context Optimizer evolves contexts with MAP-Elites by repeatedly updating niche elites to jointly improve diversity and quality. Finally, the Assessment-Guided Evolution Refiner simulates virtual participants with diverse styles and recycles weak contexts for further evolution. Experiments show that AlphaContext yields an average improvement of 8% over competitive methods across 6 quality metrics. --- ### River-LLM: Large Language Model Seamless Exit Based on KV Share Authors: Yingtao Shen, An Zou Published: 2026-04-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.18396v3 Large Language Models (LLMs) have demonstrated exceptional performance across diverse domains but are increasingly constrained by high inference latency. Early Exit has emerged as a promising solution to accelerate inference by dynamically bypassing redundant layers. However, in decoder-only architectures, the efficiency of Early Exit is severely bottlenecked by the KV Cache Absence problem, where skipped layers fail to provide the necessary historical states for subsequent tokens. Existing solutions, such as recomputation or masking, either introduce significant latency overhead or incur severe precision loss, failing to bridge the gap between theoretical layer reduction and practical wall-clock speedup. In this paper, we propose River-LLM, a training-free framework that enables seamless token-level Early Exit. River-LLM introduces a lightweight KV-Shared Exit River that allows the backbone's missing KV cache to be naturally generated and preserved during the exit process, eliminating the need for costly recovery operations. Furthermore, we utilize state transition similarity within decoder blocks to predict cumulative KV errors and guide precise exit decisions. Extensive experiments on mathematical reasoning and code generation tasks demonstrate that River-LLM achieves 1.53 to 2.16 times of practical speedup while maintaining high generation quality. --- ### One-Step Diffusion with Inverse Residual Fields for Unsupervised Industrial Anomaly Detection Authors: Boan Zhang, Wen Li, Guanhua Yu, Xiyang Liu, Wenchao Chen, Long Tian Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.18393v1 Diffusion models have achieved outstanding performance in unsupervised industrial anomaly detection (uIAD) by learning a manifold of normal data under the common assumption that off-manifold anomalies are harder to generate, resulting in larger reconstruction errors in data space or lower probability densities in the tractable latent space. However, their iterative denoising and noising nature leads to slow inference. In this paper, we propose OSD-IRF, a novel one-step diffusion with inverse residual fields, to address this limitation for uIAD task. We first train a deep diffusion probabilistic model (DDPM) on normal data without any conditioning. Then, for a test sample, we predict its inverse residual fields (IRF) based on the noise estimated by the well-trained parametric noise function of the DDPM. Finally, uIAD is performed by evaluating the probability density of the IRF under a Gaussian distribution and comparing it with a threshold. Our key observation is that anomalies become distinguishable in this IRF space, a finding that has seldom been reported in prior works. Moreover, OSD-IRF requires only single step diffusion for uIAD, thanks to the property that IRF holds for any neighboring time step in the denoising process. Extensive experiments on three widely used uIAD benchmarks show that our model achieves SOTA or competitive performance across six metrics, along with roughly a 2X inference speedup without distillation. --- ### Randomly Initialized Networks Can Learn from Peer-to-Peer Consensus Authors: Esteban Rodríguez-Betancourt, Edgar Casasola-Murillo Published: 2026-04-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.18390v1 In self-supervised learning, self-distilled methods have shown impressive performance, learning representations useful for downstream tasks and even displaying emergent properties. However, state-of-the-art methods usually rely on ensembles of complex mechanisms, with many design choices that are empirically motivated and not well understood. In this work, we explore the role of self-distillation within learning dynamics. Specifically, we isolate the effect of self-distillation by training a group of randomly initialized networks, removing all other common components such as projectors, predictors, and even pretext tasks. Our findings show that even this minimal setup can lead to learned representations with non-trivial improvements over a random baseline on downstream tasks. We also demonstrate how this effect varies with different hyperparameters and present a short analysis of what is being learned by the models under this setup. --- ### Understanding the Prompt Sensitivity Authors: Yang Liu, Chenhui Chu Published: 2026-04-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.18389v1 Prompt sensitivity, which refers to how strongly the output of a large language model (LLM) depends on the exact wording of its input prompt, raises concerns among users about the LLM's stability and reliability. In this work, we consider LLMs as multivariate functions and perform a first-order Taylor expansion, thereby analyzing the relationship between meaning-preserving prompts, their gradients, and the log probabilities of the model's next token. We derive an upper bound on the difference between log probabilities using the Cauchy-Schwarz inequality. We show that LLMs do not internally cluster similar inputs like smaller neural networks do, but instead disperse them. This dispersing behavior leads to an excessively high upper bound on the difference of log probabilities between two meaning-preserving prompts, making it difficult to effectively reduce to 0. In our analysis, we also show which types of meaning-preserving prompt variants are more likely to introduce prompt sensitivity risks in LLMs. In addition, we demonstrate that the upper bound is strongly correlated with an existing prompt sensitivity metric, PromptSensiScore. Moreover, by analyzing the logit variance, we find that prompt templates typically exert a greater influence on logits than the questions themselves. Overall, our results provide a general interpretation for why current LLMs can be highly sensitive to prompts with the same meaning, offering crucial evidence for understanding the prompt sensitivity of LLMs. Code for experiments is available at https://github.com/ku-nlp/Understanding_the_Prompt_Sensitivity. --- ### Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes Authors: Justin Bauer, Thomas Walshe, Derek Pham, Harit Vishwakarma, Armin Parchami, Frederic Sala, Paroma Varma Published: 2026-04-20 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.18381v1 Fine-tuning Large Language Models (LLMs) typically relies on large quantities of high-quality annotated data, or questions with well-defined ground truth answers in the case of Reinforcement Learning with Verifiable Rewards (RLVR). While previous work has explored the benefits to model reasoning capabilities by scaling both data and compute used for RLVR, these results lack applicability in many real-world settings where annotated data and accessible compute may be scarce. In this work, we present a comprehensive empirical study of open-source Small Language Model (SLM) performance after RLVR in low data regimes. Across three novel datasets covering number counting problems, graph reasoning, and spatial reasoning, we characterize how model performance scales with dataset size, diversity, and complexity. We demonstrate that (1) procedural datasets allow for fine-grained evaluation and training dataset development with controllable properties (size, diversity, and complexity), (2) under RLVR, models trained on lower complexity tasks can generalize to higher complexity tasks, and (3) training on mixed complexity datasets is associated with the greatest benefits in low data regimes, providing up to 5x sample efficiency versus training on easy tasks. These findings inspire future work on the development of data scaling laws for RLVR and the use of procedural data generators to further understand effective data development for efficient LLM fine-tuning. --- ### The implicated scientist: on the role of AI researchers in the development of weapons systems Authors: Alexandra Volokhova, Alex Hernandez-Garcia Published: 2026-04-20 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2604.18380v1 Artificial intelligence (AI) technologies are increasingly used in modern weapons systems. Notably, these systems have recently been involved in mass killings and destruction at scale. Furthermore, there is currently a strong interest and competition among powerful players to accelerate the proliferation of weapons with automated or AI-based components, a phenomenon known as AI arms race. This competition poses a risk of causing even more deaths and devastation in the future, as well as increased power and wealth inequality. In this work, we aim to shed light on the role of AI researchers as implicated subjects in the harms caused by weapons enabled by AI technologies. We investigate and discuss the specifics of this implication and explore ways to transfigure this position of implication into one of differentiated, long-distance solidarity with the victims of technologically fortified injustices. --- ### Forecasting Ionospheric Irregularities on GNSS Lines of Sight Using Dynamic Graphs with Ephemeris Conditioning Authors: Mert Can Turkmen, Eng Leong Tan, Yee Hui Lee Published: 2026-04-20 Categories: cs.LG, eess.SP, physics.geo-ph, physics.space-ph arXiv: https://arxiv.org/abs/2604.18379v2 Most data-driven ionospheric models operate on gridded products, which do not preserve the time-varying sampling structure of satellite-based sensing. We instead model the ionosphere as a dynamic graph over ionospheric pierce points, with connectivity that evolves as satellite positions change. Because satellite trajectories are predictable, the graph topology over the forecast horizon can be constructed in advance. We exploit this property to condition forecasts on the future graph structure, which we term ephemeris conditioning. This enables prediction on lines of sight (LoS) that appear only in the forecast horizon. We evaluate our framework on Global Navigation Satellite System data from a co-located receiver pair in Singapore spanning 2023 to 2025. The task is forecasting irregularities defined by the Rate of TEC Index (ROTI) up to 2 hours ahead as per-node binary classification. The resulting model, IonoDGNN, achieves a Brier Skill Score (BSS) of 0.55 and an area under the precision-recall curve (PR-AUC) of 0.77. These correspond to improvements over persistence of 53% in BSS and 58% in PR-AUC, with larger gains at longer lead times. Ablations confirm that graph structure and ephemeris conditioning each contribute meaningfully. Under simulated coverage dropout, the model retains predictive skill on affected nodes through spatial message passing from observed neighbors. Compared to interpolation baselines, the proposed model achieves better recovery, especially at higher dropout levels. These results suggest that dynamic graph forecasting on evolving LoS is a viable alternative for ionospheric modeling. The project and the dataset are available at https://github.com/Mert-chan/IonoDGNN. --- ### Towards Robust Text-to-Image Person Retrieval: Multi-View Reformulation for Semantic Compensation Authors: Chao Yuan, Yujian Zhao, Haoxuan Xu, Guanglin Niu Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.18376v1 In text-to-image person retrieval tasks, the diversity of natural language expressions and the implicitness of visual semantics often lead to the problem of Expression Drift, where semantically equivalent texts exhibit significant feature discrepancies in the embedding space due to phrasing variations, thereby degrading the robustness of image-text alignment. This paper proposes a semantic compensation framework (MVR) driven by Large Language Models (LLMs), which enhances cross-modal representation consistency through multi-view semantic reformulation and feature compensation. The core methodology comprises three components: Multi-View Reformulation (MVR): A dual-branch prompting strategy combines key feature guidance (extracting visually critical components via feature similarity) and diversity-aware rewriting to generate semantically equivalent yet distributionally diverse textual variants; Textual Feature Robustness Enhancement: A training-free latent space compensation mechanism suppresses noise interference through multi-view feature mean-pooling and residual connections, effectively capturing "Semantic Echoes"; Visual Semantic Compensation: VLM generates multi-perspective image descriptions, which are further enhanced through shared text reformulation to address visual semantic gaps. Experiments demonstrate that our method can improve the accuracy of the original model well without training and performs SOTA on three text-to-image person retrieval datasets. --- ### IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters Authors: Hongwei Zheng, Weiqi Wu, Zhengjia Wang, Guanyu Jiang, Haoming Li, Tianyu Wu, Yongchun Zhu, Jingwu Chen, Feng Zhang Published: 2026-04-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.18375v1 Conversational agents, such as ChatGPT and Doubao, have become essential daily assistants for billions of users. To further enhance engagement, these systems are evolving from passive responders to proactive companions. However, existing efforts focus on activation within ongoing dialogues, while overlooking a key real-world bottleneck. In the conversation initiation stage, users may have a vague need but no explicit query intent, creating a first-message barrier where the conversation holds before it begins. To overcome this, we introduce Conversation Starter Generation: generating personalized starters to guide users into conversation. However, unlike in-conversation stages where immediate context guides the response, initiation must operate in a cold-start moment without explicit user intent. To pioneer in this direction, we present IceBreaker that frames human ice-breaking as a two-step handshake: (i) evoke resonance via Resonance-Aware Interest Distillation from session summaries to capture trigger interests, and (ii) stimulate interaction via Interaction-Oriented Starter Generation, optimized with personalized preference alignment and a self-reinforced loop to maximize engagement. Online A/B tests on one of the world's largest conversational agent products show that IceBreaker improves user active days by +0.184% and click-through rate by +9.425%, and has been deployed in production. --- ### Dissecting AI Trading: Behavioral Finance and Market Bubbles Authors: Shumiao Ouyang, Pengfei Sui Published: 2026-04-20 Categories: econ.GN, cs.AI, q-fin.GN arXiv: https://arxiv.org/abs/2604.18373v1 We study how AI agents form expectations and trade in experimental asset markets. Using a simulated open-call auction populated by autonomous Large Language Model (LLM) agents, we document three main findings. First, AI agents exhibit classic behavioral patterns: a pronounced disposition effect and recency-weighted extrapolative beliefs. Second, these individual-level patterns aggregate into equilibrium dynamics that replicate classic experimental findings (Smith et al., 1988), including the predictive power of excess demand for future prices and the positive relationship between disagreement and trading volume. Third, by analyzing the agents' reasoning text through a twenty-mechanism scoring framework, we show that targeted prompt interventions causally amplify or suppress specific behavioral mechanisms, significantly altering the magnitude of market bubbles. --- ### Label-Efficient Bilateral Attention for Parkinson's Disease Screening from Wrist-Worn IMU Signals Authors: Meheru Zannat Published: 2026-04-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.18372v2 Parkinson's disease (PD) is a chronic neurodegenerative disorder. It shows multiple motor symptoms such as tremor, bradykinesia, postural instability, and freezing of gait (FoG). PD is currently diagnosed clinically through physical examination by health-care professionals, which can be time-consuming and highly subjective. Wearable IMU sensors have become a promising gateway for PD detection. We propose a time-interleaving encoder that processes bilateral wrist-worn IMU signals from the public PADS dataset, which consists of three groups, PD (Parkinson's Disease), HC (Healthy Control), and DD (Differential Diagnosis), across a total of 469 subjects. The encoder reaches 93.2%/90.9% accuracy (0.963/0.960 AUROC) on HC-vs-PD and PD-vs-DD; the lower sensitivity on the differential (0.812 vs. 0.994) confirms that separating PD from look-alike disorders is the harder clinical problem. Self-supervised representation learning with a contrastive InfoNCE objective attains 91.6%/89.5% accuracy using only 20% of the labels, within 1.5 points of the full-label ceiling, so near-saturation accuracy is reachable with minimal annotation. For real-time edge deployment we reach 124.5 ms per window on a Raspberry Pi 4. --- ### Parkinson's Disease Detection via Self-Supervised Dual-Channel Cross-Attention on Bilateral Wrist-Worn IMU Signals Authors: Meheru Zannat Published: 2026-04-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.18372v1 Parkinson's disease (PD) is a chronic neurodegenerative disease. It shows multiple motor symptoms such as tremor, bradykinesia, postural instability, freezing of gait (FoG). PD is currently diagnosed clinically through physical exam by health-care professionals, which can be time consuming and highly subjective. Wearable IMU sensors has become a promising gateway for passive monitoring of PD patients. We propose a self-supervised cross-attention encoder that processes bilateral wrist-worn IMU signals from a public dataset called PADS, consisting of three groups, PD (Parkinson Disease), HC (Healthy Control) and DD (Differential Diagnosis) of a total of 469 subjects. We have achieved a mean accuracy of 93.12% for HC vs. PD classification and 87.04% for PD vs. DD classification. The results emphasize the clinical challenge of distinguishing Parkinson's from other neurodegenerative diseases. Self-supervised representation learning using contrastive infoNCE loss gained an accuracy of 93.56% for HC vs. PD and 92.50% for PD vs. DD using only 20% of labelled data. This demonstrates the effectiveness of our method in transfer learning for clinical use with minimal labels. The real-time applicability was tested by deploying the optimized model with a mean inference time of 48.32 ms per window on a Raspberry Pi CPU. ---