# Research Papers — 2026-06 · bundle page 18 of 260 > Full-text markdown of papers #851–900 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/18 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/17.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/19.md) ### Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning Authors: Yinan Zhou, Haokun Lin, Yichen Wu, Yuxin Chen, Teng Wang, Caifeng Shan, Zhenan Sun, Chen Ma, Li Zhu, Ying Shan Published: 2026-06-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.30217v2 Large multimodal models have achieved strong reasoning on complex visual tasks, but their inference efficiency is often restricted by long chains of thought. A promising solution is to pair a small draft model with a large target model, enabling cooperative inference employing a routing signal that adaptively routes queries to either the draft or target model based on their difficulties for optimal efficiency and accuracy. Yet, the remaining bottleneck is to establish a reliable query difficulty signal under multimodal settings. Existing approaches designed for language models either rely on post-hoc token probabilities, which fall short in multimodal scenarios, or depend on supervised fine-tuning, which is a data-sensitive strategy. Both paradigms perform routing only after a complete output, and ignore whether the target model can actually solve the routed instances. To address this, we propose PRP, a Proactive Routing Paradigm that enables early decision-making by jointly evaluating the competence of both the draft and target models. Our Draft Rating Learning (DRL) equips the draft model with an internal confidence estimator, while Joint Rating Learning (JRL) predicts how well the target model can handle a given query, thereby prioritizing the allocation of samples it excels at rather than the hardest ones. These ratings enable fine-grained, instance-level \textbf{Proactive Routing} and substantially accelerate inference without compromising overall performance. Extensive experiments across multiple multimodal reasoning benchmarks validate our effectiveness and efficiency. --- ### Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion Authors: Chao Tian, Zikun Zhou, Chao Yang, Guoqing Zhu, Zhenyu He Published: 2026-06-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.30215v1 RGB-T detectors leverage the complementary strengths of visible and thermal infrared modalities, achieving robust performance under challenging conditions. Many of them resort to heavy dual backbones and exhaustive cross-modality fusion across the entire image, leading to impractically high computational costs. We observe that most image regions are smooth backgrounds (e.g., sky, ground) that can be easily handled by lightweight single-modality models. In light of this observation, we propose a sparse fusion mechanism for efficient RGB-T detection: first rapidly scanning the image to identify the proposals and then carefully examining the remaining sparse proposals via feature fusion. We propose a two-stage framework to instantiate this mechanism, which performs detection in two stages: 1) a lightweight and modality-specific detection stage that produces high-recall RoIs, and 2) a fusion-driven examination and refinement stage that filters out the false positives and refines the bounding boxes. This design enables the detector to adaptively allocate more computational resources to the potential foregrounds, improving the efficiency while ensuring detection accuracy. Extensive experiments show that our method achieves competitive performance with substantially fewer parameters and lower cost, while maintaining strong scalability to high-resolution images. --- ### A Multi Center Breast FNAC Whole-Slide Cytology Dataset for AI-Assisted Patch-Wise Classification Using C1 to C5 Reporting Categories Authors: Garima Jain, Abhijeet Patil, Surabhi Jain, Sanghamitra Pati, Amit Sethi, Sandeep Mathur, Pulkit Verma, Nishi Halduniya, Jatin Kashyap, Sharat Kumar, Simmi Kharb, Sunita Singh et al. Published: 2026-06-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.30209v1 We present a multi center breast fine needle aspiration cytology (FNAC) dataset designed for patch wise classification using C1 to C5 reporting labels. The prospective dataset includes 321 patients and 470 whole-slide images (WSIs) collected from participating tertiary medical centers in India between May 2023 and March 2026. Slides were stained using Papanicolaou (190 WSIs) or MayGrunwald Giemsa (280 WSIs), scanned on a Hamamatsu NanoZoomer S360 at 40X magnification and 0.25 microns per pixel, and stored directly in NDPI format. Across the 470 WSIs, 446 WSIs contain annotated patch regions, yielding 7,398 PNG image patches with expert-verified C1 to C5 labels. The release includes NDPI WSIs, WSI-level GeoJSON annotation files, extracted patch images, deidentified metadata, a data dictionary, a validation summary, a manifest linking WSIs to Zenodo records, and code for dataset inspection and reuse. The complete dataset is approximately 950 GB and is available through Zenodo. --- ### The Many-Body Problem of the Data Centre Authors: Marcin Korecki, Cesare Carissimo Published: 2026-06-29 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2606.30206v1 Modern Artificial Intelligence is often framed as limited by its own disembodiment, as if giving it a body would unlock its true potential. We argue to the contrary that it is the Data Centre that is, in many cases, the body of the AI. At the same time, the Data Centre is part of the labouring body of Capital and possesses staggering organismic qualities when seen through a biological lens. We elucidate the organic analogy and identify the many-body problem that stems from the Data Centre being a non-unique, universal form of embodiment. We identify the intimate connection between computation and human desires in how the Data Centre archives, serves, and computes on data born to the desires of humans. Strikingly, while the Data Centre echoes the ghosts of human desires, it acts without desire of its own. The organismic analogy begins to split at its seams, but Capital does not care. Automata and human labour are priced into the market much the same. We argue that through the pricing of artificial intelligence Capital distils most clearly the value of intelligence and allows for its comparison across the organism - mechanism divide. --- ### SHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report Generation Authors: Filippo Ruffini, Marco Salmé, Rosa Sicilia, Valerio Guarrasi, Paolo Soda Published: 2026-06-29 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2606.30201v2 Current evaluation protocols for Vision-Language Models (VLMs) in Radiology Report Generation (RRG) rely on report-level metrics that measure lexical overlap or aggregate clinical correctness. However, such metrics do not test whether individual diagnostic statements stem from the actual pathological evidence visible in the image. This allows models to achieve competitive scores by exploiting learned priors or spurious correlations, a failure mode we refer to as vision shortcut. We introduce SHOVIR, a benchmark for evaluating vision shortcut behavior in RRG. SHOVIR extends two spatially annotated chest X-ray datasets, MIMIC-CXR and PadChest-GR, with per-box CheXpert labels, and defines image-level and disease-level occlusion experiments that contrast baseline performance on clean images against localized, region-specific perturbations. Comparing predictions across these conditions isolates two failure modes at the disease-class level: direct shortcuts, where a finding persists after its visual evidence is removed, and contextual shortcuts, where detection degrades once co-occurring pathologies are occluded despite the target region remaining intact. Benchmarking eight state-of-the-art VLMs, we find that shortcut behavior varies substantially across architectures and datasets. Models achieving the highest baseline report quality do not necessarily rank highest in spatial grounding, revealing that clinically fluent generation can coexist with shallow reliance on visual evidence. These findings expose a blind spot in current RRG evaluation and motivate region-aware assessment protocols. --- ### Forewarned is Forearmed: When Non-Sequential Embedding Turns Into an Anomaly Detector Authors: Elys Allesiardo, Antoine Caubrière, Valentin Vielzeuf Published: 2026-06-29 Categories: cs.CL, cs.AI, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2606.30196v1 This paper offers an in-depth analysis of non-sequential multimodal sentence-level embeddings, with a particular focus on the SONAR model. We demonstrate that certain embedding dimensions are sensitive to perturbations and can serve as indicators of decoding anomalies. By leveraging the consistency between successive encoding and decoding, we successfully build an accurate detector. Additionally, we explore modifying specific dimensions of interest to attempt to correct them. This work underscores the importance of understanding and analyzing the embeddings themselves to enhance the reliability of multimodal representations. --- ### Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data Authors: Hyunwoo Park, Sang-Hyun Lee Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30192v1 Sim-to-real transfer remains a major obstacle for reinforcement learning (RL), especially for vision-based control where image observations exacerbate the state-distribution shift between simulation and the real world. Domain adaptation (DA) is a promising remedy for this challenge. Prior sim-to-real DA works have demonstrated encouraging results, yet these approaches typically assume substantially more target data, which is not available in practice. Indeed, their performance degrades significantly when the target data budget is reduced. To address this challenge, we propose AIDA (Adaptive Imagination for Domain Adaptation), a domain adaptation framework for visual reinforcement learning that addresses sim-to-real transfer under scarce target data without requiring additional interaction with the target environment. Our key idea is adaptive imagination: generating reliable and semantic imagination rollouts to augment limited target data. Specifically, AIDA employs a distribution-shift-aware discriminator that truncates rollouts when imagined transitions drift into low-confidence regions, so that only reliable transitions contribute to the augmentation. On these reliable transitions, AIDA introduces a self-consistency loss that cycles through state -> image observation -> state, penalizing discrepancies between the original and reconstructed states. This provides additional adaptation signals beyond the scarce target data. Our experiments demonstrate that adaptive imagination effectively truncates unreliable rollouts. By enforcing a self-consistency loss on the resulting reliable transitions, AIDA learns semantically meaningful state representations and outperforms baselines across five MuJoCo tasks and two Gymnasium-Robotics tasks. --- ### From Detecting Agency to Doing Work: Self-Caused Credit Builds a Durable Behavioral Self in a Minimal Spiking Agent Authors: Haoliang Han Published: 2026-06-29 Categories: cs.AI, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2606.30191v1 How does an agent that can tell self from world come to be durably shaped by that distinction? Recent work shows that a predictive system can detect its own agency (Ye, 2026), but detecting agency does not explain durable, self-shaped behavior. We show that agency-gated slow credit -- a conjunctive term Own*Agency*Salience driving a slow parameter update -- produces post-unload behavioral residue: on a spiking substrate (Nengo LIF/PES), a learned self-preserving choice survives episodic buffer removal (retained fraction 0.96, N=50) and collapses when the slow decoders are reset or the agency gate is removed. Reproducing the agency comparator and toggling only the slow-credit channel, we find a clean dissociation: at matched agency gain, durable behavior develops only when self-credit performs slow work (post-unload self-preservation 1.00 vs 0.00). The same dissociation holds in 24-dimensional partially-observed control (0.74 vs 0.00), and a plastic-work analysis shows that basin deformation equals net self-credit work. Across eight sequentially-learned tasks under exogenous interference, the multiplicative veto also prevents forgetting: it retains old tasks (final post-unload accuracy 0.88, forgetting 0.13) where additive pooling collapses to chance-level recall, the no-agency ablation falls below chance, and episodic/replay baselines stay near chance after unload -- all with no replay buffer and no task-boundary-dependent protection mechanism (N=50). We formalize the durable residue as an operational behavioral self and argue that self-caused credit doing slow work is a necessary building block for agents that develop a self. No claim of consciousness is made. --- ### Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation Authors: Naeem Paeedeh, Mahardhika Pratama, Wolfgang Mayer, Mukesh Prasad, Weiping Ding, Yew-Soon Ong Published: 2026-06-29 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.30190v1 Existing domain-incremental learning (DIL) strategies call for massive amounts of data to adapt to new domains and suffer from the overfitting problem in the case of data scarcity. This paper puts forward a relatively uncharted problem, namely, few-shot domain incremental learning (FSDIL), taking into account the problem of extreme data shortages in the realm of DIL. A novel algorithm, namely Continual Vision-Language Consolidation (CVLC), is proposed to address the FSDIL problem, where the key idea lies in the concept of latent space reservation in the base domain coupled with dual coalescent projection (DCP) as a parameter-efficient fine-tuning method. First, the vision prototype is calibrated while multiple templates and synonyms are generated via LLMs to induce the language prototype. The vision and language prototypes are fused. Adaptation to never-ending arrivals of new domains is done by the DCP technique, fine-tuned in such a way to prepare the model to unseen domains via latent-space reservations committed in the base domain. CVLC is structured under shared and domain-specific components to combine general knowledge and domain-specific details. The advantage of our approach is demonstrated through a range of benchmark problems and comparisons with prior arts, in which CVLC outperforms them by up to a 16% gap. Our codes are shared publicly in https://github.com/Naeem-Paeedeh/CVLC . --- ### DAIN: Dynamic Agent-Based Interaction Network for Efficient and Collaborative Multimodal Reasoning Authors: Xinxin Chen, Yuchen Li, Zihan Wang, Haoyu Zhang, Ruixin Liu, Mingyuan Zhao Published: 2026-06-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.30189v1 Current multimodal fusion approaches, particularly those based on static Mixture-of-Experts (MoE) architectures, often struggle to provide the adaptive and efficient collaborative reasoning required by complex real-world applications. We introduce the Dynamic Agent-based Interaction Network (DAIN), which reconceptualizes multimodal fusion as a dynamic, multi-agent collaborative process. DAIN employs a context-aware Meta-Controller that dynamically schedules sparse activation of specialized interaction agents and orchestrates compressed inter-agent communication for consensus-building. The framework is guided by a multi-objective loss function that jointly optimizes task accuracy, agent specialization, and operational efficiency through sparse activation and communication regularization. Comprehensive evaluations across five diverse benchmarks -- ADNI, MIMIC-IV, MM-IMDB, CMU-MOSI, and ENRICO -- establish DAIN as a new state-of-the-art, delivering significant performance improvements including a 2.6\% accuracy gain on ADNI. Ablation studies verify the critical roles of both dynamic scheduling and agent communication. Furthermore, DAIN offers enhanced interpretability by exposing context-dependent agent roles and collaboration patterns while maintaining computational efficiency through sample-wise sparse agent activation. Our work demonstrates the promise of dynamic, agent-based paradigms for multimodal reasoning. --- ### Dynamo: Dynamic Skill-Tool Evolution for Vision-Language Agents Authors: Yutao Sun, Yanting Miao, Hao-Xuan Ma, Mengyu Zhou, Mingshuai Chen, Tiancheng Zhao, Dexin Wang, Lei Lv, Li Xu, Xiaoxi Jiang, Guanjun Jiang Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30185v1 Improving vision-language models (VLMs) on visual reasoning typically requires retraining or hand-designed prompts and tools. We present Dynamo, a training-free framework that adapts a frozen VLM without any weight updates. On a small labeled training subset, the agent inspects its own correct and incorrect attempts and evolves two complementary capabilities: reusable reasoning skills for cognitive bottlenecks, and executable visual tools for perceptual ones. Each generated tool is paired with a skill that specifies when to invoke it, and both capability types accumulate in a persistent library. Across four visual reasoning benchmarks and five VLM backbones, Dynamo improves direct inference on all 20 model--benchmark settings (avg. +5.6 acc). When the tool set is given in advance, the framework learns when to call each tool, and per-step tool choice improves on every tested backbone. Against task-specific RL (VTool-R1, DeepEyes), Dynamo closes 65--99% of the RL gap at a fraction of the compute, and combines additively with RL when available. --- ### DrivenMorph: Bridging Attention Mechanism and Variational Image Registration via Difference Modeling Authors: Mingke Li, Jianping Zhang, Jinqiu Deng Published: 2026-06-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.30183v1 Medical image registration benefits significantly from deep learning, yet existing approaches often lack physical explainability and fine-grained deformation control. Motivated by Demons algorithms, we propose a novel DrivenMorph framework that bridges attention mechanisms with variational image registration by incorporating difference modeling as a physically inspired inductive bias. The resulting driving force, computed from local differences in the latent feature space, provides explicit semantic guidance throughout the registration process. It directly drives the registration process through a neural Demons layer that simulates force-displacement interactions to generate smooth and anatomically consistent deformation. Unlike previous methods, our approach not only integrates traditional registration principles with popular deep networks, providing an explainable and efficient solution for learning-based medical image registration, but also separates difference modeling from deformation, improving modularity and explainability. Extensive experiments on multiple 3D brain MRI datasets demonstrate superior performance over state of-the-art learning-based and optimization-based methods. Furthermore, visualizations and statistical analyses confirm that the learned driving force aligns closely with actual deformation patterns, supporting its explanatory value. --- ### MirrorCode: AI can rebuild entire programs from behavior alone Authors: Tom Adamczewski, David Owen, David Rein, Florian Brand, Giles Edkins, Allen Hart, Daniel O'Connell Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30182v2 AI models are rapidly improving at autonomous coding, as shown by benchmark progress and one-off demonstrations such as AI implementing a C compiler. However, existing coding benchmarks tend to focus on shorter tasks, and one-off demonstrations are hard to compare systematically because they often have some human guidance, and are not standardized or repeated across models. To address these challenges, we introduce MirrorCode, a long-horizon coding benchmark based on reimplementing entire software projects. In MirrorCode, AI agents must replicate the functionalities of an existing program, without access to its source code. AI solutions must match the original program's output exactly on end-to-end tests, including held-out tests. MirrorCode's 25 target programs span different areas of computing: Unix utilities, data serialization and query tools, bioinformatics, interpreters, static analysis, cryptography, and compression. Existing AI models can already reimplement complex software, with the strongest model scoring 56% across the benchmark. For example, AI can reimplement gotree, a 16,000-line bioinformatics toolkit - a task that we believe would take weeks for a human engineer. However, studying the frontier of performance requires a larger inference budget than typical benchmarks, for example, \$2,600 over 19 days for a single attempt on a large task. We show that AI agents can already complete long-horizon software engineering tasks, especially when requirements are precisely specified. More broadly, our work suggests AI will have transformative effects on software engineering, as autonomous agents continue to improve. --- ### HiRes: A Hierarchical Cascaded Method for Resistor Value Identification Authors: Rama Y. AlHamidi, Aseel A. Mohamed, Mustafa A. Eltayeb, Osama Hasoneh, Mohammad Shaqfeh Published: 2026-06-29 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2606.30179v1 Accurate identification of resistor values from unconstrained images remains a challenging computer vision task due to variations in lighting, orientation, scale, and background complexity. This paper presents HiRes, a hierarchical cascaded pipeline for end-to-end resistor value identification directly from full-frame images. The approach combines object detection (YOLOv8n), semantic segmentation (UNet++ with EfficientNet-B2), and structured geometric decoding via projection along the resistor axis. To improve robustness, we incorporate geometric filtering, gap-preserving band separation, and validation against the E24 resistor series. Experiments across diverse real-world images show that HiRes achieves a detection mAP50 of 0.9906, a segmentation mIoU of 0.8444, and an end-to-end identification accuracy of 85.8% (95% CI: 78.0-91.9%), outperforming the publicly available classical baseline, CVResist, which fails to generalize beyond controlled conditions. In addition, our architecture outperforms state-of-the-art MLLMs on our challenging test set, offering a lower cost, high efficiency, and an interpretable alternative method. These results demonstrate the effectiveness of integrating learned visual representations with structured reasoning for robust resistor interpretation. Code and dataset are available at https://github.com/HiRes491/HiRes. --- ### CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph Authors: Chengtao Gan, Xiaoke Guo, Yushan Zhu, Zhaoyan Gong, Zhiqiang Liu, Songze Li, Huajun Chen, Wen Zhang Published: 2026-06-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.30175v3 The continuous evolution of large language models drives escalating demands on data scale and quality, and as different training stages impose increasingly tailored data requirements, systematic organization of high-quality corpora becomes indispensable. Existing corpus construction pipelines confine the resulting corpora to flat, undifferentiated document collections, universally lacking systematic knowledge organization. We present Cortex, to our knowledge the first framework that elevates web-scale corpus construction from flat document filtering to structured knowledge organization through an Ontological Corpus Graph (OCG), a three-layer heterogeneous structure unifying a quality-refined content layer, a hierarchical lightweight ontology layer via LLM-driven automated evolution, and a cross-domain alignment layer enabling inter-domain association at arbitrary taxonomic resolution. Comprehensive experiments confirm the effectiveness of Cortex. In particular, we leverage the OCG to synthesize CortexBench, a cross-domain search-and-reasoning benchmark whose evaluation across eight frontier LLMs validates the effectiveness of quality refinement, domain organization, and cross-domain data synthesis. We will publicly release the complete codebase, a 24.14B-token refined corpus with its OCG, and CortexBench. The data is available at https://github.com/zjukg/CORTEX . --- ### CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph Authors: Chengtao Gan, Xiaoke Guo, Yushan Zhu, Zhaoyan Gong, Zhiqiang Liu, Songze Li, Huajun Chen, Wen Zhang Published: 2026-06-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.30175v1 The continuous evolution of large language models drives escalating demands on data scale and quality, and as different training stages impose increasingly tailored data requirements, systematic organization of high-quality corpora becomes indispensable. Existing corpus construction pipelines confine the resulting corpora to flat, undifferentiated document collections, universally lacking systematic knowledge organization. We present Cortex, to our knowledge the first framework that elevates web-scale corpus construction from flat document filtering to structured knowledge organization through an Ontological Corpus Graph (OCG), a three-layer heterogeneous structure unifying a quality-refined content layer, a hierarchical lightweight ontology layer via LLM-driven automated evolution, and a cross-domain alignment layer enabling inter-domain association at arbitrary taxonomic resolution. Comprehensive experiments confirm the effectiveness of Cortex. In particular, we leverage the OCG to synthesize CortexBench, a cross-domain search-and-reasoning benchmark whose evaluation across eight frontier LLMs validates the effectiveness of quality refinement, domain organization, and cross-domain data synthesis. We will publicly release the complete codebase, a 24.14B-token refined corpus with its OCG, and CortexBench. --- ### Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark Authors: Matthias Blaschke, Daniel Kienzle, Zsuzsanna Koczor-Benda, Julian Lorenz, Rainer Lienhart, Fabian Pauly Published: 2026-06-29 Categories: cs.LG, cond-mat.mes-hall, cs.AI, cs.CE, physics.chem-ph arXiv: https://arxiv.org/abs/2606.30170v2 Generative molecular design is shaped by simple proxy benchmarks for drug-like properties and models pretrained on large pharmaceutical datasets. This combination yields strong benchmark metrics but limits transferability to domains structurally distinct from drug discovery. To overcome this limitation and drive discovery toward real, scientifically grounded targets, we introduce the Nanotechnology Molecular Optimization (NMO) Benchmark, which bridges machine learning (ML) and quantum materials science. NMO acts simultaneously as a rigorous testbed for the ML community and a discovery engine for nanotechnology research. The suite replaces proxy oracles with quantum simulations and introduces strict protocols that prioritize scientific utility over leaderboard-oriented overfitting. The physics-based NMO tasks impose hard structural constraints and rugged fitness landscapes, posing fundamentally new requirements on generative models. Notably, advanced molecular optimization methods underperform much simpler approaches on the NMO tasks. We develop a new baseline method identifying the critical components to solve the NMO tasks, including a novel representation for modeling structural constraints and a domain-agnostic pretraining strategy to eliminate pharmaceutical dataset bias. Our results surpass state-of-the-art physical properties and reveal previously unknown structural motifs, offering new insights for the nanotechnology community and demonstrating that ML can drive genuine scientific discovery. --- ### Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark Authors: Matthias Blaschke, Daniel Kienzle, Zsuzsanna Koczor-Benda, Julian Lorenz, Rainer Lienhart, Fabian Pauly Published: 2026-06-29 Categories: cs.LG, cond-mat.mes-hall, cs.AI, cs.CE, physics.chem-ph arXiv: https://arxiv.org/abs/2606.30170v1 Generative molecular design is shaped by simple proxy benchmarks for drug-like properties and models pretrained on large pharmaceutical datasets. This combination yields strong benchmark metrics but limits transferability to domains structurally distinct from drug discovery. To overcome this limitation and drive discovery toward real, scientifically grounded targets, we introduce the Nanotechnology Molecular Optimization (NMO) Benchmark, which bridges machine learning (ML) and quantum materials science. NMO acts simultaneously as a rigorous testbed for the ML community and a discovery engine for nanotechnology research. The suite replaces proxy oracles with quantum simulations and introduces strict protocols that prioritize scientific utility over leaderboard-oriented overfitting. The physics-based NMO tasks impose hard structural constraints and rugged fitness landscapes, posing fundamentally new requirements on generative models. Notably, advanced molecular optimization methods underperform much simpler approaches on the NMO tasks. We develop a new baseline method identifying the critical components to solve the NMO tasks, including a novel representation for modeling structural constraints and a domain-agnostic pretraining strategy to eliminate pharmaceutical dataset bias. Our results surpass state-of-the-art physical properties and reveal previously unknown structural motifs, offering new insights for the nanotechnology community and demonstrating that ML can drive genuine scientific discovery. --- ### Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Models Authors: Kai Jiang, Ruishu Zhu, Siqi Huang, Hongyuan Zhang, Xuelong Li Published: 2026-06-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.30168v1 Multimodal large language models (MLLMs) often fail in fine-grained visual reasoning, as question-relevant visual cues are diluted by dense and redundant image tokens. Recent multimodal reasoning methods usually extend chain-of-thought from language models into visual or latent spaces, seeking to add intermediate reasoning states while overlooking the negative impact of redundant visual tokens. We propose LatEnt Noise maSk (Lens), a question-conditioned visual evidence purification framework that empowers MLLMs to reason with cleaner visual cues in latent space. Lens introduces a lightweight Lens Evidence Token (LET) to score which visual tokens support the current question and preserve them during decoding. Guided by the LET scores, it injects adaptive latent noise into low-relevance tokens, softly suppressing distractors without changing the model backbone or token sequence. With only one temporary learnable control token and a lightweight noise generator, Lens adds minimal overhead while improving the base MLLM by 2.4-6.4 points on most VQA datasets and by 4.1-6.4 points on grounding tasks. These results show that multimodal reasoning can benefit more directly from cleaner question-relevant visual evidence than from simply extending the reasoning trace. --- ### Federated Learning with Energy-Based Structured Probabilistic Inference Authors: Dario Fenoglio, Daniil Kirilenko, Martin Gjoreski, Marc Langheinrich Published: 2026-06-29 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.30161v1 Federated learning typically aggregates client updates using fixed or heuristic weighting rules, which can be suboptimal when clients have heterogeneous data and varying contributions to the global model. We propose a framework that refines client aggregation weights using Conditional Random Fields (CRFs). Our method defines unary potentials for individual clients and pairwise potentials for all client pairs, allowing the server to model both client-specific reliability and interactions between clients. The resulting CRF inference produces aggregation weights that enable better convergence of the global training objective. Experiments show that, under non-IID heterogeneity, our approach consistently improves performance over well-established federated learning baselines. --- ### A Dual-domain Refinement Network with FBP-based Jacobian Learning for Sparse-view Dual-Energy CT Material Decomposition Authors: Qian Liu, Xiaohong Fan, Ke Chen, Chong Chen, Shuaikang Wang, Jianping Zhang Published: 2026-06-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.30159v2 Dual-energy CT (DECT) exploits attenuation differences across different X-ray spectra to provide richer material information and has been widely used in medical imaging. While sparse-view acquisition can lower radiation exposure, it makes DECT material decomposition even more challenging, as the problem is nonlinear and ill-posed. Existing deep unrolling approaches generally do not explicitly incorporate the Jacobian operator induced by the nonlinear forward model, and their sparsity priors are still mainly built on conventional convolutions, which are insufficient for modeling global structural information. This study addresses the challenge of DECT multi-material decomposition in sparse-view settings by representing it as a sparse-regularized nonlinear least-squares problem. To solve it, we propose an iterative dual-domain refinement network (DECT-DRNet). In each iteration, the filtered back-projection (FBP)-based Jacobian approximation module is used first to generate an intermediate material decomposition result. Here, we characterize the forward process of material decomposition using a nonlinear operator, and then construct a theoretically grounded learnable approximation of the adjoint Jacobian operator by integrating the FBP algorithm with a U-Net into the backward process. In addition, to address the limitation of existing deep learning-based decomposition methods in globally suppressing noise and artifacts, we introduce a learnable sparse dual domain regularization term that incorporates Fourier convolutional residual blocks. This refinement block combines geometric feature extraction in the image domain with noise suppression in the frequency domain, allowing the model to capture both global and local features while maintaining structural details. DECT-DRNet demonstrates its ability to achieve more accurate material decomposition under sparse-view conditions. --- ### A Dual-domain Refinement Network with FBP-based Jacobian Learning for Sparse-view Dual-Energy CT Material Decomposition Authors: Qian Liu, Xiaohong Fan, Ke Chen, Chong Chen, Shuaikang Wang, Jianping Zhang Published: 2026-06-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.30159v1 Dual-energy CT (DECT) exploits attenuation differences across different X-ray spectra to provide richer material information and has been widely used in medical imaging. While sparse-view acquisition can lower radiation exposure, it makes DECT material decomposition even more challenging, as the problem is nonlinear and ill-posed. Existing deep unrolling approaches generally do not explicitly incorporate the Jacobian operator induced by the nonlinear forward model, and their sparsity priors are still mainly built on conventional convolutions, which are insufficient for modeling global structural information. This study addresses the challenge of DECT multi-material decomposition in sparse-view settings by representing it as a sparse-regularized nonlinear least-squares problem. To solve it, we propose an iterative dual-domain refinement network (DECT-DRNet). In each iteration, the filtered back-projection (FBP)-based Jacobian approximation module is used first to generate an intermediate material decomposition result. Here, we characterize the forward process of material decomposition using a nonlinear operator, and then construct a theoretically grounded learnable approximation of the adjoint Jacobian operator by integrating the FBP algorithm with a U-Net into the backward process. In addition, to address the limitation of existing deep learning-based decomposition methods in globally suppressing noise and artifacts, we introduce a learnable sparse dual domain regularization term that incorporates Fourier convolutional residual blocks. This refinement block combines geometric feature extraction in the image domain with noise suppression in the frequency domain, allowing the model to capture both global and local features while maintaining structural details. DECT-DRNet demonstrates its ability to achieve more accurate material decomposition under sparse-view conditions. --- ### Physically-Constrained Harmonic Separation for Robust Heart and Respiratory Rate Estimation from Wrist Photoplethysmography Authors: Nouhaila Fraihi, Ouassim Karrakchou, Mounir Ghogho Published: 2026-06-29 Categories: physics.med-ph, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.30156v1 Wrist-worn photoplethysmography (PPG) enables continuous monitoring of cardiopulmonary physiology, but reliable heart rate (HR) and respiratory rate (RR) estimation in free-living conditions remains challenging due to non-stationary motion artifacts that spectrally overlap with physiological dynamics. Existing signal-processing methods degrade under strong motion, while unconstrained deep learning approaches often lack physiological interpretability and identifiable structure. We propose a Physically-Constrained Harmonic Separation (PCHS) framework that formulates HR and RR estimation from wrist PPG as an analysis-by-synthesis problem, where accelerometer measurements condition artifact separation rather than directly regressing vital signs. A physics-guided harmonic generator decomposes the observed signal into quasi-periodic physiological components and a motion-related residual, enabling HR recovery from the fundamental frequency and RR prediction from respiratory-driven modulations of the harmonic parameters. Robust reconstruction objectives, separation constraints, and uncertainty-aware weighting stabilize the decomposition under motion. Experiments on the motion-intensive PPG-DaLiA dataset demonstrate that PCHS outperforms state-of-the-art methods while yielding interpretable signal decompositions that effectively disentangle physiological activity from motion artifacts. --- ### Estimating Grammatical Gender Directions in Contextual Embeddings under Controlled and Natural Contexts Authors: Huanping Xiao, Yingji Li Published: 2026-06-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.30152v1 Contextual language models conflate grammatical gender and social semantic bias in gendered languages such as Spanish. Existing gender debiasing approaches only operate on static word embeddings leaving contextual representations unexplored for this two dimensional gender disentanglement. To address the this issue, we make the first attempt to disentangle grammatical gender from semantic contamination for contextual embeddings. We construct both controlled templates and natural Wikipedia contexts to build balanced datasets of inanimate nouns, and design a framework equipped with centroid, Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA) gender direction estimators as well as contamination-aware weighting strategies. A set of dual-objective evaluation metrics is proposed to balance the suppression of grammatical gender leakage on inanimate nouns and the preservation of semantic gender distinctions for occupation terms. The results reveal that unweighted controlled contexts yield the purest grammatical gender direction, and the centroid estimator achieves better performance than discriminative baselines. --- ### T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation Authors: Wentao Qu, Qi Zhang, Chenxu Wang, Guofeng Mei, Yongfei Liu, Xiaoshui Huang, Gim Hee Lee, Liang Xiao Published: 2026-06-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.30147v2 Recent progress in Text-to-Image generation benefits from large-scale Text-Image pairs. However, the scarcity of Text-LiDAR pairs often causes over-smoothed scenes and limited controllability. In this paper, we rethink the limitations of Text-LiDAR generation task, focusing on alleviating insufficient training priors and constructing controllable Text-LiDAR data. We propose a \textbf{T}ext-\textbf{to}-\textbf{L}iDAR \textbf{D}iffusion \textbf{M}odel for LiDAR scene generation, T2LDM++, with a Self-Conditioned Representation Guidance (SCRG). Specifically, to alleviate object over-smoothing, SCRG employs a Guidance Network (GN) to provide reconstruction-based soft supervision to the Denoising Network (DN). This enables DN to learn geometry-aware representations through reconstruction guidance, leading to more accurate denoising in DDPMs. Meanwhile, through analysis and design, SCRG exhibits more effective and lightweight, while decoupled in inference, avoiding computational overhead. Furthermore, we construct two high-quality Text-LiDAR benchmarks ($>$100K samples) using a generalized strategy of geometric annotations, along with a controllability metric. Moreover, a directional position prior is designed to mitigate street distortion, further improving scene fidelity. Additionally, T2LDM++ supports multiple conditions, including (Semantic, Box, BEV, Camera)-to-LiDAR, Sparse-to-Dense, and Dense-to-Sparse generation, by learning a control encoder via frozen DN. With effective prior modeling and high-quality Text-LiDAR benchmarks, T2LDM++ can generate realistic LiDAR scenes with rich geometric details in unconditional and conditional settings. --- ### FacePlex: Toward Natural Full-Duplex Conversational Avatars Authors: Habin Lim, Hah Min Lew, Jae-Ho Lee, Min-Jae Kim, Seungeun Lee, Ji-Su Kang, Gyeong-Moon Park Published: 2026-06-29 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.30145v2 Natural human conversation is inherently a real-time interaction in which speech and facial behavior continuously evolve. Enabling such interaction requires a conversational avatar to jointly generate speech and facial motion in real time, prepare facial motion for upcoming speech before the corresponding audio is emitted, and produce non-verbal reactions that reflect the ongoing dialogue. However, existing conversational avatar systems cannot address such requirements: audio-driven methods rely on pre-given speech, while joint streaming generation alone does not ensure anticipatory articulation or semantically appropriate reactions. We propose $\textbf{FacePlex}$, a unified framework for full-duplex speech-facial motion generation and real-time avatar rendering. FacePlex jointly coordinates speech, facial motion, and Gaussian splatting rendering on a shared streaming timeline. To prepare facial motion for upcoming speech, FacePlex predicts a short speech continuation and uses its future hidden states through asymmetric conditioning and denoising, while continuously updating them as new user audio arrives without observing future user input. For dialogue-grounded non-verbal behavior, we construct $\textit{SemReact}$, a dataset aligning dialogue context, reaction semantics, and facial motion, and introduce a semantic behavior router that guides continuous motion during both speaking and listening. Extensive experiments show improved audio-visual synchronization and facial articulation, natural dialogue-grounded non-verbal responses, and low-latency of 122 ms end-to-end avatar interaction. --- ### FacePlex: Full-Duplex Joint Speech-Facial Motion Generation for Conversational Avatars Authors: Habin Lim, Jae-Ho Lee, Hah Min Lew, Ji-Su Kang, Gyeong-Moon Park Published: 2026-06-29 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.30145v1 Natural face-to-face conversation requires real-time speech generation together with synchronized facial motion. Existing systems only partially address this problem: speech-only full-duplex models can generate speech in real time but do not produce facial motion, while audio-driven facial motion models animate a face from already available audio rather than jointly generating speech and motion online. To bridge this gap, we first formalize full-duplex joint speech-facial motion generation, where speech tokens and facial motion tokens are produced together every step. Building on this formulation, we propose FacePlex, a unified streaming framework with two key components. First, Rolling Flow Matching adapts flow matching to online motion generation by committing new motion frames at each streaming step. Second, Rolling Cross-Attention couples the streaming audio queue with the motion queue, allowing speech and facial motion to condition each other as generation progresses. Through extensive experiments, ablation studies, and a user study, we show that FacePlex enables full-duplex joint speech-facial motion generation under online streaming constraints, while achieving stronger lip-sync quality and motion fidelity than audio-driven facial motion baselines. --- ### DNA Language Models: An Assessment of Pre-Training for Fine-Tuning Tasks Authors: Romain Karpinsky, Julien Mozziconacci, Mickaël Delcey Published: 2026-06-29 Categories: q-bio.GN, cs.CL arXiv: https://arxiv.org/abs/2606.30140v1 Recent breakthroughs in foundation models and Large Language Models (LLMs) have introduced new opportunities for studying and decoding genomic sequences. Several state-of-the-art approaches, such as DNABERT2, rely on transformer-based architectures, while others, such as ConvNova, still build upon more conventional convolutional models. However, systematic benchmark comparisons across these methods remain scarce. Given that transformer-based models require extensive and costly pretraining, it is crucial to evaluate whether their performance gains justify this overhead. Moreover, LLMs such as DNABERT2 typically rely on Byte Pair Encoding (BPE) tokenization, whose relevance for DNA sequence representation is still debated within the genomics community. In this work, we investigate three key questions: (i) do transformer-based models provide sufficient improvements on fine-tuning tasks upon heavy pretraining, (ii) what is the actual contribution of pretraining in this setting, and (iii) how does BPE tokenization impact performance on genomics-related tasks? --- ### Warranted Attention: Learning What to Pass from Attention to Prediction Authors: Minwoo Yu, Young-guk Ha Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30139v4 Relevance of information read by attention does not guarantee that its contribution benefits the current prediction. We propose Warrant, which learns how strongly attention-derived item contributions should be transmitted under the current query. Warrant applies learned item-wise permission before aggregation without renormalization, jointly controlling relative allocation and total transmission mass. Across backbones, we construct interfaces connecting these con- tributions to prediction scores or states and compare against ungated models on the same paths. On three CyGNet datasets, ungated paths reduce MRR, whereas learned permission partially or almost fully recovers the losses. In a 5-seed HotpotQA/RoBERTa experiment, distractors receive lower permission than gold support, while mean Support MRR rises from .9111 to .9141 and the unsupported selection rate falls from .2271 to .2215. Performance comparisons and contribution- level interventions across five task families reveal both the effects and limits of selective control. The results support learning the strength of contributions transmitted to prediction separately from attention relevance --- ### Relevance Is Not Permission: Warranted Attention for Value Contributions Authors: Minwoo Yu, Young-guk Ha Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30139v2 Relevance is not permission. Attention lets a model read key-value items related to the current query, but it does not guarantee that the value contribution of such an item becomes prediction evidence. A retrieved passage may be relevant to a question without being supporting evidence, and a historical fact or temporal neighbor may even blur true-tail ranking or the current edge score. This paper formalizes this gap as a permission problem for the weighted value term alpha_ij * v_j that is actually added to the prediction path. We propose Warrant, a path-localized interface that preserves attention relevance alpha_ij, exposes the value path leading to the primary metric, and, in the full model, turns alpha_ij * v_j into alpha_ij * g_ij * v_j through learned query-item permission g_ij. We place the same operator on the metric-defining value paths of CTDG link prediction, MTPP next-mark ranking, RAG supporting evidence selection, STPP next-location forecasting, and TKG tail prediction. Across 32 paired comparisons, 3 seeds, and 192 total runs, Warrant improves the primary metric in 27 comparisons; practical tiers consist of 10 substantial effects, 1 marginal effect, 8 positive but uncertain effects, 8 tie/negligible effects, and 5 drops. In the path-localization check, correct-path placement outperforms direction-aware Base performance in every domain and exceeds generic attention placement by +0.1076 AUC in CTDG and +0.0683 MRR in TKG. Ablations show that most TKG gains come from historical-tail value path exposure, whereas the core CTDG gain comes from edge-conditioned query-item permission. In conclusion, prediction evidence is not attention mass. A weighted value term becomes evidence only when it is warranted on the path to the metric. --- ### Robust Strategic Classification under Decision-Dependent Cost Uncertainty Authors: Sura Alhanouti, Güzin Bayraksan, Parinaz Naghizadeh Published: 2026-06-29 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2606.30136v1 Humans facing algorithmic decision systems have been found to ``game'' them by altering their input data (at a cost to them) in order to favorably change the algorithmic outcomes they receive (at a cost to the algorithm). The growing literature on strategic classification seeks to develop robust machine learning algorithms that account for, and reduce, unwanted strategic behavior. A limitation of these existing works is that they assume the cost of strategic behavior to be fixed and independent of the classifier's decision. In practice, however, manipulation costs evolve and depend on past algorithmic decisions: today's decisions influence tomorrow's costs. This paper proposes and analyzes a two-stage robust optimization framework with a decision-dependent uncertainty set to capture such dependencies. We highlight that awareness of policy-dependent costs not only reduces uncertainty, but also better curtails gaming of the algorithmic system over time. --- ### Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs Authors: Illia Makarov, Mykola Glybovets Published: 2026-06-29 Categories: cs.LG, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2606.30133v1 Retrieval-augmented generation built on knowledge graphs (Graph RAG) outperforms flat passage retrieval on multi-hop question answering by leveraging graph structure. In most existing systems, however, the question only sets the seed nodes; the subsequent traversal becomes "query-blind", depending solely on the graph structure. The exception is QAFD-RAG, which implements query-aware traversal via a flow-diffusion solver with combined edge re-weighting. This architecture requires loading the full graph into Python memory and an iterative solver with a variable number of iterations complicating integration with the graph database. We propose a spreading-activation method that achieves the same query-aware traversal with a single per-step semantic gate: the step weight is the cosine similarity between the candidate entity's description and the question, and the number of iterations is fixed. The whole retrieval procedure - seed mapping, propagation, top-K selection and context assembly - is expressed as a single Cypher query executed in one round-trip to Neo4j; the graph never leaves the database. On MuSiQue our method matches QAFD-RAG by exact match (32.80 vs 33.50) and outperforms the strongest purely-structural baseline in our comparison, HippoRAG, by 5.3 EM and 3.4 F1; on 2WikiMultiHopQA HippoRAG and QAFD-RAG retain an advantage due to their phrase-node architectures. An ablation with the gate disabled confirms that the gate is the source of a simultaneous F1 gain of 3.6 to 7.4 points and a retrieval-latency reduction by a factor of 1.5 to 4.9. --- ### Hyper-Network Neural Functional Maps for Unsupervised Robust 3D Shape Matching Authors: Dongliang Cao, Florian Bernard Published: 2026-06-29 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.30131v1 Functional maps are the cornerstone of recent non-rigid 3D shape matching methods due to their efficiency and performance. However, existing methods struggle with challenging scenarios, such as partiality, topological noise, and raw point clouds. A primary bottleneck is that significant intrinsic distortion prevents truncated spectral bases from being accurately aligned via linear transformations (i.e., functional maps). To address this, we introduce a hyper-network that predicts non-linear neural functional maps (NFM), learned in an unsupervised manner, to better align spectral bases. Specifically, we model the NFM as an MLP with skip-connection to refine standard FM and employ a hyper-network to predict its weights, conditioned on standard FM. Our framework is trained using a novel unsupervised spectral alignment loss. Experiments demonstrate that our approach can be seamlessly integrated into state-of-the-art unsupervised deep functional map pipelines, substantially improving matching accuracy in demanding scenarios. --- ### Does Verbose Chain-of-Thought Really Help? In-Distribution Evidence that Content, Not Length, Matters Authors: Wenlong Wang, Fergal Reid Published: 2026-06-29 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.30128v1 Chain-of-thought (CoT) prompting improves LLM reasoning, but the source is contested: do the intermediate steps help because they carry useful semantic content, or because conditioning on more tokens buys extra computation before the model commits to an answer? We bring two lines of evidence to bear. First, in distribution: we repeatedly sample each model on the same question and pair a shorter with a longer of its own natural generations that follow the same reasoning plan, so nothing is rewritten and both traces are genuinely in-distribution. Across 25 models the extra tokens leave accuracy essentially unchanged for every independently-trained reasoner, and a blind analysis of the surplus tokens shows that what gain exists elsewhere tracks validation- and checking-content, not verbosity per se. Second, as a controlled intervention, we ask whether two traces expressing the same semantic content (the same facts, operations, and intermediate values, verified through directed acyclic graph equivalence) produce different outcomes when one is more verbose, using a dual-validator design across four targets and eight benchmarks with number-redacted completion and stratified bootstrap confidence intervals. Verbose traces do improve accuracy (25 of 32 benchmark-target cells are positive under at least one validator), but the effects are modest (typically 1-4 points) and depend on the quality of the verbose prose, not merely its length. Under maximum numerical redaction the effect is amplified (median 3.24x across four arithmetic benchmarks), and length-matched non-reasoning filler recovers none of it. Both lines converge: what matters is what the extra tokens do (the reasoning and validation content they carry), not how many there are, a picture neither a pure forward-pass-compute nor a pure semantic-content account fully explains. --- ### SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation Authors: Zhiyuan Ma, Zhengfeng Shi, Yuning An, Peize Li, Jiabao Wei, Ruijie Li, Junhao Xiao, Jianjun Li, Bowen Zhou Published: 2026-06-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.30124v1 While Text-to-Image (T2I) models have shown remarkable success in generating photorealistic visual content, they still struggle with the rigorous semantic alignment and logical reasoning required for scientific imagery. Inspired by Peirce's Semiotic Triad, we introduce Scientific Image Reasoning (SciIR), a comprehensive resource for training and evaluation of scientific image generation. We formalize scientific reasoning into three core dimensions: Entity Structure (Icon), Scientific Process (Index), and Scientific Law (Symbol). Specifically, to overcome the scarcity of training data in scientific image generation, we elaborately create SciIR-82k, a large-scale dataset containing over 80,000 high-quality scientific image-text pairs from cutting-edge publications. The dataset is hierarchically organized according to the semiotic dimensions and incorporates a Scientific Reasoning Chain-of-Thought (Sci-RCoT) to explicitly model underlying visual logic. For evaluation, we propose SciIR-Bench, which aligns with these three semiotic levels and employs an Atomic Checklist to convert the outcome-oriented scientific accuracy into process-oriented, verifiable, fine-grained questions. Our extensive experiments reveal significant deficiencies in current models' scientific reasoning capabilities. Furthermore, by fine-tuning on the SciIR-82k dataset, we developed the Qwen-Image-SciIR model, which achieves a substantial improvement on the SciIR-Bench, increasing the final score from 35\% to 43\%, laying a solid foundation for future advances in scientific image generation. --- ### Gravitational Duals from Equations of State II: Large Hierarchies and False Vacua Authors: Raul Jimenez, David Mateos, Pavlos Protopapas, Pau Solé-Vilaró, Pedro Tarancón-Álvarez, Pablo Tejerina-Pérez Published: 2026-06-29 Categories: hep-th, astro-ph.CO, cs.AI, cs.LG, gr-qc arXiv: https://arxiv.org/abs/2606.30117v1 We investigate the reconstruction of holographic duals for strongly coupled quantum field theories in regimes characterized by large hierarchies and the presence of false vacua. Within the gauge/gravity duality, these features translate into non-trivial thermodynamic behaviour and exotic renormalization group flows, including skipping flows between non-adjacent fixed points. Building on previous work based on Physics-Informed Neural Networks (PINNs), we extend the holographic inverse problem of reconstructing the bulk scalar potential from boundary thermodynamic data into this new regime. This setting presents a variety of conceptual and numerical challenges, such as near-degenerate states, large hierarchies of energy scales, and regions of the potential that are not directly probed by the input data. We develop a set of methodological advances that overcome these obstacles, thereby improving the established PINNs-based methodology and extending it to new physical regimes of interest that were previously out of reach. Applying the developed framework, we demonstrate accurate reconstruction of scalar potentials deep into the false vacuum regime, achieving robust agreement with the physical features of the underlying thermodynamics despite significant numerical stiffness. Our results extend the bridge between holography and machine learning, and suggest that data-driven approaches can provide new insights into the structure of strongly coupled systems. --- ### Open Problems in Constitutional Preference Reconstruction Authors: Eleanor Clifford, Michael Amir, Arduin Findeis, Aaron Zhao, Robert Mullins Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30116v1 Pairwise preference data is widely used for training and evaluating language models (e.g., RLHF), but each datapoint records a \emph{choice}, not the rationale behind it. Methods such as Inverse Constitutional AI (ICAI) attempt to improve interpretability by compressing datasets into short ``constitutions'' of natural-language principles. We argue this framing is under-specified: a flat list of principles is not yet an executable decision rule because it leaves principle composition implicit. We use the pairwise setting as a testbed to empirically characterize three open problems in constitutional methods. First, principle quality is hard to measure: coverage and accuracy are useful but incomplete proxies for end-to-end reconstruction. Second, \emph{composition is ambiguous}: holding principles fixed, different executors (LLM judge versus majority vote) agree only $73\%$ of the time. Third, \emph{constitutions differ between LLMs}: cross-model vote agreement is $73\%$, whereas intra-model agreement is $81\%$. Across PRISM, AlpacaEval, and Chatbot Arena, we show that principle refinement (ICAI+) may be a first step towards ameliorating these problems: inter-executor agreement rises to $78\%$, and transparent executors match LLM judge accuracy ($66\%$ vs.\ $67\%$). Our results highlight that constitutions should be evaluated as \emph{constitution--executor systems}, with implications for LLMs-as-a-judge broadly. --- ### SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance Authors: Tengyue Jiang, Chunpu Xu, Jiayue Kang, Yao Mu Published: 2026-06-29 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.30113v1 Discrete action tokenization provides a compact interface for autoregressive VLA policies, but accurately recovering continuous robot actions from discrete codes remains challenging. Existing tokenizers typically map each discrete code to a fixed continuous action prototype, ignoring the robot's current proprioceptive state. This limitation is particularly pronounced in manipulation, where the same action token may require different continuous controls under different joint configurations, object poses, and contact conditions. We therefore propose SA-VLA, a state-aware action tokenizer that conditions action decoding on robot state. We study two state-injection mechanisms for VQ-based action tokenization: cross-attention between state and action features, and a lightweight state adapter that predicts action-wise modulation factors for state-conditioned action modulation and reconstruction. The adapter formulation expands the effective support of a finite codebook by allowing each discrete token to represent a family of state-dependent continuous actions, while preserving the efficiency and compatibility of discrete action modeling. Integrated into an LLM-based VLA policy, SA-VLA supports both autoregressive and parallel action-token decoding with minimal changes to the model interface. On 12 RoboTwin manipulation tasks, SA-VLA improves the average success rate from 0.29 to 0.56 over the strongest tokenizer baseline. In zero-shot sim-to-real experiments on three real-world tasks, it further improves average success from 0.15 to 0.33 over the strongest tokenizer baseline. These results demonstrate that state-conditioned action decoding is a simple and effective mechanism for reducing the compression gap in discrete VLA policies. --- ### Automating the Design of Embodied Agent Architectures Authors: Jian Zhou, Sihao Lin, Jin Li, Shuai Fu, Gengze Zhou, Qi Wu Published: 2026-06-29 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.30111v2 Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules. This modularity exposes a large architectural design space, but current systems still rely on researcher intuition to choose where information is stored, how observations are processed, and how model calls are connected. Agent Architecture Search (AAS) automates such design for text-domain agents, but has not been systematically evaluated on perceptual embodied agents through simulator rollouts. We study this transfer. We introduce AgentCanvas, a typed-graph runtime that hosts embodied executors as editable node-and-wire programs with simulator-aware execution and episode-level logs, and KDLoop, a coding-agent search procedure that cycles through proposal, critique, experiment, and distillation, with triggered reflection after stalls. We evaluate three AAS variants across four embodied executors spanning vision-language navigation, embodied question answering, and language-conditioned manipulation. The resulting 3x4 matrix shows that architecture-level search can produce deployable and directional success-rate gains on embodied tasks, while one apparent high-scoring candidate is rejected as leak-bearing. At the same time, the experiments expose constraints that are muted in text-domain AAS: optimization signals can be masked by rollout noise, search can become trapped in local edit basins, and episode-level credit assignment only partially emerges even when detailed logs are available. These results characterize both the promise and the current limits of automated architecture search for embodied agents. --- ### LETT-NeXt: A Lightweight RECIST-Guided Model for 3D CT Lesion Segmentation Authors: Sebastian Aas, Elias Stenhede, Arian Ranjbar Published: 2026-06-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.30108v1 RECIST diameter measurements are widely used for tumor response assessment, but they provide only a limited 2D description of lesion extent. We present LETT-NeXt, a lightweight RECIST-guided model that predicts 3D lesion masks from CT volumes and RECIST markers for the CVPR 2026 Foundation Models for Pan-cancer Segmentation in CT Images competition. LETT-NeXt extracts a RECIST-centered regional crop, encodes the RECIST line and endpoints as two prompt channels, and concatenates them with the CT input. A compact MedNeXt-v2 encoder--decoder predicts the lesion mask, followed by prompt-aware component selection and adaptive AutoZoom inference. On the public validation set, LETT-NeXt achieved a Dice Similarity Coefficient (DSC) of 79.4 $\pm$ 10.1 and a Normalized Surface Dice (NSD) of 72.3 $\pm$ 16.2. On the hidden test set, it achieved a DSC of 73.9 and an NSD of 67.3, corresponding to a challenge score of 70.6\%. On the public validation mirror, LETT-NeXt completed CPU inference in 6.9 $\pm$ 3.0 s per case with a peak memory use of 3.6 GB. Code is available at github.com/Ahus-AIM/lett-next. --- ### Structural Certification for Reliable Physical Design with Language Models Authors: Nakul Vyas, Iliya D. Stoev Published: 2026-06-29 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.30107v1 An unreliable language model can be made to produce reliable physical designs if the authority to assert is moved out of the model: the model proposes, and a deterministic engine alone certifies, returning certified, impossible, or unknown. We introduce Physics-Anchored Certification (PHACT), a propose-certify loop spanning five scientific domains, and identify what makes such a certificate trustworthy. A checker that accepts a model-supplied value can be forged; deriving the certified quantity from fixed inputs instead makes forgery impossible by construction. Across eighty adversarial trials spanning two models, two decoding temperatures, and a deliberately faulted engine, this contract produced zero false certifications. --- ### Propagation of~Interval Belief Structures and~Imprecise Copulas for~Neural Network Verification Authors: Francesc Pifarre-Esquerda, Eric Goubault, Sylvie Putot Published: 2026-06-29 Categories: cs.AI, cs.LO, math.PR arXiv: https://arxiv.org/abs/2606.30105v1 Quantitative verification of neural networks requires reasoning about probabilities under substantial uncertainty in both input distributions and their dependence structure. In realistic settings, this information is often only partially specified, and assuming precise probabilistic models can lead to unreliable results. We propose a sound framework for quantitative verification under imprecise probabilistic information, combining interval belief structures to represent marginal uncertainty with imprecise copulas to model uncertain dependence. We develop a propagation method for imprecisely coupled interval belief structures through feed-forward neural networks. Using mixed imprecise copula volumes, we derive sound push-forward constructions through affine transformations and activation functions. The resulting output can provide guaranteed lower and upper bounds on probabilistic safety properties, valid for all probability models compatible with the specified imprecise inputs. --- ### Temporal Feature Extractors in EEG Foundation Models: A Controlled Comparison Including a Pretrained Time-Series Model Authors: Ayşe Betül Yüce, Chris Joey Leffler, Sarun Varghese, Myra Spiliopoulou, Sebastian Stober Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30104v1 Electroencephalography (EEG) foundation models aim to learn generalizable representations from large-scale brain recordings. However, the role of temporal feature extractors and whether pretrained time-series foundation models (TSFMs) can be effectively transferred to this setting remains underexplored. We conduct a controlled comparison of three temporal feature extraction strategies, including a linear baseline, a convolutional encoder, and a frozen pretrained TSFM (MOMENT), within a unified EEG foundation model. We evaluate their impact on representation quality using two downstream tasks: motor imagery and emotion recognition. Results reveal different trends across the evaluated benchmarks. On the motor imagery dataset, simple temporal representations perform competitively, whereas the emotion dataset benefits from richer temporal modeling. Although not specifically adapted to EEG, the pretrained TSFM serves as an effective temporal feature extractor, suggesting that general-purpose time-series representations can be transferred as frozen temporal feature extractors within EEG foundation models. --- ### SIR: Structured Image Representations for Explainable Robot Learning Authors: Paul Mattes, Jan Schwab, Jens Bosch, Nils Blank, Maximilian Xiling Li, Minh-Trung Tang, Moritz Haberland, Rudolf Lioutikov Published: 2026-06-29 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2606.30101v1 Existing robot policies based on learned visual embeddings lack explicit structure and are sensitive to visual distractions. Thus, the representations that drive their behaviour are often opaque, making their decision-making process difficult to interpret. To address this, we introduce Structured Image Representations (SIR), a method that leverages Scene Graphs (SGs) as an intermediate representation for robot policy learning. Our approach first constructs a fully connected graph, using image-derived features as initial node representations. Then, a module learns to sparsify this graph end-to-end, creating a task-relevant sub-graph that is passed to the action generation model. This process makes our model intrinsically explainable. Evaluations on RoboCasa show that our sparse graph policies outperform image-based baselines on average with 19.5% vs 14.81% success rate. Most importantly, we show that the learned sparse graphs are a powerful tool for model analysis. By analysing when the model's sub-graph deviates from human expectation, such as by including distractor nodes or omitting key objects, we successfully uncover dataset biases, including spurious correlations and positional biases. https://github.com/intuitive-robots/SIR_Model --- ### CylindTrack: Depth-Aware Cylindrical Motion Modeling for Panoramic Multi-Object Tracking Authors: Buyin Deng, Kai Luo, Lingxin Huang, Xinqi Liu, Fei Cheng, Hang Zheng, Liming Yin, Kailun Yang Published: 2026-06-29 Categories: cs.CV, cs.RO, eess.IV arXiv: https://arxiv.org/abs/2606.30097v2 Multi-Object Tracking (MOT) is essential for persistent embodied perception in camera-equipped consumer and service robots. Panoramic cameras offer wide surrounding coverage, but equirectangular projection introduces a periodic horizontal domain in which conventional planar motion models and IoU-based association become unreliable near the 0°/360° seam. In addition, large-field-of-view scenes exhibit frequent interactions, scale variation, and occlusion, while frame-wise monocular depth estimates may fluctuate over time. To address these challenges, we propose CylindTrack, a depth-aware cylindrical tracking-by-detection framework for panoramic MOT. CylindTrack introduces Depth-Temporal Trajectory Modeling (DTM) to propagate instance depth as a temporally filtered trajectory-level state, providing more stable geometric cues for association. It further incorporates Spherical Spatio-Temporal Consistency Learning (SSTC), which combines a Temporal Mixer with Spherical Geometry-Aware Attention to improve temporal coherence and panoramic geometric alignment of depth-aware representations. Finally, the Topology-Aware Cylindrical Motion Model (TCMM) lifts horizontal motion into a continuous angular state space and performs seam-consistent prediction and association under panoramic periodicity. By jointly modeling depth dynamics and panoramic topology, CylindTrack improves identity preservation and trajectory continuity. Experiments on QuadTrack and JRDB achieve 33.67/31.12 HOTA and 40.45/34.33 IDF1 at 28.56/21.34 FPS, demonstrating the effectiveness and practical online efficiency of CylindTrack as a persistent perception module for panoramic consumer and service robots. The source code will be released at https://github.com/warriordby/CylindTrack. --- ### CylindTrack: Depth-Aware Cylindrical Motion Modeling for Panoramic Multi-Object Tracking Authors: Buyin Deng, Kai Luo, Lingxin Huang, Xinqi Liu, Fei Cheng, Hang Zheng, Liming Yin, Kailun Yang Published: 2026-06-29 Categories: cs.CV, cs.RO, eess.IV arXiv: https://arxiv.org/abs/2606.30097v1 Multi-Object Tracking (MOT) is a core capability for embodied perception, and panoramic cameras are attractive for embodied systems because their 360° field of view reduces blind spots and keeps surrounding targets observable for longer durations. However, panoramic MOT is not a straightforward extension of perspective MOT. In equirectangular panoramic videos, the horizontal image domain is periodic rather than Euclidean, which breaks planar motion assumptions and makes IoU-based association unreliable near the 0°/360° seam. Meanwhile, large-FoV scenes often contain more objects, stronger scale variation, and more frequent interactions, making online association particularly sensitive to unstable frame-wise depth cues. To address these issues, we propose CylindTrack, a depth-aware cylindrical tracking-by-detection framework for panoramic MOT. CylindTrack first introduces Depth-Temporal Trajectory Modeling (DTM), which promotes instance depth from an isolated frame-wise cue to a temporally filtered trajectory-level state. To improve the reliability of depth observations, we further develop Spherical Spatio-Temporal Consistency Learning (SSTC), which combines a Temporal Mixer and Spherical Geometry-aware Attention to enhance temporal coherence and panoramic geometric alignment in depth-aware representations. Finally, we design a Topology-Aware Cylindrical Motion Model (TCMM) that lifts horizontal motion into a continuous angular state space and performs seam-consistent motion prediction and association in the periodic panoramic domain. By jointly modeling trajectory-level depth consistency and panoramic topology, CylindTrack improves identity preservation and trajectory continuity in challenging panoramic scenes. The source code will be released at https://github.com/warriordby/CylindTrack. --- ### Information Dynamics of Language Communication Authors: Leonardo S. Goodall, Andrea I. Luppi, Pedro A. M. Mediano Published: 2026-06-29 Categories: cs.CL, cs.IT arXiv: https://arxiv.org/abs/2606.30096v1 Quantifying how meaning propagates through communicative exchanges remains underdeveloped in computational linguistics. Here we introduce an information-theoretic framework that quantifies the directed flow of semantic content between interlocutors and decomposes multi-source contributions into redundant, unique, and synergistic components. Our approach leverages large language models as probabilistic estimators of natural language to compute two measures: semantic transfer entropy (STE), which captures directed predictive influence between speakers, and semantic partial information decomposition (SPID), which resolves how multiple sources jointly shape a target's language. Across four experiments we show that the framework detects reduced information flow in cognitively rigid dialogue, captures the dominant role of persuaders in shaping discourse, distinguishes high- from low-quality psychotherapy by the directionality of therapist-client information exchange, and reveals synergistic premise contributions in argumentative essays. This framework opens new avenues for studying information dynamics in digital discourse, pedagogical interactions, clinical dialogues, and any domain in which the structure of linguistic exchange is of research relevance. --- ### Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs Authors: Gianluca Bonifazi, Christopher Buratti, Michele Marchetti, Federica Parlapiano, Giulia Quaglieri, Davide Traini, Domenico Ursino, Luca Virgili Published: 2026-06-29 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2606.30093v1 Retrieval-Augmented Generation (RAG) mitigates hallucinations in Large Language Models (LLMs) by grounding the generation process on external knowledge. However, standard RAG approaches struggle with multi-hop reasoning. While recent graph-based RAG methods improve the retrieval of interconnected chunks, they often rely on computationally expensive and error-prone LLM-based extraction pipelines. To address these issues, we propose TIGRAG (Token-Induced GraphRAG), an efficient graph-augmented RAG framework based on a token co-occurrence Knowledge Graph. TIGRAG directly models topological relationships between tokens using sliding-window co-occurrence statistics, thus enabling scalable graph construction. During inference, it combines graph-based semantic expansion and neural reranking to retrieve interconnected evidence for multi-hop reasoning. Specifically, it introduces an iterative entity-driven retrieval strategy that progressively expands the query using bridging entities extracted from previously retrieved contexts. We evaluated TIGRAG on three widely adopted multi-hop Question Answering (QA) benchmarks. Experimental results demonstrated that our framework consistently outperforms dense retrieval and graph-based RAG methods in both retrieval and downstream QA tasks, while substantially reducing indexing time, inference latency, and prompt footprint. --- ### Hierarchical Reinforcement Learning in StarCraft Micromanagement with Influence Maps and Cluster-based Scripts Authors: Chunhui Bai, Changhe Li, Dequan Li, Xinye Cai, Shengxiang Yang Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30092v1 Real-time strategy (RTS) games present significant AI challenges, characterized by expansive state-action spaces arising from multi-unit coordination in continuous battlefields, and sparse delayed rewards stemming from final win/lose signals. Existing approaches face a trade-off between managing the dimensionality explosion of joint actions and maintaining the interpretability of complex state representations. This complexity is further intensified by the limitation of traditional hierarchical structures in adaptively decomposing tasks into effective tactical modules. Such difficulties are compounded by the black-box nature of deep learning models and their reliance on sparse rewards, which together result in limited sample efficiency and a lack of decision-making transparency. To address these limitations, this paper proposes HRL-IM/CBS, a hierarchical reinforcement learning framework with influence map hashing and cluster-based scripts for StarCraft micromanagement. Influence map hashing encodes global battlefield situations into compact hexadecimal codes, capturing spatial control and relative advantage. Cluster-based scripts enable dynamic local coordination through adaptive unit partitioning. The hierarchical multi-Q-table architecture decomposes decision-making into upper-level clustering strategy selection and lower-level tactical execution, with reward allocation providing dense learning signals. Experiments across six asymmetric scenarios demonstrate competitive performance against deep RL baselines while offering advantages in sample efficiency and interpretability through transparent Q-table representations. --- ### SAT-RTS: A systematic framework for tactical knowledge extraction and visualization-based analysis in real-time strategy games Authors: Chunhui Bai, Changhe Li, Yuqiang Li, Lei Liu, Shoufei Han Published: 2026-06-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.30090v1 Efficient tactical knowledge extraction and analysis in real-time strategy (RTS) games micromanagement are constrained by the high-dimensional coupled state-action sequential data and the black-box decision-making process. Current research rarely provides a hierarchical visualization-based attribution analysis from the perspective of data decoupling and abstraction. To facilitate interpretable tactical knowledge extraction and visualization-based analysis in RTS games, a systematic framework named state-action-tactic analysis pipeline (SAT-RTS) is proposed. To decipher the deep-seated drivers of critical decisions in RTS learning systems, this work integrates interpretable visualization with the automated extraction of latent tactical patterns from high-dimensional sequence data. By adapting a cluster-centric BK-tree algorithm and incorporating specialized distance metrics designed to quantify multi-aspect similarities, the proposed framework facilitates robust state-stream abstraction. Furthermore, a rule-based multi-label extraction method is developed to transform unstructured state-action sequences into discrete and interpretable tactical labels, effectively bridging the gap between raw behavioral data and high-level tactical insights. By holistically integrating these computational methods into a hierarchical visualization-based pipeline, the proposed framework effectively addresses the challenges of processing massive real-time data streams while providing fitness landscape visualizations and analytical insights to decipher deep-seated tactical drivers. Comprehensive experiments demonstrate that the proposed SAT-RTS significantly enhances the interpretability and efficiency of tactical analysis in complex RTS environments. ---