Optimization
-
Recovering Black-Box Point Cloud Models from Pose Shifts via Derivative-Free Optimization
2026-10-26 05:07:36Seonghwan Park, Min-Gyu ParkAbstract
Point cloud models are increasingly deployed through score-only black-box interfaces. Under this access model, test-time rotations outside the training distribution can substantially degrade performance. Although existing mitigations such as equivariant retraining and gradient-based adaptation are effective, they are infeasible without access to model weights or gradients. To address this limitation, we propose CanDO, a test-time canonicalization method that recovers lost performance using only forward queries. Specifically, CanDO searches for an input transformation that maximizes model confidence and uses derivative-free optimization to perform this search without gradients. We further identify three conditions for successful recovery: a training augmentation gap, an accuracy-aligned confidence surrogate, and global search over a multi-modal objective. Across multiple architectures and benchmarks, CanDO recovers 76% of the oracle gap under azimuthal misorientation and 51% under arbitrary SO(3) rotations for object part segmentation. These results show that frozen score-only point cloud models can recover from rotation-induced distribution shifts through post-deployment canonicalization alone.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34850
PDF
-
Logic Hijacking of RAG: Single-Document Poisoning via Local Optimization
2026-10-26 04:23:01Hangyi Zhao, Bonan Zhang, Fusen Guo, Jiaheng Wei, Chao Chen, Tianqing ZhuAbstract
Single-document corpus poisoning under black-box access poses a severe threat to Retrieval-Augmented Generation (RAG). However, existing attacks predominantly rely on explicit factual refutations or imperative instruction overrides. Modern aligned LLMs often arbitrate such conflicts conservatively, rejecting overt contradictions in favor of parametric memory or clean retrieved context while triggering input guardrails. We propose MONOLOGUE, a single-document poisoning framework based on Logic Hijacking without explicit refutation. Rather than disputing the ground truth, our method concedes it as an authoritative historical baseline before introducing the update, weaving a grounded record-correction narrative (e.g., dated institutional reattributions) that presents the counterfactual target as the most recent update. To prevent suspicious live writes, payloads are refined entirely offline via local multi-dimensional gated optimization, coupling automated text quality audits with surrogate behavioral verification. Evaluations across three benchmarks, three retrieval backends, and four open-weight generator regimes show that our method achieves the strongest overall attack efficacy among the evaluated single-document poisoning attacks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34829
PDF
-
DynEdit: Dynamic Entropy-Guided Sequential Editing for Large Language Models
2026-10-26 03:13:26Jinhu Fu, Yan Bai, Yihang Lou, Li Sun, Jiahong Wu, Xiangxiang Chu, Sen SuAbstract
Knowledge editing aims to update outdated or incorrect knowledge in large language models without full retraining. Existing parameter-editing methods remain limited for long-sequence knowledge: single-point editors provide insufficient coverage for extended targets, while fixed chunk-based editors distribute editing effort uniformly across rigid predefined windows, failing to prioritize difficult, information-dense tokens. In this work, we show that token entropy is closely associated with both editing difficulty and semantic importance: high-entropy regions are harder to edit and often contain key factual content. Motivated by this observation, we propose DynEdit, a dynamic framework for long-sequence knowledge editing. DynEdit uses token-level entropy to guide non-uniform sliding, increasing the coverage of difficult high-entropy regions, and further applies entropy-guided token-level optimization to strengthen updates on information-dense tokens within each editing window. Experiments on three benchmarks and two backbone models show that DynEdit consistently outperforms competitive baselines across diverse long-form editing settings, achieving gains of up to +14.0 BLEU points on challenging paraphrase queries and near-saturated semantic scores on several diverse knowledge domains.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34768
PDF
-
Factorized Gradients for Scalable Highly-expressive Parametric Diffeomorphisms
2026-10-26 03:11:58Amit Aflalo, Eran Treister, Chaim Baskin, Oren FreifeldAbstract
Diffeomorphisms provide a flexible, topology-preserving mathematical tool for modeling complex spatial or temporal deformations and are used in various scientific fields. However, making these deformations simultaneously highly expressive and computationally efficient remains challenging. Continuous Piecewise-Affine Based (CPAB) transformations (Freifeld et al., ICCV 2015; IEEE TPAMI 2017) offer an attractive solution by parameterizing a family of diffeomorphisms via continuous velocity fields that are piecewise affine with respect to a chosen tessellation of the domain. Importantly, $d=\dim(\theta)$, the dimension of the parameter vector $\theta$, depends on the fineness of the tessellation rather than on the data resolution. Despite this compact parameterization, CPAB optimization has long been hindered by the tight coupling between trajectory integration and gradient computation with respect to $\theta$. We introduce FG-CPAB, a factorized-gradient formulation for scalable CPAB transformations. By separating integration from parameter-space projection, our method reduces gradient computation complexity from $\mathcal{O}(dTN)$ to $\mathcal{O}(TN+dC)$, where $T$ is the number of integration steps, $N$ is the number of transformed points, and $C$ is the number of tessellation cells. This reformulation yields speedups of up to four orders of magnitude (e.g., $\approx 10^4\times$ in 2D), substantial memory savings (e.g., $\approx 500\times$ reduction in peak GPU memory usage in 2D), and dramatically higher expressiveness. This makes fine-tessellation CPAB practical in 2D and 3D for the first time, enabling highly expressive parametric diffeomorphisms.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34766
PDF
-
CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems
2026-10-26 02:19:53Jongha Kim, Seohyun Lee, Jonathan Minho Chung, Jinsung Yoon, Hyunwoo J. KimAbstract
Multi-agent systems (MAS) require both effective coordination and specialized task execution. Existing prompt optimization approaches typically couple these functions within agent-specific prompts. We introduce Coordinator-Executor Prompt Optimization (CEPO), a general framework for improving prompt optimization in MAS. CEPO separates system-level coordination from agent-level execution through a shared coordinator prompt and agent-specific executor prompts, and guides their updates according to their respective roles. This structure allows shared coordination rules to be refined consistently across agents while keeping execution instructions separately adjustable. CEPO provides the prompt structure and optimization guidance, while existing prompt optimizers perform the underlying search. Extensive experiments spanning 11 benchmarks across four domains demonstrate that applying CEPO to four existing prompt optimizers consistently improves their performance. Ablations and qualitative analyses support the proposed design, while controlled studies on a document-understanding MAS further demonstrate improved optimization budget efficiency and performance scaling with the number of agents.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34722
PDF
-
VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware
2026-10-26 02:07:42Borui Xu, Hongshi Tan, Wenqi Jiang, Bingsheng He, Ming Wu, Jason Zeng, Michael HeinrichAbstract
Vision--language--action (VLA) models increasingly run on edge devices aboard robots, where inference latency constrains closed-loop robot control. However, it remains unclear how to design VLA models, their inference software and edge hardware so that robots can run VLA inference in real time. Most VLA models report only task success, while prior studies cover limited action-generation strategies, divide inference into at most three stages, and lack comparisons of inference optimizations on the same this http URL 18 open VLA models across released and alternative backends on NVIDIA Jetson AGX Thor and AMD Ryzen AI Max+ PRO 395, with a seven-stage inference breakdown. Our study reveals three insights. First, action-generation strategy matters more than model size. It dominates 14 of 19 Jetson configurations, latency varies by $82\times$ on Jetson and $157\times$ on AMD, and parameter count explains at most 15% of latency variance. Models that generate long action chunks in a few flow-matching steps keep up with control, whereas token-by-token decoding does not. Second, kernel fusion with 4-bit weights helps most, running $\pi_{0.5}$ and GR00T N1.7 2.6--2.9$\times$ faster than PyTorch with \texttt{this http URL}, but it exists for only these two models and only on the Jetson. Optimization also moves the time to the stages it shortens least, as CPU preprocessing grows from 12\% to 39\% of the GR00T N1.7 call. Third, after optimization, memory bandwidth limits only the stages that process few tokens on the Jetson, such as the denoising steps, whereas software limits all other stages, from unfused kernels to serial preprocessing on the host CPU. Overall, low-latency edge VLAs should use few action-generation iterations, inference software should extend kernel fusion and low-bit weights to more models and platforms, and edge hardware needs high memory bandwidth and a fast host CPU.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34717
PDF
-
Movable-Element Multi-Functional RIS-Assisted Hybrid RSMA-NOMA: A Constrained Hybrid Reinforcement Learning Approach
2026-10-26 01:46:27Li-Hsiang Shen, Chi-Te KuoAbstract
In this work, we propose a movable-element (ME) multi-functional reconfigurable intelligent surface (MF-RIS) architecture, termed MM-RIS, which integrates element mobility with adaptive signal reflection, transmission, amplification, and energy harvesting (EH) to enhance communication flexibility and energy self-sustainability. A hybrid rate-splitting multiple access (RSMA) and non-orthogonal multiple access (NOMA) transmission scheme is further designed to improve spectral efficiency. We formulate an energy efficiency (EE) maximization problem by jointly optimizing transmit beamforming, power and rate allocation, MM-RIS configurations, panel deployment, and ME positions. To address the resulting non-convex mixed continuous-discrete optimization problem, we propose constrained hybrid deep reinforcement learning with federated transformer and parametrized sharing (CRAFTS). CRAFTS integrates multi-agent proximal policy optimization (MAPPO) and multi-agent deep Q-networks (MADQN) through bi-directional parametrized sharing to handle continuous and discrete actions, respectively. Moreover, a transformer-based architecture and federated learning (FL) are incorporated to enhance state representation and distributed knowledge sharing, whilst a Lagrangian-based adaptive penalty mechanism facilitates the constraint satisfaction. Simulation results have demonstrated that the proposed MM-RIS architecture and CRAFTS framework substantially improve EE and constraint satisfaction compared to the benchmarks in the open literature. Moreover, the results validate the benefits of spatially reconfigurable MM-RIS, hybrid RSMA-NOMA transmissions, and intelligent collaborative learning, highlighting the potential of the proposed framework for energy-efficient and adaptive next-generation wireless networks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34701
PDF
-
CodeMeepo: A Multi-Agent Workflow for Repository-Level Code Migration and Optimization
2026-10-25 23:15:38Farzad Habibi, Changrong Wu, Jinzhou Jiang, Guohan LuAbstract
Repository-level code migration rewrites an entire project in a new programming language while preserving its observable behavior. It is challenging because behavior spans interdependent modules, dependencies and build infrastructure must be adapted to the target ecosystem, and the source code is often the only specification. Large language model agents can now attempt these migrations end to end, but three challenges remain. First, an agent that writes both the translation and its acceptance tests may overlook the same requirements in both, leaving missing or incorrect behavior undetected. Second, large repositories can exceed a model's context window, and dividing the work into smaller tasks does not ensure that all required behavior is migrated. Third, even behaviorally correct translations may be slower than the original implementation. We present CodeMeepo, a multi-agent pipeline for complete and efficient migration of large repositories. Each milestone is evaluated against a fixed external oracle that the agents neither author nor modify. A separate parity assessment compares source and target components in scope and adds identified gaps back into the plan as required work. Ordered milestones limit the scope of each task, while cumulative regression checks guard against breaking already-migrated behavior. A benchmark-guided optimization phase addresses performance, followed by full-suite conformance testing and repair. Eight specialized agent roles communicate through file artifacts, and a deterministic state machine governs repair, deferral, scope changes, and termination. On nine subjects in three language pairs, CodeMeepo achieves the best pass rate on every subject and passes 18% more tests than a state-of-the-art multi-agent baseline using the same model. On a production daemon, its optimization phase improves half of the benchmarks, by 25% on average.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34633
PDF
-
How Much Information Can We Fit inside a Transformer?
2026-10-25 20:28:17Amirhossein Basareh, Rishabh Sanjay, Daniel de Mello, Abulhair SaparovAbstract
How efficiently can transformers store factual knowledge? The answer to this question has implications for both model design and understanding the limits of transformer-based systems. Prior studies observe a linear relationship between the number of facts memorized and the number of model parameters required, substantially worse than what theoretical analyses predict is achievable. We re-examine empirical scaling: through rigorous and systematic experiments, including extensive hyperparameter search via Bayesian optimization, we determine the smallest model that can perfectly memorize a given set of facts, and measure how this minimum size scales with the number of facts. On synthetic datasets of random, independent (subject, relation, object) triples---e.g., (Paris, capital_of, France) ---drawn at random with no exploitable structure, we find that memorization capacity, the size of the largest dataset that a model memorizes completely, grows exponentially with the transformer dimension. Equivalently, the minimum transformer dimension $d_{\min}$ required to memorize $N$ facts grows logarithmically in $N$. Across 11 dataset sizes spanning $N = 45$ to $49{,}920$, a lack-of-fit F-test does not reject the logarithmic fit (with an offset), but it does reject all other tested alternatives including power-law. Along the depth axis, however, at fixed width, the maximum memorizable dataset size grows sublinearly with the number of layers over the measured range. We further extend our exploration to structured data containing symmetric relations or two-hop composition. In this setting, we find that transformers exploit these regularities to further improve capacity. All code to reproduce our results is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34553
PDF
-
Multimodal Requirements Traceability Link Recovery in Industrial Settings
2026-10-25 19:00:49Haoming Huang, Shinpei Hayashi, Kazuya Kohata, Myeongki Kim, Yuki KuriharaAbstract
Requirements traceability links support activities such as change-impact analysis, coverage checking, and validation. Industrial requirements can include traceable images, which text-only approaches cannot process directly. For a fixed classifier configuration, binary decisions alone offer no direct way to adjust the balance between missed and incorrect links. We extend a retrieval-augmented generation (RAG) approach for inter-requirements traceability link recovery (TLR). Our extension retrieves text and image candidates separately, classifies each retrieved pair with a vision-language model, and filters the predicted links by verbalized confidence. We evaluate our approach on three non-overlapping industrial requirement sets and six public text-only datasets. On the industrial test sets, our approach achieves an F1 score of 0.310, compared with 0.114 for our replication of the baseline approach by Hey et al. Our approach recovers links in all four modality combinations while improving text-only F1 on the industrial data and maintaining similar performance on the public datasets, but recovery remains limited by failures to retrieve related text requirements for image queries. Confidence filtering produces link sets with different precision and recall, removing false positives and some correctly recovered links from the unfiltered link set. This study provides industrial evidence on the potential and limitations of a current RAG-based TLR approach for multimodal requirements and identifies cross-modal retrieval as the component to prioritize in further optimization.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34503
PDF
-
From Outranking Flow Scores to Linear Programs: Group Decision Making in PROMETHEE II
Abstract
We study inverse and consensus analysis for PROMETHEE II ranking problems when the performance table is fixed. Existing approaches in PROMETHEE-based sensitivity and consensus analysis usually focus on deviations of criteria weights while treating preference functions as fixed. Nevertheless both sets of parameters jointly determine the outranking flow scores. We introduce a linear reparametrization of the PROMETHEE II net flow scores based on weighted preference increments over the observed differences of performances. This representation yields a linear expression of the net flows and clarifies how weights and preference functions interact. Building on this result, we derive linear optimization models for three settings: minimizing weight deviations while allowing preference functions to vary; minimizing deviations over the full set of preference parameters; and multiple decision-maker consensus analysis (with objectives based either on total deviation or on the maximal individual deviation to promote fairness). An illustrative example shows that allowing preference functions to vary can dramatically change the inverse-analysis conclusions obtained from weight-only models, and that the proposed group formulations distinguish efficient consensuses from fairer ones.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34481
PDF
-
PhysCreator: Creating Physically-Attributed 3D Assets at Will
2026-10-25 17:55:06Shiyan Zheng, Ming Li, Lei Han, Xiangyu XuAbstract
Significant advancements in 3D asset creation have enabled high-fidelity 3D generation from images. However, most existing representations remain inherently static, lacking the ability to model physically plausible behaviors under dynamic interactions. We present \textbf{PhysCreator}, a unified framework that directly generates simulation-ready 3D representations with spatially varying physical properties from images. Unlike prior approaches that treat physical attributes as simple post-hoc predictions or rely on expensive per-instance optimization, we reformulate physical property estimation within a unified 3D representation learning framework. We introduce a voxel-aligned latent space by lifting image observations into a spatially structured 3D representation, in which geometry, appearance, and physical properties are jointly modeled and inferred in a feed-forward manner. To enable scalable learning without densely annotated physical ground truth, we leverage vision-language distillation to transfer material-aware semantic priors from powerful vision-language models into spatially grounded voxel-level supervision. Experiments demonstrate that our method achieves superior visual quality, physical plausibility, and generalization compared to prior approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34473
PDF
-
Improving the Chain-of-Thought Compressibility of Pruned Reasoning Models via Long--Short Contrastive Pruning
2026-10-25 14:52:21Tao Jing, Chen Kang, Feifei Zhai, Pengyuan Liu, Dong YuAbstract
Large reasoning models are costly to serve because they are large and because they generate long chains of thought (CoT). Weight pruning and CoT compression address these two costs separately, but they interfere in that pruning adds redundant reasoning on problems the model still solves and incomplete reasoning on those it no longer solves, and on harder problems makes the model less compressible by subsequent length-preference optimization. We trace this to a blind spot on each side: pruning criteria do not distinguish necessary from redundant reasoning, and preference-based CoT compression receives no training signal on problems a pruned model always or never solves. We propose Contrastive Set-Difference (CSD), which identifies neurons enriched in redundant reasoning by contrasting their activations on long and short correct solutions of the same problem and prunes them preferentially, and we extend preference pairs to the problems a pruned model always or never solves. Pruning 20\% of DeepSeek-R1-Distill-Qwen-7B, the combination uses 8--22\% fewer thinking tokens on four math benchmarks than pruning with reasoning-aware calibration (RAC) followed by the same compression, with accuracy within 0.5 points.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34336
PDF
-
CoLink: Global Compression and Knowledge Linking for Multi-Turn Dialogue Modeling
2026-10-25 14:51:19Lian Yan, Zhenbo Xia, Haotian Wang, Chen Tang, Yi Guan, Jie Liu, Jingchi JiangAbstract
Extracting salient information from long-horizon dialogue histories remains a significant challenge for Large Language Models (LLMs) due to the restricted context windows and efficient retrieval challenges. Current methods typically rely on history organization or local token-level optimization, suffering from information loss, retrieval redundancy, and myopic attention. Inspired by the view in cognitive science that dialogue constitutes sense-making and memory association, we propose CoLink, a framework that enhances LLMs' global context awareness in domain-specific multi-turn dialogues through information linking and compression. CoLink first clusters historical contexts into topic graphs to establish cross-semantic associations with external knowledge. Guided by the adaptive control of thought, it then retrieves and activates knowledge via synergizing semantic relevance and graph-structural topology. Crucially, to achieve effective compression of history and knowledge, we ground multi-turn dialogues in information theory and derive a principled optimization objective for extracting the core sense-making information. Coupled with a competitive slot mechanism, CoLink condenses the global context into dedicated memory and knowledge slots, efficiently distilling lengthy, redundant inputs into an extremely compact latent representation. Extensive empirical results on both public and our MMD datasets validate CoLink's superiority and generalizability in knowledge linking and sense modeling.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34335
PDF
-
DuQUAD: A Dual-View Framework with Quality-Aware Evidence Pruning for Multi-Document Question Answering
2026-10-25 14:14:11Yeonjun Choi, Seyeon Jeong, Jong Wook Kim, Beakcheol JangAbstract
Large language models with retrieval-augmented generation systematically underutilize evidence in the middle of multi-document contexts, a phenomenon known as Lost in the Middle. Existing mitigation strategies, such as document reordering and attention steering, can reduce boundary bias but remain brittle in noisy settings, where inaccurate relevance estimation and spurious documents still obscure useful evidence in central positions. We propose DuQUAD, a multi-document QA framework that mitigates positional bias through dual-view reasoning and quality-aware evidence pruning. DuQUAD combines a Local Agent guided by a Structural Fusion Score with a Global Agent that reasons over the full document set, providing both targeted evidence recovery and broad contextual understanding. The framework further filters candidate evidence using explicit quality scoring and refines it at the sentence level to reduce noise. DuQUAD consistently outperforms strong Lost-in-the-Middle mitigation baselines, including hybrid retrieval and reranking, multi-agent reasoning, and context optimization methods, improving accuracy by 3.0% on average over the strongest competing baseline and gold evidence recall by 9.4%, while substantially reducing computational cost compared to existing multi-agent frameworks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37701
PDF
-
MultiEvoSkill: Structure-Aware Multi-Agent Skill Evolution for Generalizable Skill Artifacts
2026-10-25 12:43:01Kounianhua Du, Jianxing Liu, Ruoshui Shan, Yucheng Zhang, Ke Li, Xing Sun, Weinan ZhangAbstract
Skill documents are becoming the default adaptation surface for frozen large language model (LLM) agents, but current skill generators face two key limitations. First, humans and different LLMs differ in how they organize procedural knowledge and approach task solving. Skills authored from a human or single-model perspective may therefore fail to align with the reasoning behaviors of other backbones, limiting cross-model generalization. Second, sequential skill descriptions inadequately represent procedures with parallel branches and explicit dependencies, while existing skill optimizers primarily operate on prose and lack explicit support for graph-structured skill evolution. We introduce MultiEvoSkill, a skill-optimization framework comprising three core components: 1) Skill compiler casts the skill as a typed graph with tailored operators, producing a compact, informative representation with explicit procedural topology; 2) Heterogeneous agent system proposes revision advices using collective intelligence, where minimal and informative issues are identified based on multiple sets of experiences. 3) Structure-aware debate and evolution mechanism organizes candidate edits into a heterogeneous graph, resolves them under dependency and importance constraints, and distills the collective proposal into the artifact. Multi-dimensional gating ensures the information gain and topological correctness of each evolution. Optimal skills are then obtained when the system converges at a consistent state. Various experiments and ablations against SOTA methods validate the effectiveness and generalization of MultiEvoSkill.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34260
PDF
-
ParetoGS: High-Quality Continuous-Budget 3D Gaussian Splatting with Sparse Adapted Anchors
2026-10-25 12:05:18Xiaobin Deng, Changyu Diao, Min Li, Duanqing XuAbstract
Scalable 3D Gaussian Splatting allows one scene representation to serve different Gaussian-count budgets, yet its quality-budget curve may lag behind models optimized separately for each budget. Reducing the number of Gaussians changes both the selected members and the reconstruction tasks carried by the survivors; parameters inherited from a high-budget model may fit a low-budget representation poorly. We propose ParetoGS, which describes member changes and parameter evolution with a small set of adapted budget anchors and decodes intermediate budgets without separate optimization at every requested count. ParetoGS alternates pruning and fixed-member adaptation to build nested anchors with persistent identities, and encodes their parameter changes relative to the full model in a compact residual atlas. At decoding, it interpolates the states of shared members and gradually introduces the rendering contributions of new members, connecting sparse anchors into a continuous-budget representation. Across 13 scenes, ParetoGS attains better average PSNR, SSIM, and LPIPS with fewer Gaussians than the compared prefix methods at 10% of each method's own full model. From a shared full model, it also outperforms FlexGS-imp at its trained 1%, 5%, and 10% budgets and NanoGS-imp at the 1% and 0.1% budgets. On Garden, its non-anchor quality approaches an empirical reference from independently optimized GNS models at higher retention ratios and exceeds it at some lower-budget points. Across 13 scenes, encoding reduces mean additional state from 390.0 to 85.7 MB with an average PSNR change of 0.01 dB. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.34235
PDF
-
CropReward: A Human-Preference Benchmark and Reward Model for Aesthetic Image Cropping
2026-10-25 11:22:47Xiangfei Sheng, Xiaofeng Pan, Leida Li, Qian Zhang, Biao Wang, Johan Wagemans, Weisi LinAbstract
Aesthetic image cropping (AIC) aims to improve image composition and aesthetic quality by removing extraneous or distracting content. Over the past decade, AIC methods have evolved from specialized vision models to multimodal large language models(MLLMs). Reliable evaluation that reflects human preferences is essential for benchmarking AIC methods and guiding model optimization. However, the current AIC evaluation relies largely on geometry-based metrics such as intersection over union (IoU), as well as image aesthetic assessment(IAA) models. Although inconsistencies with human preferences have long been observed, the robustness and reliability of these evaluation criteria remain underexplored. To bridge this gap, we first construct CropBench, a large-scale benchmark comprising 106,995 human preference pairs for 1,019 images, with each candidate set containing the original image and candidate crops produced by 14 AIC methods. A systematic study on CropBench reveals that the existing criteria, ranging from IoU to off-the-shelf IAA assessment models, only exhibit limited alignment with human preferences. Building upon CropBench, we further propose CropReward, an MLLM-based reward model that evaluates a candidate crop by comparing with the original uncropped image and outputs a score indicating explicit aesthetic improvement or degradation relative to the original. In addition, we employ CropReward to construct CropReward-300k, the largest AIC dataset to date, and further develop CropAlign, a preference-aligned AIC model trained solely with CropReward supervision, without human-annotated crop boxes. Experimental results demonstrate that CropReward aligns with human preferences significantly better than existing criteria. CropAlign also surpasses the state-of-the-art AIC methods, demonstrating the advantage of CropReward in guiding AIC model optimization.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34221
PDF
-
StaX-Net: Stackelberg Interleaved Asymmetric Network for Cross-Modality Medical Image Translation
Abstract
Cross-modality medical image translation is challenged by anatomically inconsistent synthesis that can compromise clinical diagnosis. We propose StaX-Net, a Stackelberg interleaved asymmetric network that incorporates a partially coupled encoder-discriminator structure, and a 2D feature aggregation and spatial transformation (FAST) layer that distills target-supervised priors under the learning using privileged information paradigm. The shared blocks between the generator and discriminator enhance architectural feature alignment. To stabilize the leader-follower training, a Stackelberg-inspired asymmetric optimization scheme employs explicit shared-parameter freezing and asymmetric learning rates. The FAST layer distills target-domain priors during training and applies a source-only transform at inference. This constrains the synthesis process through target-informed feature representations relative to standard generative architectures. The code is available on GitHub for public use.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34214
PDF
-
CORMA: Constraint-Routed Decision Mamba for Generalizable Multi-Constraint Offline Safe Reinforcement Learning
2026-10-25 10:54:34Changxu Ni, Feiran You, Yongan Guo, Hongyang Du, Kang Wei, Le Liang, Yiyang Ni, Jun LiAbstract
Offline safe reinforcement learning (RL) learns safety-aware policies from static datasets while satisfying safety constraints during deployment. Motivated by the strong trajectorymodeling capabilities of Transformers, recent Decision Transformer (DT)-based methods formulate offline safe RL as conditional sequence modeling by conditioning action generation on return-to-go (RTG) and cost-to-go (CTG) tokens, thereby enabling adaptation to varying safety budgets. However, existing DT-based methods are developed for single-constraint tasks. For tasks with multiple constraints, generalizing learned policies to unseen combinations of safety budgets remains challenging due to the conflicting requirements imposed by heterogeneous constraints. Moreover, the quadratic complexity of Transformer architectures significantly increases the computational overhead in multi-constraint tasks, as representing additional constraints requires more CTG tokens. Recently, Mamba has emerged as an efficient sequence-modeling backbone, offering linear computational complexity and strong generalization capabilities. In this paper, we propose CORMA, a constraint-routed decision Mamba framework for generalizable multi-constraint offline safe RL. CORMA decomposes policy inference into constraint-aware RTG estimation and adaptive action generation, where constraint-specific experts model feasible RTG distributions and a router-guided product-of-experts mechanism fuses these distributions to provide safety-aware guidance for a Mamba-based action decoder. A three-stage optimization strategy is designed to improve training stability. Extensive experiments on OSRL benchmarks demonstrate that CORMA achieves superior reward-safety trade-offs, reduces inference latency by 37% compared with DT-based methods, and exhibits stronger zero-shot generalization to unseen safety-budget combinations than offline safe RL baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34208
PDF
