Computer Vision
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
All of arXiv
Tuesday 1 September
Collaborative perception shares information among multiple agents to obtain a comprehensive scene representation, enhancing the perceptual capability of individual agents. However, most existing methods rely on transmitting and fusing dense feature maps for collaboration, which incurs inevitable communication overhead and heterogeneity challenges, limiting their practicality for real-world deployment. To address these challenges, we propose CERF, a novel Communication-Efficient and Retraining-Free framework for open heterogeneous collaborative perception. In CERF, we introduce a new virtual modality (termed Poture), which is generated from the perception outputs of other agents, to augment the extracted Bird's Eye View (BEV) features of the ego agent. To mitigate transmission delays, we employ a Kalman-filter based tracker and a motion forecasting model to derive the current predictions from historical perception results. Extensive experiments demonstrate that CERF achieves performance comparable to mainstream intermediate-collaboration methods while reducing communication overhead by 95% across various downstream tasks. Furthermore, CERF enables seamless integration of unknown heterogeneous agents into the existing collaborative framework without additional retraining costs. Code is available at https://github.com/uestchjw/CERF.
Robotics
HitMem: Hierarchical Temporal 3D Memory with Multi-Modal Context-Aware Retrieval for Dynamic Environments
Executing long-term tasks in dynamic environments requires embodied agents to maintain robust and adaptive 3D scene representations. However, most existing 3D memory frameworks rely on static world assumptions. When objects are displaced by human activities or unobserved events, agents encounter memory-observation conflicts and often require costly geometric recomputations or inefficient global re-exploration. To address this, we propose HitMem, a hierarchical temporal 3D memory framework with a multi-modal context-aware retrieval mechanism. Through continuous perception, HitMem unifies semantic and spatial information into a lightweight topological graph that captures support relationships, while a temporal decay mechanism dynamically regulates memory activeness to mitigate the impact of stale representations. In addition, the multi-modal context-aware retrieval mechanism defaults to filtering candidates using integrated semantic, spatial, and temporal memory features, and activates a specialized two-stage retrieval process when object displacement is detected. This process combines spatial constraints inferred from external agent trajectories with semantic common sense grounded in class affinities, efficiently identifying high-probability candidate regions. Extensive evaluations on our constructed Dyna-THOR benchmark demonstrate that HitMem significantly improves object relocation accuracy, reduces exploration costs, and enhances task execution performance in dynamic environments.
Read the full abstract
Computation and Language
Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling
Multi-turn tool calling is a core evaluation scenario for large language model (LLM) agents. On public tool-calling benchmarks, open-weight models now approach or even surpass closed-source frontier models in aggregate accuracy. However, this metric averages over many different multi-turn situations and obscures whether progress is balanced across them. We propose an action-class-oriented diagnostic framework that decomposes multi-turn failures into two orthogonal modes: action-class miscalibration and action-execution failure. The framework operates over a four-class action space (TOOL_CALL/ASK/REFUSE/CONFIRM) and introduces a self-revealing upper bound Acc <= GAR (Gold Action Recall); the two modes show up as bound violation (Acc > GAR, exposing state-grader masking of miscalibration) and large bound slack (GAR >> Acc, localizing execution failure within TOOL_CALL). We validate it on a panel of tool-calling models across multiple multi-turn benchmarks. Across our panel, the diagnostic reveals action-class miscalibration as a substantial failure mode the state grader cannot see. This gap inflates standing for heavily tool-trained families, which our diagnostic separates from families with context-appropriate action choice. Calibration is reshapable through context-only perturbations, but the reshape is heterogeneous: a single perturbation moves accuracy in opposite directions across families (up to +11.5 vs -21.0 pp on the same scenario), and its effect further depends on the perturbation mechanism. We argue that multi-turn tool-calling evaluations should supplement aggregate accuracy with action-class diagnostics that expose what the model actually does in each scenario.
Read the full abstract
Computer Vision
From Terminology to Diagrams: Visual-Instruction Generation for Scientific Diagram Understanding
Vision-language models (VLMs) have demonstrated strong performance in visual question answering with natural images. However, they continue to struggle with scientific diagrams, which are designed to convey functional or relational meaning rather than literal scenes. We therefore introduce a framework for generating large-scale diagram-grounded instruction data by leveraging terminology derived from scientific curricula. Our approach systematically extracts domain concepts, synthesizes atomic facts, retrieves relevant diagrams from the web, and generates multimodal supervision in the form of diagram captions and multiple-choice questions. Using this pipeline, we construct SciGram, a dataset of over 194K diagrams and 1.4M visual instructions across life, earth, and physical sciences. Despite relying on noisy web data and synthetic annotations, models fine-tuned on SciGram achieve substantial improvements on diagram-centric benchmarks, including TQA, ScienceQA, and AI2D, outperforming or matching state-of-the-art VLMs while using fewer training instances. Furthermore, augmenting existing models such as LLaVA OneVision with SciGram establishes new state-of-the-art performance on diagram question answering. Our results highlight the effectiveness of terminology-grounded instruction generation as a general strategy for improving vision-language reasoning in scientific domains. To support future research in scientific diagram understanding, we release both the SciGram dataset and models.
Read the full abstract
Rings and Algebras
The injective envelope of simple modules over Leavitt path algebras I: simple left ideals
Let $K$ be any field and $E$ any directed graph. We characterize up to isomorphism the simple (i.e., minimal) left ideals of the Leavitt path algebra $L_K(E)$. Then, for each simple %(i.e., minimal) left ideal $I$ of %the Leavitt path algebra $L_K(E)$, we explicitly construct the injective envelope of $I$. This result generalizes to all graphs $E$ and all simple left ideals in $L_K(E)$ the construction presented previously by the three authors for the specific case of the Jacobson algebra $R=K\langle X,Y | XY=1\rangle$ and the simple left $R$-ideal $R(1-YX)$. Our method involves defining an $L_K(E)$-module structure on a $K$-vector space of infinite series. We conclude the article by showing how our construction directly gives a description of the injective envelope of simple $L_K(E)$-modules arising from two types of infinite emitters in $E$.
Read the full abstract
Machine Learning (Statistics)
Embedded Conditional Independence Tests for Large Language Model Generated Text with an Application to German Parliament Speeches
Conditional independence tests (CITs) test for conditional dependence between two random objects $X$ and $Y$ given a third random object $Z$. Existing CITs have limited applicability to high-dimensional data, especially multimodal data like text. However, we show that such tests are of interest for large language model (LLM) outputs, where we test whether an output $X$ generated from a source text $Z$ carries information about an attribute $Y$ beyond $Z$ itself. For this purpose, we propose embedded CITs (eCITs), which embed $X$ and $Z$ and apply an existing CIT to the resulting representations and to $Y$. We show that, provided the embedding of $Z$ is sufficient, i.e. retains the information $Z$ carries about either $Y$ or the representation of $X$, the null hypothesis transfers from $X$ and $Z$ to their representations, so that a CIT valid for the embedded hypothesis is valid for the original one. We further give conditions for equivalence of the two hypotheses, and show that sufficiency weakens to mean sufficiency when the embedded test targets conditional mean independence. We propose a semi-synthetic simulation design to assess type I error (T1E) control and power of the eCITs for given embedding maps on a specific dataset and task, and use it to evaluate them on our application. Applying the eCITs to German Parliament speeches, we find for all combinations of embedding maps considered that the summaries of two LLMs contain information about the speaker's faction and gender beyond the speech they were generated from.
Read the full abstract
General Relativity and Quantum Cosmology
Constraining AGN Disk Properties with Gravitational Waves from Inspiraling Stellar-Mass Binary Black Holes in Hierarchical Triple Systems
Space-based gravitational-wave detectors can observe stellar-mass binary black holes (BBHs) long before merger, allowing weak environmental perturbations to accumulate. For binaries embedded in active galactic nucleus (AGN) disks, the local gas density characterizes the environment of the supermassive black hole (SMBH) and compact-object migration. We study whether such signals can constrain this density when a stellar-mass BBH orbits a Kerr SMBH. We evolve the outer orbit with relativistic corrections and gaseous dynamical friction (DF), and construct the detector-frame waveform including BBH inspiral, de Sitter precession, DF phase correction, and moving-source effects. Using Fisher-matrix calculations for sampled systems, we estimate statistical uncertainties and systematic errors. Larger gas densities generally improve the statistical precision of several source and outer-orbit parameters, but also increase systematic errors when DF is omitted. For favorable GW190521-like systems observed by LISA for one year, the disk density can be constrained at the level of $\sigma_{\rho}\sim10^{-12}\text{--}10^{-10}\,{\rm g\,cm^{-3}}$. Such constraints would connect BBH merger environments to the gas structure of galactic nuclei and the conditions that support black hole growth. These results indicate that hierarchical BBH inspirals can probe AGN disk environments, provided that gas effects are modeled consistently.
Read the full abstract
Combinatorics
The Ramsey threshold for trees versus odd cycles
A longstanding fundamental problem of Burr, Erdős, Faudree, Rousseau and Schelp (Trans. Amer. Math. Soc., 1982) is to determine the exact value of the least integer $f(m)$, for odd $m\ge3$, such that every tree $T_n$ on $n\ge f(m)$ vertices satisfies $R(T_n,C_m)=2n-1$. We settle this problem for all sufficiently large odd $m$. Indeed, we establish $$f(m)=\left\lceil \frac{2m-1}{3} \right\rceil$$ for all such $m$, where the lower bound follows from a result by Faudree, Lawrence, Parsons and Schelp. This also confirms a conjecture of Huang, Zhang and Chen for all such $m$.
Read the full abstract
Risk Management
Illiquidity at Risk
Market efficiency relies fundamentally on stable liquidity. Consequently, forecasting liquidity dynamics is a priority for both investors and regulators. We introduce a new tail-risk metric, Illiquidity-at-Risk (IlliQaR), designed to quantify the magnitude of extreme liquidity dry-ups. Relying upon the realized Amihud (a precise illiquidity measurement derived from high-frequency data as the ratio of realized volatility to trading volume) we assess the predictive power of various linear and non-linear econometric models, with a specific focus on the impact of discontinuous jump components. Accounting for these jumps is essential for achieving accurate probability coverage and better IlliQaR predictions during periods of systemic stress, where standard continuous models systematically underestimate the severity of liquidity evaporation. Our empirical analysis, encompassing the S&P 500 index and a cross-section of 25 large U.S. equities, demonstrates that incorporating jumps significantly improves forecasts of illiquidity. Our results suggest that individual stock IlliQaR violations often cluster during periods of S&P 500 liquidity stress. This indicates that Illiquidity at Risk is not just a localized concern but a systemic one, where the main index acts as a leading indicator for extreme dry-ups in individual stock liquidity.
Read the full abstract
High Energy Physics (Theory)
Fuchsian Resonance and a Horizon-to-Boundary Dictionary for Pole-Skipping
Pole-skipping occurs at special complex frequencies and momenta where the retarded Green function of a black-hole or black-brane background is not uniquely defined. The local near-horizon mechanism is well known: at resonance, a Frobenius recurrence matrix loses rank and the space of smooth horizon solutions enlarges. We address the global question of how two boundary-normalized solutions enter this resonant horizon solution space. For a general second-order scalar radial equation on a nonextremal background analytic near the horizon, the Frobenius recurrence at the resonant order yields a solvability condition. We prove that its vanishing is equivalent to singularity of the horizon recurrence matrix, absence of the logarithmic Frobenius term, and existence of two independent smooth horizon solutions. Away from resonance, the source zero is equivalent to horizon smoothness of the response-normalized solution, while the response zero is equivalent to horizon smoothness of the source-normalized solution. We then analyze the parameter-dependent simple pole of the nonresonant ingoing solution as resonance is approached. After removing this singularity, its resonant limit is proportional to the larger-root Frobenius solution, with proportionality factor given by the same solvability function. Continuing to the boundary shows that the same condition is equivalent to simultaneous vanishing of the two regularized boundary connection coefficients. This establishes a horizon-to-boundary dictionary between local Fuchsian resonance and the boundary source-response 0/0 structure of pole-skipping. Finally, different directions of approach can select different resonant solutions, with the selection governed by the first parameter variation of the same solvability function.
Read the full abstract
Robotics
ProxPI: Proximal Prior Injection for Sampling-Based MPC under Learned-Prior Mismatch
Combining learned policies with model predictive control can leverage learned task priors while retaining online adaptation to new objectives and constraints, but performance degrades when the policy is out of distribution. In policy-guided model predictive path integral (MPPI) control, a policy-centered warm-start approach centers the sampling distribution on the policy output. When the prior is mismatched, centering the sampling distribution on the policy output restricts exploration around an unsuitable solution and prevents recovery toward the task optimum. We propose Proximal Prior Injection (ProxPI), which retains nominal-centered MPPI sampling and incorporates the policy through a soft proximity cost. This matches the in-distribution performance of existing prior-injection schemes while enabling the optimizer to escape an inaccurate policy and recover vanilla MPPI-level performance. We theoretically show that re-centering on the prior discards the optimizer's correction at every update, whereas nominal-centered sampling retains it and converges to a solution set by both the task cost and the prior, and that this failure is not removed by a larger rollout budget. Simulations and real-robot experiments demonstrate robust performance under both in-distribution and out-of-distribution tasks.
Read the full abstract
Computation and Language
A Dataset for Modeling Iterative Problem-Solving
Solving problems through repeated attempts is a sequential modeling task: at each step, the solver receives feedback and decides how to revise their solutions. Predicting whether performance improves, plateaus, or regresses across attempts is central to understanding any iterative problem-solving process in both human learners and autonomous agents. Beyond outcomes, modeling what errors persist and how strategies shift across attempts provides deeper insight into the mechanics of sequential learning. Studying these dynamics requires observing many solvers as they attempt, receive feedback, and revise. Programming courses with automated grading provide this setting, as students iteratively submit code to test suites and receive feedback on every attempt. We therefore curate CodeInsight, a large-scale dataset of over 3 million submissions from 3,286 undergraduates across 2 introductory C++ courses in 2 academic years, with test-case-level outcomes, timestamps, and source code. On this dataset, we build a benchmark that evaluates models spanning parametric, sequential, and generative traditions under a shared calibration-and-scoring protocol, including a Recurrent State Space Model (RSSM) adapted to track solver characteristics through discrete latent variables and an LLM-based predictor that generates explicit solutions. The adapted RSSM achieves the strongest predictive accuracy on three of the four courses. The LLM predictor is less accurate but produces full submissions at each attempt, enabling direct analysis of failure modes. We find that the model's coding proficiency is inversely related to predictive performance in this setting, with the LLM better understood as a generative solver conditioned on context rather than a faithful predictor of solver behavior. We publicly release our code and the dataset on request to facilitate future research.
Read the full abstract
Quantum Physics
Robust CZ gate against flux line memory
High-fidelity CZ gates are central to superconducting quantum processors, but implementations based on flux tuning are still sensitive to pulse distortion. Conventional predistortion, typically used for an isolated gate, can recover the desired flux at the chip but it fails if the flux line memory exists, causing the fidelity of repeated CZ gates to drop rapidly. To address this issue, we model the flux line distortion as the dynamics of a stateful classical actuator coupled to a quantum system. Using a first-order Dyson expansion, we derive the error generators induced by variations in the initial flux-line state. We then design a robust CZ gate by optimizing the flux pulse to suppress these generators and minimize the residual flux line state at the gate exit. A one-pole flux line model shows the expected first-order robustness plateau. For a more practical three-pole model, the optimized CZ pulse achieves $F_{\mathrm{avg}}=99.998\%$, suppresses all first-order error generators, and brings the residual flux line state close to zero. With no additional waiting time between gates, our robust pulse achieves $F_{\mathrm{avg}}=99.97\%$ for the complete ten-gate sequence and reduces the sequence infidelity by a factor of about $2.3\times10^{3}$ relative to the baseline under the same predistortion protocol. These results show that explicitly accounting for flux line memory maintains high-fidelity CZ operation across repeated gate sequences and addresses a key limitation of conventional predistortion.
Read the full abstract
Solar and Stellar Astrophysics
X-shooter survey Across Regions and Ages to probe Disk Evolution (ARADE): Accretion properties in Orion A and their relation with disk masses
We present a homogeneous VLT/X-Shooter study of accretion in young stellar objects spanning the entire Orion A complex. Our sample includes 91 pre-main-sequence stars hosting a protoplanetary disk according to Spitzer photometry, of which 34 have complementary ALMA dust mass measurements. We derived stellar and accretion properties using a self-consistent multi-component fitting procedure. Our sample encompasses spectral types from K3 down to M5, corresponding to stellar masses within $\sim$0.8-0.1 $M_{\odot}$. The accretion-stellar luminosity ($L_{acc}-L_{\star}$) and the mass accretion rate-stellar mass ($\dot{M}_{acc}-M_{\star}$) scaling relations in Orion A are consistent with those of other star-forming regions (SFRs) that span a range of stellar densities, far-ultraviolet (FUV) irradiation fields, and ages, with all regions occupying the same locus in parameter space. For the 34 sources with complementary dust mass measurements, we present the first investigation of the $\dot{M}_{acc}$ and disk mass ($M_{disk}$) correlation in Orion A, recovering a spread consistent with that reported for other regions. Despite our sample spanning nearly five orders of magnitude in local FUV field strength, we find no statistically significant correlation between $\dot{M}_{acc}$ and FUV irradiation. However, by combining our sample with literature measurements in Lupus, the Orion Nebula Cluster, and $\sigma$ Orionis, we find a tentative population-level decrease of the inferred disk lifetime $t_{\rm disk} =M_{disk}/\dot{M}_{acc}$ toward stronger FUV environments, though large intrinsic scatter and limited sample sizes at intermediate and high FUV fields prevent firm conclusions. The homogeneous $\dot{M}_{acc}$ measurements reported here provide a solid foundation for future studies of accretion and disk evolution across the diverse environments of Orion A and other SFRs.
Read the full abstract
Information Theory
Exact Payload-Decoupling Conditions for Pilot-Only BEM Channel Estimation With Application to OTFS
In high-mobility doubly dispersive links, basis expansion models (BEMs) reduce channel dimensionality, yet unknown payload symbols generally contaminate conventional matched-pilot channel estimates. This paper establishes the exact conditions under which such estimates become payload-independent and derives a pilot, guard, and data-placement rule that guarantees these conditions. We prove a necessary-and-sufficient zero pilot–data interference (ZPDI) condition under which the matched-pilot least-squares (LS) solution coincides with the maximum-likelihood (ML) estimator for the reduced pilot statistic. When ZPDI holds, estimation requires a single precomputed projection. When it does not, the estimate contains a deterministic, channel-scaled payload bias that persists at high signal-to-noise ratio. A disjoint-support rule, independent of the selected basis, realizes ZPDI through pilot, guard, and data placement. We then specialize the framework to orthogonal time–frequency space (OTFS) and examine its structural and performance consequences. With the generalized complex-exponential BEM (GCE-BEM), the ZPDI estimator remains within about $2$~dB of the perfect channel state information benchmark in bit error rate at speeds up to 500~km/h.
Read the full abstract
Algebraic Geometry
Extended Abstract of Counting Divisorial Contractions with Centre a $cA_n$-Singularity
This text is chapter 149 of the ZAG Handbook of Algebraic Geometry. We review the main results of the paper "Counting divisorial contractions with centre a $cA_n$-singularity", published in Publications of the Research Institute for Mathematical Sciences, Kyoto University.
Computation and Language
DualStake: Dual-Path Confidence Calibration in Deep Research Agents
Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. However, these agents suffer from severe overconfidence, making their expressed confidence unreliable for user trust and downstream abstention. To address this, we augment the Deep Research pipeline with step confidence elicitation after each retrieval, building on the commonly used post-answer verbalized confidence. Interestingly, we find that Evidence Confidence (E-Conf), elicited after the final retrieval step, provides a stronger uncertainty signal than Answer Confidence (A-Conf), elicited after answer generation, and that A-Conf is largely shaped by E-Conf. Based on these findings, we propose DualStake, a dual-path calibration method that applies margin-clipped, confidence-dependent stake rewards to jointly align E-Conf and A-Conf with answer correctness while limiting extreme confidence optimization. Experiments on Qwen2.5-7B, Qwen2.5-7B-Instruct, and Qwen3-4B across 8 QA benchmarks demonstrate that DualStake consistently improves calibration without sacrificing answer accuracy. The code is available at https://github.com/FloXXXt/DualStake.
Read the full abstract
General Relativity and Quantum Cosmology
Polarization Images of Neutron Stars Illuminated by a Thin Accretion Disk: A Comparison with Black Holes
We investigate linear polarization images of static, spherically symmetric neutron stars illuminated by a geometrically and optically thin accretion disk. Neutron star equilibrium configurations are constructed with a polytropic equation of state, and the null geodesic equations and the parallel transport equation for the linear polarization vector are solved in the geometric optics approximation. The numerical results show that the total polarized intensity is generally positively correlated with the total intensity and reaches its maximum near the neutron star surface. As the observer inclination increases, the symmetry of the polarization images is progressively broken. In addition, the magnetic field configuration mainly affects the direction of the polarization vectors, while its influence on the overall polarized intensity distribution is comparatively limited. To further characterize the spatial structure of the polarization direction, we introduce the net electric vector position angle $\chi_{\mathrm{net}}$ and the second azimuthal Fourier mode $\angle\beta_2$. A comparison with polarization images of a Schwarzschild black hole reveals clear differences between the two types of compact objects in the locations of strongly polarized regions and the size of the central region without a polarization signal. These results show that linear polarization images provide information beyond total intensity images for distinguishing neutron stars from black holes.
Read the full abstract
Cellular Automata and Lattice Gases
Optical free space extreme learning machine for the implementation of emergent complex systems
Cellular automata conform a set of computational models which evolve with a reduced set of simple rules, yet still are able to show extremely complex emergent phenomena such as fractals and universal computation. Despite their apparent simplicity, they have shown great potential in simulating natural systems and solving challenging computational tasks such as classification and image generation. Instead of implementing cellular automata purely at the software level, it is desirable to design novel analog computing platforms that physically evolve following the automata's underlying rules, thereby reducing power requirements and latency. Here, we introduce an optical extreme learning machine for the simulation of a wide range of cellular automata. Our system operates in free space, and uses a spatial light modulator to encode the evolution rules of the system, while coherent wave propagation performs the corresponding computations. Our results demonstrate a simple, fully-programmable, cost and power efficient, and easy to build and align platform for the implementation of a wide range of complex computational systems such as elementary cellular automata, Conway's Game of Life, and two-dimensional Turing machines.
Read the full abstract
High Energy Physics (Phenomenology)
Investigating three-body resonances in $\alpha\alpha\Omega/\Omega_{ccc}$ clusters within the $^{9}_{\Omega/\Omega_{ccc}}{\mathrm{Be}}$ nucleus
We investigate the bound and resonant states of the $\alpha+\alpha+\Omega$ and $\alpha+\alpha+\Omega_{ccc}$ three-body systems, corresponding to $^{9}_{\Omega}{\mathrm{Be}}$ and $^{9}_{\Omega_{ccc}}{\mathrm{Be}}$, within the Gaussian expansion method combined with the complex scaling method. The $\alpha\Omega$ and $\alpha\Omega_{ccc}$ interactions are constructed by folding the $N\Omega$ and $N\Omega_{ccc}$ potentials obtained from lattice QCD calculations by the HAL QCD Collaboration with the nucleon density distribution of the $\alpha$ particle. The uncertainty associated with the $\alpha$-particle matter radius is also examined. For the $\Omega$ sector, the strong $N\Omega$ attraction generates deeply bound $0_1^+$, $2_1^+$, and $4_1^+$ states in $^{9}_{\Omega}{\mathrm{Be}}$, accompanied by a pronounced contraction of the $\alpha\alpha$ core, demonstrating a strong gluelike effect of the $\Omega$ baryon. An unconventional inversion between the $0_1^+$ and $4_1^+$ levels is also predicted. In contrast, the $\Omega_{ccc}$ baryon produces considerably weaker attraction: the $0_1^+$ state of $^{9}_{\Omega_{ccc}}{\mathrm{Be}}$ is weakly bound, whereas the $2_1^+$ and $4_1^+$ states remain resonances. Their resonance energies and widths exhibit a clear dependence on the strength of the $\alpha\Omega_{ccc}$ interaction. These results reveal qualitatively different gluelike behaviors of the $\Omega$ and $\Omega_{ccc}$ baryons and provide predictions for the spectroscopy of exotic multistrange and triply charmed hypernuclei.
Read the full abstract
Materials Science
Beyond Panchromatic Absorption: Deciphering the Excited-State Maze from Light Absorption to Photocatalysis in Dye-Sensitized MOFs
Metal–organic frameworks (MOFs) are promising photocatalysts whose visible-light absorption can be extended through linker functionalization; however, a red-shifted absorption edge does not guarantee enhanced efficiency. Here, we establish a multi-spectroscopic framework to decipher the photophysical fate of photoexcited states in diazo-sensitized UiO-66 using 2D photoluminescence (PL/PLE) mapping and wavelength-resolved continuous-wave X-band photo-EPR. By correlating visible absorption with photo-EPR and PLE action spectra, we distinguish a productive red shift from a non-productive emissive red shift. In highly active UiO-66-Anisole (97% activity relative to \ch{TiO2}), photo-EPR tracks the new absorption band, confirming that excitation populates a charge-transfer pathway yielding persistent, spin-separated states. Conversely, poorly active UiO-66-$\beta$-naphthol (4%) exhibits an extended visible absorption tracked by PLE but not photo-EPR. This reflects excitation trapping in a localized state caused by an ortho-$\mathrm{OH}$ group forming a rigid intramolecular hydrogen bond, which locks the keto-hydrazone tautomer and disrupts the conjugated azo bridge. A new optical overlap descriptor ($S_{\mathrm{Exc}}$) quantitatively captures this trade-off across the series. We demonstrate that photosensitizer design must suppress rigid tautomeric traps and target specific charge-transfer manifolds ($\lambda \le 500$~nm) rather than merely maximizing apparent panchromatic absorption breadth.
Read the full abstract
Solar and Stellar Astrophysics
Kinematic Relationship Between Solar Extreme Ultraviolet Waves and Type II Metric Radio Bursts
Solar extreme-ultraviolet (EUV) waves are large-scale disturbances that manifest as bright wavefronts, often during coronal mass ejections (CMEs). According to the magnetic field line stretching model, this phenomenon comprises two components: a fast-mode CME piston-driven shock wave and a slower, nonwave component. They are often associated with solar type II radio bursts. It is expected the radio source and the fast-mode EUV wave should come from different parts of the same shock, i.e., the CME piston-driven shock, and their speeds should be strongly correlated. To investigate this relationship, we utilized high spatiotemporal resolution observations from the Solar Dynamics Observatory in conjunction with radio data from the Radio Solar Telescope Network. Our analysis reveals that there exists a linear correlation between the EUV fast-mode speeds ($v_{euv}$) and the shock speeds derived from metric (m) type II radio bursts ($v_{radio}$), which is $v_{radio}=0.89v_{euv}+51$ kms$^{-1}$, with a correlation coefficient of 0.77. This strong correlation suggests that original coronal EIT waves, which are about three times slower than type II radio bursts, are not fast-mode waves, and it is misleading to map type II radio bursts to EIT waves in the literature.
Read the full abstract
Signal Processing
Rotatable Antenna Enabled Multi-Satellite Communications: Joint Satellite Selection and Boresight Trajectory Optimization
This paper considers a satellite-to-ground communication system in which a ground station (GS) equipped with independently rotatable antenna (RA) elements jointly decodes independent streams from multiple low-Earth-orbit (LEO) satellites over a shared time–frequency resource. Specifically, we formulate a two-timescale throughput maximization problem under exogenous cochannel interference, capturing serving-set composition, RA-enabled channel shaping, time-varying satellite geometry, and mechanically constrained inter-epoch reconfiguration. We first characterize the joint effects of interference-whitened channel strength and spatial separability on multi-satellite reception, motivating the joint design of satellite selection and RA control. With the RA trajectory fixed, we establish the monotone submodularity of the epoch-level selection objective and construct an incumbent-tight modular lower-bound surrogate, leading to an efficient discrete Minorization-Maximization (MM) selection algorithm. For fixed serving sets, we develop slew-feasible RA updates based on Riemannian gradients and organize them into a two-color parallel update scheme. The two blocks are integrated into a monotone alternating algorithm with guaranteed objective convergence. Simulations demonstrate consistent gains over benchmark schemes and reveal an optimal balance between channel strength and spatial separability. The results further show that satellite selection is particularly important in underloaded and actuator-limited regimes, whereas RA shaping becomes more influential near full spatial loading.
Read the full abstract
Quantum Physics
Thermal screening and critical scaling of quantum energy teleportation in a harmonic chain
We develop a finite-temperature Gaussian-state formulation of quantum energy teleportation in the one-dimensional harmonic chain. For Gibbs states, the optimized measurement-feedback protocol reduces to thermal two-point functions. In the single-site protocol, the extracted energy is governed by a single correlator, which makes the thermodynamic and near-critical limits analytically tractable. At fixed finite temperature, the extracted energy is exponentially screened with distance and is controlled by a thermal correlation length for both critical and non-critical $\alpha$. In the zero-temperature critical limit taken after the thermodynamic limit, we derive the exact asymptotic law $E_{\mathrm{ext}}\sim d^{-4}$. Numerical results confirm both regimes and resolve the crossover responsible for the apparent drift of the effective decay exponent at intermediate distances. We also analyze squeezed Gaussian measurements and show that they modify the extraction prefactor: $p-$squeezing enhances the extracted energy, whereas $q-$squeezing suppresses it, without changing the large-distance scaling.
Read the full abstract
Optimization and Control
Real-Time Model Predictive Control Algorithms for Autonomous Spacecraft Guidance
This report studies and compares four families of Model Predictive Control (MPC) algorithms for autonomous spacecraft rendezvous guidance: Linear MPC, Tube MPC, Fast/Embedded MPC, and Successive Convexification (SCvx). Using the Clohessy-Wiltshire-Hill (CWH) relative-motion model, we show that the marginal stability of the underlying dynamics causes the condition number of the condensed Hessian to grow sharply with the prediction horizon, which explains why gradient-based solvers such as Fast MPC diverge under long-horizon stress tests while exact linear-algebra solvers (ADMM with Cholesky factorisation) remain unaffected. Tube MPC is validated across five standard rendezvous manoeuvres (Translation, R-bar, V-bar, Natural Motion Circumnavigation, and Corkscrew) using a single fixed controller configuration, and a two-sided, provably correct bound is derived to bracket the worst-case tracking error directly from the cost weight matrices. The framework is further extended to track an arbitrary, non-closed-form reference trajectory through online-recomputed linearisation, with the safety guarantee holding throughout. Finally, to assess feasibility for real flight software, the core numerical routines (Cholesky factorisation and the Riccati equation solver) are re-implemented from first principles, without external libraries, and validated against standard scientific computing tools to machine precision. Taken together, these results support Tube MPC as a robust and computationally realistic controller for onboard, real-time spacecraft rendezvous guidance.
Read the full abstract
Mesoscale and Nanoscale Physics
Cavity-control of Majorana bound states in superconductor-semiconductor heterostructures
We theoretically study a hybrid superconductor-semiconductor platform hosting Majorana bound states coupled to a single mode photonic cavity. Starting with a one-dimensional wire coupled to a bulk $s$-wave superconductor embedded in a photonic cavity, we derive an effective light-matter Hamiltonian for such a platform. Assuming that the photonic vector potential is aligned along the tunneling between a wire and a superconductor, we find that the cavity coupling enters only in the effective superconducting pairing term. By solving the coupled electron-photon Hamiltonian using different approaches, such as exact diagonalization in case of zero or large number of photons, high-frequency expansion, and mean-field decoupling, we find that the phase boundary between the topological trivial phases is shifted to smaller values of the Zeeman energy compared to the uncoupled case. Cavity embedding has the strongest effect on the phase diagram in the semiclassical regime, corresponding to a large number of photons. In all cases, we find that at large values of the light-matter coupling strength the effective superconducting pairing is suppressed, driving the system into the gapless phase. We demonstrate that even small light-matter coupling strength allows for entering the topological phase at values of the Zeeman energy compared to the uncoupled platform.
Read the full abstract
Computation and Language
Context-Grounding Gains Are Mediated by Pre-existing Machinery: Auditing GRPO, SFT, and DPO
Language models can ignore prompt evidence when it conflicts with memorized knowledge. Post-training can make models follow such evidence more reliably, but it is unclear whether these gains require new machinery or strengthen machinery already present. We compare nine post-training arms spanning GRPO, SFT, and DPO from one starting checkpoint, with key comparisons extended across scales and families. We estimate a grounding direction from that checkpoint before training. Across five tested GRPO variants, grounding gains are small. For the two variants replicated across seeds, equivalence tests bound their effects below the conflict-SFT gain even as the rewarded metric improves. Conflict-SFT improves grounding moderately, while DPO drives grounding near ceiling on its matched distribution. Conflict-SFT and DPO largely use the same causal attention-head set as the starting model. Subtracting the starting-model direction suppresses both gains, while adding it to the starting model recovers 35% of DPO's gain at a dose passing all stated side-effect checks. After a supervised warm start makes the context answer appear in more rollouts, the same GRPO recipe adds essentially no further grounding gain. In our setting, grounding gains largely depend on machinery already present in the starting model.
Read the full abstract
Computer Vision
Beyond the Image Plane: World-Grounded Queries for Multi-Object Tracking
Monocular videos record 3D scenes as sequences of 2D image-plane projections, obscuring depth and spatial relationships. Multi-object trackers localize and associate objects primarily using appearance and geometry observed only in the image plane, inheriting these ambiguities. To address this limitation, we introduce PLANET, an end-to-end multi-object tracker designed to move beyond the image plane. As an enabling step, we lift existing 2D tracking datasets into 3D. We then form world-grounded queries by embedding reconstructed 3D scene geometry into the features and positional encodings used during query formation. An auxiliary 3D location prediction task further encourages the queries to encode object positions during training. A complementary dual-resolution temporal memory preserves this evidence across longer temporal gaps. As a result, PLANET achieves state-of-the-art performance across three diverse benchmarks.
Read the full abstract
Computer Vision
On-the-Fly3R: Towards Robust Online 3D Reconstruction with Feed-Forward 3R Models for Large-Scale UAV Scenarios
While feed-forward 3D reconstruction (3R) offers efficient end-to-end modeling, its application in large-scale UAV mapping is hindered by the prohibitive memory cost of Transformer attention. Current scalable streaming 3R methods assume temporally and spatially continuous inputs, rendering them ineffective for the weakly ordered or unordered image streams common in cross-strip UAV operations. To address this, we propose On-the-Fly3R, a training-free, progressive online 3D reconstruction framework for large-scale UAV images that upgrades various 3R backbones for large-scale UAV scenarios. Our method enables reconstruction from unordered inputs via retrieval-guided dynamic subset construction, which adaptively selects spatially relevant images. To further improve the robustness, a validation-rejection-retry mechanism is designed to guarantee global consistency, performing a pre-integration consistency check and automatically rejecting misaligned images and retrying with alternative subset. Finally, inspired by VSLAM, pose graph optimization based on the retrieval loop closure is employed to mitigate camera drift. Evaluations on several UAV benchmarks show that our On-the-Fly3R successfully scales various 3R models to over 5,000 images across square-kilometer UAV scenes, delivering substantially superior accuracy compared to several SOTA streaming 3R methods. Code is available at https://github.com/Sh1nZzz/On_the_Fly3R
Read the full abstract
Differential Geometry
The Morse Index, Nullity and Jacobi Fields of Constant-Curvature Minimal 2-Spheres in Complex Projective Spaces
We determine the Morse index and normal nullity of all constant-curvature minimal two-spheres in complex projective spaces, identify the normal Jacobi kernel as an $\SU(2)$-module, and prove that every normal Jacobi field is integrable. The formulas include all totally geodesic extensions. In a fixed ambient space, the normal nullity is constant along each Veronese sequence.