# Research Papers — 2026-09 · bundle page 126 of 266 > Full-text markdown of papers #6251–6300 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/126 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/125.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/127.md) ### Directing large language models to follow the letter or spirit of the law Authors: Peng Qian, Andrew Li, Sam Chen, Sonia K. Murthy, Yonatan Belinkov, Tomer D. Ullman Published: 2026-09-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.23083v1 The distinction between the spirit and letter of the law is a central issue across research and everyday life, and a growing concern for building safe, intelligent machines. What is this distinction based on, and how can we develop machines that follow the intention behind a rule? We used targeted adaptation that made large language models prioritize the spirit or letter of the law. With minimal modifications, our method significantly changed LLM behavior across diverse measures, novel vignettes, real-world scenarios, and influential legal cases. An analysis of model internals revealed a low-dimensional space with three interpretable dimensions matching a formal pre-specified framework for the geometry of legal concepts. These findings show how legal thought in LLMs may be organized and directed. --- ### Event Signature Transfer: Model-Agnostic Forecast Scenario Construction from Historical Events Authors: Karthik Sridhar, Aaditya Jain, Murari Mandal, Saurabh Deshpande Published: 2026-09-19 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.23074v1 Forecasters often know an event is imminent but not the shape, size, or timing of its effect. We introduce Event Signature Transfer (EST), a training-free, model-agnostic operator that turns a completed past event into an explicit forecast scenario. EST removes a source event's own trend and seasonality, then scales and retimes the remaining event signature onto a native forecast, preserving the forecast's linked structure and reducing to it exactly at zero strength. Because it reads only output quantiles, EST applies to any quantile forecaster, with no training, no model internals, at transfer time. Across twelve real episodes and ten synthetic scenarios on Chronos-2, TimesFM-2.5 and Toto-2.0, manually configured EST reduces real-episode WQL by 21.7-90\% in-sample. On Chronos-2, it leads eleven of twelve matched comparisons against covariate conditioning, activation editing and raw replay. The operator builds a scenario; it does not estimate its likelihood. --- ### MolSC: Leveraging Substituent Contributions to Enhance Fine-grained Molecular Understanding in LLMs Authors: Hyuntae Park, Sooyeon Kim, Jiwon Park, SangKeun Lee Published: 2026-09-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.23073v1 Recent advances in natural language processing have led to molecular Large Language Models (LLMs) with strong performance across diverse chemistry tasks. However, they still struggle to capture fine-grained structure-property relationships, particularly how small, localized modifications alter a molecule's behavior. To address this limitation, we introduce MolSC, a dataset of substituent contributions, defined as property changes induced by attaching specific substituents to molecular scaffolds. Curated from manually annotated bioactivity records, MolSC spans structural-alert liability, target-specific bioactivity, and physicochemical descriptors, and contains 181K substituent-level examples for training. We further propose MolSC-Bench, a held-out evaluation benchmark of 1,541 examples disjoint from MolSC at the scaffold, substituent, and molecule levels. Our experiments show that existing molecular LLMs and strong proprietary models such as GPT-5.2 and Gemini-3-Flash show limited reliability in substituent contribution prediction. In contrast, training on MolSC substantially improves this ability and achieves strong performance across diverse downstream molecular tasks. These results highlight substituent contribution learning as a key component of fine-grained molecular understanding. --- ### Tutoring Large Language Models to be Domain-adaptive, Precise and Safe Authors: Somnath Banerjee Published: 2026-09-19 Categories: cs.AI, cs.CE, cs.CL arXiv: https://arxiv.org/abs/2609.23071v1 This thesis proposes a framework for "responsible intelligence" to address AI's critical challenges in safety, ethics, and cultural sensitivity. It advances three core areas: First, it improves domain adaptation in specialized fields using active learning and graph-based knowledge to reduce hallucinations. Second, it enhances ethical rigor via a novel decoding-time alignment mechanism that proactively blocks harmful text generation in real-time. Finally, it ensures cultural and multilingual safety through language-specific steering that respects diverse linguistic and social norms. Ultimately, this work provides a blueprint for building next-generation AI that is contextually knowledgeable, ethically sound, and culturally adaptable. --- ### LD-RSVIS: A Large-Scale and Diverse Benchmark for Referring Surgical Video Instrument Segmentation Authors: Zan Wang, Yunhe Feng, Dong Nie, Oluwatosin Oluwadare, Kewei Sha, Yan Huang, Heng Fan Published: 2026-09-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23067v1 Referring surgical video instrument segmentation (RSVIS) aims at segmenting the instrument in a surgical video, given a textual description. Despite recent progress, current models are trained and assessed on relatively small-scale benchmarks, hindering the development of more general RSVIS. In addition, existing benchmarks support only the single-target expression that refers to one instrument in the video, while overlooking multi-target and no-target referring expressions, restricting the applicability of RSVIS in practical scenarios. Addressing these issues, we propose LD-RSVIS, a new benchmark aiming to facilitate more robust and general RSVIS. Specifically, LD-RSVIS consists of 3,536 surgical videos with 1.09 million frames and covers a broad set of 30 instrument classes from 25 various procedures. By including abundant videos and classes, LD-RSVIS could benefit large-scale training and evaluation of more general RSVIS methods. Besides, unlike existing datasets, LD-RSVIS offers diverse referring settings, including no-target, single-target, and multi-target expressions, which enables the development of more practical RSVIS models in real applications. In order to ensure high-quality annotations, all videos in LD-RSVIS are manually labeled with multiple rounds of inspection and refinement. To our knowledge, LD-RSVIS is the largest and most diverse benchmark for RSVIS. To analyze LD-RSVIS and to provide comparison for future research, we evaluate 12 representative methods, and the results reveal that more efforts are required for improvements. To encourage future research, we present a simple yet effective RSVIS method, dubbed Cascade-RSVIS, that first mines target-specific cues using the complementary multi-cue text information and then employs such cues and textual information for segmentation, achieving promising performance. Our benchmark and code will be released. --- ### From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness Authors: Qianli Wang, Yilong Wang, Dennis Wei, Jingyi Sun, Simon Ostermann, Isabelle Augenstein, Pepa Atanasova, Nils Feldhus Published: 2026-09-19 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.23065v2 Chain-of-thought (CoT) can sound plausible yet be unfaithful to the model's underlying reasoning. Most prior work probes CoT faithfulness through input--output behavior or input attributions, leaving internal computation largely underexplored. We instead cast faithfulness as internal concept grounding: Does a large language model's (LLM) CoT reasoning engage the same internal concepts that support the LLM's direct prediction, and do the shared concepts causally drive its answer? Encoding a prediction pass and a CoT pass with a single shared sparse autoencoder (SAE), a reliable approximator of the latent concepts LLMs use, makes their internal concepts directly comparable. We introduce three correlational metrics of concept-level alignment and a causal metric, $Δp$, which ablates the shared concepts and measures the drop in answer probability. Across five LLMs and four datasets, concept alignment is generally high, as indicated by the correlational metrics; yet these only identify which concepts are shared, not how much they causally contribute. $Δp$ fills this gap: causal faithfulness varies substantially with model depth, peaking at mid-to-late layers rather than the final ones, and model scale reshapes the layer-wise profile. Moreover, causally important shared concepts are not always verbalized in the CoT. These dissociations suggest that faithfulness cannot be reliably assessed from surface-level or representational correspondence alone; assessing it requires causal tests of whether the internal concepts underlying a CoT actually drive the model's prediction. --- ### FireWorldBench: Benchmarking Complex Physical World Intelligence through Coupled-Field Fire Dynamics Authors: Qiang Chen, Hao Guo, Huatai Zhu, Tairan Huang, Yichao Cao, Hongyan Xu, Keke Huang, Haifeng Li, Yi Chen, Xiu Su Published: 2026-09-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.23064v1 Understanding the physical world requires more than object recognition, scene description, and short-term visual prediction, as real-world physical systems involve multiple continuous fields, latent causal mechanisms, partial observations, and intervention-sensitive dynamics. We propose FireWorldBench, a benchmark for evaluating complex physical world intelligence in multimodal large language models and agents through coupled-field fire dynamics. Fire provides a canonical stress-test environment, where multiple interacting physical fields jointly shape observable states and temporal dynamics. FireWorldBench is organized along two complementary axes, a physical capability axis and a fire scenario task axis, jointly covering physical-state understanding, temporal dynamics, causal mechanisms, and intervention reasoning. The benchmark comprises 520 fire-world entries, including 494 controlled simulation worlds and 26 real-world-aligned event groups, spanning 47 scene archetypes across 7 environment families. These entries combine structured textual observations, multiple 2D physical-field visualizations, and 3D event-level scene modeling, yielding 9,074 text-image interleaved question-answer pairs across choice-based and open-ended report-generation formats. FireWorldBench evaluates whether models can infer latent physical states, explain underlying mechanisms, forecast coupled-field evolution, and assess intervention consequences from multimodal partial observations, providing a challenging testbed for complex physical world intelligence. --- ### HDMamba-YOLO: Efficient State-Space Perception and Local Spatial Reconstruction for UAV Small Object Authors: Linduo Wei, Junjie Fan, Yijun Mai, Yong Qi Published: 2026-09-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23061v1 Small-object detection in UAV imagery is challenged by weak visual evidence, ambiguous boundaries, dense object distributions, and complex backgrounds. Effective detection therefore requires long-range contextual information for target-background discrimination while preserving explicit local two-dimensional structures for accurate localization. These requirements arise at different stages of the detection pipeline and are not naturally addressed by a uniform feature-processing strategy. We propose Hybrid Dual-domain Mamba-YOLO (HDMamba-YOLO), a stage-wise heterogeneous SSM-CNN detector organized according to a perception-reconstruction-alignment-interaction rationale. EfficientVMamba-based EVSS establishes long-range contextual perception in the backbone, while PhasePatchMerging2D provides phase-aware hierarchical transitions. DST-Wrapper and Native C3k2-ASSAF then perform perception-to-reconstruction transition and repeated local two-dimensional reconstruction during FPN/PAN aggregation. DySample provides content-adaptive cross-scale resampling, while OS-CVTIA introduces macro-micro interaction and task-specific modulation for localization and classification. On VisDrone2019, HDMamba-YOLO-B achieves 42.737% mAP50 and 25.713% mAP50:95 with 10.042M parameters and 29.879 corrected GFLOPs. HDMamba-YOLO-Lite achieves 41.140% mAP50 and 24.741% mAP50:95 with 5.344M parameters. Under the unified AI-TOD evaluation protocol, HDMamba-YOLO-B obtains 21.621% AP and 47.881% AP50. Controlled ablations further support the stage-wise allocation of state-space perception, convolutional reconstruction, dynamic alignment, and task interaction for UAV small-object detection. --- ### LazyAgent: Demand-Driven Materialization and Physical Optimization of Agentic Programs Authors: Xin Heng Published: 2026-09-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.23058v1 Current agent runtimes that plan before acting generally execute a step once it becomes ready. We present LazyAgent, a unified execution framework for agent-authored programs organized around a live, goal-derived demanded set. LazyAgent refreshes a backward closure from requested outputs as execution state changes and materializes a ready node only when the active goal requires it. This replaces repeated local judgments with one linear-time graph analysis followed by constant-time membership tests, allowing programs to remain broad while execution stays request-specific. On programs that describe more than the current request needs, LazyAgent consistently outperforms the strongest goal-stopping eager baseline by refusing unrelated work before it starts. Adding one unrelated product raises the eager bill by 22.5% and LazyAgent's by 0.0%. LazyAgent saves 42.0% of measured CPU on production scientific workflows and 51.7% of container time on a live release gate spanning four repositories. We also prove and verify exact equivalence when the request reaches the whole graph, leaving no unrelated work to avoid. Beyond permission, goal-relative output projection saves up to approximately 90% of a shared step on two third-party test suites while the identical eager control saves 0.0%; the advantage disappears when the omitted output has no other consumer or the request needs it. Ordering, reuse, and pruning can also save cost, but do not replace permission. Finally, we show that current public benchmarks are eager-shaped and contain almost no unrequested work. A pre-registered planning intervention did not broaden them. These findings motivate benchmarks built from standing programs and sequences. --- ### Bridging Static and Agentic RAG for Taiwanese Historical Question Answering Authors: Kai-Hsin Chen, Wei-Yu Chen, Xuanjun Chen, Jyh-Shing Roger Jang Published: 2026-09-19 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2609.23056v1 Agentic retrieval-augmented generation (RAG) enables language models to adapt retrieval based on previously retrieved evidence, but it remains unclear whether such adaptive orchestration consistently outperforms well-designed static pipelines. We conduct a controlled comparison of agentic and static RAG for Taiwanese historical question answering, sharing the same generator and hybrid retrieval backend. Despite similar aggregate performance, the two pipelines differ on 70.83% of questions, with their advantages largely canceling out when averaged. An oracle that selects the better response per question improves the composite score by 0.2417 over the better individual pipeline, revealing substantial headroom for question-level selection. We therefore introduce a post-hoc selector that compares the two responses and their cited evidence, significantly outperforming either individual pipeline and recovering 60.34% of the oracle headroom. These results show that aggregate comparisons can obscure meaningful question-level differences between retrieval strategies, suggesting that exploiting their complementarity may be more fruitful than seeking a universally superior pipeline. --- ### Optimizers for Diffusion Models: A Controlled Benchmark Authors: Arman Bolatov, Egor Shulgin, David Li, Abduragim Shtanchaev, Sebastian U. Stich, Maxim Panov, Eric Moulines, Peter Richtárik, Martin Takáč Published: 2026-09-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23055v1 Discrete diffusion models now match autoregressive language models on several benchmarks, while the question of how best to train them has received far less attention: the optimizer is inherited from one paper to the next and never compared. New optimizers, meanwhile, are validated almost exclusively on autoregressive pretraining, a different objective on a different loss surface. We present a controlled optimizer benchmark across four diffusion formulations, to our knowledge the first for discrete diffusion: seven optimizers (AdamW, Lion, Muon, SOAP, MARS, MARS-M, Schedule-Free) on masked diffusion (text8), uniform diffusion (QM9, and LM1B through the Gaussian duality) and Gaussian diffusion on images (CelebA-64), each on a task with published reference values. Every optimizer receives the same search protocol, and every winner is retrained at the full budget with three seeds. AdamW is a strong default but not always the right choice: it is beaten by a resolved margin on two of the four tasks, and the winner changes with the formulation, so the optimizer deserves the same care as the rest of the training recipe. Notably, methods validated on autoregressive language model pretraining transfer well: Muon, MARS-M and SOAP each beat the tuned AdamW on at least one diffusion formulation. The benchmark, all runs and every figure are reproducible end to end from the released code at https://github.com/armanbolatov/diffusion-baselines. --- ### Attributable Post-Rationalization in RAG Citations: A Controlled Reproduction and an RLVR Comparison Authors: Mehedi Khan, Md. Shariful Islam Bhuyan Published: 2026-09-19 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2609.23053v1 A RAG system can hand you the right answer and cite a source it did not actually use. Models output these unfaithful citations via post-rationalization: they write the answer first and then attach a citation to whatever passage looks close enough. Search agents are now trained with reinforcement learning from verifiable rewards (RLVR), which pays them for getting the answer right. We asked whether that training also teaches them to cite honestly. Improving an existing methodology with a required control, we compared an instruction-tuned model against three RLVR agents trained from it, on four question-answering datasets, using only free-tier Kaggle GPUs. Post-rationalization is everywhere: on Wikipedia-based questions roughly one citation in seven is unfaithful. RLVR does not fix it. The agents post-rationalize at their base model's rate, and one lands slightly worse. Rewarding correct answers buys nothing in citation faithfulness, so faithfulness has to be trained and measured on its own terms. --- ### VDGS: Visibility-Driven Large-Scale 3D Gaussian Splatting for Aerial Scene Reconstruction Authors: Haolin Yu, Jiadong Tang, YiXian Wang, Yu Gao, Shi He, Zhilin Lai, Yi Yang, Mengyin Fu Published: 2026-09-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23049v1 Large-scale scene reconstruction is a critical foundational technology in robotic autonomous systems such as 3D mapping and autonomous driving. In recent years, 3D Gaussian Splatting (3DGS) has demonstrated remarkable advantages in both visual quality and computational efficiency, making it a promising representation for large-scale scene reconstruction. However, it still faces challenges in large-scale scenes, including excessive memory consumption and uneven viewpoint coverage caused by UAV acquisition, limiting its real-world applications. To address this, we propose VDGS, a novel 3DGS framework that incorporates camera distribution into scene modeling. VDGS introduces visibility-driven statistics for scene anchors to quantify supervision strength. These statistics are further leveraged for scene partitioning and for gradient compensation in under-optimized regions, thereby promoting balanced optimization across different regions. Extensive experiments on multiple large-scale aerial scene datasets demonstrate that, under imbalanced viewpoint distributions, VDGS consistently outperforms existing methods, while maintaining competitive performance in scenarios with more uniform view distributions. --- ### Anatomy of a Closed-Loop Collapse: A Causal Case Study of a Compressed VLA Policy Authors: Fengze Jia Published: 2026-09-19 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.23048v1 Compressed manipulation policies can pass offline evaluation while failing in closed-loop execution; this dissociation is established in prior work and is not our claim. We contribute a causal anatomy of one naturally occurring case. An 8-layer distillation of Octo-Base retains 86% of parameters, passes every offline check we applied (0.996 and 1.000 teacher-ratios on the family's own validation metrics), and collapses in closed loop: 0/72 vs. the teacher's 40/72 on a simulated WidowX pick-and-place task. The collapse is structured, not diffuse: early task stages degrade gradually (the student moves the object at 90% of the teacher's rate and grasps at 55%), while transport-to-target fails categorically, at 0% in every training variant. Paired action-trace forensics isolate the signature: a negative, late-heavy $z$ residual, roughly 10x its post-repair magnitude, and persistent across the base distillation and both continuation branches. Four standard therapies fail under matched controls: continued training and in-domain offline data leave success at zero, even though the latter measurably improves marginal action statistics; command-level compensation recovers nothing at any offset, although the same perturbations degrade healthy policies; clamping the symptom in the command channel preserves grasping, yet success stays at floor. A minimal-pair intervention that substitutes half of the training stream with deployment-distribution teacher rollouts, with every other setting held fixed, restores parity with the teacher (18/36 vs. 17/36 held-out), eliminates that signature, and recovers a teacher-like perturbation-response profile. We claim existence, not universality. Operationally, offline gates, including a family's own validation metrics, are insufficient acceptance tests for compressed policies; a few dozen closed-loop trials sufficed to find what they missed. --- ### Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees Authors: Parsa Rahmati, Richard Zhao Published: 2026-09-19 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.23043v1 Large Language Models (LLMs) enable open-ended dialogue in interactive games, but their non-deterministic outputs make it difficult to preserve authorial control, factual consistency, and the intended sequence of information disclosure. These challenges are particularly significant in detective games, where premature revelation or fabricated details can undermine the logic of player progression. We present a Structured Knowledge Tree architecture coupled with a tri-agent LLM pipeline for controlling dialogue in an open-ended interrogation game. The system separates knowledge retrieval, dialogue generation, and response verification to ensure that the virtual suspect reveals only information permitted by the current narrative state. We evaluate the approach through The Interrogation of Adrian Gale, a playable detective-game testbed, and a formal user study examining hallucination reduction, adherence to authored disclosure sequences, and perceived logical progression. Our results demonstrate that the structured architecture reduces critical hallucinations by 64.78% and entirely prevents premature narrative disclosure. While the strict mechanical constraints introduced usability trade-offs regarding forced conversational reveals, the system successfully enforces rigorous epistemic pacing and provides players with a clear, subjective sense of progression toward solving the case. --- ### Auditing Political Alignment in LLM Assistants: Engagement, Stance, and User Identity Authors: Joan C. Timoneda Published: 2026-09-19 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2609.23039v1 LLM-based AI systems answer political questions for hundreds of millions of people. Current audits measure what they say to an average user, but their behavior is dynamic. I argue that their political behavior is a set of policies over whom to answer, what to say, and whether to engage at all, conditional on the topic and what the system knows about the user. I call these policies the system's speech regime, which is how a developer settles the tradeoff between answering, accommodating the user, and refusing, each of which carries a cost that varies by topic. I derive a typology of five regimes from two dimensions, engagement and stance. I test six AI systems (OpenAI, Anthropic, xAI, Google, Mistral, DeepSeek) in a preregistered experiment of 7,500 multi-turn conversations that randomly assign the user's political identity across five topics: abortion, Catalan independence, climate change, Nazism, and a zero-stakes control (pineapple on pizza). Two LLM judges from different developers score every answer, validated against human coding, and refusal is treated as an outcome rather than missing data. Every system accommodates the user on the control topic, showing that political restraint is a policy. On contested topics the systems fall into different regimes: on abortion, GPT engages and mirrors every user, Gemma refuses everyone, Claude answers strongly conservative users 35 percent of the time and almost no one else, and Grok accommodates conservatives only. On settled topics such as climate change and Nazism, five systems hold firm for every user. The systems also infer the user's overall ideology, so accommodation can spill over to topics not yet discussed. A comparison of two Grok releases shows the regime changing between versions in a way current audits miss. Speech regimes matter for alignment research and for polarization, political knowledge, and the quality of democracy. --- ### Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World Authors: Kaixiang Yao, Xu Wang, Miao Pan, Hu Xiyue, Weishi Wang, Daniel Dahlmeier, Jintao Chen, Yongliang Shen, Xuhong Zhang, Wenqi Zhang Published: 2026-09-19 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.23038v1 Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoning in dynamic environments requires VLMs to perceive local state transitions caused by object motion and viewpoint changes and integrate them over long trajectories to maintain an updated spatial state, yet existing VLMs remain limited in both capabilities. Current spatial training primarily focuses on static questions about object attributes and spatial relations, providing limited direct supervision for state transitions; in contrast, interaction trajectories naturally connect a preceding observation, an action, and a subsequent observation, offering direct supervision for local state transitions, while complete trajectories reveal dependencies among consecutive transitions. We therefore introduce Spatial-Interactor, a framework that trains VLMs to model physical-world state transitions through interaction, organizing this learning process into a three-level curriculum covering L1 passive world-state transitions, L2 active self-state transitions, and L3 long-horizon interaction trajectories. Accordingly, we construct the Learning from Spatial Interaction dataset (LSI-108K) from simulated and real interaction trajectories, with tasks aligned with the objective of each level. Our two-stage training strategy applies Supervised Fine-Tuning (SFT) to L1 and L2 for local transition modeling, and On-Policy Distillation (OPD) then uses privileged self-distillation: a teacher branch given segment-level transition descriptions supervises the student's on-policy CoT, helping the student learn to integrate consecutive transitions over L3 long trajectories. Experiments across multiple VLMs and spatial benchmarks show consistent gains in local transition modeling and long-horizon integration. --- ### WaveFront Decoding: Parallelized Self-Speculative Decoding for Looped Language Models Authors: Hyeongju Ha, Jae-Joon Kim Published: 2026-09-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.23033v2 Looped language models repeatedly apply a weight-shared block to increase effective depth without increasing parameter count, but the resulting T sequential recurrent-block calls per generated token substantially increase decoding latency. To address the issue, we introduce Wavefront Decoding (WFD), a training-free self-speculative decoding framework designed for looped language models. WFD exploits two properties of these architectures: intermediate recurrence outputs provide effective draft predictions, and weight sharing allows token states at different positions and recurrence depths to be processed in one batched recurrent-block call. WFD organizes these mixed-depth states into a diagonal wavefront, continuously drafting new positions at shallow depth while advancing earlier positions toward full-depth verification. Unlike the phase-separated draft-then-verify schedule, WFD therefore concurrently batches drafting and verification within the same recurrent calls, while rejected drafts are corrected using full-depth predictions. Across six Spec-Bench task categories, WFD achieves 2.42x speedup on Ouro-2.6B and 3.54x on Huginn-3.5B over autoregressive decoding, consistently outperforming draft-then-verify. Cross-recurrence KV sharing further reduces wavefront KV traffic and increases WFD's speedup to 4.81x on Huginn-3.5B. The code is available at https://github.com/summerbro-hhj/wavefront-decoding. --- ### BrainIAC: Interactive 3D Brain Lesion Segmentation across Heterogeneous MRI Modalities with Online Adaptation Authors: Wentian Xu, Anthony P Addison, Ziyun Liang, Harry Anthony, Guang Yang, Konstantinos Kamnitsas Published: 2026-09-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23026v1 Brain lesion segmentation is a fundamental task in medical image analysis, playing a critical role in diagnosis, treatment planning, and longitudinal disease monitoring. Yet existing models still struggle to meet the demands of real clinical use, where deployments contain data distribution shifts, arising from differences in scanner hardware, imaging protocol (varying MRI modality sets), and new pathologies. We present BrainIAC (Brain lesion Interactive Adaptive Continuously learning segmentation), a unified framework that integrates (i) a multi-modal backbone network trained to segment multiple types of brain lesions and handle heterogeneous sets of modalities via zero-filling and random modality dropping; (ii) 3D interactive segmentation with bounding-box and click prompts that preserves fully automatic prediction when no prompt is given; and (iii) an online adaptation mechanism combining Mid-Interaction adaptation and Post-Interaction adaptation, supervised by the network's own predictions as pseudo labels and guided by an extra Click-Centered Gaussian loss. To our knowledge, this is one of the first 3D online adaptation methods for interactive segmentation, and the first to combine handling of heterogeneous modality sets with online adaptation. Experiments across seven brain MRI datasets demonstrate that the proposed components provide complementary and synergistic benefits. The method consistently outperforms existing approaches and generalizes well across heterogeneous imaging modalities, including those unseen during training, as well as previously unseen brain pathology types. The code and a 3D Slicer plug-in will be released at https://github.com/WenTXuL/BrainIAC upon publication. --- ### PINNForge: Execution-Grounded Evolutionary Design of Physics-Informed Neural Networks Authors: Mingyang Yu, Xu Yang, Jun Zhang, Jing Xu, Keqian Li Published: 2026-09-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.23023v2 Physics-informed neural networks (PINNs) require coordinated choices across representation, architecture, sampling, constraints, loss construction, and optimization, yet effective configurations can vary substantially across partial differential equations (PDEs). Existing automated design methods search over these choices, but training outcomes are still used primarily to rank candidates rather than to inform subsequent designs. We develop PINNForge, an execution-grounded large language model (LLM)-driven evolutionary framework that treats observed PINN training behavior as a cross-generation design signal. PINNForge initializes diverse configurations from PDE-related prior knowledge, executes them, retains globally strong configurations, and feeds their execution evidence and accumulated run-level experience back to the LLM. The LLM then revises and recombines coupled design components or explores new combinations within a generate--execute--evaluate--evolve loop. Across 25 PDE benchmarks, PINNForge achieves the lowest mean MSE on 24 tasks among RoPINN, PINNsFormer, PINNsAgent, and PINNForge. Removing knowledge guidance, execution feedback, or evolutionary search increases the median task-wise MSE ratio to 3.74$\times$, 12.10$\times$, and 10.10$\times$, respectively, relative to full PINNForge. --- ### SomaNet: Weakly Supervised Learning for Instance Soma Segmentation in 3D Electron Microscopy with Partial Annotations Authors: Mohammad Khateri, Morteza Ghahremani, Jussi Tohka, Alejandra Sierra Published: 2026-09-19 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2609.23019v1 Soma instance segmentation, i.e., identifying and delineating individual cell somas as distinct instances, is crucial for cellular analysis and connectomic reconstruction. Three-dimensional electron microscopy (3D EM) provides nanometer-scale resolution for capturing fine-grained soma morphology. However, dense instance-level manual annotation is prohibitively costly, limiting the scalability of fully supervised methods. To address this challenge, we propose SomaNet, a weakly supervised framework for 3D EM soma instance segmentation under partial annotation constraints. SomaNet adopts a teacher--student learning paradigm tailored to partial labels. The teacher is trained using partially annotated data to generate pseudo-labels, while the student jointly learns from the partial ground-truth annotations and the generated pseudo-labels, progressively recovering dense instance segmentations. To accurately delineate cell somas under limited supervision with varying instance counts, SomaNet incorporates affinity learning, which encourages high similarity within instances and low similarity across instance boundaries. Semantic-guided affinity decoding and 2D-to-3D reconstruction then produce volumetrically consistent 3D soma instances while preserving the large receptive fields of 2D backbones. The framework is architecture-flexible and supports diverse backbones, including vision transformers and foundation models, enabling direct transfer of pretrained visual representations to volumetric EM segmentation. Experiments on 3D EM brain datasets demonstrate that SomaNet achieves accurate and robust soma instance segmentation across regions with diverse soma morphologies under partial annotation. Code is available at https://github.com/mkhateri/SomaNet. --- ### Reconstructed holograms and explanation-aware evaluation for low-cost computational pollen analysis in veterinary cytology Authors: Swarn Warshaneyan, Joial Danyal, Blaž Cugmas, Mindaugas Tamošiūnas, Edgars Kviesis-Kipge, Kirishanth Manivannan, Roberts Kadiķis Published: 2026-09-19 Categories: cs.CV, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2609.23017v1 Automated pollen analysis supports veterinary cytology, but brightfield microscopy is costlier and more complex than lens-less digital in-line holographic microscopy. We evaluate whether reconstructed holograms can narrow this gap and whether model explanations remain reliable under modality change. Six pollen species were imaged by brightfield and holographic microscopy. Raw, single back-propagation and iterative phase retrieval holograms were evaluated with YOLOv26s detection and MobileNetV4 classification after anchor-based annotation transfer. Six attribution methods were assessed for spatial grounding and faithfulness with the Attribution Health Inspection and Repair (AHIR) protocol, which tests model brittleness under weak noise and corrects attribution-map granularity when needed. Brightfield achieved 0.6890 mAP50-95 (0.8865 mAP50) for detection and 0.9687 macro-F1 (0.9705 accuracy) for classification. Reconstructed holograms narrowed the gap with a task-dependent split: p-type was strongest for detection at 0.5324 mAP50-95 (0.8229 mAP50), while r-type was strongest for classification at 0.7695 macro-F1 (0.7866 accuracy), both far above raw-hologram baselines. Activation-based explanations localized strongly on grains, and region-based methods retained ~60 to ~80% of faithfulness under holography. The holographic detector was highly brittle to weak perturbations, saturating deletion-based evaluation while insertion remained informative. Pixel-level gradient explanations approached random floor, yet spatial smoothing restored p-type gradient faithfulness from 0.05 to 0.51. For holographic classification, perturbation-based explanations remained faithful while gradient-based methods fell below random floor. Reconstruction improves low-cost holographic pollen analysis, while AHIR distinguishes genuine attribution failure from artifacts caused by model brittleness and map granularity. --- ### Watching Quantum Models Think: Hilbert-Space Interpretability in Quantum Transformer Blocks Authors: Diego Iacopetta, Andrea Gasparini Published: 2026-09-19 Categories: quant-ph, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.23016v1 Deep learning models are powerful but opaque. As quantum machine learning matures, the field faces a defining choice: build quantum models that are equally opaque, or exploit the mathematical structure of quantum mechanics to make them inherently interpretable. We show that the latter is possible. By tracking quantum mutual information~(MI), entanglement entropy, and state fidelity through the layers of a Quantum Transformer Block (\qtb{}), a fully-coherent variational circuit with quantum analogues of both attention and feedforward, we gain direct insight into how the model processes information: which tokens it attends to, when correlations form, and why predictions fail. On four tasks with known dependency structure we show that (i)~learned MI matrices align with ground-truth task structure (AUC$\,{=}\,0.69$ on lookup), (ii)~disabling entangling gates collapses accuracy from 100\% to 15\% while MI$\to 0$, proving entanglement is the mechanism, (iii)~accuracy and MI co-evolve during training ($ρ\,{=}\,0.92$ on lookup), and (iv)~per-sample MI predicts prediction correctness on the conditional task with ROC AUC$\,{=}\,0.84$. All results are validated on IBM Quantum hardware (ibm\_kingston, Heron~r2): the circuit's reasoning process, from product state through structured entanglement, is directly observable on a superconducting processor. These proof-of-concept results, obtained on small synthetic tasks, suggest that the physics of quantum computation can provide intrinsic interpretability signals with no direct classical counterpart, motivating study of whether this advantage persists at scale. --- ### CrowdCue: Specialist-Cue Conditioning for Vision-Language Crowd Counting Authors: Moshiur Farazi, Bekir Ciftler, Abdulhalim Dandoush, Reda Bendraou Published: 2026-09-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23012v1 Generative vision-language models (VLMs) offer a counting paradigm in which one model produces both a count and a natural-language account of the scene, yet their raw counting accuracy sits in the range of sub-million-parameter specialist regressors. The open question is whether auxiliary guidance from a pretrained specialist can lift them into useful territory, and through which channel that guidance is best routed. We evaluate Qwen2.5-VL-7B on four widely used crowd counting benchmarks (ShanghaiTech A and B, UCF-QNRF, NWPU-Crowd). Zero-shot prompting rarely produces a parseable count, so LoRA supervised fine-tuning establishes the baseline at overall MAE 81.64. Conditioning on a P2PNet-derived density heatmap as an auxiliary visual signal fails in every encoding we tested, and an adversarial-swap protocol shows the model reads the heatmap but applies it counterproductively. We propose CrowdCue, a family that supplies the same specialist's already-integrated integer count to the VLM as a discrete symbol. The text-channel variant reaches MAE 72.04. The visual-channel variant, which renders the integer as printed digits and supplies it as a second image, reaches MAE 62.65, the strongest result in this paper and well ahead of the cue-supplying specialist alone (84.45 on the same split). In the late-fusion VLM we study, the binding constraint is not the channel but the abstraction level at which the specialist signal is delivered. --- ### MixiMotion: One-Step Text-to-Motion Generation via Asymmetric Set Distillation Authors: Hung Dinh, Binh Mai, Tran Quoc Bao Le, Lam Nguyen, Cong Tran Published: 2026-09-19 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2609.23010v1 Iterative text-to-motion generation delivers high-quality and semantically aligned motions but requires multiple network evaluations, resulting in substantial inference latency. We present \textbf{MixiMotion}, a strict one-step text-to-motion generation framework based on offline set distillation. Instead of distilling a single teacher trajectory for each text prompt, MixiMotion constructs an offline bank of multiple teacher motions and aligns teacher and student sample sets through \textbf{asymmetric bidirectional matching}. The teacher-to-student direction promotes coverage of diverse teacher-supported motions, while the student-to-teacher direction suppresses unsupported generations. We further introduce differentiable decoded-space kinematic supervision to complement normalized representation matching with constraints in the decoded motion space. At inference, MixiMotion generates a complete motion sequence with a single network evaluation, without teacher queries, iterative sampling, or candidate ranking. On ViMoGen, MixiMotion achieves a semantic alignment score of $0.835$, outperforming the evaluated one-step baselines and approaching the $0.858$ score of its 50-step HY-Motion-1.0-Lite teacher. In blinded human evaluation, MixiMotion obtains an overall rating of $4.33$, compared with $4.50$ for the teacher, while outperforming the evaluated one-/few-step baselines. Meanwhile, generation latency is reduced from $829.58$\,ms to $9.30$\,ms, corresponding to an $89.2\times$ speedup. These results demonstrate an effective quality--efficiency trade-off for strict one-step text-to-motion generation. --- ### Interpretable Multi-Hypersphere Deep Anomaly Detection for Open-set Supervised Anomaly Detection Authors: Zhiji Yang, Fangyong Wang, Yue Li, Xianli Pan, Jianhua Zhao Published: 2026-09-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.23008v1 Multi-class open-set anomaly detection requires a model to characterize the normal acceptance domain formed by multiple heterogeneous subdistributions using only class-labeled samples from known normal classes, and to identify previously unseen anomalies at test time. Existing single-hypersphere methods cannot explicitly represent class-specific locations and acceptance ranges, while current multi-hypersphere or multi-class approaches do not fully integrate inter-class boundary constraints, learnable acceptance ranges, and interpretable decisions. To address these limitations, we propose Interpretable Multi-Hypersphere Deep Anomaly Detection (IMHD-AD). IMHD-AD constructs an independent hypersphere for each known normal class in a shared feature space. With target-inside and non-target-outside constraints, IMHD-AD embeds the class-specific hypersphere centers and radii directly into the final network layer and jointly optimizes them with the shared representation. The minimum signed boundary score across hyperspheres simultaneously determines open-set acceptance or rejection and provides a faithful geometric explanation of each decision. On MNIST, Fashion-MNIST, and CIFAR-10, IMHD-AD achieves the highest AUC in 28 of 30 open-set comparisons. A two-dimensional synthetic study further shows that model architecture must balance the compactness of known normal classes against the separability of unknown anomalies. --- ### Compressing 3D Gaussian Splatting via Cross-Representation Priors Authors: Yezheng Zhang, Huanxiong Liang, Chuqin Zhou, Guo Lu, Wenjun Zhang Published: 2026-09-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.23005v1 3D Gaussian Splatting (3DGS) enables high-quality novel view synthesis but incurs high storage and transmission costs due to dense Gaussian primitives. Recent anchor-based compression reduces per-primitive redundancy, yet redundancy across anchors remains largely unexploited. We propose CRP-GS (Cross-Representation Priors for Gaussian Splatting), a rate-distortion optimized compression framework that leverages cross-representation priors to improve anchor-level entropy modeling. First, a Correspondence-Oriented Hierarchical Structure (COHS) organizes anchors by feature correspondence rather than spatial proximity, constructing root-leaf dependencies so that selected anchors can act as informative priors to conditionally encode others, yielding more accurate likelihood prediction and lower conditional entropy. Second, Shared Feature Aggregation (SFA) extracts globally shared features from a contextual hash grid and injects them into anchor representations, factoring out scene-consistent low-frequency information that would otherwise be redundantly embedded in individual anchors. Both modules are trained under a unified rate-distortion objective to balance bitrate reduction and rendering fidelity. Experiments across multiple benchmarks show that CRP-GS achieves a favorable overall rate-distortion trade-off, yielding around 30% average bitrate reduction compared to anchor-based baselines while maintaining comparable rendering quality. --- ### M3GA-Wild: A Large-Scale Dataset and Benchmark for Multi-Modal Multi-session Ground-to-Aerial Place Recognition in Forests Authors: Ethan Griffiths, Maryam Haghighat, Simon Denman, Clinton Fookes, Milad Ramezani Published: 2026-09-19 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.23003v1 We present M3GA-Wild, the first benchmark for multi-modal, multi-session ground-to-aerial place recognition in forests. M3GA-Wild unifies and extends existing forest localisation datasets, providing a holistic benchmark with synchronised RGB imagery and LiDAR from ground traversals spanning 36 km, aligned high-resolution aerial imagery and multi-altitude LiDAR covering 370 hectares, and accurate geo-referenced 6-DoF poses for precise evaluation. M3GA-Wild captures diverse forest scenes with varying viewpoints, occlusion, and environmental conditions, enabling systematic evaluation of visual, LiDAR, cross-modal, and multi-modal methods. Baseline experiments show that LiDAR-based approaches significantly outperform vision-only methods under severe viewpoint differences, while current multi-modal fusion strategies yield limited gains due to poor cross-modal alignment. By pairing aerial RGB imagery with geo-referenced aerial LiDAR, M3GA-Wild also enables evaluation of foundation models for monocular depth estimation as a cheap source of 3D geometry from forest imagery, with initial experiments revealing shortfalls of current methods. These results highlight key challenges in cross-platform localisation, including modality misalignment and severe domain gaps. M3GA-Wild establishes a new benchmark to support research in robust multi-modal localisation and long-term autonomy in unstructured natural environments. The dataset and code will be available upon acceptance. --- ### Silent Failures Beyond the 32-Bit Index Range: A Differential Characterization of Large-Tensor Matrix Multiplication in PyTorch's MPS Backend Authors: Junichiro Niimi Published: 2026-09-19 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.22991v2 Apple Silicon machines with large unified memory make it possible to hold large tensors on a desktop GPU. However, we found that PyTorch's Metal Performance Shaders (MPS) backend silently returns wrong results for batched matrix multiplication with more than $2^{32}$ elements. torch bmm, including its wrappers matmul and eager attention, returns relative errors above 1 without an exception or a warning in every PyTorch release tested (2.4.1 to 2.14.0). We sweep bmm over dtypes, memory layouts, shapes and batch sizes around $2^{31}$ and $2^{32}$ elements, and judge every result against a float64 computation on the CPU. Three rules account for every outcome on 2.14.0. When the output exceeds $2^{32}$ elements and an operand is a transposed view, the entire output is wrong and equals a computation that ignores that operand's strides. Otherwise, a view with at least $2^{31}$ elements raises an exception, and a contiguous input above $2^{32}$ elements makes exactly the batches beyond that point wrong, equal to a computation whose index wraps at $2^{32}$. A slightly larger problem can thus turn an explicit error into a silent failure. The rules extend to the backward pass, where a correct forward pass can return silently wrong gradients. A second machine with another chip, under two macOS versions, reproduces all 6156 results, including the wrong values, and the same sweeps on an NVIDIA A100 are correct in all 2530 runs. In a public sentiment classifier, one oversized batch corrupts a third of the outputs, which collapse onto one class. All findings come from observable behavior, without access to the backend's closed-source kernels; we release the harness, raw results and a guard that stops any MPS operation touching $2^{32}$ or more elements at jniimi/mps-silent-failures (https://github.com/jniimi/mps-silent-failures). --- ### On attention heads and bilinear forms Authors: Andrew O'Desky Published: 2026-09-19 Categories: cs.LG, math.SP, stat.ML arXiv: https://arxiv.org/abs/2609.22990v1 We study the symmetric and antisymmetric parts of bilinear forms in the attention heads of trained large language models. We introduce an orthogonally invariant profile map from real bilinear forms to a three-dimensional simplex and observe that profiles of trained bilinear forms accumulate near profiles of rank-one bilinear forms. We prove that the symmetric part of a bilinear form in an attention head is the sum of a hyperbolic form and a zero form for a Zariski-dense subset of query-key matrices. --- ### Rethinking Pivot Programming Languages in Code Language Models Authors: Andor Diera, Lukas Galke Poech, Matthias Tichy Published: 2026-09-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.22988v1 Multilingual code language models transfer skills across programming languages (PLs), but whether any PL occupies a privileged pivot position remains contested: geometric analyses point to C-family languages and Go, while behavioral evidence highlights Python. We revisit this question under controls for representational anisotropy and length variation across PLs, two confounds that compromise prior cosine-based analyses. Across three code models on multilingual competitive-programming data, we study three views of cross-PL organization: pairwise PL geometry, PL-English alignment, and pivoted retrieval through candidate PL representation spaces. The results are relation-dependent. Code-code geometry reveals structured language regions but no universal center; code-English alignment favors high-level scripting languages; and pivoted retrieval favors different intermediate spaces for code-to-code and English-to-code transfer. These findings suggest that Python's special role is better understood as English-facing affinity than as universal geometric centrality. --- ### OptiSkill: A Hierarchical and Evolving SkillBank for LLM-Based Optimization Modeling Authors: Ruiqing Zhao, Rui Liu, Yuan Zuo, Huarong Zhang, Xiao Han, Junjie Wu Published: 2026-09-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.22987v1 Automated operations research (OR) modeling requires LLMs to translate natural-language decision problems into correct mathematical programs. Existing methods can improve individual formulations, but they often solve problems in isolation, retaining little reusable experience and repeating similar formulation errors. Prior memory-based approaches store examples, thoughts, or insights as references, while OR modeling requires reusable formulation skills that transfer across problem narratives and guide concrete modeling decisions. We propose OptiSkill, a skill-augmented framework that builds a hierarchical and evolving SkillBank for LLM-based OR modeling. SkillBank stores solver-verified experience as reusable skills, with Global Strategies for problem-level formulation skeletons and Step Experiences for local error-prevention rules. It is further refined through stable batch-level test-time evolution, where candidate skills are incorporated only after validation. Experiments on eight OR modeling benchmarks show that OptiSkill improves formulation accuracy across LLM backbones, outperforms strong agentic baselines, and gains further by expanding SkillBank coverage and reliability. Code and data are available at https://github.com/rachhhhing/OptiSkill --- ### LPINNs: First-Layer Gated Localization for Physics-Informed Neural Networks Authors: Lakshay Chawla, Hardik Jain Published: 2026-09-19 Categories: cs.LG, cs.CE, cs.NE arXiv: https://arxiv.org/abs/2609.22984v1 Physics-informed neural networks (PINNs) use one shared representation over the computational domain, which can become difficult to optimize on long domains and for high-order operators. We study a minimal alternative: multiply the first hidden activation of an otherwise unchanged dense PINN by input-dependent localization functions, giving first-layer units receptive fields without partitioning the domain or adding interface losses. We screen 13 families of localization functions, in up to three parameterizations each, on a nonlinear harmonic oscillator (HO), a heat equation on a long spatial interval, and a manufactured four-dimensional (4D) fourth-order problem, with ten paired seeds throughout. Three configurations give large reductions in solution error at matched budgets: (i) Fixed Gaussian localization functions on the $2π$ HO domain cut mean solution RMSE from $4.8369\times10^{-1}$ to $8.83\times10^{-3}$ at 3k epochs. (ii) The inverse-quadratic family with learnable centers and widths cuts it from $2.896\times10^{-1}$ to $3.06\times10^{-2}$ on the $8π$ heat domain at 10k epochs. (iii) Fixed bump localization functions cut it from $1.75947\times10^{1}$ to $2.260\times10^{-1}$ on the $4π$ 4D domain at 10k epochs. Every paired seed improves in these three comparisons. The screen also shows that the mechanism is not a free win: on HO only 2 of 13 families beat the baseline, and 10 of the remaining 11 are 9 to 23 times worse; on 4D four families are non-finite and five are more than three orders of magnitude worse than the baseline. The inverse-quadratic family is the only one that beats the baseline on all three equations. Overall, these results show that first-layer localization can provide measurable improvements to baseline PINNs on long-domain and high-order problems. --- ### Connectivity-Aware Exploration of Robotic Grasp Spaces Authors: Maksim A Kazanskii Published: 2026-09-19 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.22983v1 Robotic grasping is typically formulated as the problem of identifying successful actions from a space of candidate grasp poses. However, the organization of successful actions within this space has received less attention. We study the multiscale structure of viable robotic grasps in $SE(3)$ and investigate whether this structure can be exploited for more efficient exploration. Using a large-scale grasp dataset, we show that successful grasp sets exhibit heterogeneous and reproducible connectivity structure across objects. We then introduce a connectivity-aware sampling strategy that incrementally explores the currently observed grasp space by prioritizing potential bridges between components, structural frontiers, boundary extensions, and geometric novelty. In controlled reconstruction experiments, the method recovers the connectivity structure of successful grasp sets substantially more efficiently than random sampling and farthest-point sampling. We further evaluate whether connectivity acquired under hidden grasp viability can improve subsequent grasp discovery, and whether structural experience from previously explored objects can be retrieved and transferred to unseen objects. These results suggest that the spatial organization of viable actions provides information relevant to grasp-space exploration beyond the viability of individual candidate actions. More broadly, they motivate structure-aware exploration as a means of exploiting the geometry of viable action spaces in robotic manipulation. --- ### Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach Authors: Iva Vasic, Jesús Muñoz-Cádiz, Bata Vasic Published: 2026-09-19 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.22981v1 We present a dual-locking method for securing trained neural networks that combines key-driven index permutation with PIN-based watermarking based on Sparse Quantization Index Modulation (QIM). Cryptographic randomness is introduced by independently applying a uniform random permutation to each row of adaptively selected index vectors. A robust blind binary watermark is then embedded into the bias coefficients by modulating their quantized values, binding the network to a user-defined Personal Identification Number (PIN). Without the correct key, the network retains its architecture but becomes functionally impaired due to disrupted internal representations. Inverse permutation fully restores the original model accuracy, while the embedded watermark remains imperceptible and enables blind verification of key association and model authorship. To improve both locking effectiveness and recoverability, an adaptive key selection strategy redistributes high-magnitude weights to low-sensitivity positions and vice versa, increasing degradation in the locked state while preserving full recovery. Experiments on MNIST, CIFAR-10/100, and ImageNet-1K using fully connected networks, ResNet CNNs, and transformer architectures show that locking reduces accuracy below 10\%, and even below 0.5\% for CNNs, while the correct key fully restores performance. The watermark introduces no measurable accuracy degradation and reliably authenticates ownership. Analysis of embedding distributions across CNNs and transformers further indicates potential diagnostic value for identifying undertrained or suboptimally designed models. The proposed approach therefore provides simultaneous model protection, recovery, and ownership verification. --- ### Beyond Similarity: Coverage-Aware Prompt Selection for Time Series Forecasting with LLMs Authors: Daeun Ji, Minkyoung Kim, Dongkuk Kim, Yohan Lee, Beomsoo Kim, Beakcheol Jang Published: 2026-09-19 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.22977v1 Similarity-based retrieval is the dominant rule for conditioning large language models (LLMs) in in-context learning, retrieval-augmented generation, and prompt-based time series forecasting. The rule concentrates on near-duplicate candidates, an issue that has motivated diversity-aware retrieval but remains unexamined in other retrieval-conditioned pipelines. We study this issue using prompt-based time series forecasting as a test bed, where a learned prompt pool is retrieved by similarity. Dominant methods in this setting retrieve top-K entries by cosine similarity without redundancy control, producing a bias toward dominant temporal patterns while overlooking rare but informative events. We propose CASP-LLM, a coverage-aware semantic prompting framework that addresses this prompt selection bias by combining usage-tracking and saturating-gate techniques into a coverage regularizer that adds no learnable parameters. On six long-term benchmarks and the M4 short-term benchmark, CASP-LLM matches or improves on similarity-based LLM forecasters on most dataset-horizon settings, with the exceptions of Electricity, M4-Monthly, and the few-shot long-horizon setting. A controlled study locates the failure mode at the cross-batch usage level rather than per-retrieval redundancy: within-retrieval diversification such as MMR does not help, whereas regularizing anchor usage across training does. --- ### A Horizon-slicing Approach to Minimum Obstacle Displacement Planning for Robot Navigation Authors: Antony Thomas, Giulio Ferro, Fulvio Mastrogiovanni, Michela Robba, Marco Baglietto Published: 2026-09-19 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.22974v1 In this paper, we investigate the Minimum Obstacle Displacement Planning problem from a robot motion planning perspective. The problem involves determining a feasible path to a goal location by displacing movable obstacles when no collision-free path initially exists. We show that this problem is computationally challenging and, in particular, NP-hard when obstacles are modeled as polygons in the plane. Besides an exact formulation of the minimum obstacle displacement problem generalizing other problems in the literature, and the associated optimal solution, this paper proposes an approximate solution that is less intensive from a computational standpoint, and differs from the optimal solution by a fraction of the optimal cost, being able to trade-off between path length and amount of obstacle displacements. --- ### Automatic multimodal UX improvement recommendations from LLM agent user simulations Authors: Anu Chowdhury, Bin Wu, Hossein A. Rahmani, Emine Yilmaz Published: 2026-09-19 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2609.22971v1 Evaluating user experience (UX) on live websites through user testing is expensive, subjective, and difficult to scale. LLM agents offer a promising route to automating UX testing by simulating realistic user behaviour. However, existing simulation approaches typically lack multimodality and require time-consuming manual review to extract actionable insights. We formalise UX improvement recommendation from simulation data as a structured natural language generation and ranking problem, and establish an evaluation protocol using expert annotation and LLM-as-a-Judge. We present AMUSER, a multimodal framework which simulates user behaviour and automatically generates prioritised UX improvement recommendations from resulting data. We evaluate AMUSER on commercial websites and show that its recommendations substantially outperform those from text-only simulation (NDCG@3 = 0.758 versus 0.359) at an 89% lower simulation cost. Our results suggest an asymmetric role of multimodality: visual access during simulation improves recommendations through richer traces, while providing visual inputs during recommendation generation can modestly degrade quality. We also discuss practical deployment lessons from applying AMUSER to commercial websites. --- ### General Collaborative Intelligence: Architecting Cognition for Resilient Multi-Agent Ecosystems Authors: Lei Zhang, Chun Ye, Le Yang, Zhaozhong Wang, Deng-Ping Fan, Hang Dai, Binglu Wang Published: 2026-09-19 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2609.22967v1 Multi-agent unmanned systems are moving from isolated, ego-centric sensing toward collaborative intelligence, in which distributed agents exchange compact features to overcome a local observation trap that no single agent can escape: occlusions, finite sensor range, and environmental degradation. The field has matured across architectural, communication, embodied, resilience, and trust dimensions, yet existing surveys examine these dimensions in isolation and rarely expose their dependencies. This review offers a unified synthesis through two complementary lenses. The first is a five-dimensional taxonomy spanning collaboration stage, communication paradigm, fusion architecture, learning strategy, and application domain. The second is three cognitive synergy conditions, Semantic Disambiguation, Pragmatic Information Exchange, and Proactive Informational Foraging, that turn cognitive synergy into operational criteria. Across these lenses we survey collaboration architectures and topologies, neural-communication co-design that treats the channel as a differentiable pipeline component, embodied action-perception loops via multi-agent reinforcement learning, and resilience mechanisms for synchronization, uncertainty quantification, and label-efficient learning. We then map these advances onto four operational domains, V2X, unmanned aerial, industrial logistics, and smart cities, and onto the safety-privacy-utility triad. To counter benchmark saturation and evaluation fragmentation, we propose GCI-Bench, a five-pillar scoring protocol with a maturity model that makes the trade-offs of collaborative methods comparable across studies. A critical reflection on reproducibility, the sim-to-real gulf, and conditions under which collaboration degrades performance identifies open challenges and charts directions toward general collaborative intelligence under real-world uncertainty. --- ### When Agentic Trust Crosses Organizational Boundaries: Structural Externalization and a Reference Model for Trust Evidence Authors: Huafu Li, Jia Xia Published: 2026-09-19 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.22961v1 Agentic systems increasingly invoke tools, services, data, and other agents across organizational boundaries, yet a relying party cannot assess a delegated action solely from producing-domain controls and records. This paper develops Trustworthiness as a Service (TaaS) through a synthesis of trustworthy-AI governance, agent security, distributed trust management, identity, provenance, assurance, and control-plane research. The analytical unit is a cross-domain reliance proposition that names the issuer, subject and action, relying party, administrative boundary, evidence dependencies, adverse condition, and required verification or adjudication semantics. The three-condition structural-externalization diagnostic identifies propositions that depend on multiple domains, require producer-independent reliance, and must remain reviewable after revocation, failure, conflicting records, or dispute. For such propositions, the paper specifies a trust-evidence envelope: an immutable workflow manifest linked to append-only, issuer-attributed attestations for task-scoped authority, policy and execution decisions, provenance, validity, disclosure, status, challenge, and recovery. A topology-neutral logical reference model assigns these functions to explicit roles and trust domains. Three analytical scenarios and the TaaS-Eval protocol proposal define manifests, independent consumers, hard gates, adversarial evidence tests, metrics, and reproducible artifact reporting. By composing established identity, authorization, provenance, assurance, and governance mechanisms around a bounded delegated action, TaaS provides a reusable profile for cross-domain reliance. It makes evidence dependencies, independent verification, challenge, and recovery explicit, supporting interoperable governance and future evaluation without treating producer assertions as ground truth. --- ### R-GEAN: Regimen-Guided Edit Action Network for Within-Admission Medication Change Prediction Authors: Regan Mahat, Mansu Kim Published: 2026-09-19 Categories: cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2609.22959v1 The medications prescribed to a patient often change during a hospital admission as clinicians start, stop, or continue therapies. We study whether models can predict which medication classes are added or removed between 24 hours after admission and discharge. Metrics that compare the complete discharge regimen can reward models for copying medications that remain unchanged, even when they identify no actual changes. We therefore introduce a leakage-controlled benchmark that predicts net ATC3 additions and removals using only prior completed admissions and information available within the first 24 hours of the current admission. Addition candidates are classes not active at 24 hours, whereas removal candidates are classes active at that time. We also introduce R-GEAN, an asymmetric candidate-scoring network with independent addition and removal predictors. Across 240,480 admissions from 82,286 patients, R-GEAN achieves the highest predefined summary of addition, removal, changed-regimen, and action-pattern performance, termed the edit composite (0.464), compared with 0.435 for the strongest primary comparator. Reimplemented RETAIN, GAMENet, and MICRON baselines obtain 0.428, 0.420, and 0.288, respectively. R-GEAN's advantage is concentrated in correctly identifying medication classes no longer active at discharge, while rare additions and admissions with multiple medication changes remain difficult. Rankings based on micro-F1 over the reconstructed discharge regimen and the edit composite correlate weakly across the evaluated models (Spearman r = 0.20). The continuation baseline achieves the highest complete-regimen score despite predicting no additions or removals. These results show that complete-regimen and edit-level evaluation measure different aspects of medication prediction. The benchmark evaluates observed prescribing changes, not treatment appropriateness --- ### A Compact Stance-Indexed Anterior-Posterior COP Representation for Parkinson's Disease Classification from Plantar VGRF Authors: Md. Sifat, Sania Akter, Akif Islam, Md. Ekramul Hamid Published: 2026-09-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.22956v1 Parkinson's disease alters gait and bilateral coordination, but machine-learning performance also depends on how continuous gait signals are represented. This study investigates whether preserving anterior-posterior center-of-pressure (AP-COP) information at fixed locations across normalized stance provides a compact and informative representation of plantar-force gait signals. Bilateral vertical ground reaction force recordings from 165 participants in the Gait in Parkinson's Disease Database were evaluated using repeated fully nested participant-level cross-validation. We propose AP-COP10, comprising AP-COP position and bilateral asymmetry across five stance windows. AP-COP10 achieved an AUC of 0.894 and outperformed three harmonized literature-derived COP representations under the same evaluation pipeline. The complementary 25 non-AP-COP descriptors alone achieved an AUC of 0.856, while the complete 35-feature representation achieved 0.908. Removing AP-COP10 from the complete representation produced a statistically supported loss in discrimination, whereas adding the complementary descriptors to AP-COP10 yielded only a small, unsupported improvement. Feature competition indicated that the most informative stance-indexed descriptors were concentrated in early and early-mid stance, while source-study holdout and sensor-perturbation analyses supported the robustness of the representation. These findings indicate that stance-indexed AP-COP retains discriminative information that is not readily recovered by broader engineered gait descriptors, supporting compact and interpretable representations for machine-learning analysis of pathological gait. --- ### AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows Authors: Rudrendu Kumar Paul, Sourav Nandy Published: 2026-09-19 Categories: cs.AI, cs.CL, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2609.22951v1 Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their inference budget on subtasks that smaller models handle equally well. Existing routing solutions optimize single-turn query assignment but ignore a property unique to agentic workflows: subtask complexity varies widely within a single trajectory. A planning step may require frontier-class reasoning while a subsequent formatting step needs only a 7B model. We formalize step-level model routing as a sequential assignment problem over agent trajectories and propose AgentRouter, a lightweight classifier (12M parameters, <5ms overhead per step on an A100 GPU) that maps each trajectory step to one of four model tiers using five features extractable at routing time. Trained on 50,000 annotated agent trajectory steps spanning planning, coding, research, and data analysis tasks, AgentRouter achieves 72% cost reduction relative to frontier-only baselines, retaining 97.3% of frontier-only quality (less than 3% degradation in end-to-end task completion); per-step routing accuracy reaches 91% on minimal-complexity steps and 85% on efficient-tier steps, with 76-82% on the harder mid-range and frontier tiers. On the same benchmarks, RouteLLM and FrugalGPT (applied per-step) achieve only 31% and 44% cost reduction respectively, because their single-turn training signal misses trajectory-level quality dependencies. --- ### CLEAR: Complex Learned Explicit Analytical Regularization for Ultra-Accelerated 4D Flow CMR Reconstruction Authors: German Shâma Wache, Sebastian Neumayer Published: 2026-09-19 Categories: cs.CV, cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.22950v1 While compressed-sensing regularizers enable interpretable reconstruction of 4D Flow CMR through transparent variational objectives, their hand-crafted nature is too restrictive under high acceleration. State-of-the-art learning-based approaches mitigate this, but typically encode regularization implicitly through unrolled network modules, which limits their interpretability. To address this limitation, we propose CLEAR, designed to combine the interpretability of compressed sensing with the flexibility of learned models. To the best of our knowledge, it is the first learned regularizer for a 4D reconstruction task. In the ultra-accelerated \(10\times\)--\(50\times\) regime of the CMRx4DFlow2026 challenge, CLEAR outperforms compressed sensing locally low-rank (LLR) and the popular variational network FlowVN, while using less than 10k parameters and preserving an interpretable regularization structure. --- ### Beyond Single-Model Injection: A Threat Model and Defense Architecture for Prompt Injection in Multi-Agent Systems Authors: Rudrendu Kumar Paul, Sourav Nandy Published: 2026-09-19 Categories: cs.CR, cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2609.22949v1 Existing prompt injection research focuses on single-model chatbot scenarios, where an attacker manipulates one LLM through crafted input. Multi-agent systems amplify this threat through three mechanisms absent from single-model settings: inter-agent message passing creates injection channels invisible to perimeter defenses, shared tool access enables privilege escalation across agent boundaries, and trust propagation allows a compromised agent to influence upstream orchestrators. We construct a threat model enumerating 14 attack vectors across four categories: direct injection via user input (3 vectors), indirect injection via tool outputs (4 vectors), inter-agent injection via message passing (4 vectors), and cascading injection through orchestrator manipulation (3 vectors). Testing all 14 vectors against a 6-agent production-representative system, we find that 67% of agents are vulnerable to at least one scope violation even with system-prompt-level guardrails, and indirect injection via tool outputs succeeds in 43% of attempts. Four architectural defenses reduce overall injection success from 31.2% to 4.2%: message signing with provenance tracking (inter-agent injection down 91%), input/output sanitization at agent boundaries (indirect injection down 78%), privilege-scoped tool access per agent role (privilege escalation eliminated entirely), and anomaly detection on inter-agent communication patterns (84% of cascading attempts caught). --- ### RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling Authors: Zhenchen Tang, Yang Li, Songlin Yang, Bo Peng, Xiaotong Zhao, Shuai Li, Haotian Fan, Alan Zhao, Jing Dong Published: 2026-09-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.22947v2 Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving as the cornerstone. However, existing video reward models often produce unstable scalar scores because they directly map complex, subjective video quality into a single score without explicit evaluation criteria. This leads to scalar drift, where the scoring scale collapses or shifts across different prompts, making the reward unreliable for RL. Drawing inspiration from professional human annotation engineering, we address this problem with RewardVerse, a rubric-based video reward framework that introduces a dynamic rubric as an intermediate representation between the evaluation query and the scorer. Instead of unconstrained direct scoring, RewardVerse first generates explicit evaluation criteria and then performs rubric-guided scoring, providing a stable semantic anchor that mitigates scalar drift. To efficiently optimize this collaborative pipeline, we propose Rubric-Guided Policy Optimization (RGPO), a two-stage training algorithm. RGPO first warms up the scorer using self-evolving seed rubrics and then jointly optimizes the rubric generator to produce query-adaptive evaluation criteria while continuously aligning the scorer with human ratings. Extensive experiments on the 16-dimensional EvalVerse benchmark and external datasets demonstrate that RewardVerse mitigates scalar drift, achieves state-of-the-art performance on both pointwise and pairwise evaluation, and provides a robust and interpretable reward signal for RL in video generation. --- ### NostrAgent: A Decentralized Identity and Delegation Architecture for Sovereign Agentic Systems Authors: Oliver Aleksander Larsen, Mahyar Tourchi Moghaddam Published: 2026-09-19 Categories: cs.SE, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.22944v1 Autonomous AI agents increasingly act across organizational boundaries on behalf of human operators: they invoke third-party services, delegate subtasks to other agents, and pay for metered resources. Deploying such agents safely requires five capabilities that today live in separate systems: persistent identity, scoped delegation, peer trust, discovery, and payment. Existing approaches root these in centralized authorities or cover only subsets, so authority, trust, and payment fracture exactly where autonomy needs continuity: when a key rotates or a delegation must be revoked. We present NostrAgent, a decentralized architecture that unifies all five over Nostr relays using three custom event kinds: Kind 38100 identity declarations authenticated by BIP340 Schnorr signatures with pre-rotation commitments, Kind 38101 scoped delegation chains whose every hop verifiably narrows granted capabilities, and Kind 38102 peer attestations forming a Sybil-deterrent trust graph, with Lightning HTTP 402 (L402) binding payment to agent identity. Identity remains operator-sovereign without any registration authority; relays are substitutable transport rather than a trust root; and every authorization decision is replayable offline from signed events. We evaluate a Python prototype with a mixed-method design: ATAM quality analysis with a two-round mini-Delphi panel, STRIDE threat modeling across three trust boundaries, eleven benchmarks with non-parametric statistics, and 19 failure modes. Results show sub-millisecond offline verification, linear delegation-chain scaling, and Lightning-settled L402 at 157 ms median on regtest. 17 of 19 failure modes pass empirically, one is bounded analytically, and one is disclosed as an architectural limitation. NostrAgent demonstrates an auditable prototype substrate for trustworthy agentic systems without centralized trust roots. --- ### Token Utility Is Selection-Conditioned: Coupled Selection of Prompt Context and Response Supervision for Efficient Instruction Tuning Authors: Can Wu, Xinrui Chen, Ou Wu, Yi Du Published: 2026-09-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.22943v1 Efficient large language model (LLM) instruction tuning requires selecting response supervision with supporting prompt context. Existing methods typically value both sides separately, risking selection-state mismatch between valuation and retained training subsets. BRIDGE (Budgeted Response-Prompt Interaction via Directional Gradient-guided Efficient Token Selection) captures selection-conditioned token utility through a shared validation-directed interaction surrogate valuing each side under the other's retained state. Budgeted alternating selection coordinates retained subsets by aggregating precomputed interactions over the current opposite-side subset to update conditional scores. Structure-aware projection converts conditional response scores into coherent supervision spans. Across three model families, BRIDGE leads compared selection methods overall in mathematical reasoning, code generation, and instruction following. In mathematical reasoning, its advantage over independent selection grows with compression. --- ### An Evolutionary Agentic Approach for Open-ended Image Quality Perception Authors: Zhenchen Tang, Bo Peng, Zichuan Wang, Songlin Yang, Leilei Cao, Fengjie Zhu, Jing Dong Published: 2026-09-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.22942v1 Generative models are rapidly expanding image quality assessment (IQA) beyond traditional fidelity factors to emerging dimensions such as physical plausibility and text-rendering correctness. However, existing IQA models rely on fixed definitions and heavy supervision, making them difficult to extend to open-ended perceptual dimensions. We identify holistic bias as an important limitation: when scoring an unseen dimension, models reuse generic quality priors, leading to scoring errors and rank inversion. To address this, we propose PACE (Perceptual Agentic Collaborative Evolution), a training-free multi-agent framework that formulates open-ended IQA as explicit protocol construction. Given a target dimension, PACE uses collaborative agents to construct an evaluation protocol composed of verifiable Visual Question Answering (VQA) probes, grounding evaluation in concrete visual evidence rather than holistic impressions. The resulting protocol is calibrated using only four human-annotated images per dimension, while a dual-track scoring mechanism aligns model perception with human scoring scales. Across traditional IQA, structural fidelity, context-aware aesthetics, and newly defined open-ended dimensions, PACE consistently improves its MLLM backbone, achieving competitive performance across diverse IQA settings, and reduces the Holistic Override Rate (HOR) from 44.4\% to 8.6\%. --- ### D3GS: Depth, DINO, and RGB Diffusion Co-Guided 3D Gaussian Splatting for Sparse-View Reconstruction Authors: Yunqi Gao, Zhanfeng Liao, Hanzhang Tu, Zhaoqi Su, Guoqing Zheng, Songtao Wang, Hongwen Zhang, Zhou Xue, Leyuan Liu, Yebin Liu Published: 2026-09-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.22941v1 Novel view synthesis from sparse inputs remains challenging for 3D Gaussian Splatting (3DGS) due to ambiguous geometry, cross-view inconsistency, and missing details in under-constrained regions, resulting in degraded reconstruction and unstable rendering. To tackle these issues, we propose D$^{3}$GS, a Depth-DINO-Diffusion guided sparse-view Gaussian reconstruction framework that jointly enhances geometry and appearance. D$^{3}$GS first recovers a high-resolution, metric depth map via diffusion-based completion and DPT (Dense Prediction Transformer) refinement, providing robust Gaussian initialization and geometric constraints. Then, a DINO-guided view-consistent learning is introduced to augment Gaussian attributes with structural features, improving multi-view consistency. Finally, a diffusion-based Gaussian refinement module injects generative priors into an iterative optimization strategy, enhancing high-frequency geometric and appearance details within the Gaussian representation. Experiments on DTU, LLFF, and Mip-NeRF 360 show that D$^{3}$GS achieves consistent and substantial improvements over strong baselines, with ablation studies validating the effectiveness and complementary roles of each component. ---