Showing 1–50 of 4,907 results for author: Zhou, H

Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization

Authors: Qian Kou, Xiaofeng Shi, Xiaosong Qiu, Hua Zhou

Abstract: Large language models often fail to answer questions about a bounded document collection when the source documents are not retrieved at inference time. We study this setting as document knowledge internalization: converting a fixed corpus into usable parametric knowledge for retrieval-free question answering. We propose IAR (Inject, Align, and Recover), a three-stage post-training framework that s… ▽ More Large language models often fail to answer questions about a bounded document collection when the source documents are not retrieved at inference time. We study this setting as document knowledge internalization: converting a fixed corpus into usable parametric knowledge for retrieval-free question answering. We propose IAR (Inject, Align, and Recover), a three-stage post-training framework that separates structured document knowledge injection, QA behavior alignment, and general ability recovery. Unlike conventional continued pretraining, Inject converts source documents into continuation, rewrite, and instruction-conditioned reconstruction objectives. Align then adapts the injected model with answer-only QA supervision, while Recover merges the domain-adapted model with the base instruction model to recover general capabilities. Across Common Corpus (CC) and CCI, and across Llama, Phi, Qwen, and SmolLM model families, IAR improves the domain-primary domain-general frontier for retrieval-free document internalization. In the main comparison, IAR improves over Vanilla SFT on all four reported metrics in 7 of 8 dataset-model settings, with average gains of 3.6 percentage points in domain QA accuracy and 12.1 percentage points in mean general performance across IFEval, MMLU, and MSBench. Extended CC baselines show that LoRA and FAPM can win individual general metrics, but among methods that also reach leading or near-leading domain internalization, IAR retains one of the strongest general profiles. △ Less

Submitted 20 August, 2026; originally announced August 2026.

Comments: 21 pages, 4 figures. Includes Supplementary Material Sections A--G. Qian Kou and Xiaofeng Shi contributed equally and are co-corresponding authors. Hua Zhou is the project leader

Bringing analytic rigor to agentic AI for science: The Brain Researcher platform for neuroimaging data analysis

Authors: Zijiao Chen, Nicholas Lu, Xinhui Li, Jocelyn A. Ricard, Ce Ju, Huan H. Wang, Christian Kindermann, Jeanette A. Mumford, Steven Dillmann, James Kent, Alejandro de la Vega, Sanmi Koyejo, Vince D. Calhoun, Joshua W. Buckholtz, Juan Helen Zhou, Steffen Bollmann, Russell A. Poldrack

Abstract: AI agents can execute scientific analyses, but an analytic output becomes a defensible claim only after alternatives are weighed and the claim is limited to what the evidence supports. Agents may reproduce failures including selective analysis, premature declarations of success and optimization of imperfect criteria. We present Brain Researcher, an agentic research harness operating in a neuroimag… ▽ More AI agents can execute scientific analyses, but an analytic output becomes a defensible claim only after alternatives are weighed and the claim is limited to what the evidence supports. Agents may reproduce failures including selective analysis, premature declarations of success and optimization of imperfect criteria. We present Brain Researcher, an agentic research harness operating in a neuroimaging researcher's computational environment under rules for admissible analyses, required checks and claim scope. In benchmarks, Brain Researcher increased first-choice tool-selection accuracy across seven models by 70.2 percentage points (23.3% without it versus 93.6% with it) and verifiable grounding from 4.6% to 22.0%. In collaborator-led and self-evolving studies, multiverse analyses exposed analytic-choice sensitivity, and scientific review classified claims as accepted, qualified, revised, blocked, rejected or deferred. By linking decisions to evidence and provenance, Brain Researcher embeds methodological judgment within the workflow, not after it. △ Less

Submitted 20 August, 2026; originally announced August 2026.

Comments: 103 pages, 19 figures; Supplementary Information included

Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models

Authors: Yuanhao Ban, Jiaqi Feng, Hengguang Zhou, Xiaohuan Pei, Justin Cui, Cho-Jui Hsieh

Abstract: Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry and dynamics of a coherent world: long rollouts accumulate geometric drift and degrade into static or unnatural motion. Recent bidirectional approaches address this problem using rewards signals built upon 3D Gaussian-Spla… ▽ More Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry and dynamics of a coherent world: long rollouts accumulate geometric drift and degrade into static or unnatural motion. Recent bidirectional approaches address this problem using rewards signals built upon 3D Gaussian-Splatting reconstruction. However, a single rigid 3d reconstruction cannot model a dynamic scene, so this critic penalizes genuine object motion as reconstruction error and is maximized by freezing the video. This shortcut is especially detrimental in the AR setting, where each chunk can propagate an already-static configuration. In this work, we propose Stream4D, which replaces the static critic with a feed-forward 4D reconstruction reward that explicitly models scene dynamics, allowing coherent motion to receive high consistency rewards. To further guide motion magnitude and quality, we add a motion prior that rewards natural scene-flow magnitude while penalizing jitter and non-rigid artifacts. Our final recipe combines these two terms with a lightweight perceptual anchor. Across various autoregressive video backbones and various generation horizons, Stream4D improves 4D reconstruction quality, preserves motion more effectively, and achieves higher human-aligned preference. Project page: https://banyuanhao.github.io/Stream4D/ △ Less

Submitted 19 August, 2026; originally announced August 2026.

Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation

Authors: Huan-ang Gao, Haohan Chi, Yong Yan, Shiyuan Feng, Hanlin Wu, Zheng Jiang, Bingxiang He, Wei-Ying Ma, Ya-Qin Zhang, Hao Zhou

Abstract: Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized reinforcement learning (RL) experts into a single generalist student via dense, token-level reward supervision. Despite its practical success, the optimization dynamics governing multi-teacher capability integration remain poorly understood, and open, rigorously reproducible recipe… ▽ More Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized reinforcement learning (RL) experts into a single generalist student via dense, token-level reward supervision. Despite its practical success, the optimization dynamics governing multi-teacher capability integration remain poorly understood, and open, rigorously reproducible recipes are conspicuously lacking. In this work, we establish a controlled M-OPD benchmark on SmolLM3-3B-Base with oracle routing, isolating capability integration from routing ambiguity. Our investigation reveals a pronounced capability integration gap: standard M-OPD captures only 35.6% of the available headroom relative to a domain-routed oracle ensemble, with concise tasks such as instruction following suffering severe degradation and premature stagnation. Crucially, we show that this failure stems not from gradient conflict, but from a severe misallocation of the token-level optimization budget. This pathology is driven by three orthogonal factors: structural sequence-length disparities across domains, dynamic convergence drift due to non-uniform learning rates, and multi-step reward staleness from asynchronous policy updates. To resolve these imbalances, we introduce Open-MOPD, a principled framework incorporating token-share balancing, gap-aware dynamic budget allocation, and student reward refresh. Together, these mechanisms systematically restore cross-domain balance, elevating headroom recovery from 35.6% to 83.4% in a single deployable student. We fully open-source our end-to-end post-training recipe, training trajectories, and evaluation suites on an academically accessible hardware budget. △ Less

Submitted 19 August, 2026; originally announced August 2026.

Comments: Project page: https://bytedtsinghua-sia.github.io/Open-MOPD/

Sampling isometric tensor network states with monitored quantum circuits

Authors: Yuqing Rong, Huan-Hai Zhou, Guo-Yi Zhu, Jinguo Liu

Abstract: Projected entangled pair states (PEPS) provide an efficient variational ansatz for two-dimensional quantum phases, but computing observables remains challenging because PEPS contraction is generally costly. Here, we parameterize two-dimensional quantum states using variational PEPS subject to isometric constraints and map the resulting ansatz onto monitored quantum circuits, replacing tensor-net… ▽ More Projected entangled pair states (PEPS) provide an efficient variational ansatz for two-dimensional quantum phases, but computing observables remains challenging because PEPS contraction is generally costly. Here, we parameterize two-dimensional quantum states using variational PEPS subject to isometric constraints and map the resulting ansatz onto monitored quantum circuits, replacing tensor-network contraction with circuit sampling. For infinite cylinders, the transfer matrix defines a quantum channel on the virtual boundary. We use a fixed-point treatment and a monitored-circuit unraveling of this channel to evaluate observables efficiently. Using a constant number of variational parameters and a number of qubits that scales only with the cylinder width, our method yields a phase diagram for the $J_1$-$J_2$ model in qualitative agreement with DMRG results. Because the monitored circuits are compatible with near-term quantum hardware, this approach provides a hybrid quantum-classical framework for simulating two-dimensional quantum many-body systems. △ Less

Submitted 18 August, 2026; originally announced August 2026.

Comments: 20 pages, 12 figures

UniVerse: Benchmarking and Enhancing LALMs on Culturally Inclusive Low-Resource Music Understanding

Authors: Ziya Zhou, Shangda Wu, Shenyang Xu, Yutong Zheng, Dafang Liang, Suin Chung, Danbinaerin Han, Junyan Jiang, Yongyi Zang, Ruibin Yuan, Rongxiu Zhong, Shilei Zhang, Junlan Feng, Jinglei Liu, Haotian Zhou, Zijin Li, Dasaem Jeong, Wei Xue, Yike Guo

Abstract: Recent advances in large audio-language models (LALMs) have significantly improved performance in tasks such as music captioning, genre classification, and sound event detection. However, limited attention has been paid to improving their adaptability across diverse musical traditions, particularly folk music rooted in distinct cultural contexts. Folk-music traditions are typically resource-scarce… ▽ More Recent advances in large audio-language models (LALMs) have significantly improved performance in tasks such as music captioning, genre classification, and sound event detection. However, limited attention has been paid to improving their adaptability across diverse musical traditions, particularly folk music rooted in distinct cultural contexts. Folk-music traditions are typically resource-scarce, unevenly represented across regions, and poorly documented. Even when such samples appear in large-scale pre-training, LALMs often fail to capture their structural and stylistic characteristics, partly due to the absence of dedicated evaluation protocols and training solutions. To address these limitations, we introduce UniVerse, a reproducible solution for low-resource music understanding. Specifically, we propose UniVerseBench, a benchmark of 5,042 Q&A pairs across more than 38 cultural and linguistic entities, constructed via an expert-guided yet highly automated pipeline. In parallel, we construct a fully automated, model-generated multi-turn dialogue training dataset UniVerseSet. By training LALMs on UniVerseSet, we systematically adapt and investigate representative multimodal imbalance learning strategies across both dense and Mixture-of-Experts (MoE) architectures. Experimental results indicate that fully automated data curation combined with imbalance-aware training yields non-trivial improvements, but models still struggle to capture fine-grained acoustic features, indicating a gap between surface-level alignment and deep musical comprehension. △ Less

Submitted 18 August, 2026; originally announced August 2026.

Comments: 21 pages, 7 figures, 8 tables

StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows

Authors: Liya Zhu, Xin Ma, Tao Liu, Haodong Wang, Ge Zhang, Jingzhe Ding, Qingshui Gu, Yongjie Zhong, Jinxiang Meng, Yuan Gao, Yunqiu Zhou, Hao Zhu, Jifeng He, Yongzhi Liao, Xinyi Zhang, Chaoxin Li, Yi Zhu, Xi Lin, Duju Zeng, Xiang Gao, Wen Zhang, Yunyang Wang, Duo Wang, Huan Zhou, Zuo Wang , et al. (13 additional authors not shown)

Abstract: Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely rely on researcher-selected tasks, leaving uncertain whether such progress extends to the work that real-world users actually demand from AI systems. We introduce \textbf{StartupBench}, an E2E agent benchmark grounded in market-va… ▽ More Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely rely on researcher-selected tasks, leaving uncertain whether such progress extends to the work that real-world users actually demand from AI systems. We introduce \textbf{StartupBench}, an E2E agent benchmark grounded in market-validated AI startup products. Rather than defining tasks from pre-defined assumptions about useful agent capabilities, we systematically study AI products with demonstrated adoption, together with their product workflows and users, to identify real-world tasks for which AI has established practical demand across diverse professional domains. We translate these workflows into complete deliverable-oriented tasks and evaluate them with fine-grained rubrics capturing their complex requirements. Across representative models evaluated under a unified agent harness, even the strongest model successfully completes only approximately 30\% of StartupBench, despite making substantial partial progress on many tasks. Further analysis identifies aspects like complex instruction following and domain-specific expertise as major sources of failure. Our results reveal that many market-validated workflows remain beyond the reliable capabilities of current general-purpose agents, establishing StartupBench as an empirical measure of progress toward E2E completions of real-world user tasks. △ Less

Submitted 18 August, 2026; originally announced August 2026.

Spontaneous symmetry-breaking in equilibrium tree-packing configurations of a kinetically constrained cubic-lattice system

Authors: Hai-Jun Zhou

Abstract: We explore kinetic-constraint induced thermodynamic phase transition in the cubic lattice, employing the Fredrikson-Anderson spin model with hyperparameter $K=2$ as a representative kinetic system. Each lattice site may flip its binary occupation state if at most one of its six nearest neighbors is currently occupied. The whole set of microscopic configurations that are kinetically connected with… ▽ More We explore kinetic-constraint induced thermodynamic phase transition in the cubic lattice, employing the Fredrikson-Anderson spin model with hyperparameter $K=2$ as a representative kinetic system. Each lattice site may flip its binary occupation state if at most one of its six nearest neighbors is currently occupied. The whole set of microscopic configurations that are kinetically connected with the fully empty one is described by an equilibrium partition function with a single global constraint, that is, the occupied sites do not form closed loops but instead organize into different tree components in the lattice. We discover a continuous thermodynamic gas--crystal phase transition in the cubic system and determine the critical chemical potential $μ^* \approx -3.252$, at which the occupied sites of the equilibrium tree-packing configurations start to prefer one of the two nested cubic sublattices. This thermodynamic phase transition is absent in the two-dimensional square lattice. △ Less

Submitted 17 August, 2026; originally announced August 2026.

Comments: 15 pages, 3 figures

First measurements of the branching fractions of $J/ψ$ and $ψ(3686) \to Σ^{0} \barΣ^{0}η$

Authors: BESIII Collaboration, M. Ablikim, M. N. Achasov, P. Adlarson, X. C. Ai, C. S. Akondi, R. Aliberti, A. Amoroso, Q. An, Y. H. An, Y. Bai, O. Bakina, H. R. Bao, X. L. Bao, M. Barbagiovanni, V. Batozskaya, K. Begzsuren, N. Berger, M. Berlowski, M. B. Bertani, D. Bettoni, F. Bianchi, E. Bianco, A. Bortone, I. Boyko , et al. (750 additional authors not shown)

Abstract: Based on $(10087 \pm 44) \times 10^6$ $J/ψ$ and $(2712 \pm 14) \times 10^6$ $ψ(3686)$ events collected with the BESIII detector at the BEPCII collider, the hadronic decays $J/ψ\to Σ^{0} \barΣ^{0} η$ and $ψ(3686) \to Σ^{0} \barΣ^{0} η$ are observed for the first time. The corresponding branching fractions are measured to be… ▽ More Based on $(10087 \pm 44) \times 10^6$ $J/ψ$ and $(2712 \pm 14) \times 10^6$ $ψ(3686)$ events collected with the BESIII detector at the BEPCII collider, the hadronic decays $J/ψ\to Σ^{0} \barΣ^{0} η$ and $ψ(3686) \to Σ^{0} \barΣ^{0} η$ are observed for the first time. The corresponding branching fractions are measured to be $\mathcal{B}(J/ψ\to Σ^{0} \barΣ^{0}η)= (7.5 \pm 0.3 \pm 0.8) \times 10^{-5}$ and $\mathcal{B}(ψ(3686) \to Σ^{0} \barΣ^{0}η)= (1.3\pm 0.1 \pm 0.1) \times 10^{-5}$, respectively, where the first uncertainties are statistical, and the second systematic. The ratio $\text{Q} \approx \frac{\mathcal{B}(ψ(3686) \to Σ^{0} \barΣ^{0} η)}{\mathcal{B}(J/ψ\to Σ^{0} \barΣ^{0} η)}$ is determined to be $(17.3 \pm 1.5 \pm 1.7)\%$, which is con sistent with the 12\%-rule within 3.0$σ$.~No significant intermediate states or threshold enhancements are observed in the $Σ^0$($\barΣ^{0}$)$η$ and $Σ^0$$\barΣ^{0}$ invariant mass spectra. △ Less

Submitted 17 August, 2026; originally announced August 2026.

Measurement of Branching Fraction and Transition Magnetic Moment of the Hyperon Dalitz Decay $Σ^0 \rightarrow Λe^+e^-$

Authors: BESIII Collaboration, M. Ablikim, M. N. Achasov, P. Adlarson, X. C. Ai, R. Aliberti, A. Amoroso, Q. An, Y. Bai, O. Bakina, Y. Ban, H. -R. Bao, V. Batozskaya, K. Begzsuren, N. Berger, M. Berlowski, M. B. Bertani, D. Bettoni, F. Bianchi, E. Bianco, A. Bortone, I. Boyko, R. A. Briere, A. Brueggemann, H. Cai , et al. (683 additional authors not shown)

Abstract: Based on a data sample of 10 billion $J/ψ$ events collected with the BESIII detector operating at the BEPCII collider, the Dalitz decay $Σ^0 \rightarrow Λe^+e^-$ is studied experimentally for the first time. The $Σ^0$ hyperons are produced through the process $J/ψ\rightarrow Σ^0\barΣ^0$ and analyzed using a double-tag method. The absolute branching fraction is measured to be… ▽ More Based on a data sample of 10 billion $J/ψ$ events collected with the BESIII detector operating at the BEPCII collider, the Dalitz decay $Σ^0 \rightarrow Λe^+e^-$ is studied experimentally for the first time. The $Σ^0$ hyperons are produced through the process $J/ψ\rightarrow Σ^0\barΣ^0$ and analyzed using a double-tag method. The absolute branching fraction is measured to be $\mathcal{B}(Σ^0 \rightarrow Λe^+e^-) = (6.34 \pm 0.25_{\rm stat.} \pm 0.23_{\rm syst.}) \times 10^{-3}$. This result shows a $2σ$ discrepancy from the theoretical calculation quoted in the PDG, where the uncertainties are statistical and systematic, respectively. In addition to the branching fraction, the transition magnetic moment $μ$ is determined to be $(1.74 \pm 0.03_{\rm stat.} \pm 0.09_{\rm syst.})\,μ_N$, where $μ_N=e/(2m_p)$ represents the nucleon magnetic moment, providing valuable insight into the intrinsic structure of the $Σ^0$ hyperon. △ Less

Submitted 17 August, 2026; originally announced August 2026.

Comments: 10 pages, 3 figures; supplemental material included

Retrieval-guided Twin Fusion with Similarity-aware Contrast for Molecule-Text Alignment

Authors: Shunshun Gu, Shengqi Qiu, Hang Zhou, Xiao Luo

Abstract: This paper studies the problem of molecule-text alignment, which aims to project molecules and their textual descriptions into a joint latent space for downstream tasks including molecule search and molecular property prediction. Previous approaches typically combine graph structure mining with contrastive learning to enhance joint representation learning. However, they typically neglect fine-grai… ▽ More This paper studies the problem of molecule-text alignment, which aims to project molecules and their textual descriptions into a joint latent space for downstream tasks including molecule search and molecular property prediction. Previous approaches typically combine graph structure mining with contrastive learning to enhance joint representation learning. However, they typically neglect fine-grained semantic relationships between substructures and texts, leading to suboptimal performance on downstream tasks. Towards this end, we propose a novel approach named Retrieval-guided Twin Fusion with Similarity-aware Contrast (RISEN) for molecule-text alignment. The core idea of RISEN is to construct a latent twin molecule for each substructure with cross-modal retrieval for semantic enhancement. In particular, for each substructure query, we retrieve relevant textual descriptions and sample several molecules that share similar descriptions of substructures. Then, we aggregate their representations via attention pooling for a twin latent representation, which would be further fused with the original substructure for representation enrichment. In addition, we measure the similarity across substructures and texts, which would further guide cross-modal contrastive learning with soft thresholding. Extensive experiments on benchmark datasets validate the superiority of the proposed RISEN in comparison with existing baselines. △ Less

Submitted 16 August, 2026; originally announced August 2026.

Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search

Authors: Zhongwei Yu, Yan Song, Xue Yan, Anjie Liu, Xingyu Lu, Yihang Chen, Huichi Zhou, Siyuan Guo, Luoyang Sun, Sihan Chen, Xiangning Yu, Jun Wang

Abstract: Scientific discovery often involves optimising expensive-to-evaluate objectives over vast, structured, and open-ended hypothesis spaces, such as molecules, protein sequences, and computer programs. Generative models such as large language models (LLMs) provide expressive priors over such spaces, but their likelihoods and self-assessments are unreliable proxies for the objectives and calibrated epi… ▽ More Scientific discovery often involves optimising expensive-to-evaluate objectives over vast, structured, and open-ended hypothesis spaces, such as molecules, protein sequences, and computer programs. Generative models such as large language models (LLMs) provide expressive priors over such spaces, but their likelihoods and self-assessments are unreliable proxies for the objectives and calibrated epistemic uncertainty, especially for novel candidates outside the observed data distribution. We introduce the Large Discovery Model (LDM), an empirically grounded recurrent architecture that couples a generative model with a Bayesian non-parametric reward surrogate model. The generative model proposes and refines candidate designs, while the surrogate predicts their performance and quantifies uncertainty, yielding an uncertainty-aware value that guides candidate generation, refinement, and selection. The discovery memory and the surrogate model are continually updated as each new experimental observation arrives. We evaluate LDM on three scenarios spanning different design modalities and objectives, including neural-network training, antibody design, and molecular optimisation. Compared to LLM-only reflection or traditional statistical search across these domains, LDM achieves a $2.4\times$ greater reduction in validation BPB, an $18.2\%$ relative decrease in binding energy, and more than $60\%$ relative gains in molecular multi-objective performance. These results suggests that LDM could serve as a general-purpose discovery engine for effective search over open-ended hypothesis spaces. △ Less

Submitted 16 August, 2026; originally announced August 2026.

FedADB: Class Anchor-Driven Dual-Branch Federated Learning for Mitigating Forgetting

Authors: Zhenyan Liu, Hua Zhang, Haoran Gao, Qi Li, Hongliang Zhu, Huiyu Zhou, Zongliang Shen, Yanxin Xu, Jiahui Wang

Abstract: Multimodal data collected by heterogeneous devices are used for collaborative training, where federated learning (FL) serves as a key paradigm for effective distributed modeling with data privacy preservation. However, local training suffers from the forgetting of previously learned global knowledge under cross-client data heterogeneity, which leads to significant declines in both performance and… ▽ More Multimodal data collected by heterogeneous devices are used for collaborative training, where federated learning (FL) serves as a key paradigm for effective distributed modeling with data privacy preservation. However, local training suffers from the forgetting of previously learned global knowledge under cross-client data heterogeneity, which leads to significant declines in both performance and convergence speed. Most previous studies rely on global alignment strategies to retain global knowledge, which hinder local optimization and lead to inadequate supervision of missing classes. Some studies introduce proxy datasets to supplement supervision for missing classes. However, it remains a challenge to balance class-wise global consistency and local optimization objectives without proxy datasets. In this work, we propose FedADB, a Class Anchor-Driven Dual-Branch FL framework. Specifically, the server generates class anchors optimized in a differentiable input space, which are shared across clients. These class anchors serve as global references that provide supervision for missing classes during local training. A dual-branch collaborative training mechanism is designed for clients. In this mechanism, the anchor-based global branch focuses on learning with global consistency, achieving global knowledge alignment by class-anchor balanced sampling. The local calibration branch focuses on learning discriminative local features, mitigating the degradation of local representations caused by excessive global alignment. Extensive experiments across multiple medical and natural datasets demonstrate that FedADB achieves significant improvements in both accuracy and convergence speed. △ Less

Submitted 15 August, 2026; originally announced August 2026.

Comments: Accepted to appear in Proceedings of the 34th ACM International Conference on Multimedia (MM '26)

LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset

Authors: Yousef Emami, Mohammadhossein Homaei, Hao Zhou, Miguel Gutiérrez Gaitán, Atefeh Hajijamali Arani, Rui Zhang

Abstract: Uncrewed aerial vehicles (UAVs) are increasingly deployed for autonomous navigation in complex outdoor environments, where dynamic conditions and mission requirements require intelligent adaptive decision-making. Existing optimization-based, Machine Learning (ML), and Reinforcement Learning (RL) approaches often rely on predefined models or task-specific training, limiting their generalization and… ▽ More Uncrewed aerial vehicles (UAVs) are increasingly deployed for autonomous navigation in complex outdoor environments, where dynamic conditions and mission requirements require intelligent adaptive decision-making. Existing optimization-based, Machine Learning (ML), and Reinforcement Learning (RL) approaches often rely on predefined models or task-specific training, limiting their generalization and adaptability in uncertain scenarios. Recent Large Language Model (LLM)-assisted approaches offer promising reasoning capabilities but remain constrained by limited agentic functionality, including insufficient memory, planning, and tool interaction mechanisms.This paper proposes an LLM-Agent-Based Path Finder (LAPF) framework for autonomous UAV navigation in town-scale outdoor environments. LAPF extends LLM-assisted navigation by integrating perception, memory, planning, and action modules into a closed-loop cognitive architecture. The proposed agent leverages prior navigation experiences, performs Chain-of-Thought (CoT) reasoning, couples each detected hazard to a bounded corrective action, and dynamically refines waypoint decisions based on environmental feedback.The three independent trials per method demonstrate that LAPF achieves mean path lengths of 512.83 m and 506.37 m, compared to the straight-line optimum of 497.33 m, corresponding to path length reductions of 17.2% and 15.6% relative to CoT prompting and absolute path efficiencies of 97.1% and 98.1% in open-field and obstacle-injected scenarios, respectively. Furthermore, LAPF is the only evaluated approach that couples every detected hazard to a bounded, metric-neutral corrective action while maintaining near-goal stability, with zero clamp events in both scenarios, whereas CoT prompting increases from 9.7 to 14.0 events. △ Less

Submitted 15 August, 2026; originally announced August 2026.

Comments: 15 pages

MSC Class: 53-01 ACM Class: C.2

PACE: Phase-Progress-Aware Credit for Long-Horizon Embodied Manipulation

Authors: Chengye Song, Jiawei Zhang, Rui Song, Shengqi Wang, Xiangrong Zhang, Ziyi Wang, Huanbin Zhou, Hongzhou Wang

Abstract: Post-training of vision-language-action (VLA) models typically relies on expert demonstrations and policy interaction trajectories. However, in long-horizon manipulation, a single episode often spans hundreds of control steps and multiple phases, while success or failure is only revealed at episode termination. Policy improvement therefore requires step-level credit signals to distinguish behavior… ▽ More Post-training of vision-language-action (VLA) models typically relies on expert demonstrations and policy interaction trajectories. However, in long-horizon manipulation, a single episode often spans hundreds of control steps and multiple phases, while success or failure is only revealed at episode termination. Policy improvement therefore requires step-level credit signals to distinguish behaviors that advance the task from those that stall or regress. We present PACE, a credit-assignment framework for post-training on long-horizon manipulation, centered on a phase-progress-aware critic. PACE consists of two key modules: (1) the Global-Local Cooperative Value-Correction Critic (GLC-Critic) aggregates visual and motion-difference features within local temporal windows to infer the phase and intra-phase progress of each step, and applies residual correction to a discretized remaining-cost distribution accordingly, enabling step-level credit assignment; (2) Progressive Policy Distillation (PPD) converts credit into positive and negative conditions via task-wise thresholds and trains a credit-conditioned action generation policy: it first protects the pretrained policy with high-credit positive samples, then incorporates all positive and negative credits to learn the quality boundary, and at inference amplifies high-credit behaviors through the difference between conditional outputs. Extensive simulation experiments and diverse real-world robotic-arm experiments demonstrate that PACE consistently achieves significant improvements over the strongest baseline. △ Less

Submitted 15 August, 2026; originally announced August 2026.

Comments: 9 pages, 6 figures

Envs-FORGE: Frontier-Optimized Reward-Grounded Environment Synthesis for Agent RL

Authors: Xiaojun Wu, Cehao Yang, Honghao Liu, Xueyuan Lin, Zhichao Shi, Hao Zhou, Xuhui Jiang, Chengjin Xu, Jia Li, Jian Guo

Abstract: Reinforcement learning (RL) for terminal agents needs executable training environments with reliable rewards and useful difficulty. Fixed recipes such as few-shot, Self-Instruct, and Evol-Instruct apply the same prompting policy to every seed, even when the current policy would benefit from a harder, easier, or simply different task. We present Envs-FORGE, a prompting policy that converts verifier… ▽ More Reinforcement learning (RL) for terminal agents needs executable training environments with reliable rewards and useful difficulty. Fixed recipes such as few-shot, Self-Instruct, and Evol-Instruct apply the same prompting policy to every seed, even when the current policy would benefit from a harder, easier, or simply different task. We present Envs-FORGE, a prompting policy that converts verifier rewards into per-seed environment-synthesis actions. Envs-FORGE estimates seed pass rates, scores six projection--direction actions around a target learning frontier, and solves a per-seed mixed-integer linear program (MILP) to choose the action that conditions generation. The selected action drives synchronized rewriting of the instruction, fixtures, oracle solution, tests, and Docker environment; only gold-verified bundles enter RL training. The indexed MILP form also supports optional soft skill coverage for portfolio planning. On Qwen 3.5 35B, Envs-FORGE improves Pass@1 over Base by 9.2 percentage points on tb-core (40.0% to 49.2%) and 6.4 points on tb-2.0 (23.0% to 29.4%), exceeding the strongest fixed-recipe baseline by 2.4 and 2.1 points. It reaches 77.1% on SWE-bench Verified versus 73.4% for Base, and improves tb-core by 6.8--9.2 points across the evaluated 4B--35B models. All synthesis methods export 100 verified environments and use 2.27M--2.88M synthesis tokens, placing the comparison at the same downstream training-set size and the same operational scale. The source code is available at https://github.com/DataArcTech/DataArc-SynData-Toolkit/. △ Less

Submitted 14 August, 2026; originally announced August 2026.

Comments: 19 pages, 5 figures

Change-Point Detection for Heterogeneous High-Dimensional Functional Time Series

Authors: Xufei Tang, Dan Zhuang, Houlin Zhou

Abstract: High-dimensional functional panels consist of temporally ordered curves observed across many subjects and naturally exhibit heterogeneous structural changes. Under sparse subject-level break signals or opposite-signed shifts, traditional mean-aggregated CUSUM procedures may suffer noticeable power loss due to signal attenuation or cancellation induced by cross-sectional averaging. We propose a nov… ▽ More High-dimensional functional panels consist of temporally ordered curves observed across many subjects and naturally exhibit heterogeneous structural changes. Under sparse subject-level break signals or opposite-signed shifts, traditional mean-aggregated CUSUM procedures may suffer noticeable power loss due to signal attenuation or cancellation induced by cross-sectional averaging. We propose a novel Energy--PE statistic, which combines subject-wise squared CUSUM energy aggregation with a generalized power-enhancement component. The energy aggregation preserves subject-level evidence under sign-heterogeneous changes, while the power-enhancement component improves sensitivity to sparse weak break signals. Under regularity conditions, we establish the asymptotic behavior of the proposed statistic. We further incorporate a latent group structure and an information-criterion-based clustering algorithm to estimate the unknown group number and membership for heterogeneous break points. Numerical studies and an intraday stock application demonstrate that Energy--PE controls size, improves power under sparse and sign-heterogeneous alternatives, and yields interpretable post-test summaries. △ Less

Submitted 13 August, 2026; originally announced August 2026.

On the Structure of $(\min,+)$ Convolution

Authors: Huanyi Zhou

Abstract: The $(\min,+)$ convolution is a central problem in fine-grained complexity, and whether it admits a truly subquadratic algorithm remains open. We study it through tropical polynomials, where $(\min,+)$ convolution is exactly polynomial multiplication. We introduce tropical decomposition width, a parameter measuring how finely a tropical polynomial can be decomposed into low-degree factors. We pr… ▽ More The $(\min,+)$ convolution is a central problem in fine-grained complexity, and whether it admits a truly subquadratic algorithm remains open. We study it through tropical polynomials, where $(\min,+)$ convolution is exactly polynomial multiplication. We introduce tropical decomposition width, a parameter measuring how finely a tropical polynomial can be decomposed into low-degree factors. We prove modular convexity theorems showing that bounded tropical decomposition width forces strong convexity on arithmetic subpolynomials. This yields deterministic algorithms for computing $a\otimes b$ in $O(n\max(\operatorname{tdw}(a),\operatorname{tdw}(b))^2)$ time when the width is given, and in $O(ne^{\min(\operatorname{tdw}(a),\operatorname{tdw}(b))(1+o(1))})$ time otherwise, without requiring a decomposition. For Multiple-Sequence $(\min,+)$ Convolution, we give a randomized algorithm running in $O(kn^2\sqrt{\min(k,n)}\log^{1.5}(kn))$ time for $k$ sequences of length at most $n$, improving the natural $O(k^2n^2)$ bound. We also obtain conditional lower bounds, a faster single-entry algorithm, and new upper bounds for Multiple-Choice Knapsack. Finally, bounded-decomposition-width classes admit interpolation algebras of finite generating rank, whereas distinguishing all tropical polynomials of degree at most $n$ requires rank exactly $\lfloor n/2\rfloor+1$. We further show that tropical decomposition width cannot decrease under any flat $\mathbb T$-algebra extension. These results connect efficient tropical multiplication with structural rigidity. △ Less

Submitted 13 August, 2026; originally announced August 2026.

Comments: 52 pages, 0 figures

MSC Class: 16Y60; 15A80; 68W40; 68Q17; 68Q25; 68R05; 90C24; 90C27 ACM Class: F.1.3; F.2.2; G.2.1; G.3

High-precision measurement of the space-like $η^\prime$ transition form factor

Authors: BESIII Collaboration, M. Ablikim, M. N. Achasov, P. Adlarson, X. C. Ai, C. S. Akondi, R. Aliberti, A. Amoroso, Q. An, Y. H. An, M. S. Anderson, Y. Bai, O. Bakina, H. R. Bao, X. L. Bao, M. Barbagiovanni, V. Batozskaya, K. Begzsuren, N. Berger, M. Berlowski, M. B. Bertani, D. Bettoni, F. Bianchi, E. Bianco, A. Bortone , et al. (758 additional authors not shown)

Abstract: Using a data sample corresponding to an integrated luminosity of $20.3\ \text{fb}^{-1}$, collected with the BESIII detector at a center-of-mass energy of $3.773\ \text{GeV}$ at the BEPCII collider, we report a precision measurement of the product $Q^2|F(Q^2)|$, where $F(Q^2)$ is the single-virtual space-like transition form factor of the $η'$ meson and $Q^2$ is the squared momentum transfer of the… ▽ More Using a data sample corresponding to an integrated luminosity of $20.3\ \text{fb}^{-1}$, collected with the BESIII detector at a center-of-mass energy of $3.773\ \text{GeV}$ at the BEPCII collider, we report a precision measurement of the product $Q^2|F(Q^2)|$, where $F(Q^2)$ is the single-virtual space-like transition form factor of the $η'$ meson and $Q^2$ is the squared momentum transfer of the tagged virtual photon. The transition form factor is extracted from the differential Born cross section of the two-photon fusion processes $e^+e^- \to e^+e^-γγ^* \to e^+e^-η^\prime$ using a single-tag technique, where only one scattered lepton is detected. The measurement covers $Q^2 \in [0.1, 6.0]$ GeV$^2$, achieving unprecedented precision, better than $3.0\%$ for $Q^2 < 1.5$ GeV$^2$, and providing the first direct determination at $Q^2 < 0.3$ GeV$^2$. △ Less

Submitted 12 August, 2026; originally announced August 2026.

Alignment Drift in Single-Model Speculative Decoding for ASR: Mechanism, Correction, and Cost

Authors: Xinyu Wang, Huapeng Zhou, Ziyu Zhao, Silin Meng, Ke Bai, Dongming Shen, Xiao-Wen Chang, Alex Smola

Abstract: Speculative decoding speeds up generation by letting a cheap draft propose several tokens that a target model checks in one pass. In the single-model form, the draft is a lightweight module attached to the target rather than a separate model. Applying this design to Automatic Speech Recognition (ASR) introduces an extra problem. The draft can read the whole audio at every step, yet its proposals g… ▽ More Speculative decoding speeds up generation by letting a cheap draft propose several tokens that a target model checks in one pass. In the single-model form, the draft is a lightweight module attached to the target rather than a separate model. Applying this design to Automatic Speech Recognition (ASR) introduces an extra problem. The draft can read the whole audio at every step, yet its proposals get worse as it runs on its own. Access is not localization. The accepted text keeps the transcript position explicit, but the draft must also track the changing audio position. In the primary matched comparison, per-step audio access changes the first proposal modestly but roughly doubles later-proposal acceptance. Fixed-width windows show that the audio position explains part of this gap. A correctly placed window recovers continuation, while an equally narrow window at the wrong position reduces it. Late-draft median error reaches 21 frames in the hardest reported condition, while target attention during verification stays within a 2-frame median. We test two ways to reduce this drift. The first reads the audio position from verification attention and uses it to guide the next draft round. It saves time only when the extra accepted tokens offset the readout cost. The second is AnchorDraft, which teaches the draft to track the audio position during training without changing the inference graph. The trained draft improves end-to-end speed at both tested target scales. These results show that ASR self-speculation depends on token prediction, audio-position tracking, and draft cost. △ Less

Submitted 12 August, 2026; originally announced August 2026.

LIGO A$^\sharp$: Detector Design and Science Prospects Beyond A+

Authors: L. Sun, K. Kuns, B. J. J. Slagmolen, P. Fritschel, P. Schmidt, B. T. Lantz, S. S. Y. Chua, Divyajyoti, S. W. Ballmer, M. A. Barton, A. V. Cumming, K. L. Dooley, J. C. Driggers, A. Effler, M. Evans, B. Farr, G. González, N. Lu, D. J. Ottaway, C. Palomba, O. J. Piccinni, G. Pratten, S. Raja, A. P. Subhash, P. J. Sutton , et al. (1131 additional authors not shown)

Abstract: We present the LIGO A$^\sharp$ detector concept, an upgrade for the LIGO observatories based on room-temperature interferometers beyond the fifth observing run (O5). Building on the A+ sensitivity, A$^\sharp$ targets broadband sensitivity improvements through heavier test masses, improved suspensions and seismic isolation, increased arm-cavity power, enhanced frequency-dependent squeezing, reduced… ▽ More We present the LIGO A$^\sharp$ detector concept, an upgrade for the LIGO observatories based on room-temperature interferometers beyond the fifth observing run (O5). Building on the A+ sensitivity, A$^\sharp$ targets broadband sensitivity improvements through heavier test masses, improved suspensions and seismic isolation, increased arm-cavity power, enhanced frequency-dependent squeezing, reduced coating thermal noise considering two scenarios, and improved control of mechanical motion and optical modes. We describe the principal design choices, projected noise performance, and corresponding astrophysical prospects. LIGO A$^\sharp$ substantially increases compact-binary detection rates, strengthens population inference, and improves both early-warning times and localization for binary neutron star mergers. The improved sensitivity enables more detailed studies of compact-binary coalescences, including higher-order multipoles, intermediate-mass black holes, remnant black hole ringdown, and the neutron star equation of state. It also broadens the discovery potential for new gravitational-wave sources such as continuous waves and bursts, should enable detection of the stochastic background from compact binary mergers if it remains undetected after O5, and strengthens the role of gravitational-wave detectors as probes of fundamental physics. We discuss key technical challenges and the role of A$^\sharp$ as both a major scientific upgrade for the 2030s and a technology pathfinder for next-generation gravitational-wave observatories, such as Cosmic Explorer. △ Less

Submitted 12 August, 2026; originally announced August 2026.

Comments: 78 pages, 22 figures

Report number: LIGO-P2600307

Constraints on ultralight bosons from merging binary and remnant black holes observed during the second and third parts of the fourth LIGO-Virgo-KAGRA observing run

Authors: The LIGO Scientific Collaboration, the Virgo Collaboration, the KAGRA Collaboration, A. G. Abac, A. Abe, I. Abouelfettouh, F. Acernese, K. Ackley, A. Adam, S. Adhicary, D. Adhikari, R. X. Adhikari, V. K. Adkins, S. Afroz, A. Agapito, D. Agarwal, M. Agathos, N. Aggarwal, S. Aggarwal, O. D. Aguiar, I. -L. Ahrend, L. Aiello, A. Ain, P. Ajith, T. Akutsu , et al. (1786 additional authors not shown)

Abstract: We present constraints on ultralight bosons using binary black hole mergers observed in the second and third parts of the fourth LIGO-Virgo-KAGRA observing run. Directed searches are conducted for long-transient gravitational waves from ultralight vector boson clouds around merger remnants, using a hidden-Markov-model (HMM) tracking scheme. We target the remnant black holes formed in the binary co… ▽ More We present constraints on ultralight bosons using binary black hole mergers observed in the second and third parts of the fourth LIGO-Virgo-KAGRA observing run. Directed searches are conducted for long-transient gravitational waves from ultralight vector boson clouds around merger remnants, using a hidden-Markov-model (HMM) tracking scheme. We target the remnant black holes formed in the binary coalescences that produced GW250114 and GW250207. We find no evidence for such signals from either target. Estimating our search sensitivity at a threshold corresponding to a 1% false alarm probability, we thus disfavor vector boson masses in the range of $[2.80, 3.95]\times 10^{-13}$ eV with greater than 90% confidence. In addition, we derive constraints on ultralight scalar and vector bosons from the inferred high spins of the constituent black holes in three binaries, using events GW240515, GW241113, and GW241225_08. The excluded mass ranges in this approach depend on the assumed black-hole ages. At $10^5$ years, corresponding to typical dynamically formed binaries, we exclude scalar and vector bosons in the ranges $[1.39, 6.94]\times 10^{-13}$ eV and $[0.32, 14.4]\times 10^{-13}$ eV at 90% confidence, respectively. △ Less

Submitted 11 August, 2026; originally announced August 2026.

Comments: 27 pages (12 pages author list, 15 pages main paper), 5 figures

Report number: LIGO-P2600218

An emerging baryon cycle in a galaxy 500 million years after the Big Bang

Authors: Shengzhe Wang, Xin Wang, Hang Zhou, Zhijie Qu, Zhaozhou Li, Yuxuan Pang, Qianqiao Zhou, Shouyi Wang, Yangyao Chen, Yuguang Chen, Karl Glazebrook, Glenn G. Kacprzak, Nicha Leethochawalit, Houjun Mo, Themiya Nanayakkara, Huiyuan Wang, Weida Hu, Xunda Sun, Chao-Wei Tsai, Hu Zhan

Abstract: The emergence of stellar feedback as a regulator of galaxy growth marks a fundamental transition in cosmic history. At early times, rapid gas accretion and collapse may induce intense star formation before feedback becomes effective, producing feedback-free starbursts. When and how such bursts subsequently develop into self-regulated baryon cycles remain observationally unknown. Here we show that… ▽ More The emergence of stellar feedback as a regulator of galaxy growth marks a fundamental transition in cosmic history. At early times, rapid gas accretion and collapse may induce intense star formation before feedback becomes effective, producing feedback-free starbursts. When and how such bursts subsequently develop into self-regulated baryon cycles remain observationally unknown. Here we show that Gz9p3, a merging galaxy at $z=9.311$, is caught in this transition only 500 million years after the Big Bang. Deep JWST spectroscopy reveals a substantial neutral-gas reservoir along its merger-driven tidal structure and a multiphase outflow. Fine-structure absorption provides the first direct measurement of the electron density of the cool outflowing gas at high redshift ($\approx\,17\,{\rm cm^{-3}}$), yielding a mass-loading factor among the highest yet measured for galaxies of comparable stellar mass. The emergence of such efficient feedback after an intense burst is consistent with the delayed onset of feedback expected in feedback-free starburst models. The cool outflowing gas is unlikely to escape the host halo, implying that much of this metal-enriched material may remain available for future recycling through the circumgalactic medium. Gz9p3 therefore provides an early view of a baryon cycle being established through the interplay of merger-driven gas redistribution, bursty star formation and stellar feedback, suggesting that feedback-regulated recycling was already shaping galaxy growth during the epoch of reionization. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Comments: submitted

MSP-Net: Manifold-Guided Spectral Prompt Network for Hyperspectral Object Tracking

Authors: Juliu Li, Hanlin Qin, Shuowen Yang, Jingjing Li, Yuedong Tan, Shuai Yuan, Huixin Zhou

Abstract: Hyperspectral object tracking leverages abundant spectral information to provide unique advantages for target discrimination in complex scenes. However, existing methods typically treat hyperspectral images as multi-channel extensions of RGB images, performing feature fusion in fixed band order. This approach leads to models dependent on specific sensor configurations while neglecting manifold rel… ▽ More Hyperspectral object tracking leverages abundant spectral information to provide unique advantages for target discrimination in complex scenes. However, existing methods typically treat hyperspectral images as multi-channel extensions of RGB images, performing feature fusion in fixed band order. This approach leads to models dependent on specific sensor configurations while neglecting manifold relationships between bands, making generalization to heterogeneous sensors difficult. Moreover, the discriminative contribution of bands dynamically changes with target attributes and scene variations, further limiting the representational capacity of static fusion strategies. To address this, we propose the Manifold-Guided Spectral Prompt Network (MSP-Net). This network first reconstructs band relationships and forms adaptive spectral grouping through graph-driven manifold routing, then jointly integrates grouped spectral statistics with template appearance to construct target-related dynamic conditional prompts, enhancing target features while suppressing background interference. Furthermore, as tracking progresses, spectral conditions continuously evolve based on intermediate target representations, enabling target prompts to adapt in real-time to appearance and scene changes. Meanwhile, reliable historical states are used to constrain target localization and scale fluctuations, significantly improving temporal stability in cross-sensor tracking. Experiments on HOT2020 and HOT2023 demonstrate that MSP-Net achieves AUC and Precision exceeding 0.80 and 0.96, respectively, exhibiting exceptional robustness under heterogeneous sensors, target deformation, and complex background conditions. The code will be released at https://github.com/GGML668897/MSP-Net. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Rethink Before You Execute: Adaptive Execution for World Action Models

Authors: Feng Ye, Yiming Zhao, Yong Yu, Hongxu Zhou, Yong Pan, Yuan Xue, Peng Jia, Chuanmin Jia

Abstract: World Action Models (WAMs) jointly predict future actions and the evolution of the environment. At each inference, a WAM generates a chunk of actions and the robot executes a fixed prefix before replanning. We argue that this fixed execution horizon is poorly matched to execution dynamics: the chunk reliability varies across task stages, so when to replan depends on the result of accumulated execu… ▽ More World Action Models (WAMs) jointly predict future actions and the evolution of the environment. At each inference, a WAM generates a chunk of actions and the robot executes a fixed prefix before replanning. We argue that this fixed execution horizon is poorly matched to execution dynamics: the chunk reliability varies across task stages, so when to replan depends on the result of accumulated execution, not on the step counts. We propose TempoWAM (Timing Execution by Monitoring Progress Online), a lightweight plug-and-play execution scheme for WAMs. A Recurrent Progress Monitor first estimates task progress from the current observation, task instruction, remaining actions, and execution history; and an Adaptive Execution Protocol then evaluates whether the chunk is advancing the task to decide if replanning is needed. To bridge the training-deployment gap, the protocol is calibrated by a task-dependent calibration factor with online adaptation. Experiments on LIBERO, RoboTwin, and real-world tasks show that TempoWAM consistently improves the efficiency-success trade-off of WAM execution. On real robots, it reduces WAM inferences by 26.9% on easy tasks while maintaining success, and improves success by 13.3 points on difficult tasks. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Holographic multipartite entanglement dynamics in AdS$_3$-Vaidya

Authors: Xin-Xiang Ju, Ya-Wen Sun, Yang Zhao, Hao-Ran Zhou

Abstract: We study how multipartite entanglement is dynamically reorganized during holographic thermalization following a global quench in AdS$_3$/CFT$_2$. We first use the $n$-partite information $(-1)^n I_n$ to probe collective multipartite entanglement in holographic configurations where the full $n$-region entanglement wedge is connected while all fewer-party ones are disconnected, thereby excluding few… ▽ More We study how multipartite entanglement is dynamically reorganized during holographic thermalization following a global quench in AdS$_3$/CFT$_2$. We first use the $n$-partite information $(-1)^n I_n$ to probe collective multipartite entanglement in holographic configurations where the full $n$-region entanglement wedge is connected while all fewer-party ones are disconnected, thereby excluding fewer-party contributions. The spatial range of multipartite entanglement first expands and then contracts as the system approaches its late-time locally thermal state. Entanglement involving different numbers of parties develops on comparable early-time scales, while the entanglement that involves more parties relaxes more slowly, revealing a transient propagation from shorter to longer spatial distances. We further compute the Markov gap and the genuine tripartite multi-entropy as complementary probes of tripartite entanglement. The Markov gap can remain enhanced after local thermalization, whereas the genuine tripartite multi-entropy undergoes a nonmonotonic evolution and returns to its vacuum value for the adjacent tripartition considered in this work. These results show that a global quench redistributes the entanglement across spatial scales and reorganizes its multipartite structure. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Comments: 41 pages, 10 figures

Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution

Authors: Bohan Lin, Hejia Geng, Xinyi Xie, Heng Zhou, Qinghua Xing, Bo Liu, Chen Zhang, Yudong Zhang

Abstract: Skill-based LLM agents select reusable procedures from an external library to solve complex tasks, yet their routing decisions rely entirely on text-level signals such as task descriptions, verbal reflections, and experience-derived rules, while the model's own internal representational state remains unobserved. Recent interpretability work has shown that LLMs maintain linear emotion representatio… ▽ More Skill-based LLM agents select reusable procedures from an external library to solve complex tasks, yet their routing decisions rely entirely on text-level signals such as task descriptions, verbal reflections, and experience-derived rules, while the model's own internal representational state remains unobserved. Recent interpretability work has shown that LLMs maintain linear emotion representations that causally influence behavior; however, these representations have been exploited only for post-hoc analysis or direct output steering, and have not been used to inform agent-level decision-making. We propose Emotion2Skill, a framework that extracts LLM-internal emotion vectors and incorporates them into both skill selection and skill evolution. At each decision step, a 27-dimensional emotion state is extracted from the residual stream and mapped to a confidence-gated summary injected into the routing prompt. Beyond online selection, emotion trajectories are analyzed for abrupt internal-state shifts to pinpoint problematic skill invocations, guiding targeted SOP rewriting that replaces the coarse binary outcome signal of prior methods. On WebShop and ALFWorld, Emotion2Skill with Qwen3-8B improves over the Zero-Shot baseline by +26.9% success rate and +25.5% average success respectively, outperforming all baselines on both benchmarks with consistent gains on Qwen3-14B. Co-activation analysis further reveals semantically coherent emotion--skill pairings, confirming that the routing improvements reflect meaningful internal-state signals rather than opaque statistical correlations. These results establish LLM-internal emotion representations as an effective decision-level signal for orchestrating agent skill systems, extending their utility beyond interpretability and output steering. The code is available at https://github.com/BoHan-LIN04/Emotion2Skill. △ Less

Submitted 10 August, 2026; v1 submitted 10 August, 2026; originally announced August 2026.

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation

Authors: Yuhan Li, Fangao Zeng, Sicong Kang, Mengfei Xu, Hao Zhou, Wei Li, Pipei Huang, Bingbing Ni

Abstract: Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We instead take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate… ▽ More Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We instead take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide a natural source of distillation supervision rather than a disposable byproduct of sampling. Based on this insight, we propose REST (Reward-Enhanced Scored-Trajectory Distillation), a single-stage RL-distillation co-training framework that attaches a decoupled student to an arbitrary RL teacher. The student learns segment-wise from the teacher's evolving rollout trajectories while leaving the original teacher optimization unchanged. To prevent uniform imitation from preserving undesirable low-reward behaviors, we further introduce Advantage-Modulated Distillation (AMD), which transforms rollout advantages into signed weights over a base distillation loss. AMD strengthens supervision from preferred trajectories and mildly repels the student from low-reward ones. The resulting framework is lightweight and plug-and-play, requires no extra image rollouts, no separate distillation dataset, and no adversarial training. Experiments on compositional generation, visual text rendering, and human-preference alignment show that REST enables few-step CFG-free inference that matches or surpasses its 40-step RL teacher, with an overall additional training cost below 25% over pure RL. REST improves DrawBench PickScore over RTDMD by 0.82 while requiring only one-fifth of the training iterations. △ Less

Submitted 10 August, 2026; originally announced August 2026.

UniMoFlow: Grounding Instruction-Driven 3D Human Motion Editing in Generation

Authors: Yilei Hua, Beibei Jing, Ce Zheng, Hanyu Zhou, Yawei Luo, Wei Yang

Abstract: Instruction-driven editing of 3D human motion requires precise spatiotemporal localization, rich semantic grounding, and strict preservation of unmodified content. Existing methods either resort to training-free adaptation of generative models or rely solely on triplet supervision; however, adaptation often yields suboptimal control, and manually curated triplet datasets remain severely limited in… ▽ More Instruction-driven editing of 3D human motion requires precise spatiotemporal localization, rich semantic grounding, and strict preservation of unmodified content. Existing methods either resort to training-free adaptation of generative models or rely solely on triplet supervision; however, adaptation often yields suboptimal control, and manually curated triplet datasets remain severely limited in scale and semantic diversity. To overcome this bottleneck, we ground motion editing directly within text-to-motion generation across data, architecture, and inference. At the data level, we develop a closed-loop synthesis-and-verification pipeline that produces Omni-MoEdit, a large-scale dataset spanning body-part, amplitude, temporal, action, and style edits. At the architectural level, we introduce UniMoFlow, a unified latent flow-matching model that shares broad semantic and kinematic knowledge between generation and editing. At the inference level, SAFE (Source-Anchored Flow Editing) complements UniMoFlow with controllable, source-anchored refinement. Furthermore, we augment standard evaluations with semantics-aware metrics to account for valid edits that inherently deviate from a single ground-truth reference. Extensive experiments demonstrate improved target-text alignment, edit effectiveness, and cycle consistency, while maintaining competitive source fidelity and text-to-motion generation quality. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Comments: 18 pages, including supplementary material; 8 figures and 7 tables. Code: https://github.com/Yilei-Hua/UniMoFlow. Submitted to AAAI 2027

Evo-Bench: Can Language Models Improve Agent Harness?

Authors: Lisheng Huang, Chen Yang, Hao Zhou, Huatong Song, Zongchao Chen, Ran Le, Yang Song, Wayne Xin Zhao, Tao Zhang

Abstract: Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolution---the agent's capacity to autonomously optimize its own operating harness. However, systematically benchmarking this capability remains challenging, as existing evaluations fail to isolate harness improvements from… ▽ More Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolution---the agent's capacity to autonomously optimize its own operating harness. However, systematically benchmarking this capability remains challenging, as existing evaluations fail to isolate harness improvements from base model strength, prevent task-specific overfitting, or capture long-horizon iterative research. To address these challenges, we introduce Evo-Bench, the first benchmark designed to evaluate models' intrinsic harness-evolving capabilities across Search, Office, and General agent domains. To rigorously isolate this capability, Evo-Bench employs a novel harness-guided construction framework: it leverages auxiliary-task evolution to identify tasks genuinely sensitive to framework improvements, followed by sensitivity-aware stratified splitting to ensure robust cross-suite generalization. Extensive evaluations across nine frontier and open-weight models reveal that top models achieve massive absolute gains reaching 16.6 points, closely approaching state-of-the-art human-engineered baselines. Crucially, while autonomous evolution outpeforms artificial harness in General tasks and excels in Search tasks, it struggles in Office tasks that demand highly specific processing workflows. Furthermore, our analysis exposes critical temporal anomalies like early saturation, while demonstrating that the synthesized harnesses act as highly transferable reasoning structures, consistently boosting diverse policy models. △ Less

Submitted 10 August, 2026; v1 submitted 9 August, 2026; originally announced August 2026.

LatticeMind: A Conflict-Aware Memory Primitive for Multi-Agent Systems

Authors: Heng Zhou, Lian Zhang, Yutao Fan, Tiancheng He, Siki Chen, Hejia Geng, Philip Torr, Zhenfei Yin

Abstract: Multi-agent LLM systems often fail not for lack of candidate answers, but because they have no persistent mechanism for deciding which incompatible claim should currently be trusted. Majority vote, debate, and judge-based selection choose an output without recording which claim wins, which is contested, or why a later update supersedes it. We present \term{LatticeMind}, a conflict-aware structured… ▽ More Multi-agent LLM systems often fail not for lack of candidate answers, but because they have no persistent mechanism for deciding which incompatible claim should currently be trusted. Majority vote, debate, and judge-based selection choose an output without recording which claim wins, which is contested, or why a later update supersedes it. We present \term{LatticeMind}, a conflict-aware structured memory that handles contradiction at write time. It maintains explicit item status, applies cheap symbolic conflict checks, and invokes LLM reconciliation only for unresolved semantic cases. On a label-blind ConflictBank evaluation that removes source-name hints, LatticeMind reaches 0.97 accuracy versus 0.61 for the strongest aggregation baseline, with the gap significant at $p<10^{-6}$ by paired McNemar test. Ablations show that removing the checker or the reconciler costs 12 to 14 points. On four secondary planning benchmarks the picture is mixed: LatticeMind beats naive merge on three of four, but does not replace deliberation methods on tasks rewarding iterative search. △ Less

Submitted 8 August, 2026; originally announced August 2026.

Anisotropic Particle Transport from a Pulsar Wind Nebula Revealed by Einstein Probe and LHAASO

Authors: Zhen Cao, F. Aharonian, Y. X. Bai, Y. W. Bao, D. Bastieri, X. J. Bi, Y. J. Bi, W. Bian, J. Blunier, A. V. Bukevich, C. M. Cai, W. Y. Cao, Zhe Cao, J. Chang, J. F. Chang, E. S. Chen, G. H. Chen, H. K. Chen, L. F. Chen, Liang Chen, Long Chen, M. J. Chen, M. L. Chen, Q. H. Chen, S. Chen , et al. (320 additional authors not shown)

Abstract: Pulsar wind nebulae (PWNe) are major cosmic ray accelerators, yet the mechanisms transporting high-energy particles into the interstellar medium remain elusive. Building on the LHAASO discovery of an ultra-high-energy (UHE) $γ$-ray source near the bow-shock PWN powered by the pulsar PSR J1740+1000, we present a joint Einstein Probe (EP) and LHAASO study of this system. EP observations reveal an ex… ▽ More Pulsar wind nebulae (PWNe) are major cosmic ray accelerators, yet the mechanisms transporting high-energy particles into the interstellar medium remain elusive. Building on the LHAASO discovery of an ultra-high-energy (UHE) $γ$-ray source near the bow-shock PWN powered by the pulsar PSR J1740+1000, we present a joint Einstein Probe (EP) and LHAASO study of this system. EP observations reveal an extended X-ray tail far exceeding the structure previously seen by XMM-Newton. Updated LHAASO observations show that the $γ$-ray emission is elongated, with its major axis aligned with the extended X-ray tail revealed by EP. This is the first detection of an X-ray pulsar tail associated with a spatially coincident extended UHE $γ$-ray emission. The X-ray and $γ$-ray spectrum can be well explained with a single population of relativistic electrons via synchrotron and inverse Compton radiation, respectively, removing the need for particle re-acceleration during propagation. The results unambiguously show that electrons/positrons above 100 TeV are escaping from the PWN. Instead of the immediate, isotropic diffusion into ambient interstellar medium that is typically assumed, these particles are transported anisotropically over at least $\sim$10 pc, either guided by the background magnetic field or carried by an advective outflow. △ Less

Submitted 7 August, 2026; originally announced August 2026.

Comments: Accepted by Science China Physics, Mechanics, and Astronomy. Main text: 9 pages, 4 figures, 1 table; Supplementary Materials: 7 pages, 2 figures, 4 tables

Debiased Machine Learning for Partially Linear Accelerated Failure Time Models

Authors: Tomoki Okuno, Sijie Zheng, Brendon Chau, Gang Li, Jin Zhou, Hua Zhou

Abstract: The Cox model remains the default for survival analysis, but the proportional hazards assumption is often violated and hazard ratios can be difficult to interpret. Accelerated failure time (AFT) models provide an intuitive time-scale alternative, yet flexible covariate adjustment while preserving valid inference on a target exposure remains challenging. For the partially linear AFT model under rig… ▽ More The Cox model remains the default for survival analysis, but the proportional hazards assumption is often violated and hazard ratios can be difficult to interpret. Accelerated failure time (AFT) models provide an intuitive time-scale alternative, yet flexible covariate adjustment while preserving valid inference on a target exposure remains challenging. For the partially linear AFT model under right censoring, a rank-based debiased machine learning (DML) framework remains undeveloped: the rank-based pairwise moment is not Neyman orthogonal and standard cross-fitting does not directly apply to U-statistics. We develop the first such framework by combining an orthogonalized rank-based U-statistic, a censoring-corrected influence function, and block-pairwise cross-fitting, yielding valid inference under flexible nuisance estimation. Simulations and an application to All of Us electronic health record data demonstrate finite-sample performance and practical utility. △ Less

Submitted 7 August, 2026; originally announced August 2026.

Comments: 57 pages, 3 figures, including supplementary material

MISO: Model-Internal-State-Guided Optimization for Ranking Models

Authors: Yongzhe Zhang, Xiaoyu Deng, Yifan He, Mengying Sun, Sheng Luo, Yijia Liu, Hao Yan, Zhuo Li, Huiping Yao, Swathi Hrishikesh, Jing Chen, Dennis Choi, Steven Liu, Zhiwen Chen, Yang Jin, Haoyu Zhou, Lexi Luo, Keyi Chen, Anish Khazane, Marcio Porto, Xiaoya Wang, Emmy Wang, Kangfu Zheng, Xingyuan Wang, Peggy Yao , et al. (6 additional authors not shown)

Abstract: Ranking models are repeatedly refined within established model families, yet the choice of which component to scale, replace, or retire is often guided by expensive trial-and-error. We present Model Internal State Optimization (MISO), a systems workflow that uses model internal states (MIS), including parameters, activations, gradients, and normalization statistics, to prioritize such local optimi… ▽ More Ranking models are repeatedly refined within established model families, yet the choice of which component to scale, replace, or retire is often guided by expensive trial-and-error. We present Model Internal State Optimization (MISO), a systems workflow that uses model internal states (MIS), including parameters, activations, gradients, and normalization statistics, to prioritize such local optimization decisions. MISO extracts MIS from a trained ranking model, aggregates them into ranking, alignment, and comparison signals, and converts those signals into a small set of interpretable candidate edits. Because MIS are re-extracted after each retraining cycle, MISO naturally supports an adaptive optimization workflow that tracks evolving model behavior as data distributions and system requirements shift over time. In an ads ranking case study, MISO improves normalized entropy while requiring substantially fewer validation runs than expert-driven and black-box scaling workflows, offering a practical middle ground between manual tuning and opaque automated search. △ Less

Submitted 16 August, 2026; v1 submitted 7 August, 2026; originally announced August 2026.

Comments: Accepted at the OARS Workshop at ACM RecSys 2026

CellWorld: From Gene-Level Reconstruction to Latent Cell Prediction in Spatial Transcriptomics Foundation Models

Authors: Haiping Liu, Qian Zhao, Lijing Lin, Jingyuan Sun, Hongpeng Zhou

Abstract: This paper shows that latent-space predictive pretraining can provide a scalable route to foundation models for spatial transcriptomics. Existing spatial transcriptomics foundation models primarily reconstruct masked gene identities or expression values, potentially encouraging the reproduction of assay-specific technical variation and limiting representation transferability. To avoid directly rec… ▽ More This paper shows that latent-space predictive pretraining can provide a scalable route to foundation models for spatial transcriptomics. Existing spatial transcriptomics foundation models primarily reconstruct masked gene identities or expression values, potentially encouraging the reproduction of assay-specific technical variation and limiting representation transferability. To avoid directly reconstructing such variation, we shift the prediction target from observed gene measurements to latent cell representations and introduce CellWorld, which predicts the latent representations of masked cells from visible spatial context and a limited partial-expression hint. We pretrain four CellWorld variants, spanning 5.74M to 94.56M trainable parameters, on a corpus of 46 million human cells. Our controlled scaling experiments show that performance improves with model capacity, particularly on spatial tasks, while spatial transfer depends more on sufficient optimization and broad biological source diversity than on cell count alone. Across four held-out datasets, even CellWorld-Small, with 5.74M trainable parameters, outperforms every baseline on all 11 linear-probe benchmarks and all seven fine-tuned spatial benchmarks. Most notably, a frozen CellWorld-Large pretrained on only 5\% of the corpus with broad biological source coverage outperforms every fully fine-tuned baseline across all seven spatial benchmarks. Code is available at https://github.com/UoM-HealthAI/CellWorld. △ Less

Submitted 6 August, 2026; originally announced August 2026.

Multimodal Drivers' Emotion Recognition and Safety-Oriented Intervention for Intelligent Transportation Systems

Authors: Chang Liu, Dalai Mengke, Hanbo Zhou, Jia Hu, Peter Mihajlik, Tamas Sziranyi

Abstract: Driver emotions can affect risk perception, decision-making, and vehicle control under complex road conditions. Existing studies mainly focus on driver emotion recognition, while limited attention has been given to context-aware intervention that jointly considers driver emotion and road perception. This paper proposes a safety-prioritized multimodal driver assistance framework that analyzes speec… ▽ More Driver emotions can affect risk perception, decision-making, and vehicle control under complex road conditions. Existing studies mainly focus on driver emotion recognition, while limited attention has been given to context-aware intervention that jointly considers driver emotion and road perception. This paper proposes a safety-prioritized multimodal driver assistance framework that analyzes speech-derived emotional cues and visual road conditions to generate structured driving interventions. The framework first provides road safety reminders and then generates emotion-aligned verbal support. We construct a multimodal dataset by aligning emotional speech signals with structured road environment descriptors and introduce the CARE (Context-Aware Road-Emotion Evaluation) score to jointly evaluate emotion recognition, risk identification, and intervention generation. Experimental results show that the proposed framework balances environmental risk reporting and emotion-aware verbal regulation, providing a feasible safety-driven direction for intelligent transportation systems. △ Less

Submitted 5 June, 2026; originally announced August 2026.

Comments: 6 pages, 2 figures, IEEE ITSC 2026

Confidence matters: Leveraging Multi-view Geometric Priors for GS-based Reconstruction

Authors: Hongyu Zhou, Zorah Lähner

Abstract: 3D Gaussian splatting (3DGS) has emerged as a widely-used tool for novel view synthesis, offering real-time rendering in a sparse representation. However, the method's reliance on structure-from-motion initialization and photometric optimization can lead to suboptimal geometric reconstruction, particularly for objects with high specularity. In this work, we investigate the integration of geometric… ▽ More 3D Gaussian splatting (3DGS) has emerged as a widely-used tool for novel view synthesis, offering real-time rendering in a sparse representation. However, the method's reliance on structure-from-motion initialization and photometric optimization can lead to suboptimal geometric reconstruction, particularly for objects with high specularity. In this work, we investigate the integration of geometric priors, in the form of predicted normal and depth maps, into the 3DGS framework to improve the reconstruction quality. We analyze the effect of incorporating these priors into GS-based methods and our evaluation reveals that multi-view predictions, as they are done by the recent visual geometry grounded transformer (VGGT), outperform single-view alternatives. A major factor is the existence of a confidence map for the estimations, which comes as a by-product of multi-view models and which can significantly improve the effectiveness of priors by weighting each prediction appropriately. Extensive experiments on standard benchmarks show consistent improvement in reconstruction quality and significant gains in complex scenes including specular objects. △ Less

Submitted 6 August, 2026; originally announced August 2026.

Search for the charged lepton flavour violating decay $η'\to eμ$

Authors: BESIII Collaboration, M. Ablikim, M. N. Achasov, P. Adlarson, X. C. Ai, C. S. Akondi, R. Aliberti, A. Amoroso, Q. An, Y. H. An, M. S. Anderson, Y. Bai, O. Bakina, H. R. Bao, X. L. Bao, M. Barbagiovanni, V. Batozskaya, K. Begzsuren, N. Berger, M. Berlowski, M. B. Bertani, D. Bettoni, F. Bianchi, E. Bianco, A. Bortone , et al. (744 additional authors not shown)

Abstract: Based on $(8998\pm40)\times10^6$ $J/ψ$ events collected in $e^+e^-$ collisions at $\sqrt{s} = 3.097$ GeV with the BESIII detector, we present a search for the charged lepton flavour violating decay $η'\to eμ$ with $J/ψ\toγη'$. No significant signal is observed, and an upper limit on its decay branching fraction is set to be $6.3\times10^{-7}$ at the 90% confidence level, improving the previous bes… ▽ More Based on $(8998\pm40)\times10^6$ $J/ψ$ events collected in $e^+e^-$ collisions at $\sqrt{s} = 3.097$ GeV with the BESIII detector, we present a search for the charged lepton flavour violating decay $η'\to eμ$ with $J/ψ\toγη'$. No significant signal is observed, and an upper limit on its decay branching fraction is set to be $6.3\times10^{-7}$ at the 90% confidence level, improving the previous best result by nearly three orders of magnitude. △ Less

Submitted 6 August, 2026; originally announced August 2026.

Comments: 20 pages, 5 figures, 3 tables

Toward Blockage-Resilient 6G-V2X Connectivity: Semi-Distributed Bandit with Dynamic Arm Set for mmWave HetNets

Authors: Weiqi Chi, Bo Qian, Hanlin Wu, Donghui Li, Haibo Zhou, Manabu Tsukada

Abstract: The vision for 6G vehicle-to-everything (V2X) communications demands reliable, adaptive connectivity for fully autonomous driving across complex dynamic environments. Millimeter-wave (mmWave) user association (UA) in heterogeneous vehicular networks presents a particularly demanding instance of this problem, where dynamic blockages and rapid channel variations continuously undermine the stationary… ▽ More The vision for 6G vehicle-to-everything (V2X) communications demands reliable, adaptive connectivity for fully autonomous driving across complex dynamic environments. Millimeter-wave (mmWave) user association (UA) in heterogeneous vehicular networks presents a particularly demanding instance of this problem, where dynamic blockages and rapid channel variations continuously undermine the stationary reward assumptions of traditional multi-armed bandit (MAB) frameworks. This paper proposes a fully distributed blockage-aware non-stationary dynamic bandit algorithm (BAND) and its semi-distributed extension S-BAND for cooperative learning across vehicles. Blockage prediction is incorporated into the change-detection (CD) mechanism to suppress false alarms, while a dynamic base station (BS) set management scheme balances exploration and exploitation across large-scale BS deployments without requiring centralized channel state information (CSI) acquisition or offline training. In S-BAND, vehicles accumulate BS reward estimates as local knowledge and periodically upload them to the macro base station (MBS), which aggregates them into cluster-based central knowledge. A trajectory-aligned knowledge (TAK) region is proposed to capture the spatial correlation of mmWave channel characteristics. A knowledge inheritance fidelity (KIF) metric is introduced to quantify knowledge transfer quality. Simulation results on a realistic urban topology show that BAND and S-BAND achieve 34.9% and 59.4% regret reduction relative to a centralized MAB baseline, with performance gains sustained across blockage rates ranging from 10% to 50%. The proposed TAK region consistently outperforms the traditional K-means clustering scheme under both fidelity criteria. △ Less

Submitted 5 August, 2026; originally announced August 2026.

UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models

Authors: Haiyang Zhou, Wangbo Yu, Chaoran Feng, Xunyu Zhou, Yonghong Tian, Li Yuan

Abstract: The abundance of casually captured monocular videos and images on social media provides a valuable source for immersive content creation, where generating novel views from such sparse observations can greatly enhance user experiences. However, producing photorealistic and geometrically consistent views with precise camera control remains challenging when input coverage is extremely limited. Recons… ▽ More The abundance of casually captured monocular videos and images on social media provides a valuable source for immersive content creation, where generating novel views from such sparse observations can greatly enhance user experiences. However, producing photorealistic and geometrically consistent views with precise camera control remains challenging when input coverage is extremely limited. Reconstruction-based approaches such as NeRF and 3D Gaussian Splatting (3DGS) deteriorate severely under sparse inputs and fail to explicitly handle occlusions. Generative methods ease data requirements but still struggle with large-baseline view synthesis due to inaccurate or implicit geometric guidance. To overcome these limitations, we introduce UniWorld-View, a unified framework for controllable large-baseline novel view synthesis from monocular inputs. UniWorld-View integrates explicit 3D guidance with generative diffusion modeling to enable precise camera control and geometrically consistent view generation. The geometric guidance is obtained through an occlusion-aware point cloud rendering strategy that resolves visibility ambiguities and provides accurate priors for diffusion-based synthesis. By coupling this rendering strategy with powerful video diffusion backbones, UniWorld-View achieves high-fidelity novel view generation even under extreme camera motions and wide-baseline changes, and can further provide multi-view videos for downstream dynamic 3DGS reconstruction. Experiments on the WorldScore benchmark and zero-shot NVS benchmarks demonstrate the effectiveness of UniWorld-View in controllability, geometric consistency, and visual fidelity. △ Less

Submitted 5 August, 2026; originally announced August 2026.

Comments: Project Homepage: https://zhouhyocean.github.io/uniworld-view/ Code: https://github.com/PKU-YuanGroup/UniWorld-View

DAC-Pose: Dual-Agent Collaborative Framework for Pose-Guided Human Generation

Authors: Haotian Yang, Zhile Yang, Huiyu Zhou, Xin Sun

Abstract: AI agents have emerged as a powerful new paradigm in generative image synthesis, enabling systems to perform complex semantic reasoning rather than passive pixel-level mapping. In pose-guided human generation, conventional methods inevitably produce severe visual artifacts under drastic viewpoint shifts, fundamentally because they lack the cognitive capacity to logically deduce unseen regions and… ▽ More AI agents have emerged as a powerful new paradigm in generative image synthesis, enabling systems to perform complex semantic reasoning rather than passive pixel-level mapping. In pose-guided human generation, conventional methods inevitably produce severe visual artifacts under drastic viewpoint shifts, fundamentally because they lack the cognitive capacity to logically deduce unseen regions and model complex spatial deformations. To bridge this gap, we propose DAC-Pose, a novel agent-driven multimodal framework that reformulates single-view human generation as a collaborative dual-agent system. DAC-Pose integrates two complementary components, namely, the Prior Semantic Reasoning (PSR) agent and the Discrepancy-Aware Visual Encoding (DAVE) agent. Functioning as a cognitive engine, PSR utilizes collaborative reasoning to deduce the fine-grained attributes of unseen regions. Concurrently, acting as a specialized visual perception agent, DAVE quantifies and encodes viewpoint-induced spatial misalignments, continuously feeding robust spatial constraints back into the generative process. This autonomous feedback loop between semantic deduction and visual perception ensures high-fidelity detail synthesis. Extensive experiments on the DeepFashion and Market-1501 benchmarks validate the superiority of our agent-driven paradigm. Notably, DAC-Pose excels in preserving texture alignment and identity consistency under drastic viewpoint changes. The code is available at https://github.com/AIVRC/DAC-Pose. △ Less

Submitted 5 August, 2026; originally announced August 2026.

Comments: Code is available at https://github.com/AIVRC/DAC-Pose

Scale-CDA: A Scalable Retrofit Platform for Cooperative Driving Automation in Production Vehicles

Authors: Hao Zhou, Shengming Yuan, Yuhang Wang, Alina Hagen, Haibin Wen

Abstract: Scaling cooperative driving automation (CDA) to production passenger vehicles requires an affordable retrofit platform that can accommodate heterogeneous OEM Controller Area Network (CAN) signals and advanced driver-assistance system (ADAS) commands. Scale-CDA addresses this challenge by building on OpenDBC and openpilot, which provide vehicle interfaces and Level-2 automation support for more tha… ▽ More Scaling cooperative driving automation (CDA) to production passenger vehicles requires an affordable retrofit platform that can accommodate heterogeneous OEM Controller Area Network (CAN) signals and advanced driver-assistance system (ADAS) commands. Scale-CDA addresses this challenge by building on OpenDBC and openpilot, which provide vehicle interfaces and Level-2 automation support for more than 300 car models. The proposed open-hardware and open-software prototype integrates commodity edge computing, camera sensing, Wi-Fi, cellular communication, and a CAN adapter for less than $1,000. It exchanges telemetry and cooperative messages through MQTT over Wi-Fi~6 or LTE, avoiding costly DSRC or C-V2X sidelink radios. In moving-vehicle experiments, Wi-Fi~6 achieved a mean round-trip time of 5.25~ms and mean negotiated physical-layer rates of 98.51~Mb/s for transmission and 109.17~Mb/s for reception, with approximately 2% of observations exceeding 50~ms. These results demonstrate feasibility for non-safety-critical CDA applications. Scale-CDA also introduces a Generative AI interface that combines camera observations, CAN data, and connectivity messages through the Model Context Protocol. The model generates semantic message intents and structured MetaActions, while deterministic adapters validate and encode cooperative messages and map admissible actions to existing Level-2 functions without allowing direct actuator control. An on-road construction-zone demonstration validates driver advisory, message generation, and speed-related MetaAction pathways. Scale-CDA provides a reproducible platform for connectivity and GenAI research on supported production vehicles. △ Less

Submitted 11 August, 2026; v1 submitted 4 August, 2026; originally announced August 2026.

Local magnetic order in vacancy-disrupted spin ice Ho2TiO5

Authors: Raju Baral, Haidong Zhou, Qiang Zhang, Benjamin A. Frandsen, Stuart Calder

Abstract: We investigate how local magnetic correlations evolve when the classical pyrochlore spin-ice Ho2Ti2O7 is transformed into the partially disordered stuffed compound Ho2TiO5. Neutron scattering measurements were analyzed using real-space magnetic pair distribution function, reciprocal-space reverse Monte Carlo, and half-polarized neutron powder diffraction methods to connect the average crystal stru… ▽ More We investigate how local magnetic correlations evolve when the classical pyrochlore spin-ice Ho2Ti2O7 is transformed into the partially disordered stuffed compound Ho2TiO5. Neutron scattering measurements were analyzed using real-space magnetic pair distribution function, reciprocal-space reverse Monte Carlo, and half-polarized neutron powder diffraction methods to connect the average crystal structure with local magnetic correlations. Both compounds retain long-range $Fd-3m symmetry, but in Ho2TiO5 this average structure distorts locally through Ho-O, Ti-O and O-O bond-length disorder associated with partial Ho/Ti occupancy. Despite this disorder, half-polarized neutron powder diffraction shows that the Ho moments retain local <111> rangle Ising anisotropy and form spin-in/spin-out configurations on the tetrahedral network. In Ho2Ti2O7, real- and reciprocal-space analyses reveal a nearly ideal two-in/two-out spin-ice state at 0.3K, with 95% of tetrahedra satisfying the ice rule, followed by progressive thermal disordering on warming. In Ho2TiO5, most tetrahedra are magnetically incomplete because some tetrahedral vertices are occupied by nonmagnetic Ti rather than Ho; nevertheless, the dominant incomplete configurations are 2-in/1-out and 1-in/2-out, which are locally compatible with the ice rule if the missing Ho spin is restored. The single-ion <111> Ising anisotropy is therefore retained throughout, while the collective ice ordering is strongly disrupted: Ho2TiO5 is a vacancy-disrupted spin ice in which a local ice-rule tendency persists on a topologically incomplete magnetic network. △ Less

Submitted 4 August, 2026; originally announced August 2026.

Simultaneous Mars-orbit observations reveal Kelvin-Helmholtz instability-driven bulk atmospheric ion escape

Authors: Chi Zhang, Chuanfei Dong, Gangkai Poh, Jasper Halekas, Xuanye Ma, Ruhunusiri Suranga, Kathleen G. Hanley, Han-Wen Shen, Hongyang Zhou, Xinmin Li, Liang Wang, Jiawei Gao, Shannon Curry, Christian Mazelle

Abstract: Atmospheric ion escape driven by the solar wind is a key process controlling the long-term loss of the Martian atmosphere. Localized plasma clouds can carry substantial fluxes of planetary ions away from Mars, representing episodes of bulk escape. However, their origin has remained unclear due to the absence of simultaneous upstream measurements. Using joint observations from the MAVEN and Tianwen… ▽ More Atmospheric ion escape driven by the solar wind is a key process controlling the long-term loss of the Martian atmosphere. Localized plasma clouds can carry substantial fluxes of planetary ions away from Mars, representing episodes of bulk escape. However, their origin has remained unclear due to the absence of simultaneous upstream measurements. Using joint observations from the MAVEN and Tianwen-1 missions, which provide real-time upstream monitoring, we present direct evidence that these plasma clouds are nonlinear wave packets generated by the Kelvin-Helmholtz instability (KHI). The spatial scale of KH waves is constrained for the first time via two-point measurements. Ion fluxes within plasma clouds are one to two orders of magnitude higher than those in typical steady-state escape channels. Our results indicate that KHI is an important process for solar wind coupling to planetary upper atmospheres and plays a crucial role in shaping atmospheric ion escape for unmagnetized planets. △ Less

Submitted 4 August, 2026; originally announced August 2026.

Self-Evolving Coding Agents

Authors: Hao Zhou, Haichuan Hu, Ye Shang, Quanjun Zhang

Abstract: Large language models are increasingly embedded in software engineering workflows as coding agents that can inspect repositories, invoke tools, execute tests, debug failures, and generate patches. Yet most existing agents remain largely static after deployment, even though software development is a dynamic, feedback-rich process in which repositories evolve, dependencies change, tests fail, and re… ▽ More Large language models are increasingly embedded in software engineering workflows as coding agents that can inspect repositories, invoke tools, execute tests, debug failures, and generate patches. Yet most existing agents remain largely static after deployment, even though software development is a dynamic, feedback-rich process in which repositories evolve, dependencies change, tests fail, and repair attempts leave reusable experience. This tension has motivated a growing body of work on self-evolving coding agents, where the agent improves its future behavior by persistently updating its framework, memory, skills and tools, model-side components, workflow and topology, or environment and context from prior coding interactions. In this survey, we provide a structured synthesis of this emerging area. We first define self-evolving coding agents and distinguish them from conventional coding agents and general self-evolving agents. We then develop a target-centered taxonomy that characterizes what evolves in these systems, and complement it with two orthogonal perspectives: when evolution occurs and what code-specific signals drive it. We further examine the benchmarks used to measure adaptation and the early appearance of related mechanisms in deployed coding products. Across the literature, we find that executable feedback, repository-level context, and coding trajectories make software engineering a natural domain for agent self-evolution, but also introduce challenges in feedback reliability, benchmark overfitting, reversibility, system complexity, safety, cost, and generalization. By organizing existing work around these dimensions, this survey aims to clarify the conceptual boundaries of self-evolving coding agents and provide a foundation for designing more adaptive, reliable, and software-aware agentic systems. △ Less

Submitted 20 August, 2026; v1 submitted 4 August, 2026; originally announced August 2026.

EditFlow3D: Automated Local Editing of 3D Assets with Trajectory Preservation

Authors: Rui Nie, Chuang Wang, Haitao Zhou, Jiahe Song, Buyu Li, Sheng Wang, Qian Yu

Abstract: Controllable local editing of 3D assets requires precise target localization and appropriate visual guidance. However, existing methods lack a simple yet accurate way to obtain 3D masks and struggle to achieve the desired edit while faithfully preserving the structure and appearance of non-target regions. To address these challenges, we present EditFlow3D, a training-free framework for local 3D ed… ▽ More Controllable local editing of 3D assets requires precise target localization and appropriate visual guidance. However, existing methods lack a simple yet accurate way to obtain 3D masks and struggle to achieve the desired edit while faithfully preserving the structure and appearance of non-target regions. To address these challenges, we present EditFlow3D, a training-free framework for local 3D editing. Given a source asset and an edit instruction, a VLM-driven workflow interprets the editing intent and automatically constructs a visual guidance image and a refined 3D editing mask, enabling localized editing in the native representation space of a pretrained 3D generative model. Specifically, mask-guided differential flow focuses the edit on the target region, while step-wise trajectory preservation maintains consistency between non-target regions and the source asset without directly replacing intermediate features. Since the existing Edit3D-Bench covers only a limited range of local editing categories, we further introduce EditFlow-Bench as a complementary benchmark encompassing a broader variety of structural and appearance edits, and evaluate EditFlow3D on both benchmarks. Quantitative results, qualitative comparisons, and a user study demonstrate that EditFlow3D achieves more accurate target-region editing and better preserves non-target regions than existing 3D editing methods. △ Less

Submitted 4 August, 2026; originally announced August 2026.

SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation

Authors: Wen Wang, Jiahua Bao, Tu Yongsiqi, Yihao Liu, Haotian Zhou, Haoxuan Ma, Mengyu Zhou, Wenkui Fan, Junwei He, Xiaoxi Jiang, Guanjun Jiang

Abstract: We aim to improve model performance in multi-reward reinforcement learning training process. Existing Group reward-Decoupled Normalization Policy Optimization (GDPO) has mitigated the issue of reward signals masking one another during direct scalarization by normalizing each reward dimension separately before aggregation. However, our experiments show that GDPO still struggles to balance reward si… ▽ More We aim to improve model performance in multi-reward reinforcement learning training process. Existing Group reward-Decoupled Normalization Policy Optimization (GDPO) has mitigated the issue of reward signals masking one another during direct scalarization by normalizing each reward dimension separately before aggregation. However, our experiments show that GDPO still struggles to balance reward signals with different granularities. Specifically, in some particular training tasks, the model may receive a dense reward that assigns fine-grained scores ranging from 0.1 to 1.0, together with a sparse reward that provides only binary feedback of either 0 or 1. In such cases, we find that the sparse reward may provide an insufficient optimization signal, preventing its corresponding capability from being effectively reinforced. Therefore, how can we strengthen the optimization signal from the sparse reward without sacrificing the capability already learned from the fine-grained reward? To overcome this limitation, we propose Specialize-and-Merge Online Policy Distillation (SMOPD), a two-stage training method for multi-reward optimization. Stage1-Specialize: SMOPD first employs reward-priority configurations to train multiple reward-specialized teachers, allowing each reward to be learned under conditions where its signal can effectively drive optimization. Stage2-Merge: SMOPD then utilizes online policy distillation to combine the reward-specialized capabilities of these teachers into a single student policy, while maintaining balanced task-level optimization. To validate our method, we conduct experiments on two multi-reward settings: complementary rewards(tool-calling accuracy and format) and conflicting rewards (helpful and harmless rewards). Based on above settings, SMOPD outperforms GDPO across 1.5B, 3B and 7B backbones. △ Less

Submitted 4 August, 2026; originally announced August 2026.

Comments: 21 pages, 5 figures, 12 tables

Revealing Intrinsic Anisotropy of Collective Magnetic Excitations in Twinned Crystals of a Kitaev-Heisenberg Quantum Magnet

Authors: Naipeng Zhang, Nikolai Simonov, Mykhaylo Ozerov, Sumedh Rathi, Nolan Heffner, Sara Huszar, Long Chen, Haidong Zhou, Guangxin Ni, Chaebin Kim, Martin Mourigal, Stephen M. Winter, Zhigang Jiang, Dmitry Smirnov

Abstract: Quantum magnets with competing interactions often emerge from delicate balances among microscopic parameters, making it essential to disentangle intrinsic spin dynamics from extrinsic disorder effects. Here, we introduce a multimodal optical approach combining magneto-infrared spectroscopy with domain-resolved micro-Raman spectroscopy at high magnetic fields to reconstruct the intrinsic magnetic e… ▽ More Quantum magnets with competing interactions often emerge from delicate balances among microscopic parameters, making it essential to disentangle intrinsic spin dynamics from extrinsic disorder effects. Here, we introduce a multimodal optical approach combining magneto-infrared spectroscopy with domain-resolved micro-Raman spectroscopy at high magnetic fields to reconstruct the intrinsic magnetic excitation spectrum of twinned crystals of the Kitaev-Heisenberg quantum magnet Na$_3$Co$_2$SbO$_6$. Far-infrared spectroscopy reveals multiple field-tunable magnetic excitations, but the intrinsic response is obscured by replica features arising from twin domains. By correlating magneto-infrared and domain-resolved Raman spectra, we isolate the single-domain magnon response and uncover a pronounced twofold in-plane magnon anisotropy. This anisotropy far exceeds that expected from the measured in-plane g-factor anisotropy and is instead dominated by anisotropic bond-dependent exchange interactions. By unifying high-field, high-resolution and spatially selective optical probes, our work establishes a broadly applicable framework for revealing intrinsic spin dynamics and constraining the spin Hamiltonian in multidomain quantum magnets. △ Less

Submitted 3 August, 2026; originally announced August 2026.

Computational and Statistical Guarantees of the \textit{c}-Rectified flow

Authors: Leda Wang, Zhehao Xu, Qiang Liu, Harrison H. Zhou

Abstract: Recently, rectified flow has emerged as a fundamental framework for large-scale image generation, powering state-of-the-art systems such as FLUX.1 and Stable Diffusion 3. Despite its remarkable empirical success, the computational and statistical guarantees of iterative rectified flow have remained largely unexplored. We address this problem by studying \textit{c}-rectified flow, a cost-aware clas… ▽ More Recently, rectified flow has emerged as a fundamental framework for large-scale image generation, powering state-of-the-art systems such as FLUX.1 and Stable Diffusion 3. Despite its remarkable empirical success, the computational and statistical guarantees of iterative rectified flow have remained largely unexplored. We address this problem by studying \textit{c}-rectified flow, a cost-aware class of rectified flow that projects velocity fields onto a gradient class while preserving endpoint marginals. The ordinary rectified flow can fail to recover the optimal transport coupling: in a Gaussian case study, the iteration converges to the optimal coupling if and only if the source and target covariance matrices commute. In contrast, under suitable compactness and uniform-integrability assumptions, iterative \textit{c}-rectified flow always converges to the optimal transport coupling. We further establish quantitative one-step contraction and exponential convergence guarantees under projection-stability assumptions for both quadratic and strongly convex displacement costs. Finally, under a Hölder ball assumption, we develop new minimax-optimal score estimation rates and show that, when combined with iterative \textit{c}-rectified flow, they yield a rate-optimal estimator of the optimal transport for the dimension \(d \ge 3\) and a nearly parametric rate for \(d=1,2\). △ Less

Submitted 3 August, 2026; originally announced August 2026.

Self-Improving Large Language Models via Progressive Experience Evolution

Authors: Shijie Ren, Xiting Wang, Meng Li, Yujie Guo, Yunhang Yao, Ziheng Peng, Xunlong Wang, Yuetan Chen, Haoyang Zhou, Yunlong Liang, Fandong Meng

Abstract: Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transforming transient interaction experience into persistent model capabilities. Existing self-improvement paradigms remain fragmented: test-time methods can explicitly extract experience but cannot internalize it into model parameters, whereas training-time… ▽ More Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transforming transient interaction experience into persistent model capabilities. Existing self-improvement paradigms remain fragmented: test-time methods can explicitly extract experience but cannot internalize it into model parameters, whereas training-time optimization methods can update model parameters but lack an explicit mechanism for accumulating transferable experience. Bridging these two paradigms requires a critical intermediate stage that remains underexplored, namely \emph{experience distillation}. To address this gap, we propose \textbf{SPEE} (\textbf{S}elf-\textbf{P}rogressive \textbf{E}xperience \textbf{E}volution), a unified post-training framework that sequentially performs explicit experience evolution followed by implicit policy optimization. During explicit experience evolution, SPEE reflects on trajectories collected from multiple interactions to extract, verify, and progressively evolve transferable experience, which is subsequently internalized into the policy through privilege-guided On-Policy Self-Distillation (OPSD). During implicit policy optimization, reward-driven reinforcement learning leverages these internalized priors to explore novel solution strategies. In the experience evolution stage, a continuously evolving global experience pool consolidates knowledge from both successful and failed trajectories, filters out low-utility experience, and mitigates post-hoc rationalization induced by individual trajectories. Experiments on five mathematical reasoning benchmarks demonstrate that SPEE consistently outperforms both test-time and training-time self-evolution baselines across three model scales. The source code is available at https://github.com/rrrsj/SPEE. △ Less

Submitted 4 August, 2026; v1 submitted 3 August, 2026; originally announced August 2026.

Comments: 10 pages, 5 figures