Showing 1–50 of 2,558 results for author: Cheng, J

Evidence for $η_{c}(2S)\to p\bar{p}π^{+}π^{-}π^{0}$ and observation of $χ_{cJ} \to p\bar{p}π^{+}π^{-}π^{0}$

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: Using $(2.712\pm0.014)\times 10^9$ $ψ(3686)$ events collected by the BESIII detector at the BEPCII collider, the $ψ(3686) \to γp\bar{p}π^+π^-π^0$ process is investigated. Evidence for the decay of $η_{c}(2S)\to p\bar{p}π^{+}π^{-}π^{0}$ is found with a signal significance of 3.3$σ$. The product of branching fractions of… ▽ More Using $(2.712\pm0.014)\times 10^9$ $ψ(3686)$ events collected by the BESIII detector at the BEPCII collider, the $ψ(3686) \to γp\bar{p}π^+π^-π^0$ process is investigated. Evidence for the decay of $η_{c}(2S)\to p\bar{p}π^{+}π^{-}π^{0}$ is found with a signal significance of 3.3$σ$. The product of branching fractions of $\mathcal{B}[ψ(3686)\to γη_{c}(2S)]\times\mathcal{B}[η_{c}(2S)\to p\bar{p}π^{+}π^{-}π^{0}]$ is determined to be $(3.4\pm0.5\pm0.8) \times 10^{-6}$, where the first uncertainty is statistical and the second systematic. The hadronic decays of $χ_{cJ} \to p\bar{p}π^+π^-π^0$$~(J=0,1,2)$ are observed, and their branching fractions are measured to be $\mathcal{B}(χ_{c0}\to p\bar{p}π^{+}π^{-}π^{0})=(4.79\pm 0.01\pm0.40) \times 10^{-3}$, $\mathcal{B}(χ_{c1}\to p\bar{p}π^{+}π^{-}π^{0})=(2.13\pm 0.01\pm0.17) \times 10^{-3}$, and $\mathcal{B}(χ_{c2}\to p\bar{p}π^{+}π^{-}π^{0})=(3.72\pm 0.01\pm0.29) \times 10^{-3}$, respectively. Furthermore, the branching fractions for the intermediate processes $χ_{cJ}\to p\bar{p}ω$ are updated with significantly improved precision: $\mathcal{B}(χ_{c0}\to p\bar{p}ω)=(5.76\pm0.01\pm0.42)\times10^{-4}$, $\mathcal{B}(χ_{c1}\to p\bar{p}ω)=(1.85\pm0.01\pm0.13)\times10^{-4}$, and $\mathcal{B}(χ_{c2}\to p\bar{p}ω)=(4.51\pm0.01\pm0.33)\times10^{-4}$, respectively. △ Less

Submitted 21 August, 2026; originally announced August 2026.

Causal Generalization of Continuous Treatment Effects under Covariate Shift

Authors: Jay Jojo Cheng, Guanhua Chen

Abstract: Average dose-response functions are widely used to summarize causal effects of continuous treatments, but most existing methods assume that the observed sample represents the target population. We study a covariate-shift setting in which covariates, treatment, and outcome are observed in a labelled source sample, while only covariates are observed in the target sample. We develop a two-sample loca… ▽ More Average dose-response functions are widely used to summarize causal effects of continuous treatments, but most existing methods assume that the observed sample represents the target population. We study a covariate-shift setting in which covariates, treatment, and outcome are observed in a labelled source sample, while only covariates are observed in the target sample. We develop a two-sample local polynomial regression framework based on pseudo-outcomes that use source outcomes to address confounding and target covariates to define the population of interest. We further propose a source-to-target extension of distance covariance optimal weighting (DCOW), designed to remove treatment-covariate dependence in the source sample while aligning the weighted source covariate distribution with the target population. A central theoretical contribution is a weight-level analysis of this optimization-based procedure: we show that the population criterion identifies the oracle source-to-target weights and that approximate empirical minimizers, including exact minimizers as a special case, converge uniformly to these weights under regularity conditions. We also establish consistency and asymptotic normality of the resulting estimator. Simulations show that the proposed method improves target dose-response estimation relative to DCOW, generalized-propensity-score weighting, entropy balancing, and unweighted alternatives. We illustrate the method in a county-level analysis of PM2.5 exposure and subsequent heart-disease mortality using a source-target validation design. △ Less

Submitted 19 August, 2026; originally announced August 2026.

UBio-MolFM: Enabling Biomolecular Dynamics at DFT Accuracy and $10^5$ Atoms with One Untuned Potential

Authors: Lin Huang, Frank Peng, JiaJun Cheng, Zion Wang, Hao Yin, Hao Li, Ji Zhang, Jack Jia, Junping Zhao, Arthur Jiang, Jia Zhang

Abstract: Ion conduction, membrane permeation and metal recognition hinge on electronic structure, yet first-principles simulation reaches only hundreds of atoms. UBio-MolFM lifts that ceiling: a foundation model trained on 160 million quantum-chemical labels, its receptive field spanning non-covalent distances at near-linear cost. The barrier is cost, not principle. One untuned potential keeps force error… ▽ More Ion conduction, membrane permeation and metal recognition hinge on electronic structure, yet first-principles simulation reaches only hundreds of atoms. UBio-MolFM lifts that ceiling: a foundation model trained on 160 million quantum-chemical labels, its receptive field spanning non-covalent distances at near-linear cost. The barrier is cost, not principle. One untuned potential keeps force error near 20 meV/Å past a thousand atoms, reproduces water's X-ray structure and ion hydration, and holds an RNA Mg$^{2+}$ site without ion-specific parameters. Cyclosporine A pays 3.5 kcal/mol in water for its permeable conformer, gated by one kinetically asymmetric hydrogen bond that a fixed-charge model flattens. In a 108,964-atom KcsA channel on one GPU, the relaxed four-ion column is anhydrous in all five replicas, in direct contact in four---the knock-on geometry ten fixed-charge simulations never form. It remains orders of magnitude costlier. Where electronic structure decides the answer, first-principles simulation is in reach. △ Less

Submitted 19 August, 2026; originally announced August 2026.

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

Large Models for Small Devices: Recent Advances and Empirical Analysis of Edge AI Deployment

Authors: Subhransu Das, Jiaming Cheng, Arnav Kumar, Sadia Afrose, Mingzhe Han, Michael Silagy, Shreya Palande, Brijesh Soni, Rajiv Ramnath

Abstract: Running large AI models on resource-constrained edge devices requires model compression to reduce model size and computation. What compresses well, however, need not deploy well. We survey dozens of recent works that report compression results on real hardware and extract practical deployment guidelines from them. Following these guidelines, we deploy compact language and image models on GPU, CPU,… ▽ More Running large AI models on resource-constrained edge devices requires model compression to reduce model size and computation. What compresses well, however, need not deploy well. We survey dozens of recent works that report compression results on real hardware and extract practical deployment guidelines from them. Following these guidelines, we deploy compact language and image models on GPU, CPU, and Raspberry Pi platforms across question answering and image segmentation. No single technique wins across tasks. For question answering, Qwen3.5 0.8B reaches 93.85 SQuAD F1 and 92 EM under Q5_K_M GGUF quantization, while structured pruning at the same precision costs 16 F1 at a 1% ratio. For segmentation, the ranking reverses: default quantization leaves parameters and MACs unchanged, whereas pruning cuts model size by nearly 80% at near-constant mIoU. Pruning can even inflate the deployed artifact by 21-49% by breaking k-quant super-block alignment; combined with longer, less format-compliant outputs, this raises Raspberry Pi latency up to 3.4x. Compression can also manufacture the appearance of competence rather than destroy it visibly: one LoRA-recovered variant stays fully parseable and holds 71% strict BoolQ accuracy while sending 97 of 100 predictions to a single class, at 52.6% balanced accuracy. We explain these effects through neural-flow graph analysis and prefill-decode-level latency decomposition, and condense them into task-specific deployment research directions. The right technique depends on the task, the model, and the hardware. Our experiment code and artifacts are open-sourced at https://github.com/Arnavvvkumar/deployment △ Less

Submitted 16 August, 2026; originally announced August 2026.

Comments: Parts of this work were presented at the IEEE Consumer Communications & Networking Conference (CCNC), Las Vegas, NV, USA, January 2026

MOSS-VL Technical Report

Authors: Pengyu Wang, Chenkun Tan, Shaojun Zhou, Qirui Zhou, Yanxin Chen, Xingyang He, Huazheng Zeng, Jijun Cheng, Chenghao Wang, Xiaomeng Qian, Pengfei Wang, Zhan Huang, Shanqing Gao, Wei Huang, Longjun Cao, Wu Ran, Jie Liu, Changtai Zhu, Hongkai Wang, Yixian Tian, Chenghao Liu, Zhen Ye, Xinghao Wang, Botian Jiang, Guoguo Feng , et al. (7 additional authors not shown)

Abstract: We present MOSS-VL, an open vision-language model family that treats real-time interaction -- perceiving while it speaks -- as a first-class capability. It is co-designed across the stack: the language decoder attends to vision only through gated cross-attention, so the model can naturally see incoming frames while generating; a synthesized interaction corpus supervises when to speak, when to stay… ▽ More We present MOSS-VL, an open vision-language model family that treats real-time interaction -- perceiving while it speaks -- as a first-class capability. It is co-designed across the stack: the language decoder attends to vision only through gated cross-attention, so the model can naturally see incoming frames while generating; a synthesized interaction corpus supervises when to speak, when to stay silent, and when to revise; and a staged curriculum concentrates all real-time-specific training in one light final stage over a strong offline foundation. Offline, MOSS-VL-Instruct is competitive at comparable scale and leads temporal-reasoning video sets. Across four streaming benchmarks, MOSS-VL-Realtime posts the best average on three (second on the fourth) among open-source streaming models, sweeping the three subsets that squarely test proactive behavior -- 66.0 vs. 37.5 for the best baseline on OmniMMI Proactive Alerting. With 11.3B parameters but visual tokens outside the decoded sequence, MOSS-VL widens its time-to-first-token advantage over same-backbone Qwen3-VL-8B from 2.8x to 5.1x as visual context grows. We release all five checkpoints, the training curriculum, and the real-time inference code at https://github.com/OpenMOSS/MOSS-VL. △ Less

Submitted 15 August, 2026; originally announced August 2026.

Comments: 22 pages. Project page: https://openmoss.ai/MOSS-VL/

MazeRunner: Nonlinear Task and Clue Orchestration for LLM-driven Black-Box Automated Penetration Testing

Authors: Zhenyuan Li, Yi Jiang, Junjie Cheng, Yaokun Li, Jing Qiu, Shouling Ji

Abstract: Penetration testing is essential yet resource-intensive. Although large language models (LLMs) show promise for automating security auditing, existing agents mainly execute end-to-end workflows in simplified linear scenarios. Real-world black-box testing is fundamentally nonlinear: the attack graph is initially unknown and must be incrementally inferred from environmental feedback. Observations ma… ▽ More Penetration testing is essential yet resource-intensive. Although large language models (LLMs) show promise for automating security auditing, existing agents mainly execute end-to-end workflows in simplified linear scenarios. Real-world black-box testing is fundamentally nonlinear: the attack graph is initially unknown and must be incrementally inferred from environmental feedback. Observations may reveal multiple attack branches, failures are often ambiguous, and critical clues may span long action horizons. Existing agents therefore tend to become trapped in depth-first exploration, misdiagnose failures, and forget prior evidence. We present MazeRunner, an autonomous penetration testing system built on a three-agent task-and-clue orchestration framework. It separates global orchestration, context-intensive execution, and failure-oriented review while persistently maintaining task states and environmental evidence. This design supports action revision, prerequisite recovery, branch switching, and long-range clue correlation. We evaluate MazeRunner on 10 recently released HTB targets, limiting each system-target run to 20 million LLM tokens and preventing target-specific solution leakage. With Claude Sonnet 4.5, MazeRunner completes 47.7% of annotated subtasks, compared with 36.2% for PentestGPT-V2 and 34.2% for Claude Code. It achieves user-level or higher access on six targets, including root access on two; each same-model baseline reaches user-level access on only two targets and never obtains root access. Execution-trace analysis further shows that MazeRunner explores more attack branches and acquires shells more efficiently. △ Less

Submitted 14 August, 2026; originally announced August 2026.

Practical Lossless Volumetric Medical Image Compression via Tri-plane Context Tree Learning

Authors: Yuanchao Bai, Yifan Zhao, Kai Wang, Yuanbo Du, Jie Cheng, Teng Fang, Xianming Liu, Wen Gao

Abstract: Lossless compression of volumetric medical images is of paramount importance for clinical and research applications where data fidelity is essential. Traditional compression methods are often limited in efficiency due to rigid, handcrafted models. Conversely, deep neural network (DNN)-based compression methods, while effective, demand substantial computational resources, hindering deployment in re… ▽ More Lossless compression of volumetric medical images is of paramount importance for clinical and research applications where data fidelity is essential. Traditional compression methods are often limited in efficiency due to rigid, handcrafted models. Conversely, deep neural network (DNN)-based compression methods, while effective, demand substantial computational resources, hindering deployment in resource-constrained settings. To address these challenges, we propose a novel tri-plane context tree (TCT)-based method for lossless volumetric medical image compression that delivers high performance without relying on DNNs or external training data. To exploit intra-slice and inter-slice redundancies, we introduce a compact tri-plane context representation that decomposes complex 3D context modeling into efficient 2D modeling on three orthogonal planes. By integrating this representation with a context tree framework, we develop an input-specific TCT model employing an adaptive binary tree structure. At each tree node, the model dynamically selects from a suite of tri-plane based predictors and contextual feature extractors, enabling data-adaptive context modeling tailored to local structural characteristics. Instead of offline training, we sample a subset of the input volume to learn the TCT model by optimizing the minimum description length (MDL) through iterative construction and pruning. With the learned TCT model, each pixel retrieves its corresponding context, computes the prediction residual using the predictor dictated by the context, and performs entropy encoding based on the associated histograms. Experimental results demonstrate that the proposed method achieves compression performance on par with recent DNN-based methods on multiple datasets, while maintaining low computational cost and fast coding speeds, making it highly applicable in practice. △ Less

Submitted 13 August, 2026; originally announced August 2026.

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.

Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks

Authors: Andrew Cheng, Ali Eslamian, Jie Cheng, Mehdi Zargham, Qiang Cheng

Abstract: Neural networks can often be trained or fine-tuned through random low-dimensional reparameterization, where a small latent vector is mapped into a full parameter update by a frozen random map. This raises a practical question: how large must the latent search space be to reach a low-loss region? We first express the known accessibility transition in an equivalent conic form, centered for compact c… ▽ More Neural networks can often be trained or fine-tuned through random low-dimensional reparameterization, where a small latent vector is mapped into a full parameter update by a frozen random map. This raises a practical question: how large must the latent search space be to reach a low-loss region? We first express the known accessibility transition in an equivalent conic form, centered for compact convex targets at the statistical dimension of the polar cone. Our main theoretical contribution is an orientation-resolved quadratic master formula that predicts the random-slice residual from both the curvature spectrum and the reference-to-solution displacement profile. It yields a self-consistent isotropic-orientation predictor and, in a conservative radius-only specialization, recovers the earlier Gaussian-width quadratic bound. Building on this analysis, we introduce Random Mapping Networks (RaMaN), which instantiate the predicted latent dimension using structured Hadamard or seed-regenerated Gaussian maps. These constructions avoid the O(dP) storage of dense random maps and reduce optimizer-state memory from O(P) to O(d). We also develop matrix-free curvature approximations and sweep-free dimension selection. Across controlled quadratic and neural-curvature experiments, the orientation-resolved predictor closely tracks measured transition locations and outperforms orientation-agnostic approximations when displacement direction matters. End-to-end experiments further show sharp, protocol-dependent training transitions across image and language models. △ Less

Submitted 12 August, 2026; originally announced August 2026.

Scaling Automatic Research Agents via World Models

Authors: Xiyuan Yang, Sheikh Sarwar, Jingru Cheng, Zhan Shi, Duanshun Li, Huiyuan Chen, Haiyang Zhang, Chenlei Guo, Jingrui He, Zhenyu Liao

Abstract: Automating empirical research is a long-standing direction of AI. Recent automatic research (AutoResearch) agents bring this goal within reach, as modern LLMs show the capability to independently implement solutions and learn from the execution outcomes. Behind these gains, post-training (especially RL) plays a central role. In this paper, we identify a fundamental tension when scaling RL for thes… ▽ More Automating empirical research is a long-standing direction of AI. Recent automatic research (AutoResearch) agents bring this goal within reach, as modern LLMs show the capability to independently implement solutions and learn from the execution outcomes. Behind these gains, post-training (especially RL) plays a central role. In this paper, we identify a fundamental tension when scaling RL for these agents: the two components of every AutoResearch trajectory (agent generation and environment execution) scale in very different manners, since all generation shares compute through batching, while each execution occupies its exclusive sandbox and real machine time. As a result, the environment execution dominates the training cost and becomes the bottleneck as trajectories grow. To resolve this tension, we propose World Model RL (WMRL), which replaces environment execution with a world model to remove this bottleneck. Additionally, the world model can be imperfect, as its rewards are corrupted by bias and noise. Therefore, we further equip WMRL with two mitigations, Online Debiasing and Inverse-Variance Denoising, which offset the bias and suppress the noise respectively. Theoretically, we prove that both mitigations of WMRL strictly improve the convergence guarantee. Empirically, WMRL accelerates training by 3-4x on various tasks at different agent scales, while exceeding the performance of standard RL baselines. Moreover, our post-trained 4B and 9B agents outperform much larger open-weight agents of 48B and 120B on held-out benchmarks. Beyond AutoResearch, WMRL also transfers to post-training embodied VLA policies, which demonstrates the generalizability of our method. △ Less

Submitted 12 August, 2026; originally announced August 2026.

Adaptive Bregman Proximal Stochastic Gradient with a Stabilized Barzilai--Borwein Step Size

Authors: Chenhan Jin, Shengze Xu, Binghui Xie, Kaiwen Zhou, Fan Jia, James Cheng, Tieyong Zeng

Abstract: Bregman proximal stochastic gradient (BPSG) methods bring variance-reduced composite optimization to objectives whose geometry is poorly captured by Euclidean smoothness. Their performance, however, remains sensitive to the step size: raw stochastic curvature estimates can fluctuate sharply, whereas line searches add repeated proximal evaluations. We introduce Ada-BPSG, a line-search-free BPSG met… ▽ More Bregman proximal stochastic gradient (BPSG) methods bring variance-reduced composite optimization to objectives whose geometry is poorly captured by Euclidean smoothness. Their performance, however, remains sensitive to the step size: raw stochastic curvature estimates can fluctuate sharply, whereas line searches add repeated proximal evaluations. We introduce Ada-BPSG, a line-search-free BPSG method that couples the SAGA gradient table with a stabilized Barzilai--Borwein (BB) candidate. A mediant aggregates incremental secant information so that nearly singular local ratios receive little weight, and an explicit safeguard translates the resulting curvature estimate into the bounded step-size sequence required for convergence. This design yields a direct analytical chain from relative smoothness and component-wise variance control to convergence in finite-dimensional normed spaces. We prove an $O(n/K)$ ergodic rate for convex objectives, a restarted linear rate under relative quadratic growth, and an $O(1/K)$ bound for a Bregman proximal residual in the nonconvex setting. On logistic regression and sparse nonnegative matrix factorization, Ada-BPSG combines low objective values with substantially less sensitivity to the initial step size than standard variance-reduced baselines, while avoiding line search. △ Less

Submitted 12 August, 2026; originally announced August 2026.

ComBodied Agents: a New Paradigm of Human-Centric Agentic AI

Authors: Qianggang Ding, Xingyao Wang, Rui Feng, Zhibin Wang, Feixiang Yao, Kelong Mao, Hao Sun, Zhiyao Luo, Jiankai Tang, Lei Li, Jiadong Guo, Minheng Ni, Weicong Lin, Chenxi Yang, Hongxiang Gao, Zhenghua Chen, Yang Bai, Min Wu, Jun Cheng, Huazhu Fu, Dacheng Tao, Bang Liu

Abstract: After an older adult misses a medication dose, a software agent can send another reminder and an embodied agent can bring the medication. Yet neither explains whether the person forgot, is confused, has side effects, or deliberately refused, nor what support is appropriate. This reveals a structural gap in Agentic AI: Digital Agents primarily transform software states, while Embodied Agents transf… ▽ More After an older adult misses a medication dose, a software agent can send another reminder and an embodied agent can bring the medication. Yet neither explains whether the person forgot, is confused, has side effects, or deliberately refused, nor what support is appropriate. This reveals a structural gap in Agentic AI: Digital Agents primarily transform software states, while Embodied Agents transform physical states; neither makes a person's evolving state and agency the primary object of modeling, intervention, and evaluation. We introduce Combodied Agents, a human-centered paradigm that perceives, models, predicts, and supports individual human-state trajectories over time, using software tools, sensors, wearables, robots, and human services as action channels rather than end goals. We unify fragmented capabilities across personal assistants, health agents, AI companions, and adaptive human--AI systems into a closed loop: event-based multimodal perception reconstructs meaningful personal events; longitudinal, correctable memory provides temporal context; Personal World Models estimate future personal states and outcomes under alternative decisions and interventions; and an admissible intervention policy selects proportionate support under consent, uncertainty, safety, reversibility, and user control. Feedback from the person and environment updates the loop. Rather than requiring an exhaustive Human Digital Twin, the framework uses purpose-bounded, uncertainty-aware, user-correctable representations. We organize the design space by human-state targets, relational contexts, and agent roles, and propose scenario-centered evaluation, agency-preservation metrics, benchmark requirements, edge-native personal models, and governance directions. Combodied Agents shift Agentic AI from external task completion toward sustained human benefit. △ Less

Submitted 12 August, 2026; v1 submitted 11 August, 2026; originally announced August 2026.

Comments: 38 pages, 6 figures, 10 tables

Gated Spatial Redundancy Projection for Pathology Transformer Attentions

Authors: Zhiyuan Yang, Jiahao Cheng, Vincent Quoc-Huy Trinh, Mahdi S. Hosseini

Abstract: Transformer models are increasingly used for whole-slide image analysis in computational pathology. Yet, WSIs differ fundamentally from natural images: neighbouring patches often contain highly similar tissue type, stain, texture, and cellular composition. We identify this local spatial redundancy as a pathology-specific failure mode of self-attention, where dominant neighbourhood features can be… ▽ More Transformer models are increasingly used for whole-slide image analysis in computational pathology. Yet, WSIs differ fundamentally from natural images: neighbouring patches often contain highly similar tissue type, stain, texture, and cellular composition. We identify this local spatial redundancy as a pathology-specific failure mode of self-attention, where dominant neighbourhood features can be repeatedly mixed into patch-tokens and weaken subtle diagnostic or prognostic deviations. We propose Gated Spatial Redundancy Projection (Gated SRP), a lightweight drop-in correction module for self-attention layers. For each patch token and attention head, Gated SRP estimates a local redundancy axis from neighbouring value vectors, projects the attention output onto this axis, and applies a learned signed gate to correct the redundancy-aligned component geometrically. Across five TCGA survival cohorts, Gated SRP obtains the highest mean C-index among the compared attention variants in all cohorts, with an average improvement over the base attention, while adding only +0.02% parameters. Across five slide-level classification datasets, it improves the base attention on 12 of 16 reported metrics and achieves the best AUC on three datasets. Code is publicly available at https://github.com/AtlasAnalyticsLab/GatedSRP. △ Less

Submitted 12 August, 2026; v1 submitted 8 August, 2026; originally announced August 2026.

Comments: Accepted at BMVC 2026 Conference

Test-Time Prototype Adaptation for Open-Vocabulary Semantic Segmentation

Authors: Haozhe Wang, Jintao Cheng, Weibin Li, Xiaoyu Tang

Abstract: Open-vocabulary semantic segmentation (OVSS) repurposes a pretrained CLIP encoder for dense prediction without additional labeled supervision. Existing methods improve CLIP's spatial behavior either by redesigning its internal attention or by injecting features from auxiliary vision foundation models; both require access to the host's internal computation and are tailored to its specific forward p… ▽ More Open-vocabulary semantic segmentation (OVSS) repurposes a pretrained CLIP encoder for dense prediction without additional labeled supervision. Existing methods improve CLIP's spatial behavior either by redesigning its internal attention or by injecting features from auxiliary vision foundation models; both require access to the host's internal computation and are tailored to its specific forward pass. In this work, we propose Test-time Prototype Adaptation (TPA), a training-free plug-in that operates at the output level, leaving the host's forward pass and weights unmodified. By leveraging a lightweight transductive adaptation phase, TPA identifies confident anchor patches from the host's own output predictions on a small pool of unlabeled deployment-domain images, and aggregates their frozen DINO features into per-class prototypes; at inference, a single cosine similarity lookup against this frozen bank provides an auxiliary score fused linearly with the host's logits. TPA composes with five representative OVSS hosts spanning attention-redesign and VFM-injection designs, across three CLIP backbones, eight benchmarks, and multiple internal VFM choices. Under a single set of hyper-parameters and without per-host tuning or parameter updates, TPA consistently improves segmentation accuracy, with as few as approximately 10% of unlabeled deployment-domain images sufficing for effective bank construction on most benchmarks. △ Less

Submitted 8 August, 2026; originally announced August 2026.

Comments: 17 pages, 12 figures, preprint

ACM Class: I.2.10; I.4.6

OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching

Authors: Can Xiao, Sukmin Cho, Junbong We, Zhixiong Niu, Jianyi Cheng, Yiren Zhao, Youngjin Kwon, Yongqiang Xiong, Rui Ma, Junyi Liu

Abstract: Large language model (LLM) inference serving is increasingly constrained by memory rather than compute. As long-context and long-form reasoning workloads become more prevalent, the key-value (KV) cache dominates both memory footprint and memory traffic during LLM token generation, i.e., decode. In particular, HBM capacity has become a scarce and costly resource that heavily limits inference batch… ▽ More Large language model (LLM) inference serving is increasingly constrained by memory rather than compute. As long-context and long-form reasoning workloads become more prevalent, the key-value (KV) cache dominates both memory footprint and memory traffic during LLM token generation, i.e., decode. In particular, HBM capacity has become a scarce and costly resource that heavily limits inference batch size and system throughput. This paper presents OasisKV, a memory-centric LLM inference system design that alleviates HBM capacity pressure by decoupling full KV-cache storage from HBM during LLM decoding. Because decode-time attention is naturally sparse, OasisKV keeps only the KV entries of the most relevant tokens in HBMs for attention computation. We observe that future important tokens can be predicted accurately in advance using lookahead tokens drafted by speculative decoding (SD). OasisKV employs an efficient attention background pipeline to identify important KV blocks. They are then prefetched from higher-capacity memory tiers (e.g., host or remote memory) and staged in HBMs before being used in the next decode step. We implement OasisKV based on vLLM. The lookahead prediction is accurate enough to keep accuracy within 0.7 points of full attention under a 2,048-token KV budget. This lets OasisKV turn sparsity into throughput gain: $1.69\times$ over dense vLLM on the reasoning workload at 0.1 points of accuracy loss, and up to $2.1\times$ on multi-GPU long-context serving. Under prefill--decode disaggregation, OasisKV reaches about $2\times$ dense throughput while admitting each request with $6.5$--$9.7\times$ less KV and holding $2.2$-$2.6$ less decode-node host memory than full KV transfer. △ Less

Submitted 8 August, 2026; originally announced August 2026.

ControlRef: Efficient Layout-Guided Multi-Instance Generation via Anchored 4D-RoPE

Authors: Yunkai Yang, Yudong Zhang, Xinying Chen, Haoyuan Liang, Yizhuo Niu, Jinshuai Cheng, Kunquan Zhang, Liziyue Fang, Weitao Wan, Runmin Dong

Abstract: Layout-guided multi-instance generation is essential for controllable image synthesis in Multi-Modal Diffusion Transformers (MM-DiTs). However, integrating this capability into unified architectures remains challenging. Prior frameworks rely on redundant full-resolution canvas padding and Shifted-RoPE to manage multiple reference images. This mechanism drastically inflates computational overhead f… ▽ More Layout-guided multi-instance generation is essential for controllable image synthesis in Multi-Modal Diffusion Transformers (MM-DiTs). However, integrating this capability into unified architectures remains challenging. Prior frameworks rely on redundant full-resolution canvas padding and Shifted-RoPE to manage multiple reference images. This mechanism drastically inflates computational overhead for sparse layouts and disrupts critical low-frequency RoPE features, creating a severe spatial-frequency compromise that blurs absolute spatial correspondence. To overcome these limitations, we propose ControlRef, a highly efficient and precise multi-instance synthesis framework. ControlRef utilizes a Unified Instance-Layout Control (UILC) attention mask to strictly decouple inter-instance semantic interactions and enforce precise regional binding. To further promote region-level spatial alignment, we introduce Anchored 4D-RoPE, a novel positional encoding mechanism that directly anchors tokens to their absolute geometric centers. By pre-aligning reference images to their corresponding bounding box resolutions, physically anchoring both layout and reference tokens to their absolute geometric centers, and stacking the references along the z-axis, Anchored 4D-RoPE natively preserves spatial priors and mitigates the spatial-frequency compromise without lossy shifting. Extensive experiments demonstrate that ControlRef achieves state-of-the-art visual fidelity and localization accuracy, while concurrently slashing inference latency by over 80% in sparse layouts and reducing memory overhead by 50% in dense scenarios. △ Less

Submitted 7 August, 2026; originally announced August 2026.

PAST: Prompt-Adaptive Sampling Termination for Efficient Diffusion Model

Authors: Renye Yan, Jikang Cheng, You Wu, Wei Peng, Zongwei Wang, Ling Liang, Yimao Cai

Abstract: While diffusion models have made significant progress in text-to-image tasks, they still exhibit limitations when directly optimizing downstream objectives. Although Reinforcement Learning (RL) enables targeted optimization, existing methods are generally constrained by low-efficiency fine-tuning and sparse rewards. To address these challenges, we propose PAST, which provides differentiated reward… ▽ More While diffusion models have made significant progress in text-to-image tasks, they still exhibit limitations when directly optimizing downstream objectives. Although Reinforcement Learning (RL) enables targeted optimization, existing methods are generally constrained by low-efficiency fine-tuning and sparse rewards. To address these challenges, we propose PAST, which provides differentiated rewards while adaptively regulating training episode length by jointly perceiving denoising progress and prompt difficulty. Specifically, we design an intrinsic reward paradigm to compensate for sparse extrinsic rewards and guide the model to explore paths that diverge more efficiently from noise patterns. We further provide theoretical justification for intrinsic rewards. Then, PAST dynamically monitors denoising completion and semantic alignment between image structures and prompt semantics. When both metrics satisfy generation requirements, the system adaptively terminates training. This enables appropriate allocation of episode lengths based on prompt difficulty and the current generation process. Finally, based on the predicted residual noise level, we establish a dual adaptive coordination mechanism. Specifically, it not only balances the extrinsic and intrinsic rewards but also balances the exploration and convergence. Experimental results demonstrate that PAST enhances computational efficiency of existing RL fine-tuning methods by up to 66.7%, while improving preference optimization quality by up to 29.5% through its dual adaptive regulation mechanism. △ Less

Submitted 7 August, 2026; originally announced August 2026.

Explore or Converge? Stage-Guided Per-Step Optimization for Diffusion Models

Authors: Renye Yan, Jikang Cheng, You Wu, Wei Peng, Zongwei Wang, Ling Liang, Yimao Cai

Abstract: Diffusion models have strong generative capabilities. However, their maximum likelihood training objective only focuses on reconstructing the data distribution, making it difficult to align with specific preferences. Reinforcement learning (RL) for preference alignment in diffusion models is promising but limited by reward sparsity. Since a single reward cannot support optimization, existing RL me… ▽ More Diffusion models have strong generative capabilities. However, their maximum likelihood training objective only focuses on reconstructing the data distribution, making it difficult to align with specific preferences. Reinforcement learning (RL) for preference alignment in diffusion models is promising but limited by reward sparsity. Since a single reward cannot support optimization, existing RL methods usually backpropagate the final reward to all previous steps. However, denoising is stage-wise, with distinct semantics and controllability. Repeating the final reward across all steps creates a temporal objective mismatch, encouraging reward shortcuts that lead to reward hacking. At the same time, due to reward backfilling, each time step receives the same reward, making it impossible to distinguish between actions, thereby weakening the optimization process. To resolve this issue, we propose Stage-Guided Per-Step Optimization (SGPO) for diffusion models, which jointly leverages signal-to-noise ratio and semantic changes to identify generation stages and adaptively assign stage-specific objectives. Early denoising is chaotic and far from the final reward, resulting in weak reward-behavior correlation. This stage should prioritize exiting the chaotic state. In the mid stage, the latent transitions to a stable structure, where the final reward better corresponds to generative behavior. Therefore, this stage optimizes the final reward while exploring diversity to avoid early convergence to a single mode. In the late stage, the latent's core structure is largely fixed, and preference optimization mainly amplifies local details, risking overfitting. Therefore, stable convergence is preferred to avoid quality degradation. Results from 16 comparative experiments validate SGPO. Our method achieves 26.7% average gains in generative quality and 36.7% higher convergence speed. △ Less

Submitted 6 August, 2026; originally announced August 2026.

3D Molecular Representation Learning for Organic Mixtures: Viscosity and Density Prediction

Authors: Haicheng Qu, Yanyi Su, Ning Wang, Shangqian Chen, Zhifeng Gao, Jun Cheng, Qi Ou

Abstract: The viscosity and density of organic mixtures are essential properties for designing lubricants, solvents, and heat transfer fluids. In engineering practice, formulating a functional fluid requires understanding how these properties change with composition and temperature. However, exhaustive experimental characterization across the full parameter space is impractical due to the vast number of pos… ▽ More The viscosity and density of organic mixtures are essential properties for designing lubricants, solvents, and heat transfer fluids. In engineering practice, formulating a functional fluid requires understanding how these properties change with composition and temperature. However, exhaustive experimental characterization across the full parameter space is impractical due to the vast number of possible species and combinations. Here we introduce a mixture-aware 3D molecular representation learning strategy, built upon a pre-trained molecular encoder, that jointly encodes component structures, mole fractions, and temperature to achieve accurate predictions for organic mixtures. Fine-tuning on publicly available datasets covering a wide range of binary organic mixtures yields test-set R2 values of 0.973 for dynamic viscosity and 0.996 for density, significantly outperforming traditional machine learning baselines. Beyond this overall accuracy, the model captures non-monotonic viscosity changes upon mixing, surpassing simple linear or logarithmic mixing rules. The architecture is extendable to ternary and multicomponent mixtures, as verified via preliminary experiments. Using this model, we quantitatively analyze how molecular structure-branching, cycloalkane, and aromatic rings-affects viscosity-temperature behavior, which benefits the design of lubricants with superior viscosity-temperature performance. Altogether, this work provides a practical, data-driven tool for mixture property prediction, accelerating the rational formulation of functional fluids in chemical engineering. △ 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

When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs

Authors: Jiaming Cheng, Subhransu Das, Rajiv Ramnath

Abstract: Multi-agent LLM systems relay key--value caches instead of text and credit their gains to exchanged ``latent thoughts''. That credit is a claim about \emph{which} example's cache is relayed, not merely that one is. We audit it causally in released systems. The cache is replaced with deranged (mismatched-example), zeroed, and moment-matched random counterparts, under two regimes defined by whethe… ▽ More Multi-agent LLM systems relay key--value caches instead of text and credit their gains to exchanged ``latent thoughts''. That credit is a claim about \emph{which} example's cache is relayed, not merely that one is. We audit it causally in released systems. The cache is replaced with deranged (mismatched-example), zeroed, and moment-matched random counterparts, under two regimes defined by whether the receiver needs the sender's private information. Where it does, the battery reads ceiling: 100% against 23--25% for answer-irrelevant relays on the primary backbone, a contrast replicated across three families, five checkpoints, and a prose document-QA surface. Where it does not, a pre-registered five-seed protocol establishes equivalence within 2.8 points, a margin anchored to the audited system's reported gain, under Holm-corrected TOST on GSM8K and ARC-Challenge across three Qwen3 scales and on MedQA at 8B (one cell shows a small detected advantage inside the margin); a second family shows no detected advantage. A large cache effect need not be a pairing effect. In one natural cell, zeroing the relay costs 14.7 points; a mismatched cache, 0.4. Nor is need sufficient: under the same test, delivered channels span ceiling (LatentMAS's native relay), partial (KVComm's layer subset), and no detected example-specific transfer (C2C's released projector). Benchmark deltas do not by themselves establish latent-thought transmission; establishing it takes a mismatched-cache audit, which we release. △ Less

Submitted 5 August, 2026; originally announced August 2026.

Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Models

Authors: Xingyu Ding, Yuzhong Zhao, Yang Wu, Chaoyang Zhao, Chunhai Zhao, Yifan Zhang, Jian Cheng

Abstract: Recent Vision-Language-Action (VLA) methods improve generalization by aligning their representations with 3D scene geometry. However, these methods are fundamentally instruction-agnostic: the representations align the entire scene uniformly, neglecting the 3D geometry of the specific target object designated by the language instruction. This causes failures on fine-grained manipulation and target… ▽ More Recent Vision-Language-Action (VLA) methods improve generalization by aligning their representations with 3D scene geometry. However, these methods are fundamentally instruction-agnostic: the representations align the entire scene uniformly, neglecting the 3D geometry of the specific target object designated by the language instruction. This causes failures on fine-grained manipulation and target occlusion tasks, where success depends on accurate 3D understanding of the target object rather than the entire scene. To address this, we present Mind-VLA, an instruction-aware spatial representation alignment method for VLA models. Specifically, Mind-VLA first obtains the target object specified by the language instruction, then prepares its target-object tri-view and extracts the corresponding VAE and VGGT features. Finally, the latent representation of the VLA model is aligned with these features to enable instruction-aware 3D understanding. Mind-VLA reaches 93.9% on LIBERO and 4.47 on CALVIN with a compact 345M-parameter backbone. On real-robot tasks with target occlusion, Mind-VLA reaches 54% average success, outperforming the best-performing instruction-agnostic method in real-robot comparison by 32 percentage points. Code will be publicly available. △ Less

Submitted 5 August, 2026; originally announced August 2026.

Cost-Aware Multi-Objective Bandits: Theory and Application to Budgeted LLM Configuration Evaluation

Authors: Bo Xue, Zhi Hong, Jiayi Li, Yuanyu Wan, Ji Cheng, Shuang Qiu

Abstract: Large language model (LLM) configuration evaluation is challenging due to limited evaluation budgets, varying costs, and multiple competing objectives. In this paper, we formulate LLM configuration evaluation as a cost-aware multi-objective bandit problem, where each configuration evaluation incurs a configuration-dependent cost and yields a noisy vector-valued outcome. Under this framework, we st… ▽ More Large language model (LLM) configuration evaluation is challenging due to limited evaluation budgets, varying costs, and multiple competing objectives. In this paper, we formulate LLM configuration evaluation as a cost-aware multi-objective bandit problem, where each configuration evaluation incurs a configuration-dependent cost and yields a noisy vector-valued outcome. Under this framework, we study two fundamental problems: online configuration selection and Pareto configuration identification. For online configuration selection, we propose a hypervolume-based UCB algorithm that optimizes an optimistic hypervolume-per-cost index. We establish a budgeted regret bound of order $O\bigl(\sum_{i\ne i^\star}\frac{\log B}{Δ_i}\bigr)$, where $B$ is the evaluation budget, $i^\star$ is the optimal configuration in terms of hypervolume efficiency, and $Δ_i$ is the corresponding efficiency gap of configuration $i$. This bound retains the logarithmic budget dependence of classical single-objective budgeted bandits. For fixed-budget Pareto identification, we develop a cost-aware empirical gap elimination algorithm and prove that its error probability is of order $O\bigl(\exp(-\frac{B}{H_{μ,c}})\bigr)$, where $H_{μ,c}$ is a cost-aware Pareto identification complexity depending on configuration costs and Pareto classification gaps. This error probability decays exponentially with the evaluation budget and recovers the standard Pareto set identification guarantee when all configuration costs are identical. Experiments on LLM configuration evaluation tasks demonstrate that the proposed framework enables efficient online decision-making and accurate cost-aware Pareto identification under limited budgets. △ Less

Submitted 4 August, 2026; originally announced August 2026.

Efficient Online Lexicographic Generalized Low-Rank Matrix Bandits

Authors: Bo Xue, Ji Cheng, Haodong Jing, Hongzong Li, Shuang Qiu

Abstract: This paper studies generalized low-rank matrix bandits with multiple prioritized objectives. At each round, the learner selects a matrix-valued arm and observes a vector-valued reward, whose components correspond to multiple objectives with different priority levels. Each objective is governed by an objective-specific generalized low-rank matrix model, and the learner evaluates arms according to a… ▽ More This paper studies generalized low-rank matrix bandits with multiple prioritized objectives. At each round, the learner selects a matrix-valued arm and observes a vector-valued reward, whose components correspond to multiple objectives with different priority levels. Each objective is governed by an objective-specific generalized low-rank matrix model, and the learner evaluates arms according to a lexicographic preference order, prioritizing higher-level objectives before lower-level ones. We propose \textsc{Lexi-LowGLM}, an efficient online algorithm that first estimates objective-specific low-rank subspaces and then performs lexicographic learning in the reduced feature spaces. Unlike existing single-objective algorithms that repeatedly solve a batch generalized linear estimator using all historical observations, \textsc{Lexi-LowGLM} updates each objective-specific estimator via an online Newton step, reducing the estimator-update complexity over $T$ rounds from $O(T^2)$ to $O(T)$. We establish a regret bound of $\widetilde O\left(W_i^{\rm lex}\sqrt{m}\,(d_1+d_2)r\sqrt{T}\right)$ for each objective $i\in[m]$, where $r$ is an upper bound on the ranks of the objective-specific parameter matrices and $W_i^{\rm lex}$ characterizes the lexicographic trade-off effect. This bound depends on the effective low-rank dimension $(d_1+d_2)r$ rather than the ambient dimension $d_1d_2$. Numerical experiments further validate the effectiveness and computational efficiency of the proposed method. △ Less

Submitted 4 August, 2026; originally announced August 2026.

Quantum Contextuality and Entanglement-Free Grover Search in a Trapped-Ion Optical Qudit

Authors: Tarun Dutta, Jasper Phua Sing Cheng, Alex Jin, Sergi Ramos-Calderer, José Ignacio Latorre, Manas Mukherjee

Abstract: Quantum computational advantage is generally attributed to coherent interference and other non-classical resources, yet their respective roles remain difficult to disentangle in experimental platforms where multipartite entanglement is inherently present. High-dimensional quantum systems provide an attractive route for investigating these resources while simultaneously reducing hardware overhead f… ▽ More Quantum computational advantage is generally attributed to coherent interference and other non-classical resources, yet their respective roles remain difficult to disentangle in experimental platforms where multipartite entanglement is inherently present. High-dimensional quantum systems provide an attractive route for investigating these resources while simultaneously reducing hardware overhead for quantum information processing. Here we realize a programmable four-dimensional optical qudit encoded in a single trapped $^{138}\mathrm{Ba}^{+}$ ion and demonstrate universal coherent control through phase-programmable optical rotations. Using this platform, we implement an entanglement-free realization of Grover's quantum search algorithm, achieving target-state identification probabilities of up to $94.5\pm2.0\%$. Within the same processor, we further demonstrate state-dependent quantum contextuality through a Clauser--Horne--Shimony--Holt (CHSH)-type noncontextuality inequality, obtaining a maximum violation of $S = 2.816 \pm 0.082$, in close agreement with the Tsirelson bound. By integrating programmable quantum computation and contextuality measurements within a single multilevel trapped-ion platform, our work establishes a versatile architecture for investigating the relationship between coherent interference and contextuality in quantum information processing and provides a scalable route toward high-dimensional quantum technologies. △ Less

Submitted 4 August, 2026; originally announced August 2026.

Comments: 12 pages, 10 figures

Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility

Authors: Jo-Ku Cheng, Nikolaos Aletras, Marco Valentino

Abstract: Pre-pretraining language models (LMs) on symbolic data can accelerate and improve natural language acquisition. However, existing pre-pretraining tasks, such as Dyck and procedural algorithms, rely on narrow primitives that fail to capture the expressive capacity of natural language. Moreover, prior studies remain restricted to relatively small token budgets, offering limited insight into skill em… ▽ More Pre-pretraining language models (LMs) on symbolic data can accelerate and improve natural language acquisition. However, existing pre-pretraining tasks, such as Dyck and procedural algorithms, rely on narrow primitives that fail to capture the expressive capacity of natural language. Moreover, prior studies remain restricted to relatively small token budgets, offering limited insight into skill emergence and representational dynamics. To address these limitations, we propose logic pre-pretraining (Logic-PPT) as a principled initialization strategy, leveraging formal derivations to impart richer structural and linguistic biases. Formal derivations require abstract mechanisms that are central to natural language, simultaneously binding variables, connecting quantifiers and relational dependencies, and composing predicate-argument structures over long contexts. Scaling our evaluation to a 100B-token regime, logic pre-pretraining substantially accelerates skill acquisition in LMs, achieving 80\% accuracy on linguistic tasks with 36B fewer tokens than standard initialization, and outperforming alternative pre-pretraining baselines. Mechanistically, formal derivations induce persistent structural reorganization, distinctively characterized by a lower-rank, spectrally concentrated representation space. Crucially, we show that this internal geometry enables improved model compressibility via pruning, matching the dense baseline performance even at $\approx$33\% sparsity. △ Less

Submitted 4 August, 2026; originally announced August 2026.

Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learning

Authors: Meicong Zhang, Tiancheng Su, Jiahao Cheng, Guoxiu He, Xinqi Tao, Dejia Song

Abstract: Generating a rigorous paper introduction with large language models (LLMs) remains challenging, since it requires coordinating background, gap identification, method and contribution within a coherent narrative. Existing solutions externalize this process as multi-stage prompts or agent workflows which are expensive and vulnerable to cross-stage drift. We propose StructPO, a struct-aware policy le… ▽ More Generating a rigorous paper introduction with large language models (LLMs) remains challenging, since it requires coordinating background, gap identification, method and contribution within a coherent narrative. Existing solutions externalize this process as multi-stage prompts or agent workflows which are expensive and vulnerable to cross-stage drift. We propose StructPO, a struct-aware policy learning framework that internalizes the entire multi-stage writing workflow into a single-pass policy controlled by explicit stage tokens. StructPO introduces struct-aware credit assignment to decouple local stage quality from global coherence and refinement-guided optimization to internalize revision behavior into the first-pass policy. Experiments show that StructPO improves semantic alignment, structural rationality and inference efficiency over workflow-based baselines, generalizes to out-of-domain settings, and remains competitive with GPT-5.1 in human evaluation when scaled to Qwen3-32B. These results show that internalizing academic writing workflows through fine-grained policy optimization offers a viable alternative to costly external orchestration. △ Less

Submitted 4 August, 2026; originally announced August 2026.

DeGS: A Scalable 3DGS Architecture via Decoupled Workload Parsing and Reorganization

Authors: Minnan Pei, Gang Li, Zeyu Zhu, Siting Wang, Junwen Si, Zhuoran Song, Yu Feng, Fangxin Liu, Xiaoyao Liang, Jian Cheng

Abstract: 3D Gaussian Splatting (3DGS) has emerged as a leading technique for real-time novel view synthesis, yet existing 3DGS accelerators suffer from poor architectural scalability: increasing the number of PEs leads to marginal performance improvement during rendering. We identify that the root cause is the tightly coupled ``checking-while-blending'' dataflow, which exacerbates PE underutilization cause… ▽ More 3D Gaussian Splatting (3DGS) has emerged as a leading technique for real-time novel view synthesis, yet existing 3DGS accelerators suffer from poor architectural scalability: increasing the number of PEs leads to marginal performance improvement during rendering. We identify that the root cause is the tightly coupled ``checking-while-blending'' dataflow, which exacerbates PE underutilization caused by spatial redundancy from irregular Gaussian coverage and temporal redundancy from asynchronous pixel-wise termination under parallel execution. To address this issue, we propose DeGS, a scalable architecture for efficient 3DGS inference. To systematically eliminate the redundancies inherent in rendering, DeGS exploits a decoupled dataflow, restructuring the coupled $α$-checking, transmittance checking, and $α$-blending of the standard rendering process into consecutive workload parsing, reorganization, and blending stages. This allows the fragmented, length-variable, and temporal-dependent workloads to be reorganized into compact, conflict-free, and dense workloads prior to blending, thereby significantly improving PE utilization during parallel blending. Implemented in 28 nm technology, DeGS achieves 2.36$\times$--7.25$\times$ throughput, 1.82$\times$--6.02$\times$ end-to-end speedup, and 1.59$\times$--4.42$\times$ energy efficiency over state-of-the-art 3DGS accelerators (GSCore, GBU, GCC) across diverse scenes and resolutions (720p to 8K). Moreover, scaling from 16 to 1024 PEs, DeGS maintains over 80\% PE utilization at high resolutions, significantly outperforming existing accelerators. △ Less

Submitted 3 August, 2026; originally announced August 2026.

Comments: Accepted to the 59th IEEE/ACM International Symposium on Microarchitecture (MICRO 2026)

Roomer: Reflective Object-Grounded Model Editing and Repair for 3D Indoor Layout Synthesis

Authors: Lingwei Dang, Ziyan Qiu, Jiajia Cheng, Shishuo Shang, Zhenhao Zhang, Yufei Zhu, Qingxin Xiao, Pan Liu, Shenghui Huang, Yun Hao, Juntong Li, Qingyao Wu

Abstract: Existing indoor layout generators produce globally plausible layouts yet may retain local violations such as collisions, out-of-bounds placements, obstructed openings, and blocked circulation. Most prior work focuses on full-scene synthesis or scene-level optimization, with limited support for identifying responsible objects and locally repairing affected regions. We present Roomer, a reflective r… ▽ More Existing indoor layout generators produce globally plausible layouts yet may retain local violations such as collisions, out-of-bounds placements, obstructed openings, and blocked circulation. Most prior work focuses on full-scene synthesis or scene-level optimization, with limited support for identifying responsible objects and locally repairing affected regions. We present Roomer, a reflective repair framework that casts these violations as sparse, object-grounded repair problems. Roomer encodes layouts as ``RoState'' and uses ``RoReview'' to bind measured violations to implicated objects. A geometry-conditioned vision-language model planner proposes a structured local edit, while a deterministic solver validates it and generates a finite set of candidate edits when needed. Each candidate is committed only if full-scene verification confirms that it resolves the target violation without new hard violations or broken protected constraints. We train the planner on Roomer-CC, a controlled-corruption dataset that pairs faulty layouts with object-grounded violation evidence and known-feasible inverse StatePatches. Since existing benchmarks rarely assess whether physically valid layouts are usable, we introduce Roomer-Eval to assess distributional quality, physical validity, and practical usability. Experiments show that Roomer repairs residual violations while preserving valid regions, improves physical validity and usability, and transfers across external generators. △ Less

Submitted 3 August, 2026; originally announced August 2026.

StyleForge: Indoor Furniture Styling by Counterfactual Reasoning in a Hypergraph Field

Authors: Lingwei Dang, Shishuo Shang, Pan Liu, Jiajia Cheng, Ziyan Qiu, Zhenhao Zhang, Yufei Zhu, Shenghui Huang, Qingxin Xiao, Yun Hao, Juntong Li, Qingyao Wu

Abstract: Fixed-layout indoor furniture styling requires selecting assets that form a coherent room without changing the prescribed furniture categories, positions, orientations, or scales. Existing approaches typically retrieve each asset independently or rely on static local relations, making them prone to shape, material, and color conflicts after scene composition. We introduce StyleForge, a scene-level… ▽ More Fixed-layout indoor furniture styling requires selecting assets that form a coherent room without changing the prescribed furniture categories, positions, orientations, or scales. Existing approaches typically retrieve each asset independently or rely on static local relations, making them prone to shape, material, and color conflicts after scene composition. We introduce StyleForge, a scene-level structured selection framework built on a dynamic hypergraph style field. A frozen multimodal large language model extracts structured style priors from an open-ended style request and the fixed layout, while StyleForge maintains a learnable candidate distribution for each furniture slot. Conditioned on the target style, the dynamic hypergraph style field adaptively activates and weights layout-induced hyperedges to capture higher-order dependencies among furniture. Counterfactual style preference learning then treats each candidate as a local substitution in the current style field and evaluates its contextual compatibility using Mahalanobis energies. Training alternates between optimizing the style field and the candidate logits. At inference, the model remains frozen and test-time training updates only room-specific candidate logits, progressively correcting cross-slot style conflicts as the global scene context evolves. Experiments on 3D-FRONT demonstrate state-of-the-art furniture retrieval and scene-level style coherence, producing more coherent fixed-layout furniture arrangements than object- and scene-level retrieval baselines. △ Less

Submitted 3 August, 2026; originally announced August 2026.

GenTrack: Physical Alignment for Robot-Native Motion Generation and Zero-Shot Humanoid Tracking

Authors: Zeyu Ling, Xinyao Yu, Renye Yan, Jikang Cheng, Zhanke Wang, Qing Shuai, Changqing Zou

Abstract: General-purpose humanoid trackers can execute diverse references, but their zero-shot coverage depends on large embodied corpora that are costly to extend. Text-to-motion generators offer scalable supervision, yet models trained on human motion or retargeted data inherit a gap between kinematic plausibility and robot executability. Existing one-way pipelines fix either the generated corpus or the… ▽ More General-purpose humanoid trackers can execute diverse references, but their zero-shot coverage depends on large embodied corpora that are costly to extend. Text-to-motion generators offer scalable supervision, yet models trained on human motion or retargeted data inherit a gap between kinematic plausibility and robot executability. Existing one-way pipelines fix either the generated corpus or the reward tracker. We introduce GenTrack, an online generator--tracker framework that alternates execution-grounded, group-relative generator alignment with tracker training on newly generated references; anchoring and rehearsal constrain drift. On Unitree G1, we evaluate GenTrack with ProtoMotions and SONIC backbones across three zero-shot tracking splits including public AMASS and LAFAN benchmarks, and a private out-of-distribution test set of 1,024 prompt-motion pairs in the wild. The online co-training strategy consistently produces generators that output more robot-executable motions with strong semantic alignment, and trackers with markedly broader zero-shot coverage and improved tracking accuracy, especially on out-of-distribution references. These results demonstrate that joint online post-training effectively narrows the executability gap between retargeted references and robot-native motion, advancing zero-shot humanoid control without additional data collection and beyond the limitations of a static reference pool. △ Less

Submitted 5 August, 2026; v1 submitted 2 August, 2026; originally announced August 2026.

ACE-GraphRAG: Agentic Context Engineering for Hierarchical GraphRAG

Authors: Yongfeng Huang, Yuren Lai, Ruiying Chen, Haoyu Huang, Mingming Zhao, James Cheng

Abstract: Hierarchical Graph Retrieval-Augmented Generation (GraphRAG) organizes corpus knowledge at multiple levels of granularity, yet fixed context construction may fail to translate these multi-resolution representations into a context suited to the current query. We identify this mismatch as the representation--inference gap. We propose Agentic Context Engineering for Hierarchical GraphRAG (ACE-GraphRA… ▽ More Hierarchical Graph Retrieval-Augmented Generation (GraphRAG) organizes corpus knowledge at multiple levels of granularity, yet fixed context construction may fail to translate these multi-resolution representations into a context suited to the current query. We identify this mismatch as the representation--inference gap. We propose Agentic Context Engineering for Hierarchical GraphRAG (ACE-GraphRAG), an inference-time context policy layer that supplements and adapts the initial context for generation. ACE-GraphRAG formulates context construction as a policy over gap-aware refinement, retrieval branches, and task-conditioned adaptation. Parallel Differential Retrieval acquires supplementary evidence from depth-oriented factual and breadth-oriented semantic branches. These evidence increments are consolidated with the initial context while preserving provenance and abstraction levels. Full-ACE applies the full policy uniformly within each task family, whereas Adaptive-ACE selects task- and topology-specific policies for individual queries. We evaluate ACE-GraphRAG on HotpotQA, 2WikiMultiHopQA, and four UltraDomain subsets across multi-hop QA and query-focused summarization. Full-ACE outperforms the evaluated RAG and GraphRAG baselines across both task families, while Adaptive-ACE further improves multi-hop QA and is preferred over Full-ACE on all four UltraDomain subsets. Ablation and topology analyses support treating context construction as a query- and task-dependent inference policy rather than a fixed procedure. △ Less

Submitted 3 August, 2026; v1 submitted 2 August, 2026; originally announced August 2026.

Comments: Withdrawn because the manuscript was posted prematurely before completion of the required internal review and release authorization

Why Ammoniated Lithium Borohydrides Liquefy and Resolidify?

Authors: Qian Wang, Zixin Xu, Ryuhei Sato, Hiroki Miyaoka, Takayuki Ichikawa, Eric Jianfeng Cheng, Shin-ichi Orimo, Fangqin Guo, Hao Li

Abstract: Ammonia ($\mathrm{NH_3}$) absorption drives $\mathrm{LiBH_4\!\cdot\!xNH_3}$ through a re-entrant ``solid--liquid--solid'' transition: $\mathrm{LiBH_4\!\cdot\!NH_3}$ is a well-defined solid ammoniate, compositions near $\mathrm{LiBH_4\!\cdot\!2NH_3}$ are liquid-like or partially liquefied, whereas $\mathrm{LiBH_4\!\cdot\!3NH_3}$ returns to a more rigid non-liquid ammoniate state. However, the micro… ▽ More Ammonia ($\mathrm{NH_3}$) absorption drives $\mathrm{LiBH_4\!\cdot\!xNH_3}$ through a re-entrant ``solid--liquid--solid'' transition: $\mathrm{LiBH_4\!\cdot\!NH_3}$ is a well-defined solid ammoniate, compositions near $\mathrm{LiBH_4\!\cdot\!2NH_3}$ are liquid-like or partially liquefied, whereas $\mathrm{LiBH_4\!\cdot\!3NH_3}$ returns to a more rigid non-liquid ammoniate state. However, the microscopic origin of this unintuitive response remains a long-lasting mystery. Here, we uncover its mechanism. Cross-database analysis identifies borohydrides as a particularly state-diverse and composition-responsive material family. Structure prediction and ab initio molecular simulations reveal that $\mathrm{NH_3}$ progressively replaces $\mathrm{BH_4^-}$ in the Li coordination shell. The liquid-like state emerges not at the highest $\mathrm{NH_3}$ loading but near $x\approx2$, where Li--N and Li--B coordination modes are strongly mixed, coordination memory is weakest, and the sampled Li--N/N$\cdots$B coordination landscape is broadest. Further ammoniation produces Li--N-dominant coordination and slows $\mathrm{BH_4^-}/\mathrm{NH_3}$ contact renewal, with the resulting increase in network persistence and accompanying recovery of a rigid ammoniate state. Pressure--composition isotherm, $^{1}\mathrm{H}$ and $^{11}\mathrm{B}$ nuclear magnetic resonance, and Raman measurements support this non-monotonic state evolution and associated $\mathrm{BH_4^-}/\mathrm{NH_3}$ reorganization. These findings transform ammonia-induced liquefaction from an empirical phase anomaly into a competition between native-network disruption, mixed-coordination frustration, and ligand-built network reconstruction, providing a framework for chemically switching between transport-favouring fluidity and stability-favouring rigidity in hydrogen-rich materials. △ Less

Submitted 3 August, 2026; v1 submitted 2 August, 2026; originally announced August 2026.

Comments: 21 pages, 4 figures

SIPTraj: Map-Free End-to-End Trajectory Prediction via Physics-Guided Scene Interaction

Authors: Feifei Liu, Zejun Wei, Haozhe Wang, Yazhi Ye, Yuying Zhang, Jintao Cheng, Chi Man Vong, Xieyuanli Chen, Xiaoyu Tang

Abstract: Trajectory prediction of surrounding agents is a prerequisite for safe planning and decision making in autonomous driving. Without high-definition (HD) maps, sensor-derived bird's-eye-view (BEV) features provide no explicit lane topology or drivable-area priors, making it inherently difficult to ground each agent in its surrounding scene context. Moreover, physical feasibility remains difficult to… ▽ More Trajectory prediction of surrounding agents is a prerequisite for safe planning and decision making in autonomous driving. Without high-definition (HD) maps, sensor-derived bird's-eye-view (BEV) features provide no explicit lane topology or drivable-area priors, making it inherently difficult to ground each agent in its surrounding scene context. Moreover, physical feasibility remains difficult to capture through data-driven learning alone, as kinematic constraints on agent motion cannot be explicitly encoded without structured supervision. Existing map-free predictors extract scene context in an agent-agnostic manner through a single fusion step and treat physical constraints only as output-level penalties, leaving both challenges unaddressed. We propose SIPTraj, a map-free trajectory prediction framework that jointly addresses scene grounding and physical feasibility. SIPTraj introduces a Hierarchical Agent-Scene Encoder (HASE) progressively grounding each agent in agent-guided scene evidence and refining inter-agent relations within the scene-grounded space. To tackle physical infeasibility in predicted trajectories, we develop a Physics-Guided Iterative Decoder (PGID). It conditions decoding on instantaneous kinematic states, propagating physical supervision into internal representations rather than output trajectories alone. Extensive experiments on nuScenes and Argoverse 2 Sensor show that SIPTraj surpasses prior map-free predictors and strong map-based baselines without any HD map at inference. Our code will be released as open-source. △ Less

Submitted 1 August, 2026; originally announced August 2026.

HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation

Authors: An Liu, Bingxi Liu, Hongyu Ding, Yixuan Jiang, Yaran Chen, Fulin Tang, Cong Leng, Hong Zhang, Jian Cheng

Abstract: Vision-and-language navigation (VLN) enables robots to follow instructions in previously unseen environments. Recently, a training-free paradigm has emerged: the robot queries a multimodal LLM to understand its observations and plan the next action. However, long-horizon navigation based on either image streams or dense map inevitably introduces a growing memory and reasoning bottleneck. We presen… ▽ More Vision-and-language navigation (VLN) enables robots to follow instructions in previously unseen environments. Recently, a training-free paradigm has emerged: the robot queries a multimodal LLM to understand its observations and plan the next action. However, long-horizon navigation based on either image streams or dense map inevitably introduces a growing memory and reasoning bottleneck. We present HAM-VLN, a decision-coupled, agent-authored memory that equips the robot with a persistent, depth-grounded world graph. In the same model call used to select the next action, HAM-VLN also records semantic and reflective information---including room type, objects, navigation progress, and failure notes. Recent waypoints remain verbatim within a bounded window, while older history re-enters the context only through retrieval scored by relevance, recency, and salience, together with one-hop topological expansion. This design requires no additional LLM calls beyond the per-waypoint decision. Compared to previous methods, HAM-VLN not only improves various navigation metrics but also reduces the context length by more than 65%. Specifically, HAM-VLN achieves 61.0% Success Rate (SR) on VLN-CE R2R, 52.7% SR on VLN-CE RxR, and 79.7% SR on HM3D-v2 ObjectNav without any training. △ Less

Submitted 31 July, 2026; originally announced July 2026.

MOT-SR: Multi-Objective Tool-Augmented Scientific Equation Discovery with Large Language Models

Authors: Boxiao Wang, Runxiang Wang, Kai Li, Chongming Li, Zhiwei Chen, Yifan Zhang, Jian Cheng

Abstract: Symbolic Regression (SR) aims to discover analytical equations from observational data and plays a central role in scientific modeling. While recent Large Language Model (LLM) based approaches show promise, they face two limitations. First, they lack data analysis mechanisms for uncovering variable dependencies, which reduces the efficiency of equation discovery. Second, most methods rely on singl… ▽ More Symbolic Regression (SR) aims to discover analytical equations from observational data and plays a central role in scientific modeling. While recent Large Language Model (LLM) based approaches show promise, they face two limitations. First, they lack data analysis mechanisms for uncovering variable dependencies, which reduces the efficiency of equation discovery. Second, most methods rely on single-objective evaluation focused solely on fitting error. This neglect of structural complexity and generalization often causes models to converge prematurely to local optima, limiting their ability to explore the broader equation space. We propose Multi-Objective Tool-augmented Symbolic Regression (MOT-SR), a unified framework that integrates external analytical tools to extract structural priors and guide equation generation, while jointly optimizing for accuracy, complexity, and generalization via a multi-objective evaluation module that maintains a dynamic Pareto front. MOT-SR employs two collaborative LLM modules: a Meta Strategy Generator, which selects tools and synthesizes structural optimization strategies based on Pareto-optimal equations, and an Equation Generator, which produces new candidate equations accordingly. The system operates in a closed-loop manner, continuously refining both strategies and equation structures. Across 40 standard tasks, MOT-SR outperforms existing SR methods in accuracy, generalization, and efficiency. We further validate MOT-SR on extreme mass-ratio inspiral (EMRI) orbital modeling, an important problem in space-based gravitational-wave astronomy where small local errors can accumulate substantially over long-term evolution. The discovered interpretable correction achieves the lowest trajectory-level integration error on held-out configurations. These results demonstrate the potential of MOT-SR to enable reliable modeling of long-horizon scientific dynamics. △ Less

Submitted 31 July, 2026; originally announced July 2026.

Comments: Code is available at https://github.com/wswbx/MOT-SR

Is It Time for the Renaissance of Salient Object Detection in the Era of MLLMs?

Authors: Wenzhuo Zhao, Xiuzhi Li, Zhongkuan Mao, Ronghao Xian, Yao Jiang, Zhao Gao, Keren Fu, Qijun Zhao, Jian Cheng

Abstract: The zero-shot capabilities of multimodal large language models (MLLMs) are pushing salient object detection (SOD) beyond task-specific supervision. To disentangle MLLMs beyond conventional mask-based evaluation, we decompose SOD into localization and segmentation, and re-engineer datasets with phrases, boxes, and attributes, establishing a diagnostic benchmark for MLLM saliency perception (SaliLLM… ▽ More The zero-shot capabilities of multimodal large language models (MLLMs) are pushing salient object detection (SOD) beyond task-specific supervision. To disentangle MLLMs beyond conventional mask-based evaluation, we decompose SOD into localization and segmentation, and re-engineer datasets with phrases, boxes, and attributes, establishing a diagnostic benchmark for MLLM saliency perception (SaliLLM). SaliLLM uncovers a striking capability mismatch: MLLMs outperform state-of-the-art (SOTA) methods in localization, yet remain substantially weaker in segmentation. Further analyses attribute this gap primarily to mismatches between MLLMs and annotations over foreground cardinality, granularity, and extent. Motivated by this diagnosis, we recast zero-shot SOD as protocol-aligned Foreground Organization and introduce the first training-free framework that leverages Gestalt-inspired Collaborative attention for Unified SOD (FOCUS). FOCUS couples top-down Bayesian-surprise calibration of protocol-conditioned foreground granularity with bottom-up propagation of MLLMs evidence over entity-centric perceptual manifolds induced by self-supervised features, yielding coherent object extents as prompts for a general segmenter. Across 13 RGB, RGB-D, and RGB-T SOD benchmarks, FOCUS generally surpasses SOTA methods without training, reducing mean absolute error by 11\%, 34\%, and 48\% compared with fully, weakly, and self-supervised methods, respectively. Our findings signal the renaissance of SOD: from task-specific supervision to zero-shot foreground organization. Code is available in the supplementary material. △ Less

Submitted 31 July, 2026; originally announced July 2026.

Comments: 10 pages, 4 figures, conference

AutoPref: Automatic Discovery of Task-Specific Preference Objectives for Neural Combinatorial Optimization

Authors: Shengda Gu, Kai Li, Xinyi Ke, Haobo Fu, Yifan Zhang, Jian Cheng

Abstract: Combinatorial optimization problems (COPs) underpin many real-world decisions, but their exponentially large search spaces make high-quality solutions costly to obtain. Neural combinatorial optimization (NCO) learns fast construction policies, typically with reinforcement learning (RL), while preference-based NCO improves sample efficiency by learning from relative solution quality. However, exist… ▽ More Combinatorial optimization problems (COPs) underpin many real-world decisions, but their exponentially large search spaces make high-quality solutions costly to obtain. Neural combinatorial optimization (NCO) learns fast construction policies, typically with reinforcement learning (RL), while preference-based NCO improves sample efficiency by learning from relative solution quality. However, existing preference objectives combine two distinct design choices in manually specified, one-size-fits-all formulations: what learning signal to extract from each solution pair and how to weight each pair relative to the sampled set. We present AutoPref, the first LLM-guided framework for automated preference-objective discovery in NCO. AutoPref factorizes the objective into a pairwise loss program, which defines the learning signal, and a set-aware weighting program, which determines each pair's relative contribution. Their composition forms a unified programmatic objective space containing existing preference objectives as special cases. To make its search tractable, we introduce a staged conditional search strategy with behavioral gates that filter inadmissible programs before short-horizon training and evaluation. Across TSP, CVRP, FFSP, and JSSP, AutoPref consistently outperforms strong hand-designed baselines across problem scales, demonstrating the benefits and scalability of automated objective discovery for NCO. △ Less

Submitted 30 July, 2026; originally announced July 2026.

Comments: 8pages, 2figures

ActSWM: Action-Sensitive World Models for Long-Horizon Planning in Open-World Games

Authors: Zhenfeng Gan, ZiTong Zeng, Jiajun Cheng, Yeke Song, Yongyi Tang, Xueqian Wang

Abstract: Latent world models support efficient model-predictive control by optimizing future control sequences in latent space and replanning in a receding-horizon manner. However, existing latent predictors often lack stable long-horizon rollout ability, and prediction accuracy alone does not ensure that rollouts remain responsive to the actions being planned. We identify Context Collapse, a failure mode… ▽ More Latent world models support efficient model-predictive control by optimizing future control sequences in latent space and replanning in a receding-horizon manner. However, existing latent predictors often lack stable long-horizon rollout ability, and prediction accuracy alone does not ensure that rollouts remain responsive to the actions being planned. We identify Context Collapse, a failure mode in which autoregressive latent predictors maintain high similarity to future states while producing nearly indistinguishable futures under different action sequences. To address this issue, we propose ActSWM, an action-sensitive latent world model grounded in a transition-separation principle: a planning-useful latent dynamics model should keep alternative-action futures distinguishable and make the action associated with each local transition recoverable. Under this principle, action sensitivity is enforced as a constraint on latent rollouts rather than treated only as an auxiliary prediction target, encouraging predicted futures to preserve action-dependent differences over long horizons. Across step-drift analysis, closed-loop Minecraft planning, and cross-game local action recovery, ActSWM preserves larger action-dependent rollout gaps than existing baselines, improves task success in long-horizon interactive settings, and enables world-model-based action recovery from offline gameplay videos. △ Less

Submitted 15 August, 2026; v1 submitted 29 July, 2026; originally announced July 2026.

Comments: 10 pages, 5 figures

EvoPINN: Agentic Discovery of Executable Algorithms for Physics-Informed Neural Networks

Authors: Peng Yin, Kai Li, Yifan Zhang, Jian Cheng

Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs), yet their performance heavily relies on the manual, trial-and-error engineering of neural representations, loss formulations, and optimization dynamics. While Large Language Models (LLMs) offer a promising avenue for automated design, unconstrained code generation often y… ▽ More Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs), yet their performance heavily relies on the manual, trial-and-error engineering of neural representations, loss formulations, and optimization dynamics. While Large Language Models (LLMs) offer a promising avenue for automated design, unconstrained code generation often yields mathematically invalid or numerically unstable solutions under strict scientific computing constraints. To bridge this gap, we propose \textbf{EvoPINN}, an agentic framework that reformulates PINN development from labor-intensive manual design into a rigorous, execution-grounded algorithm discovery problem. EvoPINN navigates a modular search space by decoupling neural representations from training programs, utilizing an LLM agent to iteratively propose memory-conditioned programmatic modifications. To ensure scientific validity, all candidates undergo strict structural verification and budget-matched PDE evaluation. Extensive experiments across diverse PDE regimes (oscillatory, elliptic, dissipative, and nonlinear transport) demonstrate that EvoPINN discovers PDE-specialized learning algorithms that significantly reduce relative $L_{2}$ error compared to baselines. Crucially, EvoPINN autonomously invented SLRC-PINN, a novel architecture whose performance gains persist under rigorous parameter-matched comparisons, establishing the viability of execution-grounded agents for discovering genuinely new scientific computing mechanisms. △ Less

Submitted 29 July, 2026; originally announced July 2026.

Instruction-based Image Editing: A Survey on Data, Models, Evaluation, and Applications

Authors: Xianghao Zang, Zijian Jiang, Jiarong Cheng, Qianrui Teng, Ying He, Yuxuan Mu, Chao Ban, Huayu Zhang, Lanxiang Zhou, Zerun Feng, Chi Zhang

Abstract: Instruction-based Image Editing (IIE) aims to transform a given image into a new one based on textual instructions. Advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) have accelerated progress toward practical ``one-sentence image editing" systems. This survey presents a systematic taxonomy and comprehensive review of IIE research, structured around five core dimensions: (1… ▽ More Instruction-based Image Editing (IIE) aims to transform a given image into a new one based on textual instructions. Advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) have accelerated progress toward practical ``one-sentence image editing" systems. This survey presents a systematic taxonomy and comprehensive review of IIE research, structured around five core dimensions: (1) task definition and hierarchical categorization of editing operations, (2) methodologies for training data construction, (3) architectural evolution from GAN-based to diffusion and autoregressive paradigms, (4) standardized evaluation metrics and benchmark development, and (5) introduction of commercial solutions. Our analysis shows critical technological milestones across model generations. We further propose a Comprehensive, in-Depth, and Diagnostic benchmark for IIE task (CDD-IIE Bench), which can rigorously assess the multiple aspects of model performance. Through empirical comparisons of open-source solutions, we highlight their respective capabilities and limitations. Finally, we discuss future research directions to advance the field. △ Less

Submitted 28 July, 2026; originally announced July 2026.

Comments: 33 pages, 7 figures, Vicinagearth

Journal ref: Zang, X., Jiang, Z., Cheng, J. et al. Instruction-based image editing: a survey on data, models, evaluation, and applications. Vicinagearth 3, 3 (2026)

Tau functions of the constrained matrix KP hierarchy

Authors: Xiaohan Fan, Jipeng Cheng, Jinbiao Wang

Abstract: The constrained matrix KP hierarchy $(L^{k})_{<0}=\sum_{i=1}^{m}Q_{i}\partial^{-1}R_{i}^{\intercal}$ is investigated from the aspects of tau functions. Firstly, the matrix KP hierarchy is viewed as one special reduction of the multi-component KP hierarchy. Then bilinear equations of the constrained matrix KP hierarchy as the multi-component KP hierarchy are given in terms of tau functions. Finally… ▽ More The constrained matrix KP hierarchy $(L^{k})_{<0}=\sum_{i=1}^{m}Q_{i}\partial^{-1}R_{i}^{\intercal}$ is investigated from the aspects of tau functions. Firstly, the matrix KP hierarchy is viewed as one special reduction of the multi-component KP hierarchy. Then bilinear equations of the constrained matrix KP hierarchy as the multi-component KP hierarchy are given in terms of tau functions. Finally based upon these results, the tau functions for the constrained matrix KP hierarchy are constructed by using the multi-component boson-fermion correspondence. Notice that the solutions of the constrained matrix KP hierarchy are derived without using quasi-determinants. △ Less

Submitted 28 July, 2026; originally announced July 2026.

Comments: 22 pages

MSC Class: 35C08; 35Q53; 37K10; 37K40

PreDiff-LM: Pretrained Discrete Masked Diffusion Language Modeling with Hybrid Attention

Authors: Zhengtao Yao, Runhao Li, Xupeng Chen, Jiayi Cheng, Chenqian Le, Michael Yue, Jesson Wang, Siheng Wang, Guang Yang, Haoyan Xu, Chenhao Wei, Zhengqing Yuan, Youran Shen, Yanfang Ye, Junhao Dong

Abstract: Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requires reconciling causal pretraining with bidirectional denoising. We study this problem at the level of attention rather than claiming AR-weight reuse itself as novel. PreDiff-LM preserves causal attention within the observed prompt while allowing f… ▽ More Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requires reconciling causal pretraining with bidirectional denoising. We study this problem at the level of attention rather than claiming AR-weight reuse itself as novel. PreDiff-LM preserves causal attention within the observed prompt while allowing full bidirectional attention within the masked target. Under a matched GPT-2 Medium, WikiText-103, 90K-step setup, this hybrid mask improves unconditional perplexity from 34.1 to 28.7 and MAUVE from 0.71 to 0.78 over uniform bidirectional attention with the same AR initialization. Attention adaptation also composes with a DiffuGPT-style objective adaptation, reaching 26.9 perplexity. Pretrained initialization reduces the steps required to reach perplexity below 50 from about 350K to 8K, although a compute-matched fine-tuned AR model remains stronger at equal scale (18.9 versus 28.7). Beyond perplexity, PreDiff-LM improves repetition, distributional quality, four zero-shot downstream tasks, and human preference over prior diffusion baselines. The results position hybrid attention as a complementary mechanism for adapting pretrained causal backbones, while making explicit the remaining quality and inference-efficiency gaps to optimized AR models. △ Less

Submitted 27 July, 2026; originally announced July 2026.

Less Data, Better Alignment: Data-Centric Multi-Evaluator Agreement for Preference Optimization

Authors: Zhengtao Yao, Runhao Li, Xupeng Chen, Jiayi Cheng, Chenqian Le, Michael Yue, Siheng Wang, Haoyan Xu, Yuqi Li, Chenhao Wei, Zhengdao Li, Rongchao Zhang, Guang Yang, Yidong Wang, Junhao Dong

Abstract: Research on preference optimization often varies the training objective while holding the data fixed. We instead ask whether a small, high-confidence set of on-policy responses can provide a reliable learning signal. Our method, DMAPO (Data-centric Multi-evaluator Agreement for Preference Optimization), generates candidate responses from the target policy, evaluates helpfulness, factuality, and co… ▽ More Research on preference optimization often varies the training objective while holding the data fixed. We instead ask whether a small, high-confidence set of on-policy responses can provide a reliable learning signal. Our method, DMAPO (Data-centric Multi-evaluator Agreement for Preference Optimization), generates candidate responses from the target policy, evaluates helpfulness, factuality, and conciseness with rubric-specialized evaluators, applies a process-critic correction, and retains only high-consensus desirable or undesirable examples. This procedure accepts 1,871 of 54,236 Mistral-7B candidates (3.45%). KTO trained on this set reaches 7.50 on MT-Bench, 95.5% length-controlled win rate against a text-davinci-003 reference, and 57.3% IFEval prompt accuracy. Independent pairwise evaluation also favors DMAPO over SimPO: GPT-4o yields a net win rate of 23.3 points on 129 held-out prompts and 24.0 points on 200 out-of-distribution LMSYS-Chat prompts; Claude Opus 4.7 yields 24.1 points on the held-out set. Changing the evaluator model or rubric alters the selected examples but has little effect on downstream performance. A second-backbone study yields a similar 3.41% acceptance rate, although its performance gains are more modest. Across these experiments, consensus filtering offers a data-efficient route to preference optimization for general instructions, at the cost of additional curation compute and dependence on evaluator judgments. △ Less

Submitted 27 July, 2026; originally announced July 2026.

Comments: 19 pages

Ranked by Position: Order Sensitivity as an Exploitable Attack Surface in LLM Listwise Recommenders

Authors: Ge Zhang, Jingru Cheng, Huiyuan Chen

Abstract: Large language models (LLMs) used as listwise rerankers in recommendation systems suffer from position bias when serializing candidate sets into prompts. We show this order sensitivity creates an exploitable attack surface: an attacker can promote a label-0 target into the top-$k$ solely by reordering candidates, without changing item content, labels, or model parameters. We introduce… ▽ More Large language models (LLMs) used as listwise rerankers in recommendation systems suffer from position bias when serializing candidate sets into prompts. We show this order sensitivity creates an exploitable attack surface: an attacker can promote a label-0 target into the top-$k$ solely by reordering candidates, without changing item content, labels, or model parameters. We introduce $\mathrm{promo}@k$ to quantify this vulnerability, measuring the fraction of label-0 targets that can be elevated into top-$k$ rankings via permutation. Evaluating across three domains (MovieLens, Amazon Books, and Amazon Fashion), $\mathrm{promo}@5$ reaches up to 0.57 at an attack budget of $R$ = 50 orderings. Furthermore, ordinary permutation stability predicts vulnerability without running the attack. While a bidirectional T5 encoder scorer reduces exposure, permutation-consistency regularization and architectural invariance effectively mitigate it. Pointwise scoring avoids the bias issue but degrades ranking quality. These results demonstrate that input candidate order in listwise LLM reranking is a security-relevant attack vector. Code and data are available at https://github.com/geoz-lab/position_bias_attack. △ Less

Submitted 26 July, 2026; originally announced July 2026.

Comments: 13 pages, 6 figures, 11 tables. Code and data available at https://github.com/geoz-lab/position_bias_attack

KuaiLive-M3: A Multi-Modal, Multi-Domain, and Multi-Feedback Dataset for Live Streaming Recommendation

Authors: Ke Guo, Changle Qu, Jiayaqi Cheng, Xiao Zhang, Shijun Wang, Xiaoyu Zhang, Xueliang Wang, Le Zhang, Lantao Hu, Jun Xu

Abstract: Existing public live streaming datasets suffer from three major limitations: they provide limited access to temporally evolving multimodal live content, overlook users' cross-domain interactions between short videos and live streams, and contain only implicit behavioral signals without explicit feedback that captures users' perceived content quality and satisfaction. These limitations prevent exis… ▽ More Existing public live streaming datasets suffer from three major limitations: they provide limited access to temporally evolving multimodal live content, overlook users' cross-domain interactions between short videos and live streams, and contain only implicit behavioral signals without explicit feedback that captures users' perceived content quality and satisfaction. These limitations prevent existing benchmarks from faithfully reflecting real-world live streaming scenarios and hinder comprehensive research on live streaming recommendation. To address these limitations, we introduce KuaiLive-M3, a multi-modal, multi-domain, and multi-feedback dataset for live streaming recommendation, collected from Kuaishou, a leading live streaming and short video platform in China. KuaiLive-M3 covers 21,938 users and contains 35 million live streaming interactions and 111 million short video interactions, with fine-grained timestamps and diverse user behaviors. It further provides approximately 88 million timestamped segment-level multi-modal embeddings that capture the temporal evolution of live streaming content, as well as 25,403 questionnaire-based feedback records that bridge implicit user behaviors and explicit user preferences. Based on these unique signals, we establish benchmarks for cross-domain recommendation, live stream highlight prediction, and questionnaire-enhanced recommendation. Extensive experiments with representative baselines demonstrate that KuaiLive-M3 provides a challenging and realistic benchmark for future live streaming recommendation research. The results further highlight the importance of modeling temporally evolving content, transferring user preferences across domains, and bridging the gap between implicit behaviors and explicit user feedback. The dataset and benchmark code are publicly available at https://imgkkk574.github.io/KuaiLive-M3/. △ Less

Submitted 26 July, 2026; originally announced July 2026.

R-process nucleosynthesis from magnetar giant flares in neutron star--white dwarf mergers: A unified picture for peculiar long gamma-ray bursts

Authors: Shu-Qing Zhong, Long Li, Le Zou, Ji-Gui Cheng, Yan-Zhi Meng, Jia-Hong Gu

Abstract: Peculiar long gamma-ray bursts (GRBs), exemplified by GRBs 211211A and 230307A, exhibit a long-duration multi-component prompt emission, an X-ray plateau in their afterglow, and a kilonova signature. Their origin remains highly debated. In this work, we present a unified picture for these events based on neutron star--white dwarf (NS--WD) mergers involving a pre-merger magnetar and a massive WD. I… ▽ More Peculiar long gamma-ray bursts (GRBs), exemplified by GRBs 211211A and 230307A, exhibit a long-duration multi-component prompt emission, an X-ray plateau in their afterglow, and a kilonova signature. Their origin remains highly debated. In this work, we present a unified picture for these events based on neutron star--white dwarf (NS--WD) mergers involving a pre-merger magnetar and a massive WD. In this picture, tidal disruption of the WD forms a constant-entropy accretion disk. Hyperaccretion from this disk onto the NS during the early accretion phase amplifies its toroidal magnetic field to strengths sufficient to trigger repeated magnetar giant flares (GFs). The main burst (MB) of the prompt emission consists of a ``forest'' of initial spikes from these GFs, while the subsequent magnetic propeller phase generates the extended emission (EE) and naturally explains the observed MB--EE trough. Crucially, the $e^{\pm}$-$γ$ fireball associated with each GF initial spike shocks the NS crust, leading to crustal ejection that synthesizes r-process heavy elements via the $α$-rich freeze-out mechanism, thereby resolving the r-process deficit in conventional NS--WD hydrodynamic simulations. The ensemble of such fireballs over the MB duration collectively yields $M_{\rm ej}\gtrsim 10^{-5}-10^{-3}\,M_\odot$ of ejecta, sufficient to power the observed kilonova signature when further boosted by the spin-down of the post-merger magnetar. Meanwhile, the spin-down radiation also powers the X-ray plateau. This tidally disrupted NS--WD merger picture provides a self-consistent framework that unifies the prompt emission, afterglow, kilonova, and r-process nucleosynthesis observed in peculiar long GRBs. △ Less

Submitted 27 July, 2026; originally announced July 2026.

Comments: accepted by A&A

Understanding Machine Unlearning Through the Lens of Mode Connectivity

Authors: Jiali Cheng, Hadi Amiri

Abstract: Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch. Despite recent progress, the loss landscape and optimization geometry of unlearning are poorly understood. In this paper, we study machine unlearning through the lens of mode connectivity--the phenomenon that independently trained models can often be connected by smooth low-loss paths… ▽ More Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch. Despite recent progress, the loss landscape and optimization geometry of unlearning are poorly understood. In this paper, we study machine unlearning through the lens of mode connectivity--the phenomenon that independently trained models can often be connected by smooth low-loss paths in parameter space. We introduce {\em mode connectivity in unlearning} (MCU) and evaluate it across a range of settings, including curriculum learning, second-order optimization, and connectivity across different unlearning methods. We find that many unlearned models lie in connected basins with smooth retain/forget behavior, while changes in training dynamics can move solutions into different basins. MCU also reveals that models within the same basin can differ substantially on privacy metrics, and that unlearning progresses nonlinearly from the original model to the unlearned model. In addition, linear connectivity suggests that most approximate unlearning methods are mechanistically distinct from retraining. Finally, MCU-based ensembling can improve generalization and robustness to relearning attacks, and MCU smoothness correlates with unlearning difficulty. To our knowledge, this is the first study of machine unlearning through the lens of mode connectivity. △ Less

Submitted 3 August, 2026; v1 submitted 26 July, 2026; originally announced July 2026.

Comments: This work was intended as a replacement of arXiv:2504.06407 and any subsequent updates will appear there