# Research Papers — 2026-08 · bundle page 184 of 240 > Full-text markdown of papers #9151–9200 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/184 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/183.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/185.md) ### Bridging the Gap Between Hyperdimensional Computing and Kernel Methods via the Nyström Method Authors: Quanling Zhao, Anthony Hitchcock Thomas, Ari Brin, Xiaofan Yu, Tajana Rosing Published: 2026-08-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.06860v1 Hyperdimensional computing (HDC) is an approach from the cognitive science literature for solving information processing tasks using data represented as high-dimensional random vectors. The technique has a rigorous mathematical backing, and is easy to implement in energy-efficient and highly parallel hardware like FPGAs and "processing-in-memory" architectures. The effectiveness of HDC in machine learning largely depends on how raw data is mapped to high-dimensional space. In this work, we propose NysHD, a new method for constructing this mapping that is based on the Nyström method from the literature on kernel approximation. Our approach provides a simple recipe to turn any user-defined positive-semidefinite similarity function into an equivalent mapping in HDC. There is a vast literature on the design of such functions for learning problems. Our approach provides a mechanism to import them into the HDC setting, expanding the types of problems that can be tackled using HDC. Empirical evaluation against existing HDC encoding methods shows that NysHD can achieve, on average, 11% and 17% better classification accuracy on graph and string datasets respectively. --- ### RegionDet: A Benchmark for Region Detection Beyond Object Instances Authors: Liang Wan, Yuhan Wang, Yupeng Zhang, Zhen Xu, Han Wang, Fangjie Fu, Sirui Zhu Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.06850v1 Object detection is a fundamental task in computer vision and has achieved remarkable progress on standard benchmarks by localizing discrete and well-bounded object instances. However, many visual targets in real-world scenarios are not individual objects, but regions defined by visual states, scene context, object relations, and human activities, such as construction areas, damaged road regions, queues, group conversations, and vendor regions. Existing detection benchmarks are mainly built around object instances, providing limited support for systematically evaluating such region targets. To address this gap, we introduce Region Detection, a task that extends conventional object detection beyond object instances, and construct RegionDet, a benchmark for region target localization. RegionDet contains eight region categories, including Construction, Crossing, Damage, Queuing, Talking, Vendor, Waiting, and Walking, with COCO-style bounding-box annotations and evaluation protocols. We systematically evaluate representative closed-set and zero-shot/open-vocabulary detectors on RegionDet. Results show that closed-set detectors can partially learn region-level patterns under supervision, while zero-shot/open-vocabulary detectors struggle severely, revealing the strong object-centric bias of current vision-language detectors. Further analyses highlight key challenges in Region Detection, including weak boundary cues, strong context dependency, and insufficient relation-level region understanding. The RegionDet will be released. --- ### Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry Authors: Yehan Yang, Junyuan Shang, Yang Li, Guanqun Zhao, Shuohuan Wang, Dianhai Yu Published: 2026-08-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.06849v1 Long-context LLM inference is bottlenecked by quadratic attention computation and growing KV-cache costs. Existing sparse attention and KV-compression methods typically decide which tokens or heads to preserve from runtime attention scores, observation windows, calibration prompts, or learned gates, making head diagnosis input-dependent and costly to deploy. We propose Autonomy-of-Heads (AoH), a data-free method that identifies retrieval and streaming heads from the spectral geometry of query-key projections. AoH defines the kernel attention operator $M_h = W_K^{h\top}W_Q^h$ and uses its effective-rank as a weight-space measure of head function: concentrated spectra indicate a small number of dominant query-key matching directions and are associated with retrieval heads, whereas diffuse spectra indicate the absence of a dominant global matching direction and are associated with streaming heads. We further derive an efficient $d_\text{head}$-dimensional computation that avoids constructing the full $d_\text{model}\times d_\text{model}$ matrix. We conducted extensive experiments across models demonstrating that at 50\% sparsity, AoH retains 96.5\% of Full Attention performance on average while reducing prefill and decode latency by up to 41.4\% and 66.0\%, respectively, and KV-cache memory by 50.0\% at 256K tokens. --- ### Are Visual Place Recognition Models Recognizing Places or Conditions? Distractor-Augmented Evaluation and Condition Suppression Authors: Beomsu Kim, Minwoo Jung, Giseop Kim Published: 2026-08-07 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2608.06847v1 Long-term Visual Place Recognition (VPR) is typically evaluated by matching queries from one condition against a database from another. Crowdsourced map databases, however, may mix conditions and include images that resemble the query in condition but depict different places. In the presence of these distractors, a method may retrieve by condition similarity rather than place identity. We argue that this susceptibility arises because the discriminability of VPR methods allows them to encode information such as illumination, weather, and seasonal appearance in their descriptors. We therefore introduce Distractor-Augmented Recall (DAR) to isolate and quantify the effect of distractors, and propose condition suppression to remove condition information from VPR descriptors. Across eleven methods and six datasets, method rankings under DAR@1 differ from those under Recall@1 (R@1), while applying INLP and LEACE as condition suppression methods generally improves DAR@1 without reducing R@1. Thus, distractor robustness is distinct from standard retrieval performance and can be improved by suppressing condition information. --- ### Investigating Quantum-Embedded Transformers on Classical Datasets for Cross-Modality Classification Authors: Hao-Yuan Chen Published: 2026-08-07 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2608.06846v1 We test whether a parameterized quantum circuit (PQC) improves a hybrid quantum-classical model's performance on classical datasets, using an interface-matched classical map as the control while holding all other components fixed. Our architecture, Quantum-Embedded Attention (QEA), uses a learnable projector to compress backbone features into an $n_q$-dimensional angle vector, a shallow PQC to map those angles to one- and two-qubit Pauli expectations, and a classical attention decoder to produce class logits. We hypothesized the PQC would improve accuracy or seed-to-seed stability over a classical map with matched input/output dimensions. We test this with an interface-matched $2\times2$ factorial on Breast Cancer Wisconsin at $n_q\in\{4,8\}$, independently swapping the PQC for a classical map and the attention decoder for a linear head, across five paired seeds per cell. Three of four paired quantum-minus-classical $95\%$ confidence intervals include zero; the fourth, a $+1.63$ percentage-point contrast for the attention decoder at $n_q=4$, reverses sign at $n_q=8$ and does not survive correction across the four contrasts. The experiment thus shows no consistent PQC contribution and cannot establish equivalence. A five-dataset cross-modality grid shows comparable accuracy on AG~News, Breast Cancer Wisconsin, and BirdCLEF but a large deficit on CIFAR-10; these cells are not interface-matched and are interpreted descriptively. We report all planned canonical runs, distinguish current Pauli-readout results from legacy probability-readout experiments, and analyze bottleneck, simulation, finite-shot, and noise limitations. The results do not establish a quantum advantage; they demonstrate why controlled component attribution is necessary before crediting a hybrid model's performance to its quantum layer. --- ### ECAD: Expanding Class-Agnostic Detection Beyond Thing-Centric Objectness Authors: Liang Wan, Zixin Ren, Yupeng Zhang, Yuhan Wang, Fangzhuo Gao Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.06841v1 Object detection is a fundamental task in visual perception, providing structured region representations for recognition, grounding, reasoning, and interaction. However, existing detection paradigms largely inherit a thing-centric notion of objectness, where detectors are mainly trained to localize discrete and countable object instances. Consequently, many semantically meaningful visual elements, such as sky, road, grassland, water, and sports courts, are often absorbed into the background despite their importance for scene understanding and spatial reasoning. In this paper, we formulate Expanded Class-Agnostic Detection (ECAD), a new setting that aims to discover category-agnostic visual candidates beyond conventional thing-centric objects. To support this setting, we construct BTCO-Bench, a Beyond Thing-Centric Objectness benchmark with category-agnostic box annotations covering both real-world and cross-domain scenarios. We further propose ECADet, a lightweight DETR-based detector built upon a frozen DINOv3 encoder, and introduce Geometry-Aware Expert Regression (GAER) and Prototype-Guided Query Modulation (PGQM) to improve localization and objectness estimation for diverse visual elements, respectively. Extensive experiments show that ECADet consistently outperforms representative class-agnostic and proposal-based detectors on BTCO-Bench, demonstrating the effectiveness of expanded objectness discovery. Code and benchmark will be released. --- ### Mathematical Principles and Experimental Discoveries of the Emergence of Symbolic Patterns in Artificial Neural Networks Authors: Quanshi Zhang, Qihan Ren, Siyu Lou Published: 2026-08-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.06839v1 Artificial Neural networks (ANNs) are often treated as black-box models, making explainability a central challenge in deep learning. Many engineering methods have been proposed to approximately explain the ANN from various perspectives, such as feature attribution and visualization. However, it remains a long-standing open question whether the complex inference logic of an ANN can be explained exhaustively and concisely as sparse symbolic patterns. This raises a deeper inquiry: does the emergence of symbolic patterns reflect a natural law rather than chance? Here, we show that across a broad class of ANNs trained on diverse tasks, their inference logic can indeed be reformulated as sparse symbolic interactions. We further prove that two common mathematical criteria, which are implicitly required across tasks, lead to the emergence of such sparse symbolic interactions. Empirical evidence confirms that the two criteria hold for the majority of input samples in diverse models. Furthermore, the faithfulness of these interactions is also demonstrated by their strong sample-to-sample and model-to-model transferability, as well as their ability to explain the overall generalization power of ANNs. Our theoretical analysis and extensive experiments provide a solid foundation for symbolic explanations of ANNs, and offer novel insights into the ANN's generalization power. Our findings also highlight the potential of communicative learning, a paradigm in which the inference logic of an ANN can be directly inspected and tuned at the level of symbolic patterns, thus complementing traditional end-to-end learning paradigm. Finally, the observed emergence of symbolic patterns in ANNs suggests that similar symbolic representations may also emerge in other types of black-box systems under certain conditions, because our proof does not depend on any specific ANN architecture. --- ### GOPI: Generation-Oriented 3D Pose Inference for Furniture Insertion from Single-View RGB-D Indoor Scenes Authors: Ruifeng Zhai, Renjie Liu, Guangrun Wang, Liang Lin Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.06836v1 We study the problem of inserting new furniture into indoor scene images. Under masked single-view 2D image-plane conditioning, however, the physical scale of the inserted furniture relative to the scene cannot be uniquely determined, making physically grounded furniture placement underdetermined from image evidence alone. We therefore reformulate the task as a combination of 3D pose inference and geometry-guided image generation, where estimating a geometrically plausible 3D placement is essential for reliable synthesis. To this end, we propose a two-stage framework. For 3D placement, we introduce GOPI, a generation-oriented 3D pose inference framework that addresses the underdetermined nature of single-view furniture insertion through data-driven iterative inference, producing geometrically plausible object placements. For image generation, we develop a geometry-guided conditioning strategy that projects the inferred 3D pose into the image plane as a pixel-aligned constraint, enforcing consistency between the synthesized image and the underlying 3D geometry. Experimental results validate the proposed framework from both 3D pose estimation and image synthesis perspectives. For 3D placement, GOPI produces poses with stronger geometric feasibility and better consistency with reference layouts than direct regression and vanilla baselines. For image synthesis, our method preserves alignment with the projected 3D geometry across different furniture scales, showing stable projection-generation alignment across the tested furniture scales. --- ### Graph Machine: Exploring Edge Mechanisms as an Inductive Bias Authors: Lintai Hou Published: 2026-08-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.06834v2 Transformers provide a powerful architecture for global content-based matching, but reasoning problems may benefit from a stronger inductive bias toward iterative traversal of latent relations. We introduce Graph Machine, an architecture with two explicit edge-based mechanisms: Edge-augmented attention, in which edges modulate attention between nodes, and edge-centric referral, in which nodes exchange addresses to update their edges. Conceptually, this enables the model to dynamically and differentiably construct and revise relational graphs across layers. We study this inductive bias using Sudoku under controlled settings and find that Graph Machine outperforms Transformer baselines, with ablation studies and mechanistic analysis attributing the gains to the edge mechanisms. Surprisingly, we found that the model discovers a compact edge-based construction for Sudoku geometry. Our results support explicit edge mechanisms as a promising architectural design, motivating broader evaluation. --- ### Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image Restoration Authors: Zihao He, Yunfeng Wu, Xinchao Wang, Songhua Liu Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.06832v1 All-in-one image restoration seeks a single model that can recover images degraded by diverse and spatially non-uniform corruptions. However, many unified Transformers rely on fixed patch partitioning: task/degradation condition is injected only into the backbone blocks after tokenization, leaving the embedding and reconstruction stages insensitive to local degradation variations. In contrast to previous approaches, we present Flexible Image Transformer (FIT) that explicitly models degradation awareness across the entire pipeline, from patch sampling to pixel reconstruction. Specifically, FIT employs a lightweight Degradation Encoder to predict a global degradation vector $\mathbf{g}$ and a spatial degradation map $\mathbf{M}$ from local degradation severity, which jointly condition the patch embedding and unembedding through adaptive deformation. Moreover, to improve robustness across degradation types, we introduce a task-token dropout strategy that regularizes task conditioning during training. On five standard benchmarks (BSD68, Rain100L, SOTS, GoPro, and LOLv1), FIT achieves state-of-the-art performance with 30.72 dB average PSNR on the five-degradation setting and 32.83 dB on the three-degradation setting, outperforming recent unified restoration methods by +0.5$\sim$1.1 dB. Moreover, the learned offsets provide a direct handle for visualizing degradation-aware spatial adaptation. --- ### R2S-EGO: Dual-Proxy Refinement for Sparse-Capture Real-to-Sim Authors: Shuai Fang, Xin Deng, Yuchen Kang, Zhenjiang Li, Jie Chen Published: 2026-08-07 Categories: cs.RO, cs.CV, cs.GR arXiv: https://arxiv.org/abs/2608.06827v1 Real-to-sim (R2S) depends on scene representations that render observations along robot ego trajectories, yet dense multi-view capture limits per-environment real-image capture-count efficiency, and sparse human capture can leave behavior-scoped robot views under-supported. Camera-controlled synthesis can fill missing views, but its use in R2S requires behavior-admissible queries and capture-anchored structural conditioning. We present R2S-EGO, which couples a simulator-derived robot proxy that represents the behavior-scoped executable query domain with a capture-anchored geometry proxy that supplies scene-specific structural conditions. Within this domain, fixed- budget selection targets current support deficits for which geometry support is available. The generated observations are assimilated as pseudo-observations to refine the visual asset, while real captures remain anchors. The fused geometry proxy also supplies the scene collision surface, which is refreshed between rounds. Together, these updates refine the existing simulation scene while its robot dynamics and control stack stay fixed. Across 48 frozen Unitree G1 ego views in three Replica scenes, six-view R2S-EGO reaches 19.062 dB PSNR, compared with 14.226 dB for the strongest reported R2S baseline. Across five paired policy-training seeds, R2S-EGO achieves 82.5% +/- 6.8% real-G1 sitting success, compared with 10.0% +/- 10.5% for GaussGym. --- ### Multiscale Reward Hedging from Correct Demonstrations Authors: Pahan Dewasurendra Published: 2026-08-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.06825v2 Learning from correct demonstrations is harder than supervised learning when many answers are correct: after predicting, the learner sees one valid answer but not whether its own answer was valid, nor any reward. Existing reward-hedging guarantees consequently assume a finite reward class. We give the first horizon-free guarantee for continuous classes. The key is to hedge in one shared vote over tolerant optimality tests at every accuracy scale. A target reward has one surviving proxy per scale, and a prediction with gap above that scale doubles the proxy. This yields the simultaneous tail bound $|\{t:\ell_t>2^{-j}\}|\leq \log_2\mathcal N(\mathcal G,2^{-j-1})+j$, where $\mathcal G$ is the class of optimality-gap functions. Integrating the tails gives cumulative hidden gap bounded by a metric-entropy integral, independently of the number of rounds. Polynomial entropy $(A/ε)^d$ gives $O(d\log A)$ total gap and a fast $O(d/m)$ statistical rate. For bounded linear contextual recommendation, the result is $O(d)$ regret for arbitrary compact menus. This is the first polynomial finite bound without structural restrictions on the menus, at the price of improper prediction. Although the general vote can be expensive, it is exactly polynomial-time for one-dimensional Lipschitz parameter curves. Fixed-radius rank-two recommendation takes $O(KT^2)$ time for menus of size $K$. We also prove an $Ω(d)$ lower bound, low-rank and bounded ReLU-network corollaries, and a robust theorem that adds only the demonstrator's cumulative suboptimality. A reproducible adaptive stress test illustrates the predicted scale adaptation. After factorization, an exact MovieLens audit runs in 1.7 CPU seconds across ten users and improves mean latent gap over both a demonstrated-rating policy and a proper online baseline. The learner uses only action demonstrations and never observes a reward or a loss. --- ### Control-Anchored Residual Flow Matching Conditioned on Gene Geometry for Virtual Cell Perturbation Modeling Authors: Quanquan Li, Yihe Chi, Liuyang Song, Hongbo Zhang, Jingyu Li, Xidong Xi, Conghua Wei, Yijie Sun, Yu Chen, Xin Liu, Qi Hu, Jing Ke et al. Published: 2026-08-07 Categories: q-bio.MN, cs.AI arXiv: https://arxiv.org/abs/2608.06824v1 A central task in virtual cell modeling is predicting single-cell transcriptional responses to unseen genetic perturbations and drug combinations, and biological networks provide valuable priors on gene relationships. Existing graph-based models commonly use the same network to structure gene representations and mediate intergene interactions, thereby implicitly treating stable associations as perturbation-response pathways. Gene Ontology and control-derived coexpression networks encode relatively stable relationships rather than intervention-specific response directions or magnitudes. We therefore propose GeneGeoFlow, which conditions a control-anchored residual flow on gene-wise geometry derived from biological networks to learn intervention-specific transcriptional responses. GeneGeoFlow derives multi-scale spectral coordinates from Gene Ontology and control-derived coexpression networks. A perturbation-conditioned, gene-wise gating module selects relevant structural scales and network sources, yielding intervention-specific gene geometry. The resulting geometry conditions a control-anchored residual flow without explicitly propagating target-derived signals along the graph. Condition-wise optimal transport couples unpaired control and perturbed populations for training, while a Delta-correlation objective aligns the predicted and observed condition-level expression-shift directions. GeneGeoFlow achieves Pearson Delta scores of 0.8979 on the Norman additive benchmark and 0.9088 on five held-out drug combinations in the fixed ComboSciPlex test split. These results support perturbation-conditioned gene geometry as an effective structural prior for intervention-specific response prediction, without conflating stable gene relationships with response propagation. --- ### Weak Adversarial Neural Pushforward Method for Boltzmann Equation Authors: Jenia Fardousi Koly, Andrew Qing He, Wei Cai Published: 2026-08-07 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2608.06823v1 In this paper, we extend a weak adversary neural network pushforward method for solving time dependent Boltzmann equation and a weak formulation of the collision operator is proposed where an invertible neural pushforward mapping is used to generating samples given by the distribution governed by the Boltzmann equation. The training of the pushforward mapping is learnt by enforcing the weak form of the Boltzmann equation. Numerical results have demonstrated the effectiveness of the proposed method. --- ### FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding Authors: Quanquan Li, Hongbo Zhang, Yihe Chi, Jingyu Li, Xidong Xi, Liuyang Song, Hongzhen Zhang, Yuxiang Huang, Jing Ke, Siyuan Ma, Junyi Lin, Guitao Cao Published: 2026-08-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.06819v1 Token-level collaboration allows a large language model (LLM) to assist a small language model (SLM) when their predictions diverge. Existing methods either use LLM-generated intervention tokens or rank candidates with the LLM's next-token probabilities. Both rely on the LLM's local preference, even though an LLM-selected token may be difficult for the SLM to build on. We present FutureBridge, which ranks joint LLM-SLM token candidates according to how well they support the SLM's subsequent reasoning. During training, an answer-verified LLM trajectory supplies a fixed shared future, and a frozen SLM evaluates every candidate under this common context. The resulting counterfactual scores supervise a lightweight token reranker that observes only the current state and candidate token. At inference, FutureBridge uses the LLM only to expand the candidate pool, selects one token, and returns generation to the SLM without generating or appending a future suffix. Across five mathematical reasoning benchmarks, FutureBridge improves the Qwen3-1.7B SLM's Math Avg. by 35.1% relative to greedy SLM decoding. These results indicate that token selection benefits from modeling whether the receiving SLM can use each candidate to continue reasoning, rather than relying on the LLM's local preference alone. --- ### Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution Authors: Jiahao Zhang, Yifan Zhang, Yu Huang Published: 2026-08-07 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.06811v1 Resolving a real software issue with a large language model (LLM) agent is a long repair episode, often tens to hundreds of steps spanning exploration, hypothesis, implementation, and verification. Success depends on both the base model's local reasoning and the agent's ability to maintain an evolving plan and remember observations across phases. Existing repository-level agents typically strengthen planning or memory in isolation, leaving long trajectories vulnerable to stale evidence, repeated failed edits, and verification inferred from the agent's own claims instead of execution evidence. We present PMCoder, an issue-resolution agent that couples a hierarchical phase planner with episodic memory. The coupling is bidirectional: the current plan phase conditions memory retrieval, while memory-derived trajectory statistics inform stuck detection and replanning. When available, issue-reproduction verdicts ground verification progress in execution evidence rather than self-reported completion. On SWE-bench Verified, PMCoder resolves an average of $25$ more cases ($+5.0$pp) than a harness-matched baseline, with gains persisting even where the reproduction gate never fires. Further Verified-500 evaluations show the same positive direction across Claude Haiku 4.5, DeepSeek-V4-Flash, and an OpenHands port, with at least $14$ additional resolved cases ($+2.8$pp). Separately, evaluation on TerminalWorld's official sample suggests that the plan-memory substrate transfers beyond issue reports. Ablation and trajectory analyses show where the gains come from: coupling planning and memory outperforms either component alone and reduces repeated failed actions, empty-patch exits, and context-window exhaustion. --- ### Understanding Differentiable Embeddings Through Differential and Integral Geometry Authors: Xinyu Zhang, Klaus Mueller Published: 2026-08-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.06809v1 How can an analyst decide whether a nonlinear dimensionality reduction embedding can be trusted? Existing diagnostics provide only partial answers: projection glyphs characterize local sensitivity, map-continuity scores measure local conditioning, and transport-based analyses reveal path-dependent inconsistencies. However, these methods appear unrelated and provide no common framework for understanding when they agree or not. We show that they are all derived from a single geometric object induced by every differentiable embedding, whether defined implicitly through optimization or explicitly by a learned mapping. This framework provides two complementary geometric views of an embedding. The differential view explains local behavior: its first-order term recovers projection glyphs, while its second-order curvature quantifies how far their linear approximation remains reliable. The integral view follows the same geometry along high dimensional paths and determines whether an embedding depends only on the current state or also on the path taken to reach it. We further show that map-continuity is a prerequisite for the other analyses. The framework is theoretically complete for diagnostics derived from the embedding geometry, and we prove the integral view irreducible: no amount of local measurement at any number of points, to any order of derivative, reproduces what it detects. Classical rank-based metrics form a complementary class based on finite-scale neighborhood relationships. Experiments on synthetic and real datasets validate theoretical predictions, demonstrate accurate curvature-based trust estimates on single-cell embeddings, and show that the integral analysis distinguishes single-valued embeddings from path-dependent optimization-based embeddings in ways that existing pointwise diagnostics cannot. --- ### Evolving Parallel Algorithm Portfolios via Potential-Aware Instance Generation with LLMs Authors: Shaofeng Zhang, Shengcai Liu, Zhiyuan Wang, Ke Tang Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.06808v1 The Automatic Construction of Portfolios via Large Language Models (LLM-ACP) suffers from poor generalization in practical few-shot scenarios when solving complex combinatorial optimization problems. Instance and algorithm co-evolution frameworks address this by expanding the training dataset with generated hard instances on which the current algorithm portfolio underperforms, thereby enhancing generalization. However, this paradigm faces two critical limitations: evaluating instance hardness relies on high-quality reference solutions, and single-mode generation patterns limit instance diversity. To overcome these limitations, we introduce the Potential-aware Instance and Algorithm Co-evolution (PIAC) framework. Our core contribution is twofold. First, we propose potential gain, a novel metric that eliminates the need for reference solutions. This metric estimates generalization gain by perturbing the generated algorithms and assessing their improvement potential on generated problem instances. Second, PIAC leverages LLMs to synthesize diverse instance mutators, exploring a broader region of the problem-instance space and thereby enhancing the portfolio's generalization capabilities. Given that perturbation spaces vary across different algorithms, we instantiate our framework on Greedy Constructive, Ant Colony Optimization, and Guided Local Search algorithmic backbones. Comprehensive evaluations on the Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) across six distinct data distributions demonstrate that PIAC consistently outperforms state-of-the-art LLM-ACP baselines, notably achieving a 19.76% relative improvement for TSP Greedy Constructive portfolios. --- ### Simple-OPD: Demystifying Warm-up for On-policy Distillation Authors: Tao Liu, Taiqiang Wu, Mao Zheng, Xuan Luo, Runming Yang, Xuewei Yang, Junjie Wang, Yujiu Yang Published: 2026-08-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.06802v1 On-policy distillation (OPD) trains a student on its own rollouts with token-level supervision from teacher models, but its effectiveness can depend strongly on the warm-up stage before OPD. In this paper, we demystify warm-up for OPD from both data and training perspectives. For data, we find that effective warm-up relies on teacher-compatible chain-of-thought supervision, and that even incorrect teacher rollouts can provide comparable benefits to correct ones. This suggests that warm-up primarily transfers a teacher-compatible thinking pattern rather than merely correct answers. For training, we show that low-rank adaptation (LoRA) with a near-saturation training duration better balances in-domain adaptation and out-of-distribution generalization than full-parameter SFT. Based on these findings, we propose Simple-OPD, a plug-and-play initialization method that warms up the student on teacher-generated CoT with LoRA before OPD. Experiments across diverse settings demonstrate the effectiveness and robustness of Simple-OPD. --- ### AdvTiles: Physical Adversarial Camouflage Clothing against Person Detectors via Learnable Tiles Authors: Jinlei Wang, Jiahuan Long, Mingkai Sun, Yafei Guo, Yuanhao Huang, Ming Wang, Junqi Wu, Jiacheng Hou, Hongbo Chen, Xingxing Wei, Tingsong Jiang, Wen Yao Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.06801v1 Physical adversarial attacks against person detectors have evolved from localized patches to full-body textures. However, achieving both visual naturalness and strong attack effectiveness remains challenging. Existing natural-looking methods typically optimize camouflage textures as a whole, limiting the flexibility to refine local adversarial patterns and their spatial arrangement. To address this issue, we propose AdvTiles, a physical adversarial camouflage framework built from learnable tiles, enabling strong attack performance while preserving a natural camouflage appearance. Specifically, we use a Straight-through (ST) Gumbel-Softmax estimator for differentiable tile selection, enabling joint optimization of tile patterns and spatial layouts. This design provides fine-grained control over adversarial texture generation. To improve robustness in diverse physical conditions, we further optimize the camouflage through differentiable 3D Gaussian Splatting rendering with variations in viewpoints, scales, illuminations and backgrounds. Extensive experiments across multiple detectors demonstrate that AdvTiles achieves an average ASR of 86.2%, outperforming existing state-of-the-art attack methods. We further fabricate the optimized camouflage into wearable adversarial clothing, validating its effectiveness in real-world scenarios across diverse distances, angles and backgrounds. --- ### Is Forward Prediction Enough? Physical State Grounding for JEPA World Models Authors: Haodong Yan, Jiaguan Zhu, Mingyuan Jia, Ruiqing Yin, Junjie He, Zhide Zhong, Junfeng Li, Jinxuan Lu, Hengtao Li, Tianran Zhang, Jiayi Chen, Wenxuan Song et al. Published: 2026-08-07 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2608.06799v1 Learning structured and control-relevant latent representations remains a key challenge for world models. Recent JEPA-based world models learn action-conditioned predictive latent dynamics from observation sequences. However, their forward-prediction objectives do not explicitly enforce reliable identifiability of robot-centric physical state from individual latents or state changes from latent pairs, which can limit downstream planning and policy performance. We propose PSG-JEPA, a physically grounded JEPA world model that shapes its latent space with two complementary grounding objectives beyond forward prediction: grounding individual latents in robot proprioceptive state, and grounding latent pairs in multi-horizon joint-angle changes. Both objectives are applied only during training, leaving the inference architecture and computational cost unchanged. To comprehensively evaluate PSG-JEPA, we conduct experiments at three levels: (1) latent identifiability via probing, (2) goal-conditioned planning on frozen latents, and (3) policy learning in simulation and on a real robot. Experiments demonstrate that our PSG-JEPA consistently outperforms state-of-the-art latent world-model baselines at all three levels. --- ### LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Authors: Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo, Kaichen Yang Published: 2026-08-07 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.06795v1 Low-rank adaptation (LoRA) enables efficient specialization and distribution of large language models through compact adapters. However, untrusted adapters introduce a supply-chain threat: a backdoored adapter can cause a model to generate harmful content, malicious code, political propaganda, or covert advertisements when an input contains a hidden trigger. Adapter-agnostic defenses merge the adapter with the base model, which dilutes backdoor signals and reduces detection performance. Existing adapter-aware methods do not address how to safely use a potentially backdoored adapter. Instead, they either train a defensive adapter to repair a backdoored base model, addressing the inverse problem rather than securing the adapter itself, or rely on a classifier that flags the entire adapter as suspicious and requires separate mitigation. These methods overlook the distinct latent-space signatures produced by trigger-bearing inputs in backdoored adapters. We introduce LoRAScan, the first adapter-aware defense that detects and rejects trigger-bearing inputs at inference time without modifying adapter parameters. Our key observation is that a small subset of LoRA insertion sites, approximately 5%, remains stable across clean inputs but exhibits highly concentrated spikes in LoRA down-projection activations when a trigger is present. LoRAScan identifies these low-variance insertion sites before model deployment and monitors them during inference. Across standard LLM backdoor benchmarks, LoRAScan rejects approximately 98.49 of malicious inputs with a small error rate on clean inputs, outperforming existing defenses across diverse evaluation settings. --- ### PAST: Prompt-Adaptive Sampling Termination for Efficient Diffusion Model Authors: Renye Yan, Jikang Cheng, You Wu, Wei Peng, Zongwei Wang, Ling Liang, Yimao Cai Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.06794v1 While diffusion models have made significant progress in text-to-image tasks, they still exhibit limitations when directly optimizing downstream objectives. Although Reinforcement Learning (RL) enables targeted optimization, existing methods are generally constrained by low-efficiency fine-tuning and sparse rewards. To address these challenges, we propose PAST, which provides differentiated rewards while adaptively regulating training episode length by jointly perceiving denoising progress and prompt difficulty. Specifically, we design an intrinsic reward paradigm to compensate for sparse extrinsic rewards and guide the model to explore paths that diverge more efficiently from noise patterns. We further provide theoretical justification for intrinsic rewards. Then, PAST dynamically monitors denoising completion and semantic alignment between image structures and prompt semantics. When both metrics satisfy generation requirements, the system adaptively terminates training. This enables appropriate allocation of episode lengths based on prompt difficulty and the current generation process. Finally, based on the predicted residual noise level, we establish a dual adaptive coordination mechanism. Specifically, it not only balances the extrinsic and intrinsic rewards but also balances the exploration and convergence. Experimental results demonstrate that PAST enhances computational efficiency of existing RL fine-tuning methods by up to 66.7%, while improving preference optimization quality by up to 29.5% through its dual adaptive regulation mechanism. --- ### Progressive Alignment of Recommender Foundation Model through Multi-Phase Post-Training Authors: Oseong Choi, Hoeinn Kim, Jihoon Lee, Byungsoo Kang, Taeyeong Jang Published: 2026-08-07 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2608.06792v1 Foundation model(FM) for recommendation has shown strong ability to model long-horizon sequential user behavior. In practice, a single pretrained foundation model is often adapted to diverse downstream serving surfaces through Supervised Fine-Tuning(SFT). However, optimizing task-specific objectives such as clicks or likes does not necessarily align the serving policy with the business metrics that determine recommendation quality. We propose a three-phase progressive post-training framework that explicitly separates downstream adaptation from business-metric alignment. The adaptation stage is decomposed into Linear Probing(LP) and Full Fine-Tuning(FFT): LP first stabilizes randomly initialized downstream heads within a frozen pretrained representation space, and FFT then jointly specializes the full model for the target task. On top of this stabilized policy, Reinforcement Fine-Tuning(RFT) aligns the model with practical business objectives using a learned reward model. Rather than directly optimizing the serving policy on sparse business targets, we train the policy on dense implicit feedback and use business-metric supervision only for reward modeling. Offline experiments show that the progressive LP-FFT-RFT framework outperforms single-phase alternatives, and that reward-based alignment yields a stronger serving policy than directly using the reward model itself for ranking. Large-scale online A/B tests further show that the proposed framework improves production recommendation quality over a conventional non-foundation baseline. A reference implementation is available at https://github.com/webtoon/rec-fm-progressive-alignment --- ### HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation Authors: Yuebo Luo, Ahmad Sedigh Baroughi, Philip Stachura, Le Chen, Venkatram Vishwanath, Zhenman Fang, Caiwen Ding Published: 2026-08-07 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2608.06791v2 Application-specific FPGA accelerators offer substantial performance and energy-efficiency gains across many application domains, but developing them is costly, often requiring months of specialized effort. Even with high-level synthesis (HLS), designers still need extensive hardware expertise to build high-performance accelerators. Although large language models (LLMs) have demonstrated strong software-generation capabilities, even frontier models lack the hardware intuition and procedural knowledge needed to reliably translate baseline C/C++ programs into high-performance HLS designs: they struggle to identify effective architectures, follow the optimization processes used by HLS experts, and apply hardware transformations consistently across diverse kernels. We present HLSmith, an expert-guided framework for translating C/C++ programs into optimized HLS accelerators. HLSmith combines three components: an HLS optimization expertise library that encodes guarded transformation recipes, their applicability and prerequisite conditions, and unsafe cases to avoid; a staged, feedback-driven orchestration flow modeled on expert HLS development practice that guides agents through synthesis, bottleneck analysis, and optimization; and a tool-grounded model-adaptation pipeline that converts optimization trajectories from commercial frontier models into training data for fine-tuning open-weight LLMs. We evaluate HLSmith on PolyBench against ChatHLS, a leading prior agent-orchestration framework for HLS accelerator development. HLSmith achieves a geometric mean speedup of 4.24x over ChatHLS while producing functionally correct designs, in both software and RTL simulation, for every benchmark, compared with ChatHLS's 57% valid-design rate. It further reaches speedups of up to 252x and 138x with commercial frontier models and open-weight models, respectively. --- ### Multi-Perspective Triad Interaction Graph Neural Network for Cognitive Distortion Detection Authors: Jun Seo Kim, Hye Hyeon Kim Published: 2026-08-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.06785v1 Cognitive distortion detection is a key task in computational mental health, yet existing approaches often overlook the psychological structure of distorted thoughts. We propose MTI-GNN (Multi-Perspective Triad Interaction Graph Neural Network), which models Beck's cognitive triad---negative views of the self, world, and future---as complementary perspectives for classification. An LLM decomposes each utterance into the three perspectives, from which perspective-specific similarity graphs are constructed and encoded by a Multi-Perspective GNN. A Triad Interaction module models cross-perspective dependencies through sequential source-conditioned updates and feature-wise gating, while Prototype-Guided Perspective Fusion performs label-conditioned aggregation. Label-expanded supervision incorporates all available distortion annotations during training. We evaluate MTI-GNN on 9,764 samples from four Korean, English, and Chinese datasets spanning ten distortion categories. MTI-GNN significantly outperforms all supervised variants and exceeds eight prompted generative models under zero-shot and few-shot settings. Leave-one-perspective-out ablations show that all three perspectives contribute significantly, while human expert evaluation provides preliminary evidence of their alignment with the intended cognitive dimensions. --- ### UniCycleFlow: Bidirectional Unpaired Image Translation with a Shared Rectified Flow Authors: Xianhao Zhou, Jianghao Wu, Shaoting Zhang, Guotai Wang Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.06784v1 Bidirectional unpaired image translation must preserve source-specific structure while learning coherent transformations in both directions without paired supervision. Existing methods typically employ two direction-specific generators or train separate one-way models. Even when linked by cycle consistency, such models constrain only the round-trip endpoint reconstruction, without requiring the two directions to obey a common local transformation rule. We propose UniCycleFlow, a rectified-flow framework that represents bidirectional translation as forward and reverse integration of a single time-conditioned velocity field. This formulation organizes both directions within the same continuous dynamics, rather than coupling otherwise separate endpoint mappings. A key challenge is that unpaired data provide no meaningful source--target coupling from which rectified-flow trajectories can be constructed. UniCycleFlow addresses this challenge by learning deterministic source-conditioned endpoints whose marginal distributions are adversarially matched to the opposite domains. The resulting paths are regularized by stop-gradient self-flow matching for intermediate velocity supervision, discrete cycle closure for forward--reverse consistency, and representation path-velocity regularization for controlling localized feature changes along the trajectory. Across ten translation directions, UniCycleFlow achieves the lowest FID on 7 of 10 tasks using a single Euler evaluation and obtains the best average FID of 55.1. --- ### Genotypic Triggers: Exposing Pharmacogenomic Blind Spots via Host-Specific Backdoors in Generative Antimicrobial Peptide Models Authors: Doniyorkhon Obidov, Xiaolong Guo, Yonghui Li, Kaichen Yang Published: 2026-08-07 Categories: q-bio.QM, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.06779v1 Large Language Models (LLMs) have accelerated drug discovery, particularly in the automated design of antimicrobial peptides (AMPs). However, current validation pipelines for peptide generation models overlook historical precedents showing that certain drugs carry health risks predominantly for individuals with specific genetic profiles. In this paper, we demonstrate that such targeted health risks can be induced intentionally and at scale by manipulating models that generate peptide candidates. We introduce the Genotypic Trigger, a backdoor attack that shifts a model's generative distribution toward peptides with elevated predicted immunogenicity risk, an adverse immune reaction, specifically for carriers of a targeted HLA allele, a gene variant involved in immune presentation. Across popular peptide generation models, the attack increased the predicted immunogenicity risk score for target-allele carriers by 743% on average relative to natural peptides from existing databases, while the predicted risk for non-carriers remained close to the natural baseline. Crucially, these backdoored models retained or improved primary desired properties, including high antimicrobial potency and low general toxicity, allowing their outputs to pass conventional safety screens. --- ### Retrieval-Constrained Policy Optimization for Attack Technique Extraction from Cyber Threat Intelligence Authors: Jiayun Zhang, Junshen Xu, Zejun Xie, Yi Fan Published: 2026-08-07 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2608.06778v1 Mapping cyber threat intelligence (CTI) text to MITRE ATT&CK techniques is essential for structured threat analysis, yet manual annotation is costly and does not scale. The ATT&CK taxonomy comprises several hundred attack techniques, and a single CTI passage may describe multiple techniques, making accurate and complete extraction challenging. Existing automated approaches fall short in different ways: multi-label classifiers struggle with severe class imbalance and the large label space, while LLM-based methods--retrieval pipelines and fine-tuned generators--optimize token-level objectives that treat technique annotation as sequence generation rather than set prediction, lacking direct supervision on whether the predicted technique set is correct and complete. We propose TTP-R1, a two-stage framework that combines retrieval-augmented supervised fine-tuning (SFT) with reinforcement learning using verifiable rewards (RLVR). A hybrid retriever first narrows the large label space to a candidate set, and a fine-tuned LLM learns to select the correct techniques. We then apply Group Relative Policy Optimization with a decomposed reward that directly supervises the precision, recall, and output format of the predicted technique set. Across four CTI benchmarks, TTP-R1 achieves the best average F1, improving sub-technique-level F1 by 7.4 percentage points over Claude Sonnet 4.5 with retrieval augmentation, while running 28x faster when served as an 8B-parameter model on a single GPU. --- ### Faster Query-Key Learning Sharpens Attention in Self-Attention Models Authors: Rahul Vashisht, Harish G. Ramaswamy Published: 2026-08-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.06776v1 A standard self-attention layer consists of two interacting circuits: the query-key circuit that governs attention allocation, and the output-value circuit that maps attended representations to predictions. Collapsed and factorized parameterizations of the query-key and output-value circuits lead to qualitatively different attention patterns. In particular, some parameterizations give sharper attention to task-relevant tokens, at a similar training loss. We analyze how the parameterizations of these circuits shape the parameter trajectories in single-layer self-attention models trained for next-token prediction. Through gradient-flow analysis, we show that factorization induces implicit rescaling of the two circuits' learning rates. We derive closed-form dynamics showing that output-value and query-key parameters move along a line, with relative speeds determined by their learning rates. Faster query-key learning relative to output-value learning thus produces sharper attention, as the model compensates for slower output-value learning by increasing attention mass on relevant tokens. Experiments show that differences in the relative learning rates of the two circuits govern attention concentration. This improves attention interpretability proxies while maintaining comparable predictive performance. --- ### AnyTrack: Unifying Visual Object Tracking with Any Modalities Authors: Hao Li, Yunzhi Zhuge, Wenning Hao, Pingping Zhang, Xiaoxiong Zhang, Dong Wang, Huchuan Lu Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.06773v1 Visual object tracking aims to continuously locate specific targets within sequential frames, evolving from single-modal methods to multi-modal ones. However, existing multi-modal trackers are typically designed for fixed modality combinations, requiring separate models for different inputs. This leads to a poor adaptability to missing or imperfect modalities, and limited generalization. To address these issues, we propose a novel unified framework called AnyTrack for object tracking with any modalities. Specifically, we design a Modality-aware Interaction Module (MIM) to facilitate dynamic interaction across diverse modalities. This module bridges modality discrepancies and aggregates temporal cues to maintain spatio-temporal consistency during cross-modal interaction. Furthermore, we introduce a Context Understanding Module (CUM) to establish spatial correspondence between visual features and target locations via global-local prompts. This module employs target-aware context modeling to enhance foreground-background discrimination for precise localization. Finally, to support the training and evaluation under diverse modalities, we extend existing multi-modal object tracking benchmarks by incorporating grayscale images, language descriptions, and audio clips. Extensive experiments with both complete and missing modality settings demonstrate that our AnyTrack achieves state-of-the-art performance, validating its effectiveness and flexibility. The source code is available at https://github.com/IdolLab/AnyTrack. --- ### ArchEGraph: A Large-Scale Graph Dataset for Geometry-Topology-Physics Aligned Building Energy Modeling Authors: Yihui Li, Yihui Chen, Kaidi Zha, Xiaoyue Yan, Zhexuan Yu, Shiqi Dai, Jun Xiao, Jun Yin, Ramon Elias Weber, Borong Lin Published: 2026-08-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.06772v1 Accurate estimation of building energy use is essential for achieving carbon neutral and sustainable buildings. To better understand the influence of design decisions on building energy use and calibrate machine learning models that can give architects and engineers rapid design feedback, large-scale datasets are needed that explicitly map building geometry to performance. We present ArchEGraph, a large-scale benchmark dataset that represents buildings as heterogeneous graphs with aligned geometry, topology, weather, and zone-level thermal loads. The dataset contains 5,481 buildings and 49,326 validated building-weather simulation cases. In total, it includes over 133,000 space nodes and 1.44 million face nodes, reflecting substantial geometric and topological complexity. Based on ArchEGraph, we define two benchmark tasks: (i) graph reconstruction from polygonal meshes, aiming to recover topological structure from geometric representations; and (ii) topology-informed load prediction, which leverages graph structure and temporal weather conditions to forecast zone-level response time series. We further introduce standardized evaluation protocols for both tasks and conduct cross-building and cross-climate generalization experiments to assess model robustness. ArchEGraph provides a unified testbed for studying geometry-topology-physics coupling in building energy modeling, enabling the development and evaluation of scalable and generalizable surrogate models. --- ### Surg-UniWorld: A Unified Surgical World Model with Multimodal Control Experts Authors: Rulin Zhou, Wanhao Liu, Guoheng Ma, Liangjin Shao, Qiujie Song, Yidu Wang, Guankun Wang, Tong Chen, Long Bai, Luping Zhou, Hongliang Ren Published: 2026-08-07 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.06770v1 Controllable surgical world models can provide a generative foundation for surgical artificial intelligence and simulation by synthesizing realistic instrument--tissue interactions. However, existing methods lack a unified multimodal control paradigm, while direct fusion of heterogeneous visual conditions often causes anatomical distortion, instrument appearance drift, and temporally inconsistent interactions. In this work, we propose {Surg-UniWorld}, a unified surgical world model with multimodal control experts. Surg-UniWorld first constructs a {Hierarchical Surgical Anchor} from first-frame appearance and hierarchical semantic masks to preserve persistent scene identity, anatomical organization, and interaction boundaries. {Anchor-Relative Modality Experts} then interpret edge, depth, and optical-flow evidence relative to the shared anchor, capturing complementary boundary, geometric, and motion information. A {Multimodal Control Expert} further performs contribution-preserving stage-wise composition of the activated modality increments and generates control hints for the Wan2.2 video diffusion backbone. To support multimodal surgical world modeling, we further construct Cholec80-SurgWAM, a benchmark for controllable surgical video generation. Extensive experiments demonstrate that Surg-UniWorld consistently outperforms existing controllable video generation methods and surgical world-model baselines in generation quality, temporal consistency, and multimodal controllability. --- ### GraphVerse: A Comprehensive Visual Graph Reasoning Benchmark for Multimodal Large Language Models Authors: Yuanfu Sun, Yuanhang Ren, Kang Li, Chuanhao Ji, Jiaxi Li, Jiajin Liu, Ninghao Liu, Qiaoyu Tan Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.06769v1 Recent Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse vision-language tasks, creating an urgent need for more challenging benchmarks. Yet existing evaluations still provide limited insight into whether these models can truly reason over structured visual information. Visual Graph Reasoning (VGR) offers a compelling testbed for this challenge, requiring models to integrate perception, structural understanding, and multi-step reasoning over graph-based visual inputs. However, prior VGR benchmarks often reduce the task to visual perception followed by text-based reasoning, restrict evaluation to single-image settings, rely on answer-only metrics, and underrepresent realistic graph-centric scenarios. To bridge the gap, we introduce GraphVerse, a unified benchmark that jointly evaluates perception, visual reasoning, and text-based graph reasoning in MLLMs under both single-image and paired-image settings. At its core is a suite of Graph-centric Image Editing (GIE) strategies that modify graph images while preserving their semantics, turning them into active tests of visual reasoning. We further propose VGR-Score, a process-sensitive metric that evaluates reasoning quality beyond final-answer accuracy. Extensive experiments reveal several key limitations of current MLLMs in VGR, while also validating the effectiveness of GIE strategies and the transferability of GraphVerse to broader multimodal reasoning capabilities. The code is available at https://github.com/sunyuanfu/GraphVerse. --- ### Explore or Converge? Stage-Guided Per-Step Optimization for Diffusion Models Authors: Renye Yan, Jikang Cheng, You Wu, Wei Peng, Zongwei Wang, Ling Liang, Yimao Cai Published: 2026-08-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.06768v1 Diffusion models have strong generative capabilities. However, their maximum likelihood training objective only focuses on reconstructing the data distribution, making it difficult to align with specific preferences. Reinforcement learning (RL) for preference alignment in diffusion models is promising but limited by reward sparsity. Since a single reward cannot support optimization, existing RL methods usually backpropagate the final reward to all previous steps. However, denoising is stage-wise, with distinct semantics and controllability. Repeating the final reward across all steps creates a temporal objective mismatch, encouraging reward shortcuts that lead to reward hacking. At the same time, due to reward backfilling, each time step receives the same reward, making it impossible to distinguish between actions, thereby weakening the optimization process. To resolve this issue, we propose Stage-Guided Per-Step Optimization (SGPO) for diffusion models, which jointly leverages signal-to-noise ratio and semantic changes to identify generation stages and adaptively assign stage-specific objectives. Early denoising is chaotic and far from the final reward, resulting in weak reward-behavior correlation. This stage should prioritize exiting the chaotic state. In the mid stage, the latent transitions to a stable structure, where the final reward better corresponds to generative behavior. Therefore, this stage optimizes the final reward while exploring diversity to avoid early convergence to a single mode. In the late stage, the latent's core structure is largely fixed, and preference optimization mainly amplifies local details, risking overfitting. Therefore, stable convergence is preferred to avoid quality degradation. Results from 16 comparative experiments validate SGPO. Our method achieves 26.7% average gains in generative quality and 36.7% higher convergence speed. --- ### Hidden Gauge Controls Feature Specialization in ReLU Networks Authors: Tongxi Wang Published: 2026-08-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.06766v2 The success of deep learning depends on learning useful representations, yet predicting how training organizes these representations across neurons remains difficult. In this work, we show that changing the scale of initial weights can determine which neurons learn a feature without altering any neuron's initial contribution. We construct ReLU networks with identical initial features and predictions that reach the same final predictions with different roles for their neurons. In one, all neurons share the learned feature. In the other, one neuron acquires it while every other neuron's contribution vanishes. The only change is the relative scale of each neuron's input and output weights. Our analysis explains how an initial learning advantage persists through convergence: as one neuron learns the target, it reduces the error driving the others and limits their subsequent adaptation. We prove this outcome in a nonlinear model under gradient flow and small-step gradient descent, and quantify how scale changes the speed and path of feature learning. Experiments verify the predicted dynamics and show that scale also changes feature assignment when two features compete. These results reveal how initialization can control the organization of a learned representation without changing what the network initially represents. --- ### Where Does Neural Advantage Arise in Continuous-Time Dynamic Graph Prediction? Authors: Minwoo Yu, Young-guk Ha Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.06765v3 Aggregate performance on continuous-time dynamic graphs (CTDGs) combines, in a single score, the portion attributable to known temporal regularities and the additional predictive power of neural models. This study separates the two at the query level. We construct a mechanism-constrained predictor that uses pair recurrence, recency and history position, renewal patterns, and short sequential transitions while learning the compatibility within each mechanism. Across four CTDG datasets, this predictor recovers a substantial portion of the performance of strong neural baselines, and the recovered performance quickly saturates with a small, dataset-specific set of explicit mechanisms. Neural residuals concentrate on queries for which the positive and negative candidates have similar mechanism-execution profiles. Allowing conditional interactions among mechanisms is more effective than simply reweighting their existing contributions. Conditioning the contribution of one mechanism on the execution state of another recovers 54.9-73.2% of the original neural-only queries and improves overall paired accuracy on all four datasets. Although the magnitude of the effect varies across datasets, these results show that the performance gap of neural CTDG models need not be treated solely as an opaque difference in representational capacity. At least part of the gap is localized to queries with similar candidate execution profiles and can be functionally explained by conditional coordination among known, low-dimensional mechanisms. --- ### CubicQuant: Parametric Non-Uniform Codebooks for High-Throughput LLM Inference with 1-8-Bit Weights Authors: Xuetian Gao Published: 2026-08-07 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2608.06763v1 Weight quantization for large-language-model inference must balance adaptive reconstruction levels with representations regular enough for efficient GPU execution. Uniform integers constrain each group to a linear grid. Low-bit floating-point formats use a fixed exponent-mantissa structure, while learned codebooks gain flexibility at the cost of irregular decoding and additional metadata. We introduce CubicQuant, a parametric non-uniform scalar format that preserves a dense integer code stream while adapting reconstruction levels within each weight group. A monotonic cubic curve, specified by two shape parameters and one scale, maps uniformly spaced magnitude codes to non-uniform levels. The family spans 1-8-bit weight payloads, contains symmetric uniform integer quantization as an exact special case, and has effective width B + 64/G bits per weight for payload width B and group size G. We derive population distortion under Uniform, Gaussian, and Laplace distributions, formulate continuous and Dynamic-A8-carrier-aware fitting objectives, and describe direct packed-weight GPU execution. For finite groups of G=128 with 15,360 samples per distribution, W4 CubicQuant reduced reconstruction RMSE relative to optimally clipped four-bit uniform integer quantization by 3.90% on Uniform, 13.49% on Gaussian, and 28.14% on Laplace samples. Relative to the best enumerated four-bit finite floating-point format, the reductions were 3.90%, 9.44%, and 6.27%. Preliminary H200 kernel measurements show a workload-dependent crossover: model-dtype execution is faster for narrow GEMV, while Dynamic A8 becomes favorable as row count grows. The results establish the format's representational promise and direct executability; downstream model quality and cross-device end-to-end performance remain open evaluation questions. --- ### Sub-Quadratic Bisimulation Metrics via Approximate Nearest Neighbors: Coverage-Augmented Guarantees and Computable Two-Sided Certificates Authors: Ibne Farabi Shihab, Joyanta Jyoti Mondal Published: 2026-08-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.06762v1 Bisimulation metrics quantify behavioral similarity in Markov decision processes, but their Wasserstein fixed-point operator updates every state pair and incurs quadratic pairwise work. We give a certificate-carrying sub-quadratic method for MDPs with bounded transition support and a useful low-dimensional indexing representation: an approximate-nearest-neighbor index selects the pairs updated by the exact restricted operator, while monotone lower and upper runs enclose the exact metric at every sweep. The main analytical result is a coverage-augmented anytime bound: local index quality alone cannot control global error, because uncovered pairs retain their initialization gap. The limiting error is at most $\max(ρ,\eop/(1-γ))$, and with exact covered backups the lower arm satisfies $\|\dann-d\|_\infty=ρ$. Because $ρ$ depends on the unknown exact metric, the algorithm returns the observable sandwich width instead; agreement of the induced lower and upper clusterings certifies exact recovery of the covered aggregation. A reward-oblivious lower bound shows sub-quadratic index-first coverage cannot remove the coverage term, while a separate adaptive lower bound requires $Ω(|\Scal|)$ pair evaluations. Exact-operator experiments verify the identity and enclosure in every seeded run, and timing experiments recover quadratic versus sub-quadratic scaling under both cheap and full Wasserstein backups. On the grouped $|\Scal|=64$ benchmark, exact restricted refinement reaches the exact-metric skyline once retrieval covers roughly half of all pairs, while independently trained MICo and DBC baselines stay $22$-$33\times$ above that skyline at every retrieval budget. Taxi shows the certificate abstaining under an uninformative embedding, while a $2500$-state gridworld improves over a reward-only metric by $28.6\%$ using $12.8\%$ of one quadratic sweep. --- ### Stockmark-Nemotron-3-Nano-Omni-JapanDocReader: Structured Document Parsing via Capability Injection and Forgetting Control Authors: Shi Chen, Hayato Aida, Makoto Morinaga, Shohei Tanaka, Kosuke Arima Published: 2026-08-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.06758v1 We present Stockmark-Nemotron-3-Nano-Omni-JapanDocReader, a Japanese document understanding model built from Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16. The central goal of this work is structured document parsing via capability injection and forgetting control: we inject Japanese structured document parsing capability into a reasoning-oriented multimodal model while preserving its document VQA capability as much as possible. We study parsing-centric SFT, which uses only structured document parsing data; mixed SFT, which combines structured document parsing and VQA data; and parsing-centric RL, which optimizes structured parsing with a task-level reward. Our experiments show that parsing-centric SFT substantially improves structured document parsing performance but causes measurable VQA forgetting. Mixed SFT mitigates this forgetting while preserving nearly the same structured parsing performance. Applying DAPO-based parsing-centric RL on top of the mixed SFT checkpoint further improves structured document parsing beyond the SFT ceiling, producing the final released model. The training data is constructed with a data engine consisting of two complementary synthetic streams: a Japanese Document VQA Stream and a programmatic structured document parsing stream. We also discuss reward design and variance-based prompt filtering for continuous structured document parsing rewards, highlighting their importance for making RL effective in long-reasoning structured document parsing tasks. --- ### Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence Authors: Ying Chen, Weizhen Li, Zhe Hu, Zhenjiang Li, Rui Jiang, Zhifeng Gu, Lihuang Fang, Jiangping Liu, Lei Yi, Jie Chen Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.06756v1 Vision-language models are increasingly serving as the reasoning core of embodied agents. Robot execution is inherently iterative: each action reshapes the scene and physical state, continually renewing what must be perceived, reasoned about, and verified. Meeting these demands requires complementary capabilities that differ in supervision signals, prediction formats, and verification criteria. Existing approaches typically develop these capabilities against isolated, task-specific objectives, leaving open how they should be organized and integrated around execution as a whole. We present Capek 0.5, an embodied vision-language model built around an execution-centric capability taxonomy. Rather than organizing training by datasets or tasks, the taxonomy groups embodied capabilities according to their functional roles throughout execution and comprises four capability families: Spatial Reasoning, Temporal Understanding, Action Guidance, and State Verification. Each capability is first acquired by a dedicated specialist through reinforcement learning with verifiable rewards from a shared backbone, and the specialists are then consolidated into a single inference-time model through weight-space merging followed by routed policy-space distillation. We instantiate Capek 0.5 at the 2B and 35B-A3B scales and evaluate it from three complementary perspectives: comprehensive benchmark suites including Capek-StateBench, a new benchmark for state verification; a controlled study of capability retention from specialists to the unified model; and closed-loop evaluation in simulated embodied environments. Capek 0.5 improves the large majority of matched benchmark rows over its initialization, retains all four specialized capabilities in one checkpoint with quantified losses, and transfers to closed-loop embodied task execution. --- ### Mind the Gap: A Dual Knowledge Graph Framework for Unified Multi-task User Intent Inference Authors: Tzu-Cheng Peng, Chien Chin Chen, Chih-Hao Ku, Yung-Chun Chang Published: 2026-08-07 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.06752v1 This paper proposes DKG-MTI, a dual knowledge graph framework for unified multi-task user intent inference from online travel reviews. Existing approaches often rely on hierarchical pipelines that suffer from error propagation or retrieval methods that ignore structural relationships in domain knowledge. To address these limitations, we introduce an inference-only knowledge augmentation framework that dynamically constructs a User-Specific Intent Knowledge Graph from each review and aligns it with a Global Hotel Knowledge Graph through structure-aware semantic smoothing. The aligned knowledge is combined with the original review and processed by a large language model to simultaneously predict aspect ratings and generate reverse user intent statements. Experiments on TripAdvisor reviews show that DKG-MTI consistently outperforms strong LLM and retrieval-based baselines in both classification and intent generation tasks, demonstrating the effectiveness of structure-aware knowledge alignment for scalable and explainable intent inference. --- ### Beyond Starry Night: Shortcut-Aware Control-State Planning for Artist-Grounded Text to Image Generation Authors: Kuan Xing, Ye Wang, Changyi Gan, Yuheng Li, Thao Nguyen, Yi Chang, Yilin Wang Published: 2026-08-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.06751v1 Artist-grounded image generation requires more than appending an artist name to a prompt. Image models often respond to artist names through canonical shortcuts, such as recurring motifs, generic palettes, or overrepresented period signatures, rather than preserving the user's intended scene. We introduce Atelier, a shortcut-aware control-state planning framework for artist-grounded image generation. Atelier translates underspecified artistic intent into an explicit control state that separates scene anchors, preserve/transform decisions, style-regime hypotheses, role-bound artist evidence, and shortcut-avoidance constraints. It grounds this state using artist-level knowledge and local patch references, compiles backend-aware generation plans, and iteratively refines candidates through global and local authenticity feedback. We further introduce ArtIntentBench, a benchmark covering Van Gogh and Qi Baishi across artwork re-rendering, period/style-controlled generation, historically unseen subjects, shortcut auditing, and human preference evaluation. Across open-weight and closed-source generators, Atelier improves artist-level style fidelity, preserves source structure more faithfully, and substantially reduces shortcut substitution compared with prompt-engineered, retrieval-augmented, and general-purpose agent baselines. These results suggest that artist-grounded generation is bottlenecked not only by image synthesis, but by the upstream inference of explicit, evidence-grounded artistic controls. --- ### Progressive Content Refinement with Decaying Reward Joint LinUCB Authors: Shion Ishikawa, Pablo Loyola, Young-joo Chung, Yun Ching Liu Published: 2026-08-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.06750v1 Iterative refinement has significantly enhanced Large Language Model (LLM) performance; however, existing methods ranging from feedback-based Self-Refine to traditional bandit approaches often rely on static options or overlook the saturation effect. This neglect leads to over-exploitation, where the continuous use of identical prompts or arms results in diminishing rewards over time. To address this challenge, we propose a novel contextual bandit algorithm that explicitly incorporates reward decay modeling. Utilizing an Expectation-Maximization (EM) algorithm, our method simultaneously estimates both arm-specific and decay parameters. Furthermore, by embedding prompts as arms, we facilitate the joint learning of arm values, distinguishing our approach from the traditional disjoint Linear Upper Confidence Bound (LinUCB) framework. Experimental results on Sentiment Reversal and GSM8K benchmarks demonstrate that our method achieves significant performance gains over strong baselines. Finally, our ablation study confirms that the integration of reward decay modeling within the bandit framework is crucial for mitigating over-exploitation and optimizing the iterative refinement process. --- ### KReF: Training-Free Retrieval for Long-Term Time-Series Forecasting and Predictive Uncertainty Authors: Yang Zhang, Rui Su Published: 2026-08-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.06748v1 Probabilistic long-term time-series forecasting commonly relies on trained models. Training-free conformal methods typically construct intervals around a pre-existing point forecaster and do not natively represent a complete predictive distribution; sequential variants additionally suffer from increasingly delayed feedback at long horizons. We propose KReF, a training-free retrieval framework that treats retrieved historical futures as a querylocal empirical predictive distribution. After robust preprocessing, KReF embeds each lookback using handcrafted statistics or frozen random Fourier features and retrieves similar historical lookback-future pairs. Their similarity weights directly define predictive masses, quantiles, CRPS, and a weighted-mean point forecast. KReF further uses the observed query lookback to construct a probability-integral-transform map and applies validation-selected expansion and shrinkage rates to adapt interval boundaries. Across six LTSF benchmarks and four horizons, KReF obtains the lowest CRPS in all 12 dataset-embedding settings and the lowest IS90 in 9 settings. Without gradient-based fitting, its point forecasts also match or surpass trained baselines on two of six datasets. An archive-oracle analysis further reveals substantial headroom under finer horizon- and channel-wise routing. These results establish retrieval as a useful and underexplored inductive bias for LTSF. --- ### MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents Authors: Zhisheng Chen, Bingfan Zeng, Bangde Cao, Zhengwei Xie, Yuxuan Li, Jinhan Li, Zheng Lu, Xiangchen Guan, Zikai Xiao, Rui Qian, Jingwei Song Published: 2026-08-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.06745v1 Long-horizon agents rely on memory to reuse experiences, yet existing memory systems often assume that evidence can be directly consumed through a fixed representation. This leads to representation mismatch, where relevant information is available but not organized for the current decision. To this end, we propose MemPrism, a task-conditioned relational memory framework that separates persistent experience storage from decision-time working memory. MemPrism records interactions as the event stream and dynamically constructs relational views according to the current task context. A lightweight view policy selects the relation structure, evidence range, outcome condition, and granularity, while a deterministic composer and render transform historical facts into a temporary optical working-memory view for a frozen task policy. Experiments on long-horizon embodied and web-agent benchmarks show that MemPrism consistently improves the task performance, especially as trajectories become longer, while reducing memory token consumption. Furthermore, the learned view policy transfers across different VLMs without additional adaptation, demonstrating the effectiveness of task-conditioned relational views as a general memory interface for agents. --- ### Solver-Guided Reasoning for Mixed-Equilibrium Strategies Authors: Han Wang, Philippe Beardsell, Boning Li, Aaron Sasmita, Shuai Li, Hongyuan Zha, Baoxiang Wang Published: 2026-08-07 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2608.06741v1 Reasoning in large language models (LLMs) is often grounded in human text, human demonstrations, and human-generated rationales. For equilibrium reasoning in complex games, however, relying on human data can be suboptimal. In fact, human play is often guided by intuition and heuristics and can deviate substantially from game equilibrium. This discrepancy is amplified in games with mixed-strategy equilibria, where human data is heavily biased toward pure strategies. Consequently, conditioning LLMs on this data yields weak game strategies. To grant LLMs the reasoning capacity in games, in this work, we study how to elicit equilibrium play using solver output. We propose Mixed-Strategy Decision Tree (MDT), which articulates the silent optimality of the equilibrium into sparse strategic rules that both humans and LLMs could understand. Using solver output rather than human annotation allows us to extend the input to arbitrarily new states and continuations. We instantiate this study on No-Limit Texas Hold'em by querying a solver oracle for over \textbf{250 million mixed-strategy decisions}; MDT together with other techniques \textbf{reduces the $\ell_1$ distance to the equilibrium by $52.6\%$} across $8$ different LLM configurations. A Route-only ablation tests the incremental contribution of the shadow-based contrast, while complete River-endgame and Liar's Dice experiments evaluate strategic fidelity and portability beyond the original NLH communication setting. --- ### IB-RL: Isolated Bilateral Reinforcement Learning for Strategic Dialogue Agents Authors: Senhao Wang, Chenghao Cai, Haitao Hu, Mingxing Huang, Xingguang Wang, Wenhao Li, Zecheng Lin Published: 2026-08-07 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.06735v1 Reinforcement learning (RL) has achieved strong results in improving large language models (LLMs) on tasks with stationary, verifiable rewards, such as mathematical reasoning and code execution. In these settings, the environment follows fixed rules and does not adapt strategically to the agent. Strategic dialogue differs in this respect: the environment is another agent that adapts to the policy, and success depends on the interaction between the two sides. Despite this interactive nature, current RL approaches typically train a target agent against a fixed counterpart or simulator. We find that this training paradigm encourages the policy to exploit counterpart-specific regularities rather than learn strategies that generalize across counterparts. We call this problem the static-counterpart mismatch, which we quantify directly in our experiments. To address it, we propose Isolated Bilateral Reinforcement Learning (IB-RL), in which the two roles coevolve through joint rollouts while each role optimizes its own reward through fully independent advantages, action masks, and update paths. We evaluate frozen policies against fully independent held-out counterparts in both domains. On Vehicle TeleSales, IB-RL achieves 89.6% Success@1, compared to 84.6% for the best unilateral RL baseline. On Deal-or-NoDeal, it reaches 98.4% agreement against DeepSeek V4 Pro, compared to 86.4% for the best unilateral baseline. These results indicate that jointly training both roles with strict peragent isolation produces policies that generalize more effectively to unseen counterparts. --- ### From Cheap Fakes to Pure Synthesis: Addressing the New Era of T2V Fake News Videos Authors: Yifeng Luo, Yupeng Li, Liang Lan, Tian Wang Published: 2026-08-07 Categories: cs.AI, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2608.06732v1 Recent text-to-video (T2V) generation models enable fake news videos to be synthesized from scratch, shifting the threat beyond cheap fakes assembled from existing footage. Such news videos can closely match fabricated narratives, creating a modality alignment trap for existing detectors. Existing datasets lack pure synthesis fake news videos. Although directly prompting T2V models with descriptions of fake news videos can yield perfectly aligned samples, it reduces the fake news video detection (FNVD) to unimodal shortcuts and causes semantic-visual degeneration. To counter this, we formulate T2V-FNVD as a novel ternary classification task with three labels (real, cheap fake, and pure synthesis fake) and construct the first pure synthesis fake news video dataset (PS-FNVD). PS-FNVD includes fabricated events with aligned deception (Type 1) and true events with false visual provenance (Type 2), preventing models from exploiting unimodal shortcuts. Furthermore, we propose the Reasoning-guided T2V-FNVD (R-T2V) framework. Trained through conditioned rationale generation and supervised fine-tuning, R-T2V integrates high-level semantic logic with low-level physical generative traces to predict the ternary veracity label. Extensive experiments across 10 prevailing baselines show that R-T2V achieves the state-of-the-art performance, outperforming the second-best baseline by 12.20 percentage points in accuracy and 8.46 percentage points in macro $F_1$. --- ### AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models Authors: Guiyu Zhao, Longteng Guo, Yanghong Mei, Zilin Zhu, Yu Zhang, Bin Cao, Mingming Yu, Xingjian He, Jie Jiang, Jing Liu Published: 2026-08-07 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2608.06729v1 While Vision-Language-Action (VLA) models have advanced embodied AI, their fundamentally reactive paradigm severely limits performance in partially observable and long-horizon tasks. When restricted to a single wrist-mounted camera, they inevitably suffer from perception forgetting as objects exit the field of view, and temporal task-progress forgetting} during multi-step execution. To overcome these bottlenecks, we propose AtlasVLA, a novel framework that transitions from direct reactive manipulation to proactive reasoning through a persistent world-ego state. AtlasVLA features a dual-memory architecture: a 4D Persistent World State Memory that lifts transient 2D observations into a globally updated, voxel-hashed spatial state to resolve visual blind spots, and an Ego-Working State Memory that tracks historical ego state and task progress. By conditioning a diffusion transformer (DiT) on this joint World-Ego state, AtlasVLA enables robust spatial reasoning. Extensive evaluations across LIBERO, RLBench, and real-world benchmarks demonstrate that AtlasVLA achieves state-of-the-art performance using solely a wrist camera. Remarkably, it decisively outperforms multi-view baselines, yielding absolute success rate improvements of 9.4% on LIBERO-Long and 17.5% in real-world long-horizon tasks. ---