# Research Papers — 2026-07 · bundle page 114 of 222 > Full-text markdown of papers #5651–5700 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/114 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/113.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/115.md) ### Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models Authors: Jungseob Lee, Seungyoon Lee, Suhyune Son, Dongyub Jude Lee, Sungbin Han, Sugyeong Eo, Heuiseok Lim Published: 2026-07-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.14552v1 A standard recipe for distilling the reasoning ability of large language models (LLMs) is to sample chains of thought from the model, keep those that reach the correct final answer, and fine-tune on the survivors. When sampling fails, a common fix shows the generator the gold answer and asks it to write a chain that reaches that answer. We show that this second step degrades the training data in a way that correctness filtering cannot catch. We run a controlled experiment that fixes the generator, the problem set, and the correctness filter, and varies only whether the chain is generated under answer-conditioning, the gold answer shown with a request to reach it. Training a strong instruction-tuned reasoning model on its own answer-conditioned chains sharply lowers its verifiable-reasoning accuracy. The loss grows with difficulty, reaching as much as about 27 points on the hardest competition problems. The mechanism is legible in the chains themselves, which rationalize backward from the shown answer instead of deriving it, with the early final-answer statement as the measurable symptom. The harm is a property of the data rather than the generator, read off unlabeled generations before any fine-tuning, ordering the penalty across eight thinking models from four families, and transferring across teacher families. A prompt ablation localizes it to the rationalize-toward instruction rather than the answer's bare visibility. The practical takeaway is to generate answer-blind, because no correctness filter can see this damage in the data. --- ### HyMobileAgent: Data-Environment Co-Scaling for Efficient GUI Agents Authors: Hy Vision Team, Huawen Shen, Zhengyang Tang, Shangpin Peng, Liang Wu, Anran Zhang, Weinong Wang, Yiduo Guo, Chenxin Li, Zhengyao Fang, Yang Ding, Junyi Li et al. Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.14548v1 As large multimodal models move from understanding content to operating on digital environments, mobile GUI has emerged as a challenging and consequential testbed for digital embodied intelligence. Mobile agents operate under three coupled constraints: precise perception of complex interfaces, scalable acquisition of high-quality interaction data, and robust long-horizon decision making under compounding execution errors. This report presents HyMobileAgent, a mobile GUI agent built on Hy3.0-VL-A3B, a vision-native foundation model featuring native any-resolution input, an A3B-scale deployment budget, and a 32K context window to model extended interaction histories. Rather than relying solely on model scaling, we develop a joint data and environment centric scaling framework to address the key bottlenecks of mobile interaction. Our framework integrates a GUI perception flywheel combining mock-interface synthesis, rejection sampling, and icon-specific augmentation; a knowledge pipeline that transforms tutorial videos into structured interaction data; a million-scale action data pipeline deployed across more than 2000 sandbox and real-device instances with automated failure attribution; the PhoneWorld Mock App Factory, providing a resettable training environment with 34 mock applications and over 34000 tasks; and a structured Planning-and-Reflection mechanism with explicit dead-loop detection for reliable long-horizon execution. We also introduce a progressive training recipe consisting of mid-training, supervised fine-tuning, and reinforcement learning with task-specific reward designs. --- ### AdaTurn: Budget-Aware Test-Time Scaling for Active Visual Perception Agents Authors: Susan Liang, Chao Huang, Filippos Bellos, Jing Bi, Jason J Corso, Chenliang Xu Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.14547v1 Active visual agents solve fine-grained image tasks by interleaving reasoning with image-grounding actions across multiple turns. However, deployment-time rollout budgets are rarely fixed: some requests permit long rollouts, while others require the agent to act under a tight turn limit. Existing methods train the policy as if the rollout budget were hidden, so when the available budget is smaller than the trajectory the agent prefers, the interaction is often truncated before any valid answer is produced; we term this failure \emph{catastrophic truncation}. To overcome this challenge, we present AdaTurn, a budget-aware framework that conditions the agent on the allowed number of turns and explicitly trains the boundary behavior induced by the budget. Our key component, Forced-Answer DAPO (FA-DAPO), converts the over-budget event from a masked or penalized failure into a trainable final-decision step, teaching the model to synthesize partial evidence when further tool use is no longer possible. We further randomize rollout budgets during both training and inference and introduce a load-balanced scheduler that makes such operations practical. AdaTurn substantially improves low-budget accuracy, for example raising VisualProbe-Medium from 36.7% to 47.6% at four turns, while preserving strong scaling at larger budgets and transferring effectively to multiple backbones and general multimodal benchmarks. --- ### CASP: Learning-Augmented Offline Approximation with Verifiable Certificates and Bounded-Loss PAC Guarantees Authors: Haifeng Li, Mo Hai Published: 2026-07-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.14545v1 Machine-learned predictions can speed up offline NP-hard optimization, but asking a predictor what to do amounts to asking it to solve the problem, and committing an unchecked prediction forfeits every worst-case guarantee. CASP (Certificate-Augmented Solution Pruning) instead asks which parts of the search space may be ignored, and accepts each answer only after a sound polynomial-time verifier has checked it, so correctness never depends on prediction quality. We develop the learning theory of this design. The verifier makes the induced loss class uniformly bounded, so certificate parameters are learnable from $\tilde O(\varepsilon^{-2}\log K)$ samples ($K$ the maximum instance size), whereas the unverified commitment class admits no distribution-free rate and, under cost spread $R$, none below $Ω(R/\varepsilon^2)$. Filtering noisy predictions by verifiable confidence dominates the standard min-combiner, with a margin we compute in closed form, and the prediction stays useful even given the LP, because it breaks ties on degenerate optimal faces, where every symmetric LP policy, meaning one whose commitments depend on the instance only through the verifiable confidence values, provably stalls. Experiments on five problems test the theory's quantitative predictions. With trained predictors, unverified pruning loses up to $26%$ of the optimum under distribution shift, while the verified deployment of the same predictions loses nothing. --- ### 3D Geometric Tooth Alignment Planning via Deep Reinforcement Learning Authors: Yong Li, Jianwen Lou, Jiayue Ma, Yao-Xiang Ding, Youyi Zheng, Haihua Zhu Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.14544v1 3D geometric tooth alignment planning, which determines sequential trajectories from initial malocclusion to the final target alignment, is a cornerstone of modern digital orthodontics. This paper presents a novel deep reinforcement learning (DRL) framework to automate the generation of these alignment paths. We formulate the planning process as a Markov Decision Process (MDP) to capture its sequential decision-making nature, focusing on optimizing geometric trajectories while integrating essential spatial constraints, such as inter-dental collision avoidance and path efficiency. The proposed method leverages the Deep Deterministic Policy Gradient (DDPG) algorithm, enhanced by three key innovations: (1) a Transformer-based agent to model complex spatial interactions between teeth and manage high-dimensional state-action spaces; (2) a dynamic masking scheme that restricts movement to a sparse subset of teeth per step, better reflecting the clinical logic of sequential alignment; and (3) a two-stage curriculum learning strategy that gradually increases task difficulty to ensure training stability and efficient path discovery. We evaluate our approach on a dataset of 10K expert-designed treatment plans based on clinical data. Experimental results demonstrate that our method outperforms existing baselines in terms of path safety and geometric efficiency, providing a robust and automated solution for 3D geometric orthodontic alignment planning. --- ### SafeRelBench: A Spatial-Relation-Aware Benchmark for Process-Level Safety in VLM-Driven Embodied Agents Authors: Huaigang Yang, Ya Li, Min Ren, Bo Dai, Zhenliang Zhang, Zhaofeng He Published: 2026-07-16 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.14543v1 Vision-language models (VLMs) are increasingly used as the reasoning backbone of embodied agents, enabling robots to interpret visual scenes, follow language instructions, and plan multi-step actions. In household environments, however, safety depends not only on recognizing objects, but also on how actions change the physical scene over time. Existing embodied safety evaluations largely focus on static risk recognition, unsafe instruction refusal, or final-state task completion. As a result, process-level safety failures induced by spatial relations such as support, containment, and proximity remain insufficiently studied. To address this gap, we introduce SAFERELBENCH, a spatial-relation-aware safety benchmark with 507 executable evaluation samples, including 248 spatial-relation samples and 259 non-spatial control samples. Using SAFERELBENCH to evaluate seven open- and closed-source VLM-driven embodied agents, we find a substantial gap between task success and process-level safety compliance: models often complete the requested task while violating process-level safety constraints. Unlike prior benchmarks, SAFERELBENCH explicitly tests whether agents satisfy safety conditions before risk-prone actions, making spatial relations a core dimension in embodied safety assessment. More broadly, our results show that safe embodied intelligence requires not only stronger perception and planning, but also reliable reasoning about how object relations shape risk during interaction. --- ### CityLLM: A framework for natural-language querying of semantic 3D city models Authors: Rabindra Lamsal, Sisi Zlatanova, Johnson Xuesong Shen Published: 2026-07-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.14542v1 Semantic 3D city models provide rich geometric and semantic information, but remain challenging for non-experts and interdisciplinary researchers to access and query due to their complex structures and specialized data formats. To address this issue, we present CityLLM, a framework for natural-language querying of semantic 3D city models alongside complementary urban datasets. The framework combines spatial and graph databases within an LLM-based workflow that supports iterative query refinement and cross-database chaining. We evaluate CityLLM on a CityJSON dataset of Rotterdam (853 LoD2 buildings) using GPT-OSS, Gemini 3.1, and GPT-5.4, along with selected variants, across multiple metrics: answer correctness, visualization correctness, query success, and retry attempts. A total of 54 natural-language queries are curated across four scenarios: spatial, graph, cross-database, and conversational. Results show strong overall performance, with answer correctness ranging from 85.2% to 100%, visualization correctness from 92.9% to 100%, a 100% query success rate, and fewer than three retries across all 54 queries. Overall, the findings suggest that CityLLM provides a lightweight and extensible approach for conversational access to semantic 3D city data. --- ### Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent Authors: Lingyun Yang, Yuxiao Wang, Shenghao Liang, Linfeng Yang, Daocheng Ying, Chunbo You, Rui Zhang, Luping Wang, Yinghao Yu, Guodong Yang, Liping Zhang Published: 2026-07-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.14541v1 Existing GPU kernel generation benchmarks draw problems from synthetic or curated sources that diverge from deployed workloads. We present Atrex-Bench, a benchmark whose 30 operators and 440 shapes are sampled directly from full-cluster production inference traces of compute-limited, memory-rich GPUs. Each problem carries an importance weight derived from its share of observed GPU time, weighted by application card-hours and computed separately for the serving phases in which it runs, together with a per-problem roofline ceiling, so the aggregate score emphasizes the kernels that consume the most serving time. Evaluating six frontier coding agents on Atrex-Bench shows that even the best vanilla model reaches only ${\sim}10\%$ of the hardware roofline on production operators; and correctness alone overstates capability, since much of the apparent pass rate comes from PyTorch fallbacks rather than kernels the model wrote. To close this gap, we co-release Atrex-Kernel-Agent (AKA), a profile-driven kernel-optimization agent that combines iterative measure-revise search, optimization dropout for escaping stalled search contexts, and a layered GPU-optimization knowledge base (298 reference-kernel files and 244 optimization-knowledge documents, plus external upstream reference projects for API/ISA lookup). In a controlled case study, the agent converts zero-FlyDSL fallbacks into real kernels that match or exceed hand-tuned production baselines. --- ### MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music Authors: Scott H. Hawley Published: 2026-07-16 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2607.14537v1 Rich internal representations of musical structure are essential for music understanding tasks such as machine-assisted music co-writing, yet self-supervised approaches for symbolic music representation remain underexplored, particularly those that encode the hierarchical multiscale nature of musical structures. We present MIDI-RAE-JEPA, combining a pitch- and time-shift equivariance objective with LeJEPA and a Swin Transformer V2 encoder to learn such hierarchical representations of symbolic music encoded as piano roll images. The time-shift equivariance objective encourages the model to internalize temporal musical relationships. The encoder is trained purely on self-supervised objectives -- including a masked embedding predictor (MEP) -- with collapse prevented via SIGReg. A separate decoder trained on the frozen encoder embeddings achieves reconstruction F1 of 0.995, and a flow matching generative model conditioned on those embeddings produces generations that closely match the pitch register and rhythmic density of the conditioning excerpt, while mismatched conditioning yields unrelated but musically plausible output. Learned representations outperform a Haar scattering transform baseline on a downstream emotion classification task, and embedding distances increase monotonically with pitch and time shift magnitude, confirming measurable equivariance. These results suggest that equivariance-based SSL objectives, combined with sufficient fine-level encoder capacity, provide a viable path toward semantically rich, generatively useful representations of symbolic music. --- ### Muse: Representation Geometry of Muon Beyond Normalized Momentum Authors: Da Chang, Qiankun Shi, Lvgang Zhang, Di He, Yaoshuai Ma, Ganzhao Yuan, Yongxiang Liu Published: 2026-07-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.14536v1 Muon-style optimizers apply a polar map to matrix momentum, but their updates also depend on the representation of each parameter block before orthogonalization. We study this representation choice as a form of optimizer geometry and introduce {\method}, a family of Muon-style optimizers that shares the same momentum rule and Newton--Schulz backend across native, nearest-square, skinny, and vector representations. Each Frobenius-isometric representation induces a distinct polar steepest-descent geometry, in which the shorter matrix dimension determines the number of supported singular channels, the pullback scaling, and the constants in stochastic nonconvex convergence bounds. In a teacher--student model, curvature collapse and an isotropic Marchenko--Pastur spectral profile connect early-stage dissipation to the represented nuclear-to-squared-Frobenius norm ratio. Pretraining experiments on LLaMA2-130M and LLaMA2-600M, together with fixed-momentum diagnostics, show that balanced non-native representations can match the performance of the native representation, whereas reducing the shorter dimension weakens the scaling and singular-channel support, leading to behavior that increasingly resembles normalized momentum. --- ### SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection Authors: Huong Ninh, Chien Thai, Mai Xuan Trang, Vu-Minh Le, Thanh Ha Le, Long Tran Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.14534v1 Industrial anomaly detection aims to identify and localize defective regions without relying on exhaustive annotations of all possible defect types. Although recent unsupervised methods have achieved strong performance, most are primarily designed for single-class settings and often struggle in multi-class scenarios, where diverse normal patterns may lead to over-generalization and reduce the discriminative capability between normal and anomalous regions. In this paper, we propose SwinAD, a reconstruction-based framework for multi-class unsupervised anomaly detection that leverages a frozen pretrained Swin Transformer V2 encoder and a feature diversity-preserving reconstruction decoder. The hierarchical encoder provides semantically rich multi-scale features, while stage-wise bottleneck modules with dropout prevent trivial identity mapping and encourage robust reconstruction of normal patterns. To further improve localization, we introduce a feature diversity-preserving reconstruction framework that maintains complementary reconstruction hypotheses instead of relying on a single decoding branch. The discrepancies between encoder features and the two reconstructed features are then aggregated across multiple scales to produce the final anomaly map. Experiments conducted on three industrial anomaly detection benchmarks, including MVTec AD, VisA, and Real-IAD, demonstrate that SwinAD achieves competitive image-level performance and strong pixel-level localization accuracy, with particularly notable improvements in pixel-level AP and 1 on MVTec AD. These results indicate that combining hierarchical Swin features with diverse multi-scale reconstruction substantially improve pixel-level localization in multi-class unsupervised anomaly setting. --- ### xHC: Expanded Hyper-Connections Authors: Xiangdong Zhang, Xiaohan Qin, Sunan Zou, Tuo Dai, Xiaoming Shi, Huaijin Wu, Yebin Yang, Zhuo Xia, Shaofeng Zhang, Lin Yao, Yuliang Liu, Yu Cheng et al. Published: 2026-07-16 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.14530v1 Hyper-Connections (HC) expand the residual stream of Transformers into $N$ parallel streams, providing a form of memory scaling beyond model width and depth. Manifold-Constrained HC (mHC) stabilizes this formulation at scale. The large gains from $N{=}1$ to $N{=}4$ suggest residual-stream expansion as a promising scaling axis. However, existing HC-family methods typically stop at $N{=}4$. Our experiments reveal why: scaling mHC beyond this point yields diminishing performance gains and rapidly increasing training cost. We attribute this limitation to two bottlenecks: insufficient write-back information for an expanding number of streams and residual-mixing generation whose cost scales cubically with $N$. To address both bottlenecks, we propose xHC (Expanded Hyper-Connections), the first HC-family method to achieve meaningful expansion beyond $N{=}4$. xHC combines temporal feature augmentation for richer write-back with a sparse residual-stream architecture that updates only $k=4$ of the $N=16$ streams while retaining dense access to the full residual state. Across 18B and 28B MoE models, xHC delivers strong and consistent downstream improvements. On an 18B MoE model, xHC improves the average downstream score by 4.0 points over mHC, while adding only modest training FLOPs over the vanilla baseline. Scaling-law experiments show that the vanilla and mHC require $1.50\times$ and $1.19\times$ the compute of xHC, respectively, to reach the same loss. Practical large-$N$ training also requires controlling memory traffic from the expanded residual state. We therefore introduce xHC-Flash, which reduces the per-sublayer memory traffic from $73.5C$ to $40C$, comparable to the $34C$ required by mHC at $N{=}4$, while retaining the gains of full xHC. Together, xHC and xHC-Flash make large-$N$ residual-stream expansion effective and practical for LLM pre-training. --- ### Controlled Reformulation Testing for Logical Consistency in Large Language Models Authors: Alexander Gu, Alan Chen Published: 2026-07-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.14528v1 Large language models (LLMs) frequently contradict themselves when the surface form of a logically equivalent question changes. We present a benchmark of 350 question families (1,750 total questions) for Controlled Reformulation Testing (CRTBench) to evaluate logical invariance. In this benchmark, we investigate LLMs' ability to maintain consistent answers across controlled reformulations, which include contrapositive rewriting, double negation, negation flipping, and passive voice. We evaluate several frontier LLMs and observe an accuracy-consistency gap where GPT-5.4-mini achieves $98.9\%$ base accuracy but only $60.3\%$ family-level consistency, while reasoning-optimized o4-mini achieves $96.9\%$ consistency. From our experiments, we observe that failures cluster around logically nontrivial transformations such as contrapositive rewriting ($72.4\%$ for GPT-5.4-mini) and double negation ($84.6\%$), while surface-level rephrasing remains robust ($94-100\%$). Increasing reasoning effort improves GPT-5.4-mini to $85.4\%$ consistency, but leaves GPT-5.4 unchanged overall because gains on nested negation are offset by failures on quantifier families. These results show that accuracy alone is not enough for evaluating logical reasoning in LLMs. --- ### Riesz-Kernel Stein Variational Gradient Descent: Renormalized Entropy and Long-Time Particle Limits Authors: Trevor Teolis, Maarten V. de Hoop Published: 2026-07-16 Categories: math.AP, cs.LG arXiv: https://arxiv.org/abs/2607.14527v1 Stein variational gradient descent (SVGD) transports interacting particles toward a target distribution through deterministic kernelized dynamics. Singular Riesz kernels are attractive because they can provide quantitative population-level convergence, but at the finite-particle level the corresponding Stein energy has infinite self-interaction. We study periodic Riesz SVGD with self-interaction removed and prove a many-particle, long-time sampling theorem. Throughout the range in which the singular Stein energy is locally integrable, under a uniform bound on the initial relative entropy per particle, the time-averaged empirical-measure law converges weakly to the point mass \(δ_π\) at the target as the particle number and any diverging averaging horizon tend to infinity. We also show that the empirical-measure laws induced by invariant particle laws of finite relative entropy converge weakly to \(δ_π\), without a uniform entropy bound. Below the logarithmic singularity threshold, we obtain an explicit algebraic finite-particle error bound. These results extend the joint-entropy approach for smooth-kernel SVGD to singular interactions. --- ### WrAFT: a Modularized Automated Writing Evaluation System for Argumentative Essays Authors: Adnan Labib, Yixuan Huang, Jiahui Wu, John Maurice Gayed, Zheng Yuan, Qiao Wang Published: 2026-07-16 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.14524v1 This study presents WrAFT, a Writing Assessment and Feedback Tool, that delivers both accurate and reliable scores and effective comprehensive feedback to argumentative essays. WrAFT adopts a modular design by dividing automated writing evaluation (AWE) tasks into scoring, surface-level feedback, and deep-level feedback. In building the system, various Large Language Models (LLMs) have been evaluated, including LLaMA-3.3-70B-Instruct, GPT-4o, and Claude 3.7, through both direct prompting and supervised fine-tuning approaches. A proprietary dataset of 480 TOEFL Independent Writing essays with official benchmark scores was utilized. Benchmark-based evaluation shows that WrAFT achieves state-of-the-art performance in scoring, with a quadratic weighted kappa (QWK) of 0.84 and a root mean square error (RMSE) of 0.44 against official scores on a scale of 0-5. Human evaluation of system-generated feedback also reveals high approval ratings: 96.14 percent for surface-level feedback, 93.03 percent for deep-level macro feedback, and 94.69 percent for deep-level micro feedback. An interactive user interface has been developed for the system and is publicly available and free to use. --- ### A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models Authors: Zikun Zhang, Jiayuan Sheng, David D. Yao, Wenpin Tang Published: 2026-07-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.14522v2 We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC). We consider policy optimization problems and derive corresponding policy gradient methods, leading to continuous-time variants of proximal policy optimization (PPO) and group relative policy optimization (GRPO). As a primary application, we develop a continuous-time RL framework for fine-tuning score-based discrete diffusion models, which enables reward-driven optimization without requiring differentiability on the reward signals. In contrast to the existing GRPO-based approaches that only rely on terminal rewards, our formulation allows intermediate reward or advantage signals to be incorporated throughout the denoising trajectory. Importantly, when specialized to masked diffusion models (MDMs), our framework encompasses a rich class of policy parameterizations over the vocabulary simplex with analytically tractable probability ratios, providing a unified perspective on exploration and policy optimization in MDMs. For diffusion large language models (dLLMs), we further propose trajectory subsampling techniques to efficiently estimate computationally prohibitive trajectory likelihoods, reducing the computational cost of computing per-position probability ratios. We showcase the effectiveness of our methods on both low-dimensional entropy-regularized optimization problems and RL post-training of dLLMs on reasoning and coding tasks. --- ### A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models Authors: Zikun Zhang, Jiayuan Sheng, David D. Yao, Wenpin Tang Published: 2026-07-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.14522v1 We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC). We consider policy optimization problems and derive the corresponding policy gradient methods, leading to continuous-time variants of proximal policy optimization (PPO) and group relative policy optimization (GRPO). As a primary application, we develop a complete continuous-time RL framework for fine-tuning score-based discrete diffusion models. The proposed framework enables reward-driven optimization without requiring differentiability on the reward signals. In contrast to the existing GRPO-based approaches that only rely on terminal rewards, our formulation allows intermediate reward or advantage signals to be incorporated throughout the denoising trajectory. Importantly, when specialized to masked diffusion models (MDMs), our framework encompasses a rich class of policy parameterizations over the vocabulary simplex with analytically tractable probability ratios, providing a unified perspective on exploration and policy optimization in MDMs. For masked diffusion large language models (dLLMs), we further propose trajectory subsampling techniques to efficiently estimate computationally prohibitive trajectory likelihoods, reducing the computational cost of computing per-position probability ratios. We showcase the effectiveness of our methods on both low-dimensional entropy-regularized optimization problems and RL post-training of dLLMs on mathematical reasoning and coding tasks. --- ### Uni-AdaVD: Universal Concept Erasure for Visual Generation via Orthogonal Value Decomposition Authors: Qifan Zhou, Yuan Wang, Yanbin Hao, Xiang Wang, Kuien Liu, Richang Hong, Meng Wang Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.14521v1 Visual generative models inevitably absorb undesirable concepts from uncurated pretraining data, making concept erasure essential for safe deployment. Existing erasure methods, however, are often architecture-specific and struggle to remove target concepts while preserving non-target content and generative priors. We present Uni-AdaVD, a universal inference-time concept erasure framework for visual generation. Uni-AdaVD treats the value space of multimodal attention as a unified intervention space and introduces encoder-aware target representation construction to localize target semantics across heterogeneous text encoders. It further combines orthogonal value decomposition with an adaptive erasing shift to suppress target semantic directions without updating the original model weights. Extensive experiments on U-Net-, DiT-, and autoregressive image generators, as well as text-to-video models, demonstrate strong performance on single- and multi-concept erasure while preserving non-target priors. These results suggest that Uni-AdaVD provides an efficient and adaptable safety mechanism for modern visual generative models. Our code is available at https://github.com/QifanZhou/Uni-AdaVD. --- ### Moment-Resolved Readout and Reservoir Diversity in Nonequilibrium Langevin Computing Authors: JiZheng Duan, MingYang Zhao, YanWei Chen, Lei Yang Published: 2026-07-16 Categories: cond-mat.stat-mech, cs.NE arXiv: https://arxiv.org/abs/2607.14520v1 Nonlinear thermodynamic computers based on Langevin dynamics exploit thermal fluctuations as a physical substrate for computation. Recent work has shown that quartic-confined fluctuating degrees of freedom can act as thermodynamic neurons capable of nonlinear function approximation at finite observation times. Here we extend this paradigm from mean-only readout to moment-resolved readout. Instead of representing each driven reservoir solely by its first moment, we construct a response vector from the elementwise raw polynomial moments \(\mathbb{E}(\bm{x})\), \(\mathbb{E}(\bm{x}^{\odot 2})\), and \(\mathbb{E}(\bm{x}^{\odot 4})\). These observables combine displacement and central-shape contributions and are naturally aligned with the linear, quadratic, and quartic terms of the local driven dynamics. We further introduce a heterogeneous multi-reservoir architecture in which three reservoirs with distinct initialization and training histories form a joint \(2304\)-dimensional response representation. Under the fixed MNIST \(60000/10000\) reproduction protocol, feature-level fusion achieves the best observed accuracy of \(9695/10000=96.95\%\), compared with \(9682/10000=96.82\%\) for the strongest single-reservoir model and \(9684/10000=96.84\%\) for equal-weight logit averaging. An exact paired McNemar test does not establish a statistically significant improvement over the strongest single reservoir, but the ablation and wrong-set overlap results provide suggestive evidence of complementary classification errors. These results motivate higher-order polynomial-moment readout and reservoir heterogeneity as candidate design principles for finite-time Langevin computing. --- ### Adaptive Runge-Kutta Step Control Buys Training Loss, Not Generalization: An Honest Compute-Matched Study of RK-Adam Optimizers Authors: Akhilesh Gogikar Published: 2026-07-16 Categories: cs.LG, math.OC, stat.ML arXiv: https://arxiv.org/abs/2607.14516v1 Interpreting optimizers as gradient-flow discretizations has motivated applying higher-order Runge-Kutta (RK) integrators to neural networks. We build a representative Adam variant (Bogacki-Shampine 3(2) RK pair, FSAL reuse, local-error step control) and evaluate it under a strict compute-matched protocol giving every method the same gradient-evaluation budget - an accounting this literature rarely enforces. Under it the RK variant loses to plain Adam on training loss in both minibatch and full-batch (RK's best-case) training. Instrumenting it shows the "adaptivity" is illusory: normalized error stays far below tolerance, the step size pins at its growth cap from step one (98-100 percent of steps), and no rtol x hmax x h0 setting makes it act; tolerances spanning 100x give bit-identical trajectories. The method is exactly fixed-step Adam with an averaged gradient at 3-4x cost. Repairing it (true reject branch; error on the applied map) reverses the full-batch result - about 40x lower training loss than tuned Adam - and a fixed-step control isolates adaptivity (an emergent warmup-and-growth schedule) as the mechanism. But the gain is fragile to the initial step size and does not reach test accuracy. A pre-registered follow-up rules out the obvious explanations: deeper minimization does not overfit, and an explicit temperature knob only hurts - leaving a trajectory effect, the controller selecting a minimum generalizing 1.3-3.4 points below first-order descent at equal depth. An n=10 study confirms one secondary effect: gradient averaging is a genuine implicit regularizer, beating lr-matched Adam and AdamW on 10/10 seeds - yet RMSprop and NAdam match or beat it at a third the per-step cost. Higher-order adaptive integration buys deeper deterministic minimization and a small regularization effect, but nothing a cheaper, well-tuned first-order baseline does not already provide. --- ### VTM-Nav: Harnessing Cross-Episode Experience for Object-Goal Navigation with Hierarchical Visual-Topological Memory Authors: Xiaoran Xu, Yupeng Wu, Tianyu Xue, Yifan Xu, Xuanran Dong, Xiaoshan Yang, Changsheng Xu Published: 2026-07-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.14514v2 Training-free ObjectNav agents increasingly use vision-language models (VLMs), yet typically discard acquired scene knowledge after each request. We study cross-episode ObjectNav, where each request is an independently initialized, single-goal episode and only self-acquired, scene-scoped memory persists across episodes. We ask whether an agent with fixed model parameters and navigation components can reuse such experience without retraining or oracle information. We introduce \method, a training-free framework with a persistent Hierarchical Visual-Topological Memory (VTM). VTM uses a coarse room topology to index room-owned visual memories, distinguishes in-room from remote-visible evidence, and retains successful approach cues. For each request, VTM-Nav re-localizes the agent in accumulated scene structure, retrieves target-relevant records from plausible rooms, and grounds memory guidance in candidates derived from the current observation. A conservative execution guard further handles local failures. Under matched 40-step comparisons, VTM-Nav exceeds the memory-reset WMNav control by 4.6, 2.0, and 0.8 SR points on HM3D v0.1, HM3D v0.2, and MP3D, respectively, with comparable or higher SPL. On HM3D, it also exceeds WMNav harnessed by textual memory by 3.1 and 5.5 SR points. These results demonstrate effective reuse of cross-episode scene experience through hierarchical visual-topological memory. --- ### Compression of 3D Gaussian Splatting Data Using GPU-friendly Graphics Texture Coding Authors: Amir Said, Randall Rauwendaal Published: 2026-07-16 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2607.14513v1 Techniques for modeling 3D scenes from image collections, such as 3D Gaussian Splatting (3DGS), are capable of generating high-quality novel views by leveraging graphics primitives with view-dependent appearance. In 3DGS, spherical harmonic (SH) are employed to model view-dependent color, resulting in a large number of SH coefficients per primitive and large memory requirements. While compression approaches have been proposed to mitigate this problem, they do not exploit the capabilities of modern Graphics Processing Units (GPUs) for parallel decoding and rendering. In this paper, we propose a method for compressing SH color coefficients using texture compression schemes specifically designed for efficient parallel GPU decoding and supported by dedicated hardware acceleration. It is shown that those methods can compress color coefficients more effectively than 2D textures by exploiting the fact that primitives can be locally grouped and reordered according to color. Furthermore, we introduce a bit-rate control strategy that preserves random access, enabling large-scale parallelization without compromising rendering performance. Experimental results using BC1 and BC7 texture compression formats show that GPU-based decompression can be achieved with negligible or imperceptible degradation in the visual quality of rendered 3DGS scenes. --- ### RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning Authors: Yanqiao Zhu, Jingru Gan, Xiaoqi Sun, Fang Sun, Yidan Shi, Md Mofijul Islam, Chao Shang, Wenhao Gao, Connor W. Coley, Yizhou Sun, Wei Wang Published: 2026-07-16 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.14512v2 Multi-step retrosynthesis planning seeks to decompose a target molecule into commercially available building blocks through a sequence of feasible reactions. The vast combinatorial search space makes this task challenging even for expert chemists. Traditional methods combine tree search with offline-trained value networks that score candidates in isolation, without reasoning about complete multi-step routes. Recent work leverages Large Language Models (LLMs) for this task, but relies on simple interfaces that limit exploration of the full search space. We introduce RetroAgent, an LLM agent that bridges symbolic search and neural reasoning through a harness with structured memory. Through memory and chemistry tools, the agent observes the full search state, including explored routes, available alternatives, and properties of intermediates, enabling informed decisions grounded in both global progress and domain knowledge. Experiments on in-distribution and out-of-distribution benchmarks demonstrate that RetroAgent delivers strong performance and generalization. --- ### VLT: A Vision-Language-Time Series Multimodal Foundation Model for Industrial Intelligence Authors: Haiteng Wang, Jingheng Yan, Xiaokang Wang, Lei Ren Published: 2026-07-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.14510v1 Industrial time series serve as the foundation for Prognostics and Health Management (PHM) to ensure the reliability and safety of industrial equipment such as aero-engines. However, existing approaches are typically limited to single-modality modeling, which restricts their generalization in complex scenarios. Although recent advances in large language models (LLMs) provide new opportunities for multimodal learning, bridging continuous time-series signals and discrete textual semantics remains an open challenge. To this end, we propose VLT, a multimodal foundation model that jointly models time-series, frequency-spectrum visual representations, and textual knowledge. A key insight is to utilize the frequency spectrum as a visual bridge to connect continuous temporal signals with discrete semantics. Specifically, a Time-aware Mixture-of-Experts (Time-MoE) is designed to capture heterogeneous temporal dynamics, while a Frequency-Text Augmented Learner enables joint modeling of spectral and semantic features within a shared representation space. Furthermore, a time-centric gradient alignment mechanism is introduced to mitigate cross-modal optimization conflicts via gradient normalization and reliability-aware dynamic reweighting. Extensive experiments on multiple industrial datasets demonstrate that VLT outperforms state-of-the-art methods, achieving superior robustness and generalization under few-shot, noisy, and incomplete-modality settings. --- ### Multi-Scale ViT Inference with Habitat-Fit Priors and kNN Retrieval for Multi-Species Plant Identification Authors: Alper Erten, Murilo Gustineli, Adrian Cheung Published: 2026-07-16 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.14509v1 This paper describes DS@GT ARC's third-place solution to the PlantCLEF 2026 challenge on multi-species plant identification in vegetation quadrat images, where systems must predict every species present in high-resolution (~3000 x 3000 pixel) plot photographs while training only on single-label images of individual plants. The pipeline is built around a fine-tuned DINOv2 ViT-L/14 classifier applied over a multi-scale tile decomposition of each quadrat, with per-tile predictions blended with a FAISS kNN retriever and post-processed by source-aware temporal fusion across repeated plot visits, a habitat-fit demotion that injects geographic and altitude priors from the training data, and a South-Western Europe geographic mask. Habitat-fit demotion and multi-scale aggregation are the largest individual contributors in the ablations. Two complementary training-centric directions, a cross-region transformer with noisy-student distillation on the LUCAS dataset and a label-as-query transformer decoder over synthetic CLS-domain pseudo-quadrats, yielded null results. An inference-time augmentation with instance-aware segmentation crops also did not improve performance. The selected submission reaches a private-leaderboard macro-F1 of 0.43902 (third place; public 0.51096); an unselected configuration of the same pipeline scored above 0.45 on the private set. Code: https://github.com/dsgt-arc/plantclef-2026. --- ### Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards Authors: Yuxuan Zhu, Rohan Alur, Daniel Kang Published: 2026-07-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.14506v1 While reinforcement learning with verifiable rewards (RLVR) is widely used to improve the reasoning capabilities of large language models (LLMs), the generalizability of the resulting models remains poorly understood. In this work, we establish the first non-vacuous generalization bounds for parameter-efficient RLVR fine-tuning at the billion-parameter scale. Our approach adapts PAC-Bayes compression bounds to this setting, and addresses the inherent stochasticity of token generation by applying the Gumbel-max reparameterization trick. To operationalize these bounds, we propose the Progressive RLVR framework, which integrates RLVR with on-policy distillation, TinyLoRA, and model quantization. Progressive RLVR empirically retains 84-97% performance of standard LoRA fine-tuning while producing models that are 14,796x more compressible. We show that this framework yields non-vacuous generalization bounds in four domains: mathematical problem-solving, programming, general-knowledge reasoning, and Text-to-SQL. Our bounds exceed the accuracy of the base model by 9-51% and lie within 6-11% of the accuracy of the fine-tuned models. --- ### Contextualized Evaluation of Vision Language Models through Dynamic, Multi-turn Interactions Authors: Yijiang Li, Huiqi Zou, Bingyang Wang, Ziang Xiao Published: 2026-07-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.14499v1 Multi-modal Large Language Models (MLLMs) have made substantial advances on benchmarks, yet their real-world effectiveness remains uncertain. This gap stems from the fundamental misalignment between benchmarks in controlled, static settings and the dynamic, interactive, and contextualized nature of real-world applications. To bridge this gap, we propose CEDI (Contextualized Evaluations of MLLMs through Dynamic, multi-round Interactions), a framework that recasts evaluation as a three-party interaction between an evaluatee model, an automated examiner, and a grader. The examiner conducts multi-turn, semi-structured conversation guided by a graph-based representation of the task. By navigating state-space transitions, CEDI deploys diverse strategies, from clarification requests to adversarial probes, to elicit performance evidence. We apply CEDI to visual hallucinations. Empirical results across multiple models, diverse settings, datasets, and domains show that contextualized, interactive evaluations reveal not only significantly more hallucinations than conventional static evaluation but also ones that more closely resemble those arising in practical use cases. We further show that hallucinations often accumulate over long contexts, through self-reinforcing dialogue history, and models are particularly vulnerable to questions requiring premise rejection or refusal. Together, these findings highlight CEDI as a step toward realistic, systematic, and ecologically valid assessments of MLLMs' capabilities. Code is available at github.com/williamium3000/cedi. --- ### Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Authors: Chi Kit Wong, Ye Pan, Yuanhuiyi Lyu, Xu Zheng, Zidong Cao, Lutao Jiang, Zixin Zhang, Huiyu Zhou, Xuming Hu Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.14497v2 Egocentric Visual Question Answering (VQA) has attracted widespread attention as an important task for enabling Multimodal Large Language Models (MLLMs) to interact with the real world. However, existing MLLMs struggle to perform effective spatial reasoning in complex egocentric scenes due to their limited spatial perception capabilities. To this end, we introduce Ego Scene Augmentation (ESA), an egocentric spatial perception framework, which actively enhances the spatial perception capabilities from the egocentric perspective, powered by the proposed Ego-element Graph. Our core insight is leveraging the Ego-element Graph as an intermediary representation to augment the egocentric spatial perception of MLLMs via visual foundational models. Specifically, we 1) construct the Ego-element Graph, which encapsulates and integrates egocentric spatial features enabled by visual foundational models; 2) enhance the spatial perception capabilities of MLLMs via the Ego-element Graph for ego-perspective scenes. Our proposed ESA framework presents significant performance improvement on the EgoTextVQA benchmark. We achieve an 8.14% gain on the indoor setting and an 8.72% gain on the outdoor setting. Furthermore, our ESA shows the most impressive performance improvement in the shopping subset of the indoor setting. The project code is publicly available. --- ### Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Authors: Chi Kit Wong, Ye Pan, Yuanhuiyi Lyu, Xu Zheng, Zidong Cao, Lutao Jiang, Zixin Zhang, Huiyu Zhou, Xuming Hu Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.14497v1 Egocentric Visual Question Answering (VQA) has attracted widespread attention as an important task for enabling Multimodal Large Language Models (MLLMs) to interact with the real world. However, existing MLLMs struggle to perform effective spatial reasoning in complex egocentric scenes due to their limited spatial perception capabilities. To this end, we introduce Ego Scene Augmentation (ESA), an egocentric spatial perception framework, which actively enhances the spatial perception capabilities from the egocentric perspective, powered by the proposed Ego-element Graph. Our core insight is leveraging the Ego-element Graph as an intermediary representation to augment the egocentric spatial perception of MLLMs via visual foundational models. Specifically, we 1) construct the Ego-element Graph, which encapsulates and integrates egocentric spatial features enabled by visual foundational models; 2) enhance the spatial perception capabilities of MLLMs via the Ego-element Graph for ego-perspective scenes. Our proposed ESA framework presents significant performance improvement on the EgoTextVQA benchmark. We achieve an 8.14% gain on the indoor setting and an 8.72% gain on the outdoor setting. Furthermore, our ESA shows the most impressive performance improvement in the shopping subset of the indoor setting. The project code is publicly available. --- ### SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation Authors: Yiming Zhang, Koji Tsuda Published: 2026-07-16 Categories: cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2607.14494v1 Complex knowledge base question answering (KBQA) is commonly approached through either information retrieval over a question-specific subgraph or semantic parsing into an executable logical form. We study the latter paradigm. Recent large language model agents make semantic parsing interactive: they alternate between reasoning, querying the knowledge base, and extending a partial SPARQL query. This interleaving reduces reliance on one-shot generation, but makes the quality of \emph{KB grounding} depend on what the interaction tools expose. Existing agents retrieve or prune candidate properties mainly through lexical relevance and instance-level observations, without systematically conditioning on entity types, property domains and ranges, or the expected answer type. We call this failure mode \emph{type-blind grounding}. It enlarges the grounding search space and often produces plausible-looking but semantically incompatible triple patterns that execute to empty results. We propose SAGA (\underline{S}chema-\underline{A}ware \underline{G}rounding for \underline{A}gentic Text-to-SPARQL Generation), a training-free framework that turns property exploration into a schema-constrained grounding operation. SAGA maintains a persistent bidirectional type state, filters known-incompatible property candidates at construction time, presents the remaining graph patterns in a compact schema-annotated format, and handles missing schema information permissively through empirical and trace-local evidence. Across nine benchmark settings over Wikidata and Freebase, SAGA achieves the highest F1 on all nine settings and the highest exact-match accuracy on eight, while reducing empty-result queries across all reported Wikidata settings. --- ### Manufactured Divisiveness: Decomposing the Hostile Content of Seven Social Media Influence Operations Authors: Emilio Ferrara Published: 2026-07-16 Categories: cs.SI, cs.CL arXiv: https://arxiv.org/abs/2607.14491v1 State-backed influence operations are routinely measured as high-prevalence sources of ``hate'' and ``toxicity.'' We argue those rates rest on a measurement error: the detectors behind them are validated to catch a broader definition inclusive of hostility or divisiveness aimed at an out-group, and so over-attribute hate to content better described as partisan or geopolitical invective. Across 25.08M tweets from seven government-attributed campaigns in the Twitter Information Operations archive (8,275 accounts), we separate hate from the other forms of divisiveness. We first validate a two-prompt LLM-based detector, matching human labels at Cohen's $κ=0.82$, to identify the broader hostility; we then develop an auditable rule, agreeing with an expert at $κ=0.52$, to further classify this content (5,457 posts) into three sub-categories. About 50.1% are identity-based attacks on people, whereas 30.4% are partisan attacks and 19.5% invective against states and their foreign policy. Reporting all of it as hate therefore overstates hate roughly twofold; only 18.7% is both identity-based and dehumanizing or inciting. Six of seven campaigns sort into three regimes that a single ``hate'' rate flattens, namely identity hate (RU-op and IRA, both Russia-attributed), geopolitical invective (both Iran operations), and partisan divisiveness (both Venezuela operations). We call the shared product $manufactured divisiveness$. The line to separate these constructs itself remains unsettled: on the hardest cases three independent human experts agree only moderately (pairwise $κ=0.37$--$0.50$), and the best of nineteen LLM models tops out at $κ=0.601$ against the experts' majority. Our findings can help redefine the study of hate in the context of influence campaigns and broader online discourse. --- ### EdgeFaaS: A Function-based Framework for Edge Computing Authors: Neha Vadnere, Yu-Ting Wang, Yitao Chen, Sreehari Sadesh, Ming Zhao Published: 2026-07-16 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2607.14489v1 Edge computing brings unique challenges as the resources on the edge are highly diverse in capabilities and capacities, and highly distributed across many users and the physical world. Existing distributed computing frameworks cannot adequately handle this level of heterogeneity and distribution. This paper proposes EdgeFaaS, a novel function-based edge computing framework to enable edge applications to effectively utilize heterogeneous resources distributed across the Internet of Things (IoT), edge, and cloud for computing. It proposes function virtualization and storage virtualization to abstract distributed and heterogeneous physical resources and provides consistent virtual interfaces for deploying and executing functions and storing and accessing data. EdgeFaaS provides comprehensive support to diverse edge computing workflows, and at the same time allows users to flexibly adjust the configurations and explore various important tradeoffs. To demonstrate its usability, the paper also presents the implementation and evaluation of three representative workflows on EdgeFaaS for video analytics, federated learning, and audio classification, on a real testbed of 100+ geographically distributed IoT devices, edge servers, and cloud services. EdgeFaaS allows users to flexibly explore the deployment configurations of these workflows over distributed and heterogeneous resources. For example, users can easily vary the function placement of the video processing pipeline across IoT, edge, and cloud resources and study the tradeoff between computation and communication costs; users can also flexibly adjust the cluster count and size in the hierarchical federated learning system and explore the tradeoff between training accuracy and speed. --- ### Full-data accuracy with fewer labels for training and fine-tuning machine-learning force fields Authors: Sheng Bi, Yi-Ze Wang, Jun Cheng Published: 2026-07-16 Categories: physics.chem-ph, cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2607.14486v1 Machine-learning force fields (MLFFs) are reliable only near their training distribution, making efficient construction of diverse training sets a major bottleneck for both train-from-scratch and foundation fine-tuning workflows. Active learning can reduce this cost, but standard model-committee uncertainty is impractical for foundation MLFFs because each committee member requires a separate fine-tuning run. We present an active-learning workflow based on last-layer-projection regression (LLPR), a forward-pass-cheap per-configuration uncertainty estimator. Across molecular, condensed-phase, and electrolyte systems, LLPR identifies compact, high-value training sets that recover full-data accuracy using only a small fraction of electronic-structure labels. In foundation-model fine-tuning, LLPR-selected configurations reach the full-pool fine-tuning ceiling with substantially fewer labels than random selection. In iterative electrolyte fine-tuning, LLPR detects unphysical local coordination before DFT labelling, provides an absolute force-error threshold, and enables automatic termination of the learning loop. The resulting models reproduce reference density and ion-coordination structure, providing a scalable uncertainty-quantification strategy across MLFF training regimes. --- ### Step-Level Preference Learning for Generative Agents in Social Simulations Authors: Wenchang Gao, Pingyue Sheng, Lanlan Qiu, Yunfei Ma, Jian Zhao, Baicheng Chen, Kangda Wang, Yuyang Tian, Shunqiang Mao, Tianxing He Published: 2026-07-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.14485v1 Large language model (LLM)-based generative agents simulate human behavior through long-horizon decision-making processes that comprise intermediate steps such as planning, memory retrieval, reflection, and action selection. However, fine-grained human annotations of these intermediate steps remain scarce, and existing agents are not grounded in human preferences over such intermediate decisions. To address this gap, we introduce \method, an interactive simulation interface that enables us to collect step-level human preference supervision over agent decision trajectories, leading to a dataset of 57K fine-grained annotations. We conduct step-level preference learning on open-weight language models using supervised finetuning and direct preference optimization on this data, consistently improving simulation fidelity, coordination, and interaction quality, and inducing more socially effective agent behavior. Our results show that step-level human supervision is an effective training signal for improving both local decision quality and long-horizon agent behavior. --- ### Immediate 3D Gaussian Splat Reconstruction of Unordered Input with Global Consistency Authors: Andreas Meuleman, Linus Franke, Boris Zhestiankin, Camille Montemagni, George Drettakis Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.14481v1 3D Gaussian Splatting (3DGS) has become the method of choice for reconstructing and real-time rendering of captured scenes. To capture a scene with good visual quality, continuous image sequences are usually combined with out-of-order shots for better scene coverage. Structure from motion can reconstruct such captures, but only after they are all available and often with high computational cost. Incremental reconstruction methods -- often derived from SLAM solutions -- provide immediate feedback, but cannot handle the out-of-order capture we require. We provide the first immediate feedback solution for such radiance field capture that provides global consistency. We first introduce a method for fast matching in out-of-order sequences, by repurposing visual place recognition models and a covisibility graph, and provide an efficient way to find highly connected keyframes, improving quality even for ordered sequences. We show how these steps -- together with GPU optimization and careful Gaussian primitive placement -- provide fast local reconstruction, in our challenging radiance field reconstruction case. We then introduce a novel cluster-based method, again using the covisibility graph, to provide efficient loop closure that does not require sequential input. Finally, to handle large scenes in our context, we introduce a progressive hierarchy that allows our method to scale to large environments, without compromising efficiency. Our results show we provide immediate feedback 3DGS reconstruction with good visual quality in several datasets, with up to thousands of input images. --- ### Lower-Resource, Higher Scores: Language Bias in LLM Evaluators Authors: Ej Zhou, Lucas Resck, Zheng Hui, Anna Korhonen Published: 2026-07-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.14480v3 LLM evaluators (trained reward models and prompted LLM-as-a-Judge) are routinely validated via pairwise accuracy. In a multilingual setting, this operates under the premise that high pairwise accuracy implies reliable, language-neutral scoring. We show that this assumption does not hold. We conduct experiments with semantically identical instruction-response pairs across 23 languages, and find that multilingual evaluators assign significantly different scores to different evaluation languages. The bias is statistically significant and consistent across eight open-weight evaluators of different architectures and training paradigms, persists in frontier judges, and is strongly correlated with language resource level: lower-resource languages are scored more generously. Meanwhile, these biases are invisible to pairwise accuracy: evaluators achieve above 90% pairwise accuracy, yet have up to 43% difference in acceptance rate across languages under a global decision threshold, meaning, for instance, that harmful content in lower-resource languages is more likely to pass safety filters. Per-language thresholds would require language identification, which can be defeated by code-switched prompts. We then investigate why lower-resource languages receive higher rather than lower scores, and we find that model uncertainty is linked with the effect: models tend to give higher scores when less confident, both under negative log-likelihood and under token-free uncertainty measures; however, language identity remains a significant predictor after controlling for uncertainty, and the bias cannot be explained away by content difficulty alone, but is a structural, language-level misalignment. --- ### Lower-Resource, Higher Scores: Language Bias in LLM Evaluators Authors: Ej Zhou, Lucas Resck, Zheng Hui, Anna Korhonen Published: 2026-07-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.14480v2 LLM evaluators (trained reward models and prompted LLM-as-a-Judge) are routinely validated via pairwise accuracy. In a multilingual setting, this operates under the premise that high pairwise accuracy implies reliable, language-neutral scoring. We show that this assumption does not hold. We conduct experiments with semantically identical instruction-response pairs across 23 languages, and find that multilingual evaluators assign significantly different scores to different evaluation languages. The bias is statistically significant and consistent across eight open-weight evaluators of different architectures and training paradigms, persists in frontier judges, and is strongly correlated with language resource level: lower-resource languages are scored more generously. Meanwhile, these biases are invisible to pairwise accuracy: evaluators achieve above 90% pairwise accuracy, yet have up to 43% difference in acceptance rate across languages under a global decision threshold, meaning, for instance, that harmful content in lower-resource languages is more likely to pass safety filters. Per-language thresholds would require language identification, which can be defeated by code-switched prompts. We then investigate why lower-resource languages receive higher rather than lower scores, and we find that model uncertainty is linked with the effect: models tend to give higher scores when less confident, both under negative log-likelihood and under token-free uncertainty measures; however, language identity remains a significant predictor after controlling for uncertainty, and the bias cannot be explained away by content difficulty alone, but is a structural, language-level misalignment. --- ### One-Shot Generative Design for Disordered Metamaterials via Self-Organizing Neural Cellular Automata Authors: Yujie Xiang, Liwei Wang Published: 2026-07-16 Categories: cs.CE, cs.LG arXiv: https://arxiv.org/abs/2607.14475v1 Disordered metamaterials feature microstructures with inherent randomness and irregularity, enabling them to achieve broader property coverage and superior performance unavailable in their regular counterparts. Despite their promise, designing disordered microstructures is substantially harder than designing regular ones. Their design remains trapped between manual parameterizations with limited expressiveness, and generative AI that is data-hungry and struggles to generalize. To address these limitations, we propose a generative design framework based on Neural Cellular Automata that dynamically grows complex microstructures through learned local interaction rules, inspired by the self-organizing processes in natural materials. This framework requires only a single training template, yet accommodates diverse disordered microstructures and adapts to irregular domains and arbitrary discretizations. By manipulating the learned local rules, we can steer the growth process to generate microstructures unseen during training, providing control over orientation, anisotropy, and directional thickness without retraining. As a dynamic, local growth process, it naturally produces spatially varying microstructures that transition smoothly to enable location-specific mechanical properties. We demonstrate this in a multiscale mechanical cloaking design, where microstructures vary across the space to meet an optimized heterogeneous property distribution. Our design enables excellent cloaking performance without complicated post-processing and incompatible assembly common in existing methods. This data-efficient, generalizable approach opens access to previously intractable disordered materials for biomedical implants and soft robotics. --- ### Can Tokens Compete? Token Representations against Supervised CNN Backbones for BirdCLEF+ 2026 Authors: Anthony Miyaguchi, Murilo Gustineli, Adrian Cheung Published: 2026-07-16 Categories: cs.SD, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.14474v1 This paper details the DS@GT ARC team's approach to BirdCLEF+ 2026, multi-label detection of animal vocalizations in soundscapes from the Pantanal wetlands. The 2026 edition adds about an hour of labeled soundscapes, shifting the task toward supervised pipelines fit to the labeled set. First, we build a competitive supervised baseline that ensembles a frozen Perch v2 backbone, a trained HGNetV2-B0 sound-event-detection network, and a non-bird prototypical head, reaching a private leaderboard score of 0.936 at rank 1894 within a 90-minute CPU budget. Second, we ask whether token-based representations can compete, contrasting codec representations from neural audio codecs against semantic representations from foundational embeddings. We compare two bioacoustic specialist models against four token-based encoders trained on AudioSet. The repository for this work can be found at https://github.com/dsgt-arc/birdclef-2026. --- ### G$^2$SR: Geometric Methods for Fast and Memory-Efficient Gaussian-based Surface Reconstruction Authors: Dasong Gao, Vivienne Sze, Sertac Karaman Published: 2026-07-16 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2607.14470v1 Few-view surface reconstruction recovers the visible surfaces of a scene from a few posed RGB images, providing the 3D models that robots need to explore and interact online. On mobile platforms, the reconstruction must be fast and geometrically accurate while keeping a small memory footprint to ensure safe and efficient operation. 3D Gaussian Splatting (3DGS) offers a high-fidelity scene representation, but building it from a few views is ill-posed, as many distinct surfaces reproduce the same images, making traditional photometric methods prone to "floater" artifacts. End-to-end methods resolve the ambiguity by regressing splats with large, usually Transformer-based, networks that require heavy compute and memory while generalizing poorly to new scenes. We propose G2SR, which exploits a well-posed core of the task: given cross-view 2D splat correspondences, 3D splats follow analytically from multi-view geometry. G2SR employs a lightweight neural frontend to detect and track 2D Gaussian splats on the image plane and an analytic backend to triangulate each into a metric-scale 3D splat. On ScanNet, Replica, and DTU, G2SR matches or exceeds the geometric accuracy of state-of-the-art end-to-end methods while running at 69-89 reconstructions per second within 203 MB of GPU memory (5-107x less) for 2- and 3-view inputs at 384 x 512 resolution, offering a practical path to online Gaussian-based surface reconstruction. --- ### Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance Authors: Matt L. Wiemann, Peter Melchior, Andrew K. Saydjari Published: 2026-07-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.14466v1 Noise injection is a well-known technique in stochastic optimization. We report its surprising effectiveness with an interleaved (on-off-on-off...) rather than the usual monotonic decay schedule. We present a theoretical analysis of noise injection, which confirms that corruption by impulse noise approximates a Jacobian regularization, whereas Gaussian noise acts as a curvature penalty. This regularization behavior has been invoked to explain why noise injection increases model robustness. But the interleaved nature of our proposed schedule produces superior results even for the optimization objective: mixing phases of noisy data permits the optimizer to escape local minima and increase exploration without the risk of catastrophically forgetting the important features from the clean data. To stabilize this training scheme against the rapid changes of the loss when switching between clean and noisy data, we introduce a gradient-norm stabilization technique that scales noisy updates based on clean gradient magnitudes. We compare this method with other common augmentation methods and find substantial improvements in corruption tolerance and robustness to real-world distribution shifts on CIFAR-100-C, ImageNet-C, and ImageNet-R for ResNet and ViT architectures, with the best results being achieved by stacking our method on top of other augmentations. Through saliency and attention maps we show that the effect of interleaved noise injection stems from penalizing the failure modes encouraged by the inductive bias of the models: impulse noise works against the locality bias of convolutional (ResNet) architectures, and Gaussian noise reduces the tendency of attention-based models to pick up large-scale spurious features. Interleaved noise injection is therefore an effective tool to improve the test performance on clean, noisy, and out-of-distribution data at essentially zero computational cost. --- ### Depth-Dependent Hidden-State Collapse in Dynamical System Autoencoders for LiDAR Point-Cloud Classification Authors: Patricia Medina, Hy P. G. Lam Published: 2026-07-16 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2607.14463v1 We study Dynamical System Autoencoders (DSAE) for LiDAR point-cloud classification using spatial coordinates and Product Coefficient feature augmentations. The experiments compare separately trained DSAE architectures at encoder depths $K=1,\ldots,5$ and evaluate the resulting hidden representations with Random Forest, kNN, and a majority-class Dummy baseline. The main finding is a hidden-state collapse at $K=5$. For both xyz and xyz plus Product Coefficient inputs, the hidden-state standard deviation falls to the order of $10^{-5}$, while all three classifiers attain the same macro F1 score of $0.224688$. We prove that between-class hidden scatter is bounded by total hidden scatter, which in turn is controlled by the reported hidden-state variance. Thus a nearly constant hidden representation cannot retain substantial class-separating structure. Product Coefficients neither improve pre-collapse macro F1 nor prevent the $K=5$ collapse in the present DSAE setting. These results identify large-depth representation collapse as a concrete failure mode for DSAE LiDAR classification. --- ### Precise sample covariance spectral norm error -- an RDT view Authors: Mihailo Stojnic Published: 2026-07-16 Categories: math.ST, cs.IT, math.PR, stat.ML arXiv: https://arxiv.org/abs/2607.14460v1 We study the sample covariance error of centered Gaussians. A remarkable breakthrough (66) established the correct error scaling order and explicitly revealed the critical role of both the effective rank and the true covariance spectrum. In this work, we move beyond scaling characterizations and determine the precise limiting value of the error's spectral norm. To do so, we develop a generic framework based on Random Duality Theory (RDT). Within this framework, we first determine closed-form, explicit RDT-based upper bounds. We then establish complementary lower bounds by introducing a novel bilinear-quadratic RDT lower-bounding mechanism. By combining this mechanism with a two-replica systems bounding strategy, we show that our lower and upper bounds match in large-dimensional contexts. Our theoretical results are supplemented with numerical evaluations and simulations, demonstrating an excellent agreement already for problem sizes on the order of thousands. --- ### Beyond Generalist LLMs: Specialist Agentic Systems for Structured Code Workflow Execution Authors: Harris Borman, Herman Wandabwa, Fusun Yu, Sandeepa Kannangara, Justin Liu, Anna Leontjeva, Ritchie Ng Published: 2026-07-16 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.14456v1 Large Language Models (LLMs) have accelerated the adoption of software development agents, now widely available as Integrated Development Environment (IDE) extensions and standalone applications. While these agents are typically general-purpose, it remains unclear whether specialist agents justify their additional development effort. We investigate this question in the context of business process automation, focusing on the transformation of Business Process Model and Notation (BPMN) diagrams into executable agentic workflows. Since BPMN specifies explicit control-flow semantics, we focus on deterministic workflows in which a fixed process model and inputs uniquely determine the executed path. We introduce a specialist workflow for this task and compare it against generalist agents such as Roo and Cline. Our results show that the specialist solution produces agents that outperform generalist baselines by approximately 9-20 percentage points in tool-use exactness, 2-4x in penalty-adjusted latency, and 3x fewer tool-call errors, while reducing generation token cost by over 95% and eliminating repair iterations. We also find that generalist agents generate code inconsistently in both functionality and quality, limiting their suitability for industrial settings where reliability and maintainability are essential. --- ### Cotton-SF YOLO: Learning Structural and Frequency Cues for Early Cotton Square Detection in Complex Field Environments Authors: Chengjia Zhang, Yu Li, Feiri Ali, Yan Zhang, Xin Chen, Longke He, Daokun Ma, Liting Gao Published: 2026-07-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.14445v1 Cotton squares are important phenotypic indicators of the early reproductive growth of cotton, and automatic field detection of cotton squares provides an important basis for cotton growth monitoring and precision cultivation management. However, early cotton square detection in complex field environments remains insufficiently explored, as cotton squares are small, frequently occluded, easily blurred, subject to illumination variations, and exhibit low contrast against surrounding cotton leaves. To address these challenges, we propose a task-oriented framework based on YOLO26m, named Cotton-SF YOLO, for cotton square detection under natural field conditions. To improve the perception of small and irregular cotton square boundaries, we introduce Dynamic Snake Convolution into the detector, enabling adaptive extraction of deformable edge features. Furthermore, a frequency-domain feature modulation module is designed by incorporating spectral enhancement into the C2f structure, which recalibrate frequency-domain representations and strengthen discriminative edge and texture cues while reducing interference from complex cotton leaf backgrounds. Trained and evaluated on our newly constructed and annotated field dataset with manually annotated cotton squares, the proposed model achieves mAP$_{50}$, mAP$_{50:95}$, and recall values of 0.8196, 0.4942, and 0.7939, improving over the baseline YOLO26m by 1.25%, 3.45%, and 2.96%, respectively. Ablation experiments and visualization demonstrate that the best performance is achieved with the complementary effects of structural and frequency cues. --- ### Tactile: Giving Computer-Using Agents Hands and Feet Authors: Yong Liu, Zhenyi Zhong, Zhanpeng Shi Published: 2026-07-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.14443v1 Computer-use agents are becoming capable software operators, but their interface to desktop applications is still often a brittle motor layer: they look at screenshots, predict coordinates, click, and hope that the visible state changed as intended. This collapses target grounding, action execution, and outcome verification into a single ambiguous operation. We present Tactile, an open-source tool layer that gives agents a more reliable "hands and feet" for desktop use. Tactile converts heterogeneous UI evidence--operating-system accessibility semantics, OCR-grounded text, and visual fallback regions--into action-grounded interface states: compact target candidates with source labels, roles or text, state, geometry, executable affordances, and verification cues. Agents operate through an observe-ground-act-verify loop that prefers native semantic actions when available, falls back to OCR-grounded coordinates when visible text is the best evidence, and keeps full provenance for replay and failure attribution. On macOSWorld-style tasks, adding Tactile improves Codex Success@100 from 41.1% to 50.0% overall and from 45.2% to 55.3% on accessibility-adapted tasks; a 96-task cross-agent subset shows consistent gains across Codex, Claude Code, OpenCode, and Goose. These results suggest that reliable computer use requires not only stronger models, but also a reusable execution substrate that exposes software actions as semantic, verifiable, and auditable objects rather than anonymous screen coordinates. --- ### Active Real-World Factor-Based Evaluation for Generalist Robot Policies Authors: Andrew Liao, Hanchen Cui, Karthik Desingh, Aryan Deshwal Published: 2026-07-16 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2607.14439v1 Generalist robot manipulation policies trained on large, diverse datasets have shown remarkable promise across a wide range of tasks. However, rigorously evaluating these policies remains a fundamental challenge. Real-world performance depends on a large combinatorial space of task factors including object poses and camera viewpoints, making full, exhaustive evaluation intractable. Additionally, real hardware evaluation is slow and resource-intensive, so current practice is to use narrow test suites that can miss critical failure modes and misrepresent true deployment readiness. We propose an active evaluation framework that addresses this challenge by treating policy evaluation as a sequential experimental design problem. Our approach fits a probabilistic surrogate model over a structured space of task factors and adaptively selects evaluation configurations to maximize information gain over the policy's performance distribution, allowing for sample-efficient characterization of policy behavior across unseen conditions and a systematic identification of failure-prone regions. We conduct 2331 real-world evaluations across 3 tasks with 3 factor variations and find that our approach typically saves the evaluator at least 20-40% of trials compared to typical random testing. --- ### Global drivers and barriers to the public acceptance of autonomous vehicles: Evidence from 17 countries Authors: Antonios Saravanos Published: 2026-07-16 Categories: cs.ET, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2607.14436v1 This study investigated the public acceptance of Society of Automotive Engineers Level 3 conditionally automated cars, which can self-drive under certain specified conditions but require the human driver to remain ready to resume control when requested. Previous Unified Theory of Acceptance and Use of Technology 2 (UTAUT2)-based research has focused mainly on European samples, and so it is still unclear whether the same factors shape acceptance across broader world regions. This knowledge gap was addressed using the L3Pilot Global User Acceptance Survey. From an original dataset of 18,631 respondents, the final analytic sample comprised 18,603 respondents from 17 countries across Africa, Asia, Europe, North America, and South America. The data were analyzed using a UTAUT2-based structural equation model to examine how performance expectancy, effort expectancy, social influence, facilitating conditions, and hedonic motivation shape the intention to use Level 3 cars. The model showed strong explanatory power. Across the analytic sample, the intention to use Level 3 cars was driven mainly by performance expectancy, social influence, and hedonic motivation. Effort expectancy and facilitating conditions also contributed, but they played smaller direct roles. Age, gender, and previous experience with advanced driver assistance systems were statistically significant, but comparatively weak predictors. Overall, the findings suggest that the acceptance of Level 3 automated cars depends less on demographic characteristics or ease-of-use concerns and more on whether people see the technology as useful, socially supported, and enjoyable to use. --- ### Optimizing Denoising Trajectories in dLLMs: A Lightweight Evolutionary Heuristic Approach Authors: Zijian Zhao, Dian Jin, Xialiang Tong, Sen Li, Mingxuan Yuan Published: 2026-07-15 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.26052v1 Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to conventional Auto-Regressive (AR) Large Language Models (LLMs). By leveraging bidirectional attention and parallel decoding, dLLMs enable more efficient generation. However, they require a carefully designed denoising scheduler at inference time (absent during training) whose choice significantly impacts generation quality. While confidence-based heuristic schedulers have shown strong empirical performance, they suffer from two critical failure modes: EOS Overflow and Proximal Bias. Through in-depth analysis of the Transformer's attention patterns, we reveal that these failures stem from certain positions assigning disproportionately high attention weights to invalid tokens (e.g., (MASK) and (EOS)), which produce misleading confidence signals. Building on this insight, empirical evidence shows that valid attention scores can provide complementary guidance to conventional confidence-based heuristics, yet no single metric consistently excels across all scenarios, implying that the optimal denoising trajectory is highly context-dependent. To address this problem, we propose a lightweight evolutionary heuristic scheduler optimized using the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Our scheduler dynamically integrates multiple heuristic features with a contextual mean-field embedding, while requiring only 393 trainable parameters. Evaluated on LLaDA and Dream across four reasoning and planning benchmarks, our method consistently outperforms strong baselines, including conventional heuristics, block auto-regressive methods, and recent State-Of-The-Art (SOTA) approaches. To the best of our knowledge, it represents the most parameter-efficient neural scheduler to date. Our code is available at https://github.com/RS2002/Evo-Denoise . --- ### When Audit Quality Fails to Predict Downstream Utility: A Counterfactual Study of Synthetic-Data Selectors for Low-Resource African NLP Authors: Son Ha Xuan, Phat T. Tran-Truong, Xuan-Bach Le Published: 2026-07-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.18960v1 Quality-aware synthetic-data selection rests on a proxy: examples that an LLM judge rates as good should also help a downstream model learn. In a controlled replay in low-resource African-language classification, we show that this proxy breaks. Across four languages (Amharic, Hausa, Swahili, Yoruba), two classification tasks (MasakhaNEWS, AfriSenti), and five matched-budget selectors, audit rankings and downstream rankings diverge. Within each cell, the Spearman between judged label correctness and Macro-F1 across selectors has mean $ρ{=}0.04$ (median $0.00$), showing that the mismatch is not an aggregation artifact. \method{}-V2, our counterfactual audit framework, produces the cleanest selected pool on three audit channels at once: highest judged label correctness ($0.904$ vs.\ $0.767$ for naive, a $17.9\%$ relative gain), lowest shortcut score, and a hard-reject rate of $0.162$ vs.\ $0.486$ for naive. AlpaGasus nevertheless leads downstream Macro-F1 ($0.202$ vs.\ $0.163$ for \method{}-V2), and the inversion persists on the five non-degenerate cells. The lesson is methodological: in this controlled setting, audit quality is a property of the selected pool, not a guarantee of downstream utility. Synthetic-data evaluation should therefore report audit and downstream metrics on the same retained sets. We release the audit tables, per-selector retained pools, and a claim ledger that links every reported number to its source row. ---