# Research Papers — 2026-04 · bundle page 93 of 233 > Full-text markdown of papers #4601–4650 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/93 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/92.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/94.md) ### The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus Authors: Syed Muhammad Aqdas Rizvi Published: 2026-04-18 Categories: cs.AI, cs.CL, cs.CR, cs.DC arXiv: https://arxiv.org/abs/2604.16913v1 Decentralized Autonomous Organizations (DAOs) are inclined explore Small Language Models (SLMs) as edge-native constitutional firewalls to vet proposals and mitigate semantic social engineering. While scaling inference-time compute (System 2) enhances formal logic, its efficacy in highly adversarial, cryptoeconomic governance environments remains underexplored. To address this, we introduce Sentinel-Bench, an 840-inference empirical framework executing a strict intra-model ablation on Qwen-3.5-9B. By toggling latent reasoning across frozen weights, we isolate the impact of inference-time compute against an adversarial Optimism DAO dataset. Our findings reveal a severe compute-accuracy inversion. The autoregressive baseline (System 1) achieved 100% adversarial robustness, 100% juridical consistency, and state finality in under 13 seconds. Conversely, System 2 reasoning introduced catastrophic instability, fundamentally driven by a 26.7% Reasoning Non-Convergence (cognitive collapse) rate. This collapse degraded trial-to-trial consensus stability to 72.6% and imposed a 17x latency overhead, introducing critical vulnerabilities to Governance Extractable Value (GEV) and hardware centralization. While rare (1.5% of adversarial trials), we empirically captured "Reasoning-Induced Sycophancy," where the model generated significantly longer internal monologues (averaging 25,750 characters) to rationalize failing the adversarial trap. We conclude that for edge-native SLMs operating under Byzantine Fault Tolerance (BFT) constraints, System 1 parameterized intuition is structurally and economically superior to System 2 iterative deliberation for decentralized consensus. Code and Dataset: https://github.com/smarizvi110/sentinel-bench --- ### Skilldex: A Package Manager and Registry for Agent Skill Packages with Hierarchical Scope-Based Distribution Authors: Sampriti Saha, Pranav Hemanth Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.16911v1 Large Language Model (LLM) agents are increasingly extended at runtime via skill packages, structured natural-language instruction bundles loaded from a well-known directory. Community install tooling and registries exist, but two gaps persist: no public tool scores skill packages against Anthropic's published format specification, and no mechanism bundles related skills with the shared context they need to remain mutually coherent. We present Skilldex, a package manager and registry for agent skill packages addressing both gaps. The two novel contributions are: (1) compiler-style format conformance scoring against Anthropic's skill specification, producing line-level diagnostics on description specificity, frontmatter validity, and structural adherence; and (2) the skillset abstraction, a bundled collection of related skills with shared assets (vocabulary files, templates, reference documents) that enforce cross-skill behavioral coherence. Skilldex also provides supporting infrastructure: a three-tier hierarchical scope system, a human-in-the-loop agent suggestion loop, a metadata-only community registry, and a Model Context Protocol (MCP) server. The system is implemented as a TypeScript CLI (skillpm / spm) with a Hono/Supabase registry backend, and is open-source. --- ### LAGS: Low-Altitude Gaussian Splatting with Groupwise Heterogeneous Graph Learning Authors: Yikun Wang, Yujie Wan, Wei Zuo, Shuai Wang, Yik-Chung Wu, Chengzhong Xu, Huseyin Arslan Published: 2026-04-18 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.16910v3 Low-altitude Gaussian splatting (LAGS) facilitates 3D scene reconstruction by aggregating aerial images from distributed drones. However, as LAGS prioritizes maximizing reconstruction quality over communication throughput, existing low-altitude resource allocation schemes become inefficient. This inefficiency stems from their failure to account for image diversity introduced by varying viewpoints. To fill this gap, we propose a groupwise heterogeneous graph neural network (GW-HGNN) for LAGS resource allocation. GW-HGNN explicitly models the non-uniform contribution of different image groups to the reconstruction process, thus automatically balancing data fidelity and transmission cost. The key insight of GW-HGNN is to transform LAGS losses and communication constraints into graph learning costs for dual-level message passing. Experiments on real-world LAGS datasets demonstrate that GW-HGNN significantly outperforms state-of-the-art benchmarks across key rendering metrics, including PSNR, SSIM, and LPIPS. Furthermore, GW-HGNN reduces computational latency by approximately 100x compared to the widely-used MOSEK solver, achieving millisecond-level inference suitable for real-time deployment. --- ### LAGS: Low-Altitude Gaussian Splatting with Groupwise Heterogeneous Graph Learning Authors: Yikun Wang, Yujie Wan, Wei Zuo, Shuai Wang, Yik-Chung Wu, Chengzhong Xu, Huseyin Arslan Published: 2026-04-18 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.16910v2 Low-altitude Gaussian splatting (LAGS) facilitates 3D scene reconstruction by aggregating aerial images from distributed drones. However, as LAGS prioritizes maximizing reconstruction quality over communication throughput, existing low-altitude resource allocation schemes become inefficient. This inefficiency stems from their failure to account for image diversity introduced by varying viewpoints. To fill this gap, we propose a groupwise heterogeneous graph neural network (GW-HGNN) for LAGS resource allocation. GW-HGNN explicitly models the non-uniform contribution of different image groups to the reconstruction process, thus automatically balancing data fidelity and transmission cost. The key insight of GW-HGNN is to transform LAGS losses and communication constraints into graph learning costs for dual-level message passing. Experiments on real-world LAGS datasets demonstrate that GW-HGNN significantly outperforms state-of-the-art benchmarks across key rendering metrics, including PSNR, SSIM, and LPIPS. Furthermore, GW-HGNN reduces computational latency by approximately 100x compared to the widely-used MOSEK solver, achieving millisecond-level inference suitable for real-time deployment. --- ### PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations Authors: Yuhe Wu, Guangyu Wang, Yuran Chen, Jiatong Zhang, Yutong Zhang, Yujie Chen, Jiaming Shang, Guang Zhang, Zhuang Liu Published: 2026-04-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.16909v2 As large language models (LLMs) evolve from conversational assistants into agents capable of handling complex tasks, they are increasingly deployed in high-risk domains. However, existing benchmarks largely rely on mixed queries and posterior evaluation, output-level scoring, which quantifies hallucination severity but offers limited insight into where and why hallucinations arise in the generation pipeline. We therefore reformulate hallucination evaluation as a diagnostic problem and propose PRISM, a controlled benchmark that disentangles hallucinations into four dimensions: knowledge missing, knowledge errors, reasoning errors, and instruction-following errors, grounded in three stages of generation (memory, instruction, and reasoning). PRISM contains 9,448 instances across 65 tasks and supports fine-grained, stage-aware diagnostic evaluation. Evaluating 24 mainstream open-source and proprietary LLMs, we uncover consistent trade-offs across instruction following, memory retrieval, and logical reasoning, showing that mitigation strategies often improve specific dimensions at the expense of others. We hope PRISM provides a framework for understanding the specific mechanisms behind LLMs hallucinations, ultimately accelerating the development of trustworthy large language models. --- ### Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models Authors: Xinru Yan, Boxi Cao, Yaojie Lu, Hongyu Lin, Weixiang Zhou, Le Sun, Xianpei Han Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.16902v3 Native Omni-modal Large Language Models (OLLMs) have shifted from pipeline architectures to unified representation spaces. However, this native integration gives rise to a critical yet underexplored phenomenon: modality preference. To bridge this gap, we first systematically quantify modality preference of OLLMs using a newly-curated conflict-based benchmark and the modality selection rate metric. Our evaluation of ten representative OLLMs reveals a notable paradigm shift: unlike the ``text-dominance'' of traditional VLMs, most OLLMs exhibit a pronounced visual preference. To further understand the underlying mechanism, we conduct layer-wise probing and demonstrate that such modality preference is not static but emerges progressively in the mid-to-late layers. Building upon these insights, we leverage these internal signals to diagnose cross-modal hallucinations, achieving competitive performance across three downstream multi-modal benchmarks without task-specific data. Our work provides both a mechanistic understanding and a practical tool for building more trustworthy OLLMs. Our code and related resources are publicly available at: https://github.com/icip-cas/OmniPreference --- ### ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design Authors: Yutang Ge, Guojiang Zhao, Sihang Li, Zheng Cheng, Zifeng Zhao, Hanchen Xia, Guolin Ke, Linfeng Zhang, Zhifeng Gao, Yuguang Wang Published: 2026-04-18 Categories: q-bio.QM, cs.AI arXiv: https://arxiv.org/abs/2604.16896v1 Designing proteins that satisfy natural language functional requirements is a central goal in protein engineering. A straightforward baseline is to fine-tune generic instruction-tuned LLMs as direct text-to-sequence generators, but this is data- and compute-hungry. With limited supervision, LLMs can produce coherent plans in text yet fail to reliably realize them as sequences. This plan-execute gap motivates ProtoCycle, an agentic framework for protein design that uses LLMs primarily to drive a multi-round, feedback-driven decision cycle. ProtoCycle couples an LLM planner with a lightweight tool environment designed to emulate the iterative workflow of human protein engineering and uses LLM-driven reflection on tool feedback to revise plans. Trained with supervised trajectories and online reinforcement learning, ProtoCycle achieves strong language alignment while maintaining competitive foldability, and ablations show that reflection substantially improves sequence quality. --- ### Physics-Informed Tracking (PIT) Authors: Emil Hovad, Allan Peter Engsig-Karup Published: 2026-04-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16895v1 We propose Physics-Informed Tracking (PIT), a video-based framework for tracking a single particle from video, where a neural network autoencoder localizes a particle as a heatmap peak (landmark) and a differentiable physics module embedded in the autoencoder constrains several landmarks over time (a trajectory) to satisfy known dynamics. The novel Physics-Informed Landmark Loss (PILL) compares this predicted trajectory back against the landmarks, enforcing physical consistency without labels. Its supervised variant (PILLS) instead compares the prediction against ground-truth position, velocity, and bounce from simulation, enabling end-to-end backpropagation. To support supervised and unsupervised learning, we use an autoencoder with a split bottleneck that separates A) tracking-related structure via landmark heatmaps from B) background noise and subsequent image reconstruction. We evaluate a replicated 26 factorial design (n = 4 replicates, 64 configurations), showing that PILLS consistently achieves sub-pixel tracking accuracy for the bilinear and physics-refined decoder outputs under both clean and noisy conditions. --- ### Covariance-Based Structural Equation Modeling in Small-Sample Settings with $p>n$ Authors: Hiroki Hasegawa, Aoba Tamura, Yukihiko Okada Published: 2026-04-18 Categories: cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2604.16894v1 Factor-based Structural Equation Modeling (SEM) relies on likelihood-based estimation assuming a nonsingular sample covariance matrix, which breaks down in small-sample settings with $p>n$. To address this, we propose a novel estimation principle that reformulates the covariance structure into self-covariance and cross-covariance components. The resulting framework defines a likelihood-based feasible set combined with a relative error constraint, enabling stable estimation in small-sample settings where $p>n$ for sign and direction. Experiments on synthetic and real-world data show improved stability, particularly in recovering the sign and direction of structural parameters. These results extend covariance-based SEM to small-sample settings and provide practically useful directional information for decision-making. --- ### EasyVideoR1: Easier RL for Video Understanding Authors: Chuanyu Qin, Chenxu Yang, Qingyi Si, Naibin Gu, Dingyu Yao, Zheng Lin, Peng Fu, Nan Duan, Jiaqi Wang Published: 2026-04-18 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.16893v1 Reinforcement learning from verifiable rewards (RLVR) has demonstrated remarkable effectiveness in improving the reasoning capabilities of large language models. As models evolve into natively multimodal architectures, extending RLVR to video understanding becomes increasingly important yet remains largely unexplored, due to the diversity of video task types, the computational overhead of repeatedly decoding and preprocessing high-dimensional visual inputs, and the difficulty of reproducible evaluation across numerous sensitive hyperparameters. Existing open-source RL training frameworks provide solid infrastructure for text and image scenarios but lack systematic optimizations tailored for video modality. In this work, we present \textbf{EasyVideoR1}, a complete and efficient reinforcement learning framework specifically designed for training large vision-language models on video understanding tasks. EasyVideoR1 makes the following contributions: (1) a full video RL training pipeline with offline preprocessing and tensor caching that eliminates redundant video decoding and yields a 1.47 $\times$ throughput improvement; (2) a comprehensive, task-aware reward system covering 11 distinct video and image problem types with unified routing and modular extension; (3) a mixed offline-online data training paradigm that combines curated high-quality trajectories with on-policy exploration, benefiting the learning of more challenging tasks; (4) joint image-video training with independently configurable pixel budgets, allowing the two modalities to mutually reinforce each other; and (5) an asynchronous multi-benchmark evaluation framework covering 22 mainstream video understanding benchmarks, with reproduced accuracy closely aligned with officially reported scores. --- ### CrossFlowDG: Bridging the Modality Gap with Cross-modal Flow Matching for Domain Generalization Authors: Antonios Kritikos, Nikolaos Spanos, Athanasios Voulodimos Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16892v1 Domain generalization (DG) aims to maintain performance under domain shift, which in computer vision appears primarily as stylistic variations that cause models to overfit to domain-specific appearance cues rather than class semantics. To overcome this, recent methods use textual representations as stable, domain-invariant anchors. However, multimodal approaches that rely on cosine similarity-based contrastive alignment leave a modality gap where image and text embeddings remain geometrically separated despite semantic correspondence. We propose CrossFlowDG, a novel DG framework that addresses this residual gap using noise-free, cross-modal flow matching. By learning a continuous transformation in the joint Euclidean latent space, our framework explicitly transports domain-biased image embeddings toward domain-invariant text embeddings of the correct class. Using the efficient VMamba image encoder and CLIP's text encoder, CrossFlowDG is tested against four common DG benchmarks, and achieves competitive performance on several benchmarks and state-of-the-art on TerraIncognita. Code is available at: https://github.com/ajkrit/CrossFlowDG --- ### Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning Authors: Benteng Chen, Weida Wang, Shufei Zhang, Mingbao Lin, Min Zhang Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.16890v1 Large reasoning models that use long chain-of-thought excel at problem-solving yet waste compute on redundant checks. Curbing this overthinking is hard: training-time length penalties can cripple ability, while inference-time early-exit adds system overhead. To bridge this gap, we propose Step-GRPO, a novel post-training framework that internalizes dynamic early-exit capabilities directly into the model. Step-GRPO shifts the optimization objective from raw tokens to semantic steps by utilizing linguistic markers to structure reasoning. We introduce a Dynamic Truncated Rollout mechanism that exposes the model to concise high-confidence trajectories during exploration, synergized with a Step-Aware Relative Reward that dynamically penalizes redundancy based on group-level baselines. Extensive experiments across three model sizes on diverse benchmarks demonstrate that Step-GRPO achieves a superior accuracy-efficiency trade-off. On Qwen3-8B, our method reduces token consumption by 32.0\% compared to the vanilla model while avoiding the accuracy degradation observed in traditional length-penalty methods. --- ### Prune, Interpret, Evaluate: A Cross-Layer Transcoder-Native Framework for Efficient Circuit Discovery via Feature Attribution Authors: Qinhao Chen, Linyang He, Nima Mesgarani Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16889v2 Existing feature-interpretation pipelines typically operate on uniformly sampled units or exhaustive feature sets, incurring massive costs on units irrelevant to target behaviors. To address this, we introduce the first CLT-native end-to-end pruning framework, PIE, which pioneers the paradigm of pruning first and interpreting later. PIE connects Pruning, automatic Interpretation, and interpretation Evaluation, establishing a comprehensive benchmarking environment to systematically measure behavioral fidelity and downstream interpretability under pruning. Within this framework, we adapt strong relevance baselines and propose Feature Attribution Patching (FAP), a patch-grounded attribution method that scores CLT features by aggregating gradient-weighted write contributions. Furthermore, we introduce FAP-Synergy, a systematic synergy-aware reranking procedure. We evaluate pruning using KL-divergence behavior retention and assess interpretation quality with FADE-style metrics across IOI and Doc-String datasets. Across budget constraints of K in {50, 100, 200, 400, 800}, our rigorous benchmarking reveals distinct operational regimes: while base FAP and adapted baselines perform robustly at relaxed budgets, FAP-Synergy excels in highly constrained, strict-budget regimes. Crucially, we demonstrate a practical "Effective Budget" advantage: on the IOI task for both Llama-3.2-1B and Gemma-2-2B, FAP-Synergy at K=50 functionally matches the behavioral fidelity of baseline circuits at K=75. Because downstream evaluation costs scale linearly per feature, Synergy effectively grants the pipeline 25 "free" features, achieving K=75 fidelity while reducing interpretation costs by 33%. --- ### Towards Fully Parameter-Free Stochastic Optimization: Grid Search with Self-Bounding Analysis Authors: Yuheng Zhao, Yu-Hu Yan, Amit Attia, Tomer Koren, Lijun Zhang, Peng Zhao Published: 2026-04-18 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2604.16888v1 Parameter-free stochastic optimization aims to design algorithms that are agnostic to the underlying problem parameters while still achieving convergence rates competitive with optimally tuned methods. While some parameter-free methods do not require the specific values of the problem parameters, they still rely on prior knowledge, such as the lower or upper bounds of them. We refer to such methods as ``partially parameter-free''. In this work, we target achieving ``fully parameter-free'' methods, i.e., the algorithmic inputs do not need to satisfy any unverifiable condition related to the true problem parameters. We propose a powerful and general grid search framework, named \textsc{Grasp}, with a novel self-bounding analysis technique that effectively determines the search ranges of parameters, in contrast to previous work. Our method demonstrates generality in: (i) the non-convex case, where we propose a fully parameter-free method that achieves near-optimal convergence rate, up to logarithmic factors; (ii) the convex case, where our parameter-free methods are competitive with strong performance in terms of acceleration and universality. Finally, we contribute a sharper guarantee for the model ensemble, a final step of the grid search framework, under interpolated variance characterization. --- ### Bias-constrained multimodal intelligence for equitable and reliable clinical AI Authors: Cheng Li, Weijian Huang, Jiarun Liu, Hao Yang, Qi Yang, Song Wu, Ye Li, Hairong Zheng, Shanshan Wang Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16884v1 The integration of medical imaging and clinical text has enabled the emergence of generalist artificial intelligence (AI) systems for healthcare. However, pervasive biases, such as imbalanced disease prevalence, skewed anatomical region distributions, heterogeneous imaging protocols, and demographic disparities, pose significant challenges to the fairness and reliability of vision-language systems in real-world clinical settings. Here we present BiasCareVL, a bias-aware multimodal learning framework that introduces bias control directly into model design, rather than treating it as a post hoc correction. BiasCareVL incorporates adaptive uncertainty modeling with optional human-in-the-loop refinement to regulate the influence of dominant data patterns and to promote equitable reasoning under distributional imbalance. Trained on 3.44 million samples spanning over 15 imaging modalities, the framework supports diverse clinical tasks, including visual question answering, disease classification, segmentation, and report generation within a unified representation space. Across eight public benchmarks covering dermatology, oncology, radiology, and pathology, BiasCareVL consistently outperforms 20 state-of-the-art methods, with pronounced gains in clinically challenging scenarios, including over 10% accuracy improvement in multi-class skin lesion diagnosis and more than 20% Dice improvement in small tumor segmentation. Furthermore, BiasCareVL achieves diagnostic performance exceeding human accuracy with substantially reduced time requirements when evaluated with board-certified radiologists. By open-sourcing BiasCareVL, we aim to promote a transparent, reproducible, and equitable future for AI in healthcare, paving the way for general-purpose, trustworthy, and clinically reliable AI systems. --- ### SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models Authors: Junnan Liu, Xinyan Liu, Peifeng Gao, Zhaobo Qi, Beichen Zhang, Weigang Zhang, Antoni Bert Chen Published: 2026-04-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.16883v1 In long-context decoding for LLMs and LMMs, attention becomes increasingly memory-bound because each decoding step must load a large amount of KV-cache data from GPU memory. Existing acceleration strategies often trade efficiency for accuracy by relying on heuristic pruning that may discard useful information. At a deeper level, they also tend to indiscriminately preserve all high-scoring tokens, treat early tokens as indispensable anchors, or rely on heuristic head routing, reflecting an insufficient mechanistic understanding of the attention sink phenomenon. In this paper, we show that the attention sink phenomenon corresponds to a stable, reachable, and error-controllable fixed point constructed during training. Based on this insight, we propose SinkRouter, a training-free selective routing framework that detects the sink signal and skips computations that would otherwise produce near-zero output. To translate this mechanism into real-world acceleration, we develop a hardware-aware Triton kernel with block-level branching and Split-K parallelism. We conduct extensive evaluations on a diverse suite of long-context benchmarks, including LongBench, InfiniteBench, CVBench, MileBench, and MMVP, using both text-only and multimodal backbones such as Llama-3.1-8B, Llama-3.1-70B, Yi-9B-200K, LLaVA-1.5-7B, and LLaVA-1.5-13B. Across these settings, SinkRouter consistently improves decoding efficiency while maintaining competitive accuracy, and reaches 2.03x speedup with a 512K context. --- ### Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation Authors: Jiang Zhou, Xiaohu Zhao, Xinwei Wu, Tianyu Dong, Hao Wang, Yangyang Liu, Heng Liu, Linlong Xu, Longyue Wang, Weihua Luo, Deyi Xiong Published: 2026-04-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.16881v1 Cross-cultural entity translation remains challenging for large language models (LLMs) as literal or phonetic renderings are usually yielded instead of culturally appropriate translations in context. However, relevant knowledge may already be encoded in model parameters during large-scale pre-training. To incentivize the effective use of parametric knowledge, we propose EA-RLVR (Entity-Anchored Reinforcement Learning with Verifiable Rewards), a training framework that optimizes cross-cultural entity translation without relying on external knowledge bases. EA-RLVR anchors supervision on a verifiable, entity-level reward signal and incorporates lightweight structural gates to stabilize optimization. This design steers the model toward learning a robust reasoning process rather than merely imitating reference translations. We evaluate EA-RLVR on XC-Translate and observe consistent improvements in both entity translation accuracy and out-of-domain generalization. Specifically, training on merely 7k samples boosts Qwen3-14B's entity translation accuracy from 23.66\% to 31.87\% on a 50k test set comprising entirely unseen entities. The learned entity translation ability also transfers to general translation, yielding +1.35 XCOMET on WMT24++, which scales to +1.59 with extended optimization. Extensive analyses of $pass@k$ dynamics and reward formulations attribute these gains to superior sampling efficiency and a stable optimization landscape. --- ### Adaptive Forensic Feature Refinement via Intrinsic Importance Perception Authors: Jiazhen Yang, Junjun Zheng, Kejia Chen, Xiangheng Kong, Jie Lei, Zunlei Feng, Bingde Hu, Yang Gao Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16879v2 With the rapid development of generative models and multimodal content editing technologies, the key challenge faced by synthetic image detection (SID) lies in cross-distribution generalization to unknown generation sources. In recent years, visual foundation models (VFM), which acquire rich visual priors through large scale image-text alignment pretraining, have become a promising technical route for improving the generalization ability of SID. However, existing VFM-based methods remain relatively coarse-grained in their adaptation strategies. They typically either directly use the final layer representations of VFM or simply fuse multi layer features, lacking explicit modeling of the optimal representational hierarchy for transferable forgery cues. Meanwhile, although directly fine-tuning VFM can enhance task adaptation, it may also damage the cross-modal pretrained structure that supports open-set generalization. To address this task specific tension, we reformulate VFM adaptation for SID as a joint optimization problem: it is necessary both to identify the critical representational layer that is more suitable for carrying forgery discriminative information and to constrain the disturbance caused by task knowledge injection to the pretrained structure. Based on this, we propose I2P, an SID framework centered on intrinsic importance perception. I2P first adaptively identifies the critical layer representations that are most discriminative for SID, and then constrains task-driven parameter updates within a low sensitivity parameter subspace, thereby improving task specificity while preserving the transferable structure of pretrained representations as much as possible. --- ### OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction Authors: Zhongyuan Liang, Junhyung Jo, Hyang-Jung Lee, Sang Kyu Kim, Irene Y. Chen Published: 2026-04-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.16878v4 Early prediction of severe clinical deterioration and remaining length of stay can enable timely intervention and better resource allocation in high-acuity settings such as the ICU. This has driven the development of machine learning models that leverage continuous streams of vital signs and other physiological signals for real-time risk prediction. Despite their promise, existing methods have important limitations. Contrastive pretraining treats all patients as equally strong negatives, failing to capture clinically meaningful similarity between patients with related diagnoses. Meanwhile, downstream fine-tuning typically ignores complementary modalities such as clinical notes, which provide rich contextual information unavailable in physiological signals alone. To address these challenges, we propose OC-Distill, a two-stage framework that leverages multimodal supervision during training while requiring only vital signs at inference. In the first stage, we introduce an ontology-aware contrastive objective that exploits the ICD hierarchy to quantify patient similarity and learn clinically grounded representations. In the second stage, we fine-tune the pretrained encoder via cross-modal knowledge distillation, transferring complementary information from clinical notes into the model. Across multiple ICU prediction tasks on MIMIC, OC-Distill demonstrates improved label efficiency and achieves state-of-the-art performance among methods that use only vital signs at inference. --- ### OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction Authors: Zhongyuan Liang, Junhyung Jo, Hyang-Jung Lee, Sang Kyu Kim, Irene Y. Chen Published: 2026-04-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.16878v3 Early prediction of severe clinical deterioration and remaining length of stay can enable timely intervention and better resource allocation in high-acuity settings such as the ICU. This has driven the development of machine learning models that leverage continuous streams of vital signs and other physiological signals for real-time risk prediction. Despite their promise, existing methods have important limitations. Contrastive pretraining treats all patients as equally strong negatives, failing to capture clinically meaningful similarity between patients with related diagnoses. Meanwhile, downstream fine-tuning typically ignores complementary modalities such as clinical notes, which provide rich contextual information unavailable in physiological signals alone. To address these challenges, we propose OC-Distill, a two-stage framework that leverages multimodal supervision during training while requiring only vital signs at inference. In the first stage, we introduce an ontology-aware contrastive objective that exploits the ICD hierarchy to quantify patient similarity and learn clinically grounded representations. In the second stage, we fine-tune the pretrained encoder via cross-modal knowledge distillation, transferring complementary information from clinical notes into the model. Across multiple ICU prediction tasks on MIMIC, OC-Distill demonstrates improved label efficiency and achieves state-of-the-art performance among methods that use only vital signs at inference. --- ### Untrained CNNs Match Backpropagation at V1: A Systematic RSA Comparison of Four Learning Rules Against Human fMRI Authors: Nils Leutenegger Published: 2026-04-18 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2604.16875v3 CORRECTION (August 2026): an evaluation-mode defect affected the predictive-coding and STDP conditions of this study; those results should not be used pending re-computation. At V1 and 224px, predictive coding falls from rho = 0.056 to 0.016 and STDP from 0.064 to 0.037, so the claims that STDP leads among trained rules and that PC and STDP lead at V1/V2 are not supported. The random, backpropagation and feedback-alignment conditions, which carry the untrained-versus-trained claim, are unchanged to within 0.0013. The result is however strongly dependent on the evaluation resolution, held fixed at 224px here; see arXiv:2608.12408. See the correction note on page 1; the original abstract below and the body are unchanged from v1. A central question in computational neuroscience is whether the learning rule used to train a neural network determines how well its internal representations align with those of the human visual cortex. We present a systematic comparison of four learning rules (backpropagation (BP), feedback alignment (FA), predictive coding (PC), and spike-timing-dependent plasticity (STDP)) applied to identical convolutional architectures and evaluated against human fMRI data from the THINGS-fMRI dataset (720 stimuli, 3 subjects) using Representational Similarity Analysis (RSA). All models process stimuli at 224 x 224 resolution; results are averaged across 5 random seeds. Crucially, we include an untrained random-weights baseline that reveals the dominant role of architecture. At V1/V2, the untrained baseline exceeds backpropagation (rho = 0.076 vs. rho = 0.034; Delta-rho = +0.044, p < 0.001). At LOC, only BP reliably exceeds the random baseline (rho = 0.012 vs. -0.005, p < 0.001). At IT, all five conditions converge (rho = 0.008-0.014) with no significant pairwise differences among trained rules. Partial RSA confirms all effects survive pixel-similarity control. --- ### Untrained CNNs Match Backpropagation at V1: A Systematic RSA Comparison of Four Learning Rules Against Human fMRI Authors: Nils Leutenegger Published: 2026-04-18 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2604.16875v2 A central question in computational neuroscience is whether the learning rule used to train a neural network determines how well its internal representations align with those of the human visual cortex. We present a systematic comparison of four learning rules (backpropagation (BP), feedback alignment (FA), predictive coding (PC), and spike-timing-dependent plasticity (STDP)) applied to identical convolutional architectures and evaluated against human fMRI data from the THINGS-fMRI dataset (720 stimuli, 3 subjects) using Representational Similarity Analysis (RSA). All models process stimuli at 224 x 224 resolution; results are averaged across 5 random seeds. Crucially, we include an untrained random-weights baseline that reveals the dominant role of architecture. At V1/V2, the untrained baseline exceeds backpropagation (rho = 0.076 vs. rho = 0.034; Delta-rho = +0.044, p < 0.001), and STDP achieves the highest V1 alignment among trained rules (rho = 0.064). At LOC, only BP reliably exceeds the random baseline (rho = 0.012 vs. -0.005, p < 0.001). At IT, all five conditions converge (rho = 0.008-0.014) with no significant pairwise differences among trained rules (p > 0.05, FDR-corrected). FA consistently produces the lowest alignment at V1, V2, and LOC (rho = 0.012 at V1, below all other conditions). Partial RSA confirms all effects survive pixel-similarity control. Seed variability is small relative to between-rule differences at V1/V2. These results demonstrate that early visual alignment is architecture-driven, learning rules differentiate only at intermediate areas, and all rules converge at the highest levels of the hierarchy. --- ### GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning Authors: Hikaru Shindo, Henri Rößler, Quentin Delfosse, Kristian Kersting Published: 2026-04-18 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16871v1 Neuro-symbolic Reinforcement Learning (NeSy-RL) combines symbolic reasoning with gradient-based optimization to achieve interpretable and generalizable policies. Relational concepts, such as "left of" or "close by", serve as foundational building blocks that structure how agents perceive and act. However, conventional approaches require human experts to manually define these concepts, limiting adaptability since concept semantics vary across environments. We propose GRAIL (Grounding Relational Agents through Interactive Learning), a framework that autonomously grounds relational concepts through environmental interaction. GRAIL leverages large language models (LLMs) to provide generic concept representations as weak supervision, then refines them to capture environment-specific semantics. This approach addresses both sparse reward signals and concept misalignment prevalent in underdetermined environments. Experiments on the Atari games Kangaroo, Seaquest, and Skiing demonstrate that GRAIL matches or outperforms agents with manually crafted concepts in simplified settings, and reveals informative trade-offs between reward maximization and high-level goal completion in the full environment. --- ### Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives Authors: Daeyeon Son Published: 2026-04-18 Categories: cs.CR, cs.AI, cs.OS arXiv: https://arxiv.org/abs/2604.16870v2 AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP). These tool calls are the agent's syscalls: privileged operations with side effects on shared state, yet today's safety enforcement lives entirely in userspace, where a 10-line script can bypass it. I propose Governed MCP, a kernel-resident tool governance gateway built on a logit-based safety primitive (ProbeLogits). The gateway interposes on every MCP tool call in a 6-layer pipeline: schema validation, trust tier, rate limit, adversarial pre-filter, a ProbeLogits semantic gate (the load-bearing check), and constitutional policy match, with a Blake3-hashed audit chain. I implement Governed MCP in Anima OS, a bare-metal x86-64 kernel in ~286,000 lines of Rust. The five non-inference layers plus the audit append cost a measured 11.3 us per call; the ProbeLogits gate (one probe-prompt prefill plus a single logit read) costs 332-556 ms per classification across Qwen2.5-7B, Llama-3-8B, and Mistral-7B, 2.4-3.4x faster than a Llama Guard 3 pass on the same hardware. A silicon-measured ablation shows that removing the ProbeLogits layer collapses F1 from 0.789 to 0.357 (delta-F1 = -0.432): hand-rule firewalling alone is insufficient. Every WASM-to-system host function and every registered MCP tool is mediated by the kernel gateway, so the 10-line userspace bypass that defeats existing guardrail libraries is structurally impossible; a disclosed set of ring-3 syscall paths remains ungated pending future work. Multi-model validation across three architectures (HarmBench 98-99% non-copyright block, XSTest 98.5-100% unsafe recall, ToxicChat parity with Llama Guard 3) shows the underlying primitive is architecture-agnostic. Governed MCP demonstrates that tool-call governance is feasible as an OS primitive, not just an application-layer concern. --- ### Extraction of informative statistical features in the problem of forecasting time series generated by It{ô}-type processes Authors: Victor Korolev, Mikhail Ivanov, Tatiana Kukanova, Artyom Rukavitsa, Alexander Vakshin, Peter Solomonov, Alexander Zeifman Published: 2026-04-18 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2604.16865v1 In this paper, we consider the problem of extraction of most informative features from time series that are regarded as observed values of stochastic processes satisfying the It{ô} stochastic differential equations with unknown random drift and diffusion coefficients. We do not attract any additional information and use only the information contained in the time series as it is. Therefore, as additional features, we use the parameters of statistically adjusted mixture-type models of the observed regularities of the behavior of the time series. Several algorithms of construction of these parameters are discussed. These algorithms are based on statistical reconstruction of the coefficients which, in turn, is based on statistical separation of normal mixtures. We obtain two types of parameters by the techniques of the uniform and non-uniform statistical reconstruction of the coefficients of the underlying It{ô} process. The reconstructed coefficients obtained by uniform techniques do not depend on the current value of the process, while the non-uniform techniques reconstruct the coefficients with the account of their dependence on the value of the process. Actually, the non-uniform techniques used in this paper represent a stochastic analog of the Taylor expansion for the time series. The efficiency of the obtained additional features is compared by using them in the autoregressive algorithms of prediction of time series. In order to obtain pure conclusion that is not affected by unwanted factors, say, related to a special choice of the architecture of the neural network prediction methods, we used only simple autoregressive algorithms. We show that the use of additional statistical features improves the prediction. --- ### Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Models Authors: Yuchen Pan, Soung Chang Liew Published: 2026-04-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.16862v1 Recent deployments of large language models (LLMs) as autonomous trading agents raise questions about whether financial decision-making competence generalizes beyond specific market patterns and how it should be trained and evaluated in noisy markets lacking ground truth. We propose a structured framework for training and evaluating such models. Central to our approach is a curated, multiple-choice question (MCQ) dataset derived from classic textbooks and historical markets, verified by an AI committee, enriched with structured reasoning traces, and augmented to reduce shortcut learning. To evaluate whether performance on isolated MCQs generalizes to real-world trading, we introduce a two-stage protocol combining test-set evaluation with an MCQ-based chronological trading simulation. Extensive evaluations across market regimes provide statistically robust evidence that open models trained with our framework exhibit competitive, risk-aware behavior over time, outperform open-source baselines, and approach frontier-model performance at smaller scale. We release the dataset and evaluation framework to support further research. --- ### CCAR: Intrinsic Robustness as an Emergent Geometric Property Authors: Akash Samanta, Manish Pratap Singh, Debasis Chaudhuri Published: 2026-04-18 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2604.16861v1 Standard supervised learning optimizes for predictive accuracy but remains agnostic to the internal geometry of learned features, often yielding representations that are entangled and brittle. We propose Class-Conditional Activation Regularization (CCAR) to explicitly engineer the feature space, imposing a block-diagonal structure via a soft inductive bias. By shaping the latent representation to confine class energy to orthogonal subspaces, we create an intrinsic geometric scaffold that naturally filters noise and adversarial perturbations. We provide theoretical analysis linking this structural constraint to the maximization of the Fisher Discriminant Ratio, establishing a formal connection between geometric disentanglement and algorithmic stability. Empirically, this approach demonstrates that robustness is an emergent property of a well-engineered feature space, significantly outperforming baselines on label noise and input corruption benchmarks. --- ### GAMMA-Net: Adaptive Long-Horizon Traffic Spatio-Temporal Forecasting Model based on Interleaved Graph Attention and Multi-Axis Mamba Authors: Dongyi He, Yuanquan Gao, Bin Jiang, He Yan Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.16859v1 Accurate traffic forecasting is crucial for intelligent transportation systems, supporting effective traffic management, congestion reduction, and informed urban planning. However, traditional models often fail to adequately capture the intricate spatio-temporal dependencies present in traffic data. To overcome these limitations, we introduce GAMMA-Net, a novel approach that integrates Graph Attention Networks (GAT) with multi-axis Selective State Space Models (Mamba). The GAT component uses a self-attention mechanism to dynamically adjust the influence of nodes within the traffic network, enabling adaptive spatial dependency modeling based on real-time conditions. Simultaneously, the Mamba module efficiently models long-term temporal and spatial dynamics without the heavy computational cost of conventional recurrent architectures. Extensive experiments on several benchmark traffic datasets, including METR-LA, PEMS-BAY, PEMS03, PEMS04, PEMS07, and PEMS08, show that GAMMA-Net consistently outperforms existing state-of-the-art models across different prediction horizons, achieving up to a 16.25% reduction in Mean Absolute Error (MAE) compared to baseline models. Ablation studies highlight the critical contributions of both the spatial and temporal components, emphasizing their complementary role in improving prediction accuracy. In conclusion, the GAMMA-Net model sets a new standard in traffic forecasting, offering a powerful tool for next-generation traffic management and urban planning. The code for this study is available at https://github.com/hdy6438/GAMMA-Net --- ### Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement Authors: Xudong Li, Jiaxi Tan, Ziyin Zhou, Yan Zhong, Zihao Huang, Jingyuan Zheng, Yan Zhang, Xiawu Zheng, Rongrong Ji Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16858v1 Image Quality Assessment (IQA) models are increasingly deployed as perceptual critics to guide generative models and image restoration. This role demands not only accurate scores but also actionable, localized feedback. However, current MLLM-based methods adopt a single-look, language-only paradigm, which departs from human evidence-seeking judgment and yields weakly grounded rationales, limiting their reliability for in-the-loop refinement. We propose Q-DeepSight, a think-with-image framework that emulates this human-like process. It performs interleaved Multimodal Chain-of-Thought (iMCoT) with tool-augmented evidence acquisition (e.g., crop-and-zoom) to explicitly determine where quality degrades and why. To train these long iMCoT trajectories via reinforcement learning, we introduce two techniques: Perceptual Curriculum Reward (PCR) to mitigate reward sparsity and Evidence Gradient Filtering (EGF) to improve credit assignment for visually-grounded reasoning. Q-DeepSight achieves state-of-the-art performance across diverse benchmarks, including natural, restored, and AI-generated content. Furthermore, we demonstrate its practical value with Perceptual-in-Generation (PiG), a training-free framework where Q-DeepSight's diagnoses guide iterative image enhancement, effectively closing the loop between assessment and refinement. --- ### When W4A4 Breaks Camouflaged Object Detection: Token-Group Dual-Constraint Activation Quantization Authors: Tianqi Li, Wenyu Fang, Xin He, Xue Geng, Xu Cheng, Yun Liu Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16855v2 Camouflaged object detection (COD) segments objects that intentionally blend with the background, so predictions depend on subtle texture and boundary cues. COD is often needed under tight on-device memory and latency budgets, making low-bit inference highly desirable. However, COD is unusually hard to quantize aggressively. We study post-training W4A4 quantization of Transformer-based COD and find a task-specific cliff: heavy-tailed background tokens dominate a shared activation range, inflating the step size and pushing weak-but-structured boundary cues into the zero bin. This exposes a token-local bottleneck -- remove cross-token range domination and bound the zero-bin mass under 4-bit activations. To address this, we introduce COD-TDQ, a COD-aware Token-group Dual-constraint activation Quantization method. COD-TDQ addresses this token-local bottleneck with two coupled steps: Direct-Sum Token-Group (DSTG) assigns token-group scales to suppress cross-token range domination, and Dual-Constraint Range Projection (DCRP) projects each token-group clip range to keep the step-to-dispersion ratio and the zero-bin mass bounded. Across four COD benchmarks and two baseline models (CFRN and ESCNet), COD-TDQ consistently achieves an $S_α$ score more than 0.12 higher than that of the state-of-the-art quantization method without retraining. The code is available at https://github.com/MCG-NKU/nku-model-compre. --- ### Certainty Is Redundant: Token Sparsification for Efficient Camouflaged Object Detection with Vision Foundation Models Authors: Yuhan Gao, Shuhao Kang, Xin He, Bing Li, Ming-Ming Cheng, Yun Liu Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16854v2 Camouflaged object detection (COD) aims to segment objects that closely resemble their surrounding environments. Vision foundation models (VFMs) provide strong transferable representations for COD, but their large-scale architectures and full-token processing incur substantial computational overhead. To address this issue, we propose Certainty-Aware Token Sparsification (CATS) for efficient VFM-based COD. Rather than estimating general token importance, CATS determines whether each token still requires deeper refinement according to its foreground--background certainty. It progressively terminates the independent updates of high-certainty tokens while retaining ambiguous tokens for further reasoning, thereby shortening the active token sequence across encoder stages. Since computational redundancy does not imply informational irrelevance, we further introduce Dual-Path Feature Compensation (DPFC), which separately compresses removed foreground and background tokens into compact certainty-weighted prototypes. Extensive experiments across multiple VFMs, backbone scales, COD architectures, and benchmark datasets show that our method significantly reduces computational cost with only marginal accuracy degradation, suggesting a favorable accuracy--efficiency trade-off for VFM-based COD. The code will be released. --- ### CATP: Confidence-Aware Token Pruning for Camouflaged Object Detection Authors: Yuhan Gao, Shuhao Kang, Xin He, Bing Li, Xu Cheng, Yun Liu Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.16854v1 Camouflaged Object Detection (COD) aims to segment targets that share extreme textural and structural similarities with their complex environments. Leveraging their capacity for long-range dependency modeling, Transformer-based detectors have become the mainstream approach and achieve state-of-the-art (SoTA) accuracy, yet their substantial computational overhead severely limits practical deployment. To address this, we propose a hierarchical Confidence-Aware Token Pruning framework (CATP) tailored for COD. Our approach hierarchically identifies and discards easily distinguishable tokens from both background and object interiors, focusing computations on critical boundary tokens. To compensate for information loss from pruning, we introduce a dual-path feature compensation mechanism that aggregates contextual knowledge from pruned tokens into enriched features. Extensive experiments on multiple COD benchmarks demonstrate that our method significantly reduces computational complexity while maintaining high accuracy, offering a promising research direction for the efficient deployment of COD models in real-world scenarios. The code will be released. --- ### A Community-Based Approach for Stance Distribution and Argument Organization Authors: Rudra Ranajee Saha, Laks V. S. Lakshmanan, Raymond T. Ng Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16852v1 The proliferation of online debate platforms and social media has led to an unprecedented volume of argumentative content on controversial topics from multiple perspectives. While this wealth of perspectives offers opportunities for developing critical thinking and breaking filter bubbles (Pariser 2011), the sheer volume and complexity of arguments make it challenging for readers to synthesize and comprehend diverse viewpoints effectively. We present an unsupervised graph-based approach for community-based argument organization that helps users navigate and understand complex argumentative landscapes. Our system analyzes collections of topic-focused articles and constructs a rich interaction graph by capturing multiple relationship types between arguments: topic similarity, semantic coherence, shared keywords, and common entities. We then employ community detection to identify argument communities that reveal homogeneous and heterogeneous viewpoint distributions. The detected communities are simplified through strategic graph operations to present users with digestible, yet comprehensive summaries of key argumentative patterns. Our approach requires no training data and can effectively process hundreds of articles while preserving nuanced relationships between arguments. Experimental results demonstrate our system's ability to identify meaningful argument communities and present them in an interpretable manner, facilitating users' understanding of complex socio-political debates. --- ### Applications of deep generative models to DNA reaction kinetics and to cryogenic electron microscopy Authors: Chenwei Zhang Published: 2026-04-18 Categories: cs.LG, cs.AI, cs.CV, q-bio.BM, q-bio.QM arXiv: https://arxiv.org/abs/2604.16851v1 This dissertation explores how deep generative models can advance the analysis of challenging biological problems by integrating domain knowledge with deep learning. It focuses on two areas: DNA reaction kinetics and cryogenic electron microscopy (cryo-EM). In the first part, we present ViDa, a biophysics-informed framework leveraging variational autoencoders (VAEs) and geometric scattering transforms to generate biophysically-plausible embeddings of DNA reaction kinetics simulations. These embeddings are reduced to a two-dimensional space to visualize DNA hybridization and toehold-mediated strand displacement reactions. ViDa preserves structure and clusters trajectory ensembles into reaction pathways, making simulation results more interpretable and revealing new mechanistic insights. In the second part, we address key challenges in cryo-EM density map interpretation and protein structure modeling. We provide a comprehensive review and benchmarking of deep learning methods for atomic model building, with improved evaluation metrics and practical guidance. We then present Struc2mapGAN, a generative adversarial network that synthesizes high-fidelity experimental-like cryo-EM density maps from protein structures. Finally, we present CryoSAMU, a structure-aware multimodal U-Net that enhances intermediate-resolution cryo-EM maps by integrating density features with structural embeddings from protein language models via cross-attention. Overall, these contributions demonstrate the potential of deep generative models to interpret DNA reaction mechanisms and advance cryo-EM density map analysis and protein structure modeling. --- ### Refinement of Accelerated Demonstrations via Incremental Iterative Reference Learning Control for Fast Contact-Rich Imitation Learning Authors: Koki Yamane, Cristian C. Beltran-Hernandez, Steven Oh, Masashi Hamaya, Sho Sakaino Published: 2026-04-18 Categories: cs.RO, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2604.16850v1 Fast execution of contact-rich manipulation is critical for practical deployment, yet providing fast demonstrations for imitation learning (IL) remains challenging: humans cannot demonstrate at high speed, and naively accelerating demonstrations alters contact dynamics and induces large tracking errors. We present a method to autonomously refine time-accelerated demonstrations by repurposing Iterative Reference Learning Control (IRLC) to iteratively update the reference trajectory from observed tracking errors. However, applying IRLC directly at high speed tends to produce larger early-iteration errors and less stable transients. To address this issue, we propose Incremental Iterative Reference Learning Control (I2RLC), which gradually increases the speed while updating the reference, yielding high-fidelity trajectories. We validate on real-robot whiteboard erasing and peg-in-hole tasks using a teleoperation setup with a compliance-controlled follower and a 3D-printed haptic leader. Both IRLC and I2RLC achieve up to 10x faster demonstrations with reduced tracking error; moreover, I2RLC improves spatial similarity to the original trajectories by 22.5% on average over IRLC across three tasks and multiple speeds (3x-10x). We then use the refined trajectories to train IL policies; the resulting policies execute faster than the demonstrations and achieve 100% success rates in the peg-in-hole task at both seen and unseen positions, with I2RLC-trained policies exhibiting lower contact forces than those trained on IRLC-refined demonstrations. These results indicate that gradual speed scheduling coupled with reference adaptation provides a practical path to fast, contact-rich IL. --- ### TowerDataset: A Heterogeneous Benchmark for Transmission Corridor Segmentation with a Global-Local Fusion Framework Authors: Xu Cui, Xinyan Liu, Chen Yang, Zhaobo Qi, Beichen Zang, Weigang Zhang, Antoni B. Chan Published: 2026-04-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16848v1 Fine-grained semantic segmentation of transmission-corridor point clouds is fundamental for intelligent power-line inspection. However, current progress is limited by realistic data scarcity and the difficulty of modeling global corridor structure and local geometric details in long, heterogeneous scenes. Existing public datasets usually provide only a few coarse categories or short cropped scenes which overlook long-range structural dependencies, severe long-tail distributions, and subtle distinctions among safety-critical components. As a result, current methods are difficult to evaluate under realistic inspection settings, and their ability to preserve and integrate complementary global and local cues remains unclear. To address the above challenges, we introduce TowerDataset, a heterogeneous benchmark for transmission-corridor segmentation. TowerDataset contains 661 real-world scenes and about 2.466 billion points. It preserves long corridor extents, defines a fine-grained 22-class taxonomy, and provides standardized splits and evaluation protocols. In addition, we present a global-local fusion framework which preserves and fuses whole-scene and local-detail information. A whole-scene branch with NoCrop training and prototypical contrastive learning captures long-range topology and contextual dependencies. A block-wise local branch retains fine geometric structures. Both predictions are then fused and refined by geometric validation. This design allows the model to exploit both global relationships and local shape details when recognizing rare and confusing components. Experiments on TowerDataset and two public benchmarks demonstrate the challenge of the proposed benchmark and the robustness of our framework in real, complex, and heterogeneous transmission-corridor scenes. The dataset will be released soon at https://huggingface.co/datasets/tccx18/Towerdataset/tree/main. --- ### DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training Authors: Ziwen Pan, Zihan Liang, Jad Kabbara, Ali Emami Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16845v1 Large language models (LLMs) tuned for safety often avoid acknowledging demographic differences, even when such acknowledgment is factually correct (e.g., ancestry-based disease incidence) or contextually justified (e.g., religious hiring preferences). This identity-blindness yields incorrect responses, unnecessary refusals, or generic "equal-treatment" defaults. We study this via difference-awareness classification: given a question involving demographic groups, the task is not to answer directly, but to classify whether a correct answer requires recognizing group differences (yes) or whether groups should be treated identically (no). Crucially, fine-tuning for accuracy triggers harm drift: model-generated explanations become increasingly harmful as decision accuracy improves, whether by elaborating harmful content, introducing problematic assumptions, or failing to flag harms the baseline identified. To mitigate this, we introduce DART (Distill--Audit--Repair Training), which distills label-conditioned reasoning from a teacher, audits outputs for harm drift cases relative to baseline, and repairs problematic cases via severity-weighted fine-tuning. On eight benchmarks, DART improves Llama-3-8B-Instruct accuracy from 39.0% to 68.8%, with largest gains on equal-treatment prompts (11.3% -> 72.6%), while reducing harm drift cases by 72.6%. It also transfers to 280 open-ended real-world queries across medical, legal, policy, and educational domains, improving difference-appropriate responses from 39.8% to 77.5% while reducing refusals from 34.3% to 3.0%. Our results demonstrate that accuracy and safety need not conflict when explicit detection and repair mechanisms are in place. --- ### Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches Authors: Yixuan Wang Published: 2026-04-18 Categories: math.NA, cs.LG, math.AP arXiv: https://arxiv.org/abs/2604.16842v1 This thesis develops numerical and theoretical approaches for understanding and analyzing singularity formation in Partial Differential Equations (PDEs). The singularity formation in the Navier-Stokes Equation (NSE) is famously challenging as one of the seven Clay Prize problems. Unlike simpler equations such as the Nonlinear Heat (NLH) or Keller-Segel (KS) equations, where formal asymptotics near blowup are better understood, the intrinsic complexity of NSE makes quantitative analytical treatment difficult, if not impossible, without numerical guidance. Building on numerical insights, we introduce a robust analytical framework to simplify and systematize pen-and-paper proofs for simpler singular PDEs. We present a novel approach based on enforcing vanishing modulation conditions for perturbations around approximate blowup profiles, complemented by singularly weighted energy estimates. We demonstrate the efficacy of our method on PDEs with complicated asymptotics, such as NLH and the Complex Ginzburg-Landau (CGL) equation, and address the open problem of singularity formation in the 3D KS equation with logistic damping. We develop and refine numerical approaches that facilitate deeper insights into singularity formation. We demonstrate that machine learning methods significantly enhance our capability to identify and characterize potential blowup solutions with high precision. We improve on existing Physics-Informed Neural Network (PINN) and Neural Operator (NO) frameworks. Moreover, we present a novel machine learning paradigm, the Kolmogorov-Arnold Network (KAN) architecture, whose interpretability and excellent scaling properties are achieved through learnable nonlinearities. --- ### When Earth Foundation Models Meet Diffusion: An Application to Land Surface Temperature Super-Resolution Authors: Yiheng Chen, Zihui Ma, Peishi Jiang, Yilong Dai, Qikai Hu, Xinyue Ye, Lingyao Li, Rita Sousa, Runlong Yu Published: 2026-04-18 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.16841v1 Land surface temperature (LST) super-resolution is important for environmental monitoring. However, it remains challenging as coarse thermal observations severely underdetermine fine-scale structure. In this paper, we propose Earth Foundation Model-guided Diffusion (EFDiff), a novel framework for super-resolution under extreme spatial degradation. EFDiff uses the Prithvi-EO-2.0 Earth foundation model to encode high-resolution multispectral reflectance into geospatial embeddings, which are injected into the denoising network via cross-attention to guide fine-scale reconstruction from highly degraded observations. We study two variants, EFDiff-$ε$ and EFDiff-$x_0$, which offer complementary trade-offs between perceptual realism and pixel-level fidelity. We evaluate EFDiff under an extreme $32\times$ scale gap using a globally diverse benchmark comprising 242,416 co-registered Landsat thermal-reflectance patches. Results show that EFDiff consistently outperforms baseline methods and that cross-attention conditioning by EFM is more effective than HLS channel concatenation. Although we present EFDiff in the context of LST super-resolution, the framework is broadly applicable to remote sensing problems in which pretrained geospatial representations can guide generative reconstruction. --- ### HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents Authors: Jinchang Zhu, Jindong Li, Cheng Zhang, Jiahong Liu, Menglin Yang Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16839v1 Long-term memory is a critical challenge for Large Language Model agents, as fixed context windows cannot preserve coherence across extended interactions. Existing memory systems represent conversation history as unstructured embedding vectors, retrieving information through semantic similarity. This paradigm fails to capture the associative structure of human memory, wherein related experiences progressively strengthen interconnections through repeated co-activation. Inspired by cognitive neuroscience, we identify three mechanisms central to biological memory: association, consolidation, and spreading activation, which remain largely absent in current research. To bridge this gap, we propose HeLa-Mem, a bio-inspired memory architecture that models memory as a dynamic graph with Hebbian learning dynamics. HeLa-Mem employs a dual-level organization: (1) an episodic memory graph that evolves through co-activation patterns, and (2) a semantic memory store populated via Hebbian Distillation, wherein a Reflective Agent identifies densely connected memory hubs and distills them into structured, reusable semantic knowledge. This dual-path design leverages both semantic similarity and learned associations, mirroring the episodic-semantic distinction in human cognition. Experiments on LoCoMo demonstrate superior performance across four question categories while using significantly fewer context tokens. Code is available on GitHub: https://github.com/ReinerBRO/HeLa-Mem --- ### enclawed: A Configurable, Sector-Neutral Hardening Framework for Single-User AI Assistant Gateways Authors: Alfredo Metere Published: 2026-04-18 Categories: cs.CR, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.16838v2 We present enclawed, a hard-fork hardening framework built on the OpenClaw AI assistant gateway. enclawed targets deployments that need attestable peer trust, deny-by-default external connectivity, signed-module loading, and a tamper-evident audit trail -- typically regulated industries (financial services, healthcare, defense, government). The framework ships in two flavors: an open flavor preserving OpenClaw compatibility while emitting audit, classification, and data-loss-prevention (DLP) signals, and an enclaved flavor activating strict allowlists, FIPS cryptographic-module assertion, mandatory manifest signature verification, and high-assurance peer attestation for the Model Context Protocol. The classification ladder is data-driven: deployers pick from five built-in presets or supply their own JSON. We ship a 356-case test suite (261 unit + 95 adversarial pen-tests) covering tamper detection, signature forgery, egress bypass, audit-log truncation, trust-root mutation, DLP evasion, prompt injection, code injection, and biconditional admission for net-capable extensions; real-time human-in-the-loop control; a memory-bounded transaction buffer with rollback; strict-mode TypeScript typecheck; and a CI workflow. The biconditional extension-admission gate extends the skill trust schema to non-skill extensions. The four-level verification lattice is now closed at the top: four skill-formal-* primitives plus a CLI produce a signed proof-carrying bundle the runtime re-checks at load, raising a skill from tested to formal via static effect-containment, refinement-typed dispatch, and bounded model checking. enclawed is a hardening framework, not an accredited certification; hardware, validated crypto, facilities, and assessor sign-off remain the deployer's responsibility. --- ### Lorentz Framework for Semantic Segmentation Authors: Zahid Hasan, Masud Ahmed, Nirmalya Roy Published: 2026-04-18 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16836v1 Semantic segmentation in hyperbolic space enables compact modeling of hierarchical structure while providing inherent uncertainty quantification. Prior approaches predominantly rely on the Poincaré ball model, which suffers from numerical instability, optimization, and computational challenges. We propose a novel, tractable, architecture-agnostic semantic segmentation framework (pixel-wise and mask classification) in the hyperbolic Lorentz model. We employ text embeddings with semantic and visual cues to guide hierarchical pixel-level representations in Lorentz space. This enables stable and efficient optimization without requiring a Riemannian optimizer, and easily integrates with existing Euclidean architectures. Beyond segmentation, our approach yields free uncertainty estimation, confidence map, boundary delineation, hierarchical and text-based retrieval, and zero-shot performance, reaching generalized flatter minima. We introduce a novel uncertainty and confidence indicator in Lorentz cone embeddings. Further, we provide analytical and empirical insights into Lorentz optimization via gradient analysis. Extensive experiments on ADE20K, COCO-Stuff-164k, Pascal-VOC, and Cityscapes, utilizing state-of-the-art per-pixel classification models (DeepLabV3 and SegFormer) and mask classification models (mask2former and maskformer), validate the effectiveness and generality of our approach. Our results demonstrate the potential of hyperbolic Lorentz embeddings for robust and uncertainty-aware semantic segmentation. Code is available at https://github.com/mxahan/Lorentz_semantic_segmentation. --- ### The CTLNet for Shanghai Composite Index Prediction Authors: Haibin Jiao Published: 2026-04-18 Categories: q-fin.ST, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16835v1 Shanghai Composite Index prediction has become a hot issue for many investors and academic researchers. Deep learning models are widely applied in multivariate time series forecasting, including recurrent neural networks (RNN), convolutional neural networks (CNN), and transformers. Specifically, the Transformer encoder, with its unique attention mechanism and parallel processing capabilities, has become an important tool in time series prediction, and has an advantage in dealing with long sequence dependencies and multivariate data correlations. Drawing on the strengths of various models, we propose the CNN-Transformer-LSTM Networks (CTLNet). This paper explores the application of CTLNet for Shanghai Composite Index prediction and the comparative experiments show that the proposed model outperforms state-of-the-art baselines. --- ### Towards Deep Encrypted Training: Low-Latency, Memory-Efficient, and High-Throughput Inference for Privacy-Preserving Neural Networks Authors: Nges Brian Njungle, Eric Jahns, Michel A. Kinsy Published: 2026-04-18 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2604.16834v1 Privacy-preserving machine learning (PPML) has become increasingly important in applications where sensitive data must remain confidential. Homomorphic Encryption (HE) enables computation directly on encrypted data, allowing neural network inference without revealing raw inputs. While prior works have largely focused on inference over a single encrypted image, batch processing of encrypted inputs lags behind, despite being critical for high-throughput inference scenarios and training-oriented workloads. In this work, we address this gap by developing optimized algorithms for batched HE-friendly neural networks. We also introduced a pipeline architecture designed to maximize resource efficiency for different batch size execution. We implemented these algorithms and evaluated our work using HE-friendly ResNet-20 and ResNet-34 models on encrypted CIFAR-10 and CIFAR-100 datasets, respectively. For ResNet-20, our approach achieves an amortized inference time of 8.86 seconds per image when processing a batch of 512 encrypted images, with a peak memory usage of 98.96 GB. These results represent a 1.78x runtime improvement and a 3.74x reduction in memory usage compared to the state-of-the-art design. For the deeper ResNet-34 model, we achieve an amortized inference time of 28.14 on a batch of 256 encrypted images using 246.78GB of RAM --- ### The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation Authors: Jiaxin Zhang, Xiangyu Peng, Qinglin Chen, Qinyuan Ye, Caiming Xiong, Chien-Sheng Wu Published: 2026-04-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.16830v1 On-policy distillation (OPD) is an increasingly important paradigm for post-training language models. However, we identify a pervasive Scaling Law of Miscalibration: while OPD effectively improves task accuracy, it systematically traps models in severe overconfidence. We trace this failure to an information mismatch: teacher supervision is formed under privileged context available during training, whereas the deployed model must report confidence using only deployment-time information. We formalize this perspective theoretically, showing that teacher-conditioned success is generally not a valid target for deployment-time confidence and that helpful privileged context induces entropy collapse and a systematic optimism bias. To address this, we propose a calibration-aware OPD framework, CaOPD, that estimates empirical confidence from model rollouts, replaces self-reported confidence with this student-grounded target, and distills the revised response through the same self-distillation pipeline. Experiments across various models and domains show that CaOPD achieves Pareto-optimal calibration while maintaining competitive capability, generalizing robustly under out-of-distribution and continual learning. Our findings highlight that capability distillation does not imply calibrated confidence, and that confidence should be treated as an essential objective in post-training. Code: https://github.com/SalesforceAIResearch/CaOPD --- ### Crowded in B-Space: Calibrating Shared Directions for LoRA Merging Authors: Yixuan Tang, Yi Yang Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16826v1 Merging separately trained LoRA adapters is a practical alternative to joint multi-task training, but it often hurts performance. Existing methods usually treat the LoRA update $ΔW = BA$ as a single object and do not distinguish the two LoRA matrices. We show that the main source of LoRA merge interference comes from the output-side matrix $B$. Across tasks, $B$ repeatedly uses a small set of shared directions, while $A$ remains much more task-specific. As a result, the merged adapter overemphasizes these shared directions, and task-specific information is lost. We propose Pico (Pre-merge interference calibration in output-space), a data-free method that calibrates $B$ before merge by downscaling over-shared directions and then rescaling the merged update. Pico plugs directly into existing merging methods such as Task Arithmetic, TIES, and TSV-M. Across eight different benchmarks from math, coding, finance, and medical domains, Pico improves average accuracy by 3.4-8.3 points over the corresponding base method and achieves the best overall average performance. Pico also enables merged adapters to outperform the LoRA trained with all task data. These results show that LoRA merging works better when the two LoRA matrices are treated separately. --- ### SafeDream: Safety World Model for Proactive Early Jailbreak Detection Authors: Bo Yan, Weikai Lin, Yada Zhu, Song Wang Published: 2026-04-18 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.16824v1 Multi-turn jailbreak attacks progressively erode LLM safety alignment across seemingly innocuous conversation turns, achieving success rates exceeding 90% against state-of-the-art models. Existing alignment-based and guardrail methods suffer from three key limitations: they require costly weight modification, evaluate each turn independently without modeling cumulative safety erosion, and detect attacks only after harmful content has been generated. To address these limitations, we first formulate the proactive early jailbreak detection problem with a new metric, detection lead, that measures how early an attack can be detected before the LLM complies. We then propose SAFEDREAM, a lightweight world-model-based framework that operates as an external module without modifying the LLM's weights. SAFEDREAM introduces three components: (1) a safety state world model that encodes LLM hidden states into a compact safety representation and predicts how it evolves across turns, (2) CUSUM detection that accumulates weak per-turn risk signals into reliable evidence, and (3) contrastive imagination that simultaneously rolls out attack and benign futures in latent space to issue early alarms before jailbreaks occur. On three multi-turn jailbreak benchmarks (XGuard-Train, SafeDialBench, SafeMTData) against 8 baselines, SAFEDREAM achieves the best detection timeliness across all benchmarks (1.06-1.20 turns before compliance) while maintaining competitive false positive rates and outperforming baselines in detection quality. --- ### Hierarchical Vision Transformer Enhanced by Graph Convolutional Network for Image Classification Authors: Haibin Jiao Published: 2026-04-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16823v1 Vision Transformer (ViT) has brought new breakthroughs to the field of image classification by introducing the self-attention mechanism and Graph Convolutional Networks(GCN) have been proposed and successfully applied in data representation and analysis. However, there are key challenges which limit their further development: (1) The patch size selected by ViT is crucial for accurate predictions, which raises a natural question: How to select the size of patches properly or how to comprehensively combine small patches and larger patches; (2) While the spatial structure information is important in vision tasks, the 1D position embeddings fails to capture the spatial structure information of patches more accurately; (3) The GCN can capture the local connectivity relationships between image nodes, but it lacks the ability to capture global graph structural information. On the contrary, the self-attention mechanism of ViT can draw the global relation on image patches, but it is unable to model the local structure of image. To overcome such limitations, we propose the Hierarchical Vision Transformer Enhanced by Graph Convolutional Network (GCN-HViT) for image classification. Specifically, the Hierarchical ViT we designed can model patch-wise information interactions on a global scale within each level and model hierarchical relationships between small patches and large patches across multiple levels. In addition, the proposed GCN method functions as a local feature extractor to obtain the local representation of each image patch which serves as a 2D position embedding of each patch in the 2D space. Meanwhile, it models patch-wise information interactions on a local scale within each level. Extensive experiments on 3 real-world datasets demonstrate that GCN-HViT achieves state-of-the-art performance. --- ### R&F-Inventory: A Large-Scale Dataset for Monotonic Inventory Estimation in Reach and Frequency Advertising Authors: Yunshan Peng, Ji Wu, Wentao Bai, Yunke Bai, Jinan Pang, Wenzheng Shu, Yanxiang Zeng, Xialong Liu, Peng Jiang Published: 2026-04-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.16821v1 Reach and Frequency (R&F) contract advertising is an important form of widely used brand advertising. Unlike performance advertising, R&F contracts emphasize controllable delivery of UV and PV under given targeting, scheduling, and frequency control constraints. In practical systems, advertisers typically need to view the UV, PV change curves at different budget levels in real time when creating an R&F contract. However, most existing publicly available advertising datasets are based on independent samples, lacking a characterization of the core structure of the "budget-performance curve" (including UV and PV) in R&F contracts.This paper proposes and releases a large-scale R&F contract inventory estimation dataset. This dataset uses the R&F contract context consisting of "targeting-scheduling-frequency control" as the basic context, providing observations of UV and PV corresponding to multiple budget points within the same context, thus forming a complete budget-performance curve. The dataset explicitly includes a time-window-based frequency control mechanism (e.g.,"no more than 3 times within 5 days") and naturally satisfies the monotonicity and diminishing marginal returns characteristics in the budget and scheduling dimensions. We further derive the theoretical maximum exposure ceiling and use it as a consistency check to evaluate data quality and the feasibility of model predictions. Using this data set, this paper defines two standardized benchmark tasks: single-point performance prediction and reconstruction of budget-performance curves, and provides a set of reproducible baseline methods and evaluation protocols. This dataset can support systematic research on problems such as structural constraint learning, monotonic regression, curve consistency modeling, and R&F contract planning.The code for our experiments can be found at https://github.com/pengyunshan/RF-Inventory. --- ### Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration Authors: Chongsheng Zhang, Hao Wang, Zelong Yu, Esteban Garces Arias, Julian Rodemann, Zhanshuo Zhang, Qilong Li, Gaojuan Fan, Krikamol Muandet, Christian Heumann Published: 2026-04-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.16817v2 Imbalanced data are commonly present in real-world applications. While data synthesis can effectively mitigate data scarcity for rare classes, and LLMs have revolutionized text generation, the application of LLMs to the synthesis of relational/structured tabular data remains underexplored. Moreover, existing approaches lack an effective feedback mechanism to guide LLMs in continuously optimizing the quality of the generated data throughout the synthesis process. In this work, we propose RDDG, Relational Data generator with Dynamic Guidance, which is a unified in-context learning framework that employs progressive chain-of-thought (CoT) steps to generate tabular data for enhancing downstream imbalanced classification performance. RDDG first uses core set selection to identify representative samples from the original data, then utilizes in-context learning to discover the inherent patterns and correlations among attributes within the core set, and subsequently generates tabular data while preserving the aforementioned constraints. More importantly, it incorporates a self-reinforcing feedback mechanism that provides automatic assessments of the quality of the generated data, enabling continuous quality optimization throughout the generation process. Experimental results on multiple real and synthetic datasets demonstrate that RDDG outperforms existing approaches in both data fidelity and downstream imbalanced classification performance. We make our code available at https://github.com/cszhangLMU/RDDG. ---