Game Theory
Sharp Second-Best Welfare in Bilateral and Matching Markets
Zhengyang Liu, Ying Qin and Zihe Wang
How much social welfare must a
market lose because values are private? We determine the sharp ratio of second-best to first-best welfare under independent nonnegative types,
Bayesian incentive compatibility, interim individual rationality, and no expected budget deficit. The ratio is approximately $0.8882516903$ for arbitrary priors and $0.9113893681$ when buyers have monotone hazard rates and sellers are unrestricted. The arbitrary-prior guarantee holds for every downward-closed family of feasible matchings; the MHR guarantee holds when every matching of a compatibility graph is feasible. Both constants are \revise{attained}{sharp} already in bilateral trade. The proof keeps the sellers' initial endowment inside the budget Lagrangian. For arbitrary priors, a common threshold decomposition reduces the problem to three-parameter power-law distributions. For monotone hazards, common transformations of buyer and seller scores reduce it to shifted capped exponential buyers; a typewise allocation certificate and an explicit worst-case seller satisfy the same boundary equation. The bilateral-to-matching framework, with a welfare endowment charge and an MHR-preserving packing argument, transfers these affine inequalities without loss. We give exact variational characterizations of both constants and reproducible interval certificates for their numerical evaluation. Unrestricted signed transfers also permit pointwise strong budget balance.
Read the full abstract ▾
Signal Processing
Bias-Compensated Complex-Valued Bilinear Filtering
Bernhard Plaimer, Andreas Meingassner-Lang, Yannis Kowalewski et al. (+3 more)
Complex-valued optimal and adaptive filters are widely used to identify unknown systems in a broad range of practical applications. Recently, a number of complex-valued bilinear filters, such as the complex-valued bilinear Wiener filter (C-BWF), and the complex-valued bilinear least mean squares (C-BLMS) filter, have been proposed to model and identify complex-valued systems, which are bilinear with respect to their coefficients. However, if the input signals are contaminated with noise, the performance of these complex-valued bilinear filters degrades significantly due to an additional noise-induced bias. To overcome this issue, we propose novel bias-compensated complex-valued bilinear filters that estimate and account for input-noise statistics. Specifically, a bias-compensated C-BWF and a bias-compensated C-BLMS filter are derived in this work. We further include a convergence analysis for the latter. Since practical applications require knowledge of the input-noise variance, we briefly present an adapted method from literature to estimate this quantity. Finally, simulation results demonstrate the superior performance of the proposed filters compared to their standard (non-bias-compensated) counterparts and several state-of-the-art methods.
Read the full abstract ▾
All authors Bernhard Plaimer, Andreas Meingassner-Lang, Yannis Kowalewski, Matthias Wagner, Oliver Lang, Mario Huemer
Spectral Theory
Periodic graph operators with reducible dispersion polynomials for all potentials
Diantong Li
We give a complete characterization of periodic graph operators whose dispersion
polynomials are reducible for every potential. Consequently, the reducibility dichotomy for parameter-dependent Laurent
polynomials implies that, for every other periodic graph operator, the dispersion
polynomial, and hence the Bloch variety, is irreducible for generic potentials. Our proof proceeds through two reductions. We first use the monodromy of the roots of the dispersion
polynomial with respect to the potential parameters to reduce the problem to the splitting case. We then show that the splitting property passes to the principal submatrices of the Floquet
matrix, reducing the problem further to the case that the fundamental domain contains two vertices.
Read the full abstract ▾
Analysis of PDEs
The compactness of Moser-Trudinger type inequalities in the unit ball
Qi Xia and Yufeng Lu
In this paper, we employ the concentration-compactness principle to show that if the Dirichlet norm is replaced by the standard Sobolev norm, then the supremum of $$ \int_{\mathbb{B}} |x|^{N \epsilon} \Phi \left( \alpha_N \left( 1+ \epsilon \right) |u|^{ \frac{N}{N-1} } \right) dx $$ over all such functions is uniformly bounded. Furthermore, we also prove the existence of extremals. Finally, we consider the compactness of the sequence of extremals of the inequalities and the limit of this sequence is the extremal of $$ \int_{\mathbb{B}} \Phi \left( \alpha_N |u|^{ \frac{N}{N-1} } \right) dx $$ in $C^1 \left( \mathbb{B} \right)$, where $\alpha_N = N \omega_{N-1}^{ \frac{1}{N-1} } $, $\Phi \left( t \right) := e^t - \sum_{j=0}^{N-2} \frac{t^j}{j!} $ and $\omega_{N-1}$ is the surface of the unit ball in $\mathbb{R}^N$.
Read the full abstract ▾
Artificial Intelligence
Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing
Guannan Lai and Han-Jia Ye
Large
language model (LLM) routing aims to assign each query to the most suitable model from a heterogeneous candidate pool, improving the quality–efficiency trade-off of LLM inference. Existing routers are typically learned through local fitting: a router is optimized for a particular query workload and candidate pool, and often requires additional supervision or retraining as the routing environment changes. We ask whether LLM routing can instead be approached from a foundation-model perspective, learning a reusable routing capability that generalizes across tasks, candidate models, and deployment conditions. To this end, we introduce RouteFM, which learns to characterize anonymous candidate models from behavioral context and infer their target-specific capabilities, rather than binding routing decisions to fixed model identities or a single environment. Through episodic pretraining across heterogeneous routing environments, this capability can be reused by a frozen router and adapted to new environments through context alone. Experiments demonstrate transfer across changes in domains, modalities, candidate pools, and context budgets, with the largest gains when behavioral evidence is limited. On MMR-Bench, which is excluded from pretraining, RouteFM outperforms the strongest baseline by 2.23 quality points with only eight observations per candidate. These results support moving LLM routing from repeated local fitting toward a pretrain once, route anywhere paradigm. Our code is publicly available at https://github.com/LAMDA-Model-Reuse/RouteFM.
Read the full abstract ▾
Computation and Language
SemOPT: Fixing Semantic Errors in LLM-based Optimization Modeling via Reward-Guided Search
Zetong Zhou, Wentao Zhang, Jingyuan Wang et al. (+3 more)
Operations research supports decision-making in domains such as energy, economics, and healthcare. Solving operations research problems typically begins with optimization modeling, which translates a natural-
language problem description into executable solver code. LLMs offer a promising way to automate this process, but they remain prone to errors. In practice, these errors can be divided into two categories: syntactic errors refer to solver code that fails to run successfully or is judged infeasible by the solver; semantic errors refer to solver code that successfully returns an objective value but violates the intent of the original problem. Since semantic errors do not trigger runtime failures, they are difficult to detect and rectify. To address this problem, we introduce SemOPT, a semantic-guided framework for correcting LLM-based optimization models. SemOPT combines a semantic reward model that distinguishes faithful math models from plausible but incorrect ones with an adaptive correction system that applies hierarchical reward-guided search over the modeling space. Experiments on seven optimization modeling
benchmarks show that SemOPT establishes a new state of the art and achieves an average 7.6% accuracy improvement over the strongest baseline on complex
datasets.
Read the full abstract ▾
All authors Zetong Zhou, Wentao Zhang, Jingyuan Wang, Yifan Yang, Zizhuo Wang, Shixi Hu
Computer Vision
Visual Anomaly Synthesis for Model Selection in Data Scarcity
Daniel Pröll, Thomas Kraxner, Tobias Schaefer et al. (+1 more)
Defect detection systems for industrial condition monitoring can only be relied upon if they are validated, yet defective samples are rare and, for a specific asset, often nonexistent. We present a framework that synthesizes severity-graded defects on real non-defective images without any defect references for the target asset, that can be used for model selection and validation. A defect taxonomy for common failure modes is distilled from literature into prescriptive
prompts at varying defect severities. Regions of interest are cropped from in defect-free images and edited with a pre-trained image generation model ("FLUX.2 [klein]"). Color-matching and blending are employed to improve structural coherence with the original image. Generations are filtered out by a scorer and by estimated detection difficulty. Model selection experiments on MVTecAD show image AUROC choice regret over model selection can be nearly halved compared to the best fixed model chosen with access to test data. Experiments show the need for severity-graded anomaly synthesis. A case study investigates the proposed method for in-situ monitoring of Pelton turbine runners in hydropower, where real defect images are rare and expensive to collect. A PatchCorebased anomaly detection model is fit on Pelton turbine images and selected and validated using synthetic images, showing strong detection performance (94 % correct detection at optimal threshold and AUROC 0.97). The model reliably detects moderate and advanced defects, while early-stage defects remain challenging, indicating the synthetic data meaningfully stresses detector sensitivity.
Read the full abstract ▾
All authors Daniel Pröll, Thomas Kraxner, Tobias Schaefer, Sebastian Hegenbart
Robotics
Encore: Few-Shot Agentic Discovery of Manipulation Strategies
Yifan Kang, Zihan Wang, Zhiwen Fan et al. (+1 more)
Coding
agents can now write, run, and debug programs with little human help.
Robot tasks, however, are usually specified by a sentence that leaves out how to grasp, in what order to make contact, and what the result should look like, and an
agent given only the sentence must find these details by trial and error. We introduce ENCORE, which gives the
agent a few demonstrations as evidence to read rather than as training data. A deterministic builder distills each demonstration into a pack of multi-view keyframes, gripper events, frame strips, and the full trajectory. A coding
agent studies the pack, writes a policy program against a fixed perception and action API, refines it iteratively over a few development rollouts, and freezes it before a sealed evaluation that never reveals the success signal. On LIBERO-PRO, the
agent's first program already succeeds in half of the perturbed tasks with demonstrations and in one task without them, and the frozen programs outperform the strongest prior agentic system run with the same
language model (96.3% against 89.3%). On RoboDojo tasks whose instructions leave the goal unstated, no program succeeds without demonstrations. ENCORE also runs on a real bimanual
robot, learning cube handover and cup inversion from five demonstrations each.
Read the full abstract ▾
All authors Yifan Kang, Zihan Wang, Zhiwen Fan, Bangya Liu
Astrophysics of Galaxies
The ALPINE-CRISTAL-JWST Survey: Investigating the role of interstellar dust, gas and stars in high-z galaxies at kpc-scales
F. Lopez, M. Relano, I. De Looze et al. (+37 more)
A comprehensive understanding of
galaxy evolution requires a detailed analysis of gas and
dust, their distribution, and
evolution within
galaxies. We analyse spatially resolved (~kpc) rest-frame [CII] and
dust continuum ALMA observations together with JWST/NIRSpec IFU data of a sample of
galaxies at z~4-5. We focus on deriving the spatial distributions of atomic and molecular gas masses,
dust and
stellar masses,
star formation rates (SFR), and
metallicity. The oxygen abundance maps have values in the range of 12+log(O/H)~8.1-8.3 with variations of the order of 1dex within the same
galaxy. The calibration used in this study to estimate the atomic gas mass in our
galaxies seems to overestimate the atomic gas mass surface densities up to 1-2 orders of magnitude. However, a calibration based on a spatially resolved [CII] conversion factor gives a more robust estimation of the total gas mass.
Galaxies exhibiting signatures of strong
outflows have lower
dust-to-
stellar surface mass density ratio and lower gas mass fractions than the
galaxies with no
outflow signatures. While the latter is consistent with these
galaxies ejecting part of their gas reservoir to the circumgalactic medium, the low
dust-to-
stellar surface mass density ratios also suggest that part of the
dust content is expelled outside the
galaxy, which reinforces previous theoretical suggestions of
dust removal by
stellar feedback or radiation pressure to explain the high UV luminosities in
galaxies at very high-
redshifts. Some
galaxies of our sample have almost an order of magnitude higher
dust-to-gas and
dust-to-
stellar surface mass density ratio than
galaxies in the local Universe, suggesting that a large
dust reservoir has been built up already at time scales of ~1 Gyr in these
galaxies.
Read the full abstract ▾
All authors F. Lopez, M. Relano, I. De Looze, A. L. Faisst, R. Herrera-Camus, R. A. Jorgenson, E. Pérez-Montero, M. Palla, C. Accard, R. O. Amorin, M. Aravena, R. J. Assef, A. J. Battisti, M. Boquien, E. da Cunha, P. Dam, R. L. Davies, M. Dessauges-Zavadsky, A. Ferrara, S. Fujimoto, M. Ginolfi, N. Gutierrez-Vera, A. Hadi, E. Ibar, H. Inami, A. M. Koekemoer, L. L. Lee, J. Li, J. Molina, A. Nanni, D. Narayanan, F. Pozzi, F. Rizzo, M. Romano, D. B. Sanders, P. Sawant, L. Vallini, S. A. van der Giessen, V. Villanueva, G. Zamorani
Group Theory
Additive subgroups of Q: logarithmic description and intersection configurations
Jordi Delgado, Antoni Massegú and Enric Ventura
We develop a logarithmic framework to study the
lattice of subgroups of the additive group of rational numbers. By encoding positive rationals via their
prime exponent sequences, one obtains a bijection between $\mathbb{Q}^+$ and finitely supported integral sequences indexed by the
prime numbers. This correspondence extends to arbitrary subgroups of $(\mathbb{Q},+)$ through a logarithmic greatest common divisor, yielding a classification of subgroups in terms of eventually nonpositive sequences in $\mathbb{Z}\cup \{- \infty\}$. Within this framework, subgroup inclusion, sum, product, and intersection admit simple coordinatewise descriptions, providing a transparent interpretation of the subgroup
lattice and recovering several classical results such as the subgroup classification up to isomorphism. Exploiting this perspective, we obtain a complete characterization of the intersection configurations realizable in subgroups of $(\mathbb{Q},+)$. For rank configurations, realizability is characterized by the decreasing condition together with restrictions on the possible ranks and on the minimal zero sets, and, in the finite-support case, by an additional cardinality condition. For binary configurations, this reduces to saying that every decreasing configuration is realizable in the infinite-support case, whereas in the finite-support case the mentioned cardinality condition is required.
Read the full abstract ▾
Artificial Intelligence
Teaching LLMs to Generate Challenging MILP Instances via Solver Feedback
Jitin Singla, Parikshit Pareek, Pratik Jawanpuria et al. (+1 more)
Generating optimization instances that are both feasible and computationally challenging is crucial for benchmarking solvers and training learning-based optimization
algorithms. Existing non-LLM generators rely on seed instances or parameter tuning, resulting in high test-time computational cost, while existing LLM generators lack explicit hardness measures. Recent reinforcement learning methods with verifier feedback evaluate only binary correctness, which is misaligned with generating challenging problems. We note that an optimization solver reports the cost of solving at several stages of its pipeline, and leverage this to design a reward that scores both the solvability and the hardness of generated problems, measured by branch-and-bound nodes and post-cut relaxation gaps. Our key idea is a challenger-solver asymmetric self-play approach, where an LLM challenger generates progressively harder instances and the solver verifies feasibility and hardness, so no seed or training MILP instances are required. We fine-tune Gemma-4-12B and Qwen3.5-4B with GRPO and a size curriculum into OptiScribe-12B and OptiScribe-4B, which generate feasible yet challenging MILP problems from natural
language instructions. On capacitated facility location and max-cut, OptiScribe-12B raises median SCIP search nodes by 1.7-5x and post-cut gaps by 1.1-1.7x over its base model and improves the feasibility rate on facility location by 9-19 points, while OptiScribe-4B raises median nodes by up to 15.6x. The problems cover a wider difficulty range than public
benchmarks of the same size, follow instructions on density and difficulty, and can tune solver settings for families that public libraries lack. These results indicate that optimization-specific rewards, used in self-play mode, can teach LLMs to generate high-difficulty optimization
benchmarks. We will release our code and models publicly on acceptance.
Read the full abstract ▾
All authors Jitin Singla, Parikshit Pareek, Pratik Jawanpuria, Parag Singla
Neurons and Cognition
An adaptive fractional state links circuit mechanisms to cortical dynamics across the visual hierarchy
Brendan Harris and Pulin Gong
Cortical
circuits must respond flexibly to new inputs while integrating information about the past, yet the way in which neural activity reconciles these competing demands remains unclear. Combining Neuropixels recordings from six mouse visual areas with mechanistic
circuit modeling, we identify a dynamical regime in which heavy-tailed superdiffusive fluctuations coexist with long-range temporal dependence and oscillations. We formalize this regime as the adaptive fractional (AF) state, using an effective mean-field theory in which spatial and temporal fractional derivatives capture heavy-tailed excursions and long-range
memory, respectively. We find that dynamical exponents characterizing the AF state vary systematically across the visual hierarchy: higher visual areas exhibit weaker superdiffusion and stronger temporal
memory. In the
circuit model, this hierarchical shift emerges from a progressive weakening of effective inhibition. These findings extend the classical hierarchy of timescales to a hierarchy of dynamical regimes and suggest that the AF state allows cortical areas to jointly express rapid responses and long-term temporal integration.
Read the full abstract ▾
High Energy Physics (Phenomenology)
Generalized parton distributions of the nucleon in the chiral quark soliton model: Sum over all quark states at nonzero skewness and momentum transfer
Josuke Minamiguchi
We compute the combinations $E_M=H^{u+d}+E^{u+d}$ and $H_E=H^{u-d}+tE^{u-d}/(4M_N^2)$ of unpolarized generalized parton distributions (GPDs) of the nucleon in the
chiral quark soliton model at nonzero skewness $\xi$ and nonzero momentum transfer $t$. The combinations contain the GPDs $H^{u-d}$ and $E^{u+d}$, which are subleading in the expansion in the inverse number of colors. Both combinations are double sums over the
quark states. A multipole expansion of the light-cone operators makes the sums computable at every $\xi$ and every $t\le0$. The contribution of the Dirac continuum is summed over the
quark states, without an interpolation formula and without a gradient expansion. The first moments satisfy the form-factor sum rules, and the second moments satisfy polynomiality.
Read the full abstract ▾
Artificial Intelligence
Seek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation
Zhimin Wang, Meiyuan Zhu, Duo Wu et al. (+8 more)
Vision-
Language Navigation (VLN) requires
agents to continuously ground task progress from long-horizon instructions and partial
egocentric observations. Existing VLM-based
navigation agents typically reason only over available observations and may remain confident even when task-relevant evidence is missing. For example, an
agent may confidently proceed forward and get lost even though the landmark indicating the next turn lies outside its current field of view. We term this failure mode Progress Myopia: the
agent fails to recognize unreliable progress grounding and continues acting on insufficient evidence. To address it, we propose SeekVLN, an evidence-seeking framework that couples semantic progress
reasoning with active acquisition of task-relevant observations. SeekVLN is trained in two stages: First, Future-guided Reverse Generation (FRG) uses future expert actions to augment offline expert trajectories with supplementary views and evidence annotations. Supervised fine-tuning on these trajectories establishes a prior for evidence seeking and progress
reasoning without additional expert interaction. However, imitation alone does not reveal whether seeking improves subsequent
navigation. We therefore introduce Counterfactual Contrastive Policy Optimization (C2PO) for reinforcement fine-tuning. By comparing each evidence-seeking branch with a counterfactual direct-
navigation branch from the same state, C2PO uses a contrastive reward to assign credit to seeking decisions based on subsequent
navigation benefit. Experiments on simulated
benchmarks show that SeekVLN achieves state-of-the-art performance, improving success rate by 12.7% and 7.5% over the base model on R2R-CE and RxR-CE, respectively. Both simulated and real-world evaluations exhibit human-like evidence-seeking behaviors for more reliable progress grounding.
Read the full abstract ▾
All authors Zhimin Wang, Meiyuan Zhu, Duo Wu, Linjia Kang, Yajun Wang, Yuan Ni, Xiaohang Wang, Tianlu Pan, Jingyan Jiang, Yaowei Wang, Zhi Wang
Statistical Methodology
The MCMC convergence graph: a diagnostic for multimodal posteriors
Cici Chen Gu, Eszter Lakatos and Sara Hamis
Multimodality is common in many scientific and engineering applications. However, standard Markov chain Monte Carlo (MCMC) convergence diagnostics often penalise multimodality in practice by conflating overall poor mixing with groups of chains that have mixed well within distinct modes. To diagnose multimodality rather than flag it as a sampling failure, we introduce the MCMC convergence graph: a graph-based diagnostic that computes pairwise R-hat values between chains and summarises them in a graph, revealing sets of chains that explore the same posterior mode. We implement the method in the probabilistic programming framework Stan and demonstrate its use on worked examples ranging from regression models with inherent multimodality in the data, to a pharmacokinetic model for which multimodality reflects non-identifiability. The graph-based diagnostic, which we make freely available in the R package mcmcConvergenceGraph and which accepts MCMC output from any sampler, provides both graphical and numerical summaries of MCMC behaviour for diagnosing multimodality.
Read the full abstract ▾
Machine Learning
Typed Edge-Tensor Non-Reciprocal Port-Hamiltonian Deliberation for Counterfactual Open-World Deductive Reasoning
Zeyu Jia
Scaling test-time computation in continuous latent spaces offers an attractive alternative to verbose
token-by-
token generation for multi-step deductive
reasoning. However, unregularized recurrent latent updates suffer from a deliberation drift cliff when rolled out beyond training horizons, while strictly energy-conserving or symmetric message-passing dynamics cannot break parent-to-child causal
symmetry or suppress cyclic modus-ponens amplification on cyclic distraction graphs. We introduce Typed Edge-Tensor Non-Reciprocal Port-
Hamiltonian Deliberation (TE-BPHD), a neuro-symbolic continuous-time latent
reasoning architecture that couples skew-symmetric port-
Hamiltonian conservation with relation-typed non-reciprocal directional transport and monotone dissipative damping on a semantic entity-state
manifold. We prove (i) unconditional input-to-state stability and exponential contraction of autonomous rollouts across arbitrary inference depths without external norm projection, (ii) strict directional DAG reachability separation over symmetric message passing, and (iii) exact cycle-suppression margins under finite cyclic horn perturbations. Across counterfactual open-world deductive
benchmarks (PrOntoQA-OOD up to depth 15, ProofWriter-OWA Cyclic at depths 5-10, FOLIO-Symbolic, and Cluttr-Relational), TE-BPHD eliminates the deep-horizon drift cliff, improves depth-10 cyclic
reasoning accuracy to 90.0% (+/- 0.8%) over symmetric port-
Hamiltonian and standard
Transformer baselines, and supports zero-retraining adaptive Lyapunov halting that reduces average solver evaluations by 44% with negligible accuracy loss.
Read the full abstract ▾
Computer Vision
PCaPaint: Prostate Cancer Inpainting by Mitigating Shortcut Learning
Levente Lippenszky, Hongxu Yang, Marcell Dömötör et al. (+2 more)
The development of AI systems for tumor-specific applications is limited by the scarcity of labeled data. Synthetic tumor inpainting offers a promising approach but faces challenges for prostate cancer MRI which contains high-resolution multi-sequence data. Although methods leveraging latent
diffusion models (LDMs) enable large-volume synthesis, they are prone to shortcut learning, simply reproducing the condition image created by masking the lesion region. In this work, we introduce PCaPaint, a prostate cancer inpainting method based on LDMs that explicitly addresses this failure mode. To overcome shortcut learning that compromises synthetic tumor texture, we propose a simple yet efficient conditioning strategy in which the condition image is filled with Gaussian noise, and we provide theoretical justification. In addition, we propose a novel training objective for LDM that emphasizes the error within the lesion region. Furthermore, we introduce a multi-sequence latent design, in which T2w scans and DWI&ADC scans are compressed using two separate autoencoders to preserve their distinct frequency characteristics. Extensive experiments demonstrate that the generated synthetic data improves downstream performance in prostate lesion
segmentation, patient-level classification and lesion-level detection. Furthermore, our method significantly outperforms a recent state-of-the-art LDM-based tumor inpainting method both in downstream performance and in synthetic image quality.
Read the full abstract ▾
All authors Levente Lippenszky, Hongxu Yang, Marcell Dömötör, Krisztian Koos, László Ruskó
Computer Vision
TAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAG
Yalun Wu, Bingzhou Wang, Boyang Wang et al. (+5 more)
Multi-step visual
retrieval-augmented generation (RAG) answers complex questions by repeatedly retrieving visual evidence, updating an intermediate state, and deciding whether to continue searching or answer. Yet retrieving relevant evidence does not ensure its effective use throughout the
reasoning trajectory. As multi-step
reasoning progresses, redundant sources occupy context capacity needed for missing evidence, observations tied to resolved requirements or unproductive searches linger in context, and visual sources are revisited with insufficient detail for fine-grained reading. We term this loss of usable evidence over a
reasoning trajectory trajectory-level evidence utilization degradation. To address it, we propose Trajectory-Aware Evidence Coordination (TAEC), a training-free framework that coordinates evidence use around unresolved answer requirements. TAEC tracks these requirements in a shared trajectory state to guide which evidence enters the context, how accumulated
memory is retained, and at what level of detail visual evidence is examined. Under a unified evaluation protocol on ViDoSeek, SlideVQA, and MMLongBench-Doc, TAEC achieves the best overall performance against leading training-free visual RAG baselines, with the highest average accuracy across multiple proprietary
vision-
language models. These results demonstrate that aligning evidence with evolving
reasoning needs improves evidence use throughout multi-step visual RAG.
Read the full abstract ▾
All authors Yalun Wu, Bingzhou Wang, Boyang Wang, Peiying Wang, Shaojie He, Yunhan Wang, Shaozu Yuan, Jiawei Wang
Robotics
DROM: A Language-Guided Diffusion Framework for Multi-Skill Robotic Manipulation
Vincenzo Pomponi, Rocco Felici, Paolo Franceschi et al. (+5 more)
Learning robust manipulation policies for diverse, long-horizon tasks from limited demonstrations remains a fundamental challenge in robotics. We present DROM, a
language-guided
diffusion framework that enables
robots to learn, represent, and compose multiple manipulation skills within a single generative policy. DROM leverages Dynamic Movement Primitives (DMPs) to augment a small set of expert demonstrations into expressive multi-skill
datasets, substantially reducing data collection while improving spatial generalization beyond the demonstrated workspace. Building upon Motion Planning
Diffusion (MPD), we extend the
diffusion architecture to support
language-conditioned multi-skill trajectory generation through cross-
attention, allowing a single model to generate skill-consistent motions for a diverse set of manipulation primitives, including orientation-sensitive behaviors that are difficult to design using conventional motion planning or hard-coded controllers. For long-horizon manipulation, a large
language model decomposes high-level operator requests into executable sequences of skills, enabling natural
language interaction and autonomous task execution. We validate DROM on a Franka Emika Panda
robot, a FANUC CRX25ia
robot, and in MuJoCo simulation across a wide range of manipulation tasks. Experimental results demonstrate that DROM outperforms Motion Planning
Diffusion and Behavior Cloning baselines, achieves robust multi-skill generalization, and composes learned skills to reliably execute long-horizon manipulation tasks from natural
language instructions using only a limited number of human demonstrations.
Datasets, simulation environments, and more at https://github.com/automation-robotics-machines/drom.
Read the full abstract ▾
All authors Vincenzo Pomponi, Rocco Felici, Paolo Franceschi, Stefano Baraldo, Oliver Avram, Loris Roveda, Luca Maria Gambardella, Anna Valente
Statistical Methodology
The INSIDE assumption under all positive coding: interpretation and partial empirical assessment
Fernando Pires Hartwig, George Davey Smith, Frank Dudbridge et al. (+1 more)
Mendelian randomisation (MR) implemented through instrumental variable (IV) analysis is a popular strategy for strengthening causal inference in observational studies. A key assumption for several MR
estimators, including MR-Egger regression, is the INstrument Strength Independent of Direct Effect (INSIDE) assumption. However, there is no established empirical test for assessing the plausibility of this assumption. Moreover, INSIDE depends on how genetic variants are coded (i.e., on the choice of the effect allele), which is often arbitrary and therefore hampers assessing the plausibility of this assumption on substantive grounds. In this paper, we show that the all-positive coding scheme (i.e., for all variants, choosing the allele positively associated with the exposure as the effect allele), which is typically used in MR-Egger, is equivalent to a coding-invariant model that can be given a natural interpretation because the direct effect parameters under this coding scheme are in the same direction as the bias of individual-variant ratio
estimators. Moreover, using both theoretical arguments and simulations, we show that, under commonly assumed data-generating models in the MR methodological literature, heteroscedasticity of instrument-outcome coefficients according to instrument-exposure coefficients is a feature of at least some types of INSIDE violation, indicating that heteroscedasticity tests could contribute to assessing the plausibility of the INSIDE assumption. We further highlight specific cases where the test would not work. We illustrate its application by re-analysing a real
dataset assessing the causal effect of large particle high density lipoprotein cholesterol on age-related macular degeneration.
Read the full abstract ▾
All authors Fernando Pires Hartwig, George Davey Smith, Frank Dudbridge, Jack Bowden
High Energy Physics (Theory)
Relic of the Kink Shape Mode in a Topological Thick Brane - some implications
Gahan Chattopadhyay and Soumitra Sengupta
The kink
soliton provides a simple construction of a topological thick 3-brane sourced by a minimally coupled canonical scalar field in five-dimensional general relativity. Although the flat-space kink is a solution of $\varphi^4$ theory, the gravitating configuration requires $M_*$-suppressed $\varphi^6$ corrections to support a stable warped geometry. Unlike its flat-space counterpart, the scalar perturbation spectrum contains no normalizable bound state. We nevertheless identify a single quasi-bound, or resonant, mode. Using a time-independent relative-probability analysis, direct time
evolution, and a four-turning-point WKB calculation, we establish a direct connection between this resonance and the massive bound shape mode of the flat-space $\varphi^4$ kink. We also show that, within an EFT-consistent parameter window, the resonance can transfer energy from bulk
geometric fluctuations to localized matter, thereby allowing the possibility of high-scale reheating in the early universe.
Read the full abstract ▾
Computer Vision
When to Retrieve, When to Stay: Uncertainty-Aware Temporal Evidence Allocation for Streaming Video-LLMs
Xiang Hu, Jiazuo Yu, Lu Zhang et al. (+2 more)
Streaming
video understanding requires
Video Large
Language Models (
Video-LLMs) to reason over continuous visual streams under causal constraints. As the visual history grows, a bounded visual?processing budget requires evidence selection that balances temporal recency with query relevance. Recent-only selection excludes potentially relevant historical evidence, whereas Semantic-only
retrieval can displace useful recent context when relevance scores are ambiguous. We introduce WRWS (When to Retrieve, When to Stay), a training-free framework for uncertainty-adaptive evidence allocation. A lightweight external
vision-
language encoder scores query relevance across the observed history, while an adaptive allocation module uses the normalized
entropy of the similarity distribution as a proxy for
retrieval uncertainty. WRWS favors semantic
retrieval when relevance cues are reliable and strengthens the recency prior under uncertainty. Following a retrieve-first, encode-later pipeline, WRWS selects evidence before target-model visual encoding, such that only the selected observations are processed by the costly target
Video-LLM. Experiments across four
Video-LLM families and multiple model scales demonstrate competitive accuracy on StreamingBench and OVO-Bench. In our efficiency evaluation, WRWS reduces average
vision-to-answer time to 47.93% of the state-of-the-art method. Code will be released.
Read the full abstract ▾
All authors Xiang Hu, Jiazuo Yu, Lu Zhang, Yunzhi Zhuge, Huchuan Lu
Machine Learning
A Sharp Transition in Data Reconstruction under Differential Privacy
Max Cairney-Leeming, Simone Bombari and Marco Mondelli
Data reconstruction attacks have empirically been successful in recovering training samples from learned models, raising
privacy concerns and motivating defenses with guarantees that remain valid against future threats. While differential
privacy (DP) provides formal protection, choosing the
privacy budget remains a challenge: small budgets severely reduce utility, but it is hard to quantify how large the budget can be without allowing accurate reconstruction. In this work, we study informed attackers who aim to reconstruct a single $d$-dimensional training sample from a $\rho$-zero-concentrated DP model, knowing all other training data. Our main contribution is to establish a sharp transition at $\rho \asymp d$ for data reconstruction: on the one hand, we derive
entropy-based lower bounds for any private mechanism and any attack, characterizing a set of target priors for which reconstruction is information-theoretically impossible for $\rho \ll d$; on the other hand, we analyze a simple attack on private linear regression with output perturbation, showing that reconstruction is practically feasible for $\rho \gg d$. Remarkably, the transition moves to $\rho \asymp s$ for data lying in an $s$-dimensional subspace, demonstrating that the
privacy budget guaranteeing adequate protection must be assessed in terms of the effective dimension of the data. We validate our findings via experiments on synthetic data and natural images (CIFAR-10, ImageNet).
Read the full abstract ▾
General Economics
Classification as Search Infrastructure: How Category Creation, Addition and Cleanup Shape Knowledge Retrieval
Kerstin Hötte, Nicolò Barbieri and Su Jung Jee
Classification systems shape how searchers find relevant objects. We study how revisions to classification architecture affect
retrieval by changing the routes through which objects enter consideration. We theorize that creating a cross-cutting category can reduce classificatory distance and translation costs, whereas adding routes to an established system can increase route-selection and updating costs; category cleanup can restore contrast. Empirically, we exploit the 2013 creation and 2020 revision of Y02/Y04 green-technology codes in the Cooperative Patent Classification. We match treated patents to unchanged green patents within technology-cohort
cells and estimate examiner- and applicant-specific effects on first-citation timing and citation volume. Category creation is associated with a 25% higher examiner first-citation hazard. In the mature system, additions are associated with 13-15% lower examiner hazards, while cleanup is associated with a 14% higher hazard and 12% higher citation volume. Effects are generally stronger for examiners, whose search task is more tightly coupled to patent classification. Timing and volume need not move together: creation and green-domain entry shift timing without detectable changes in volume, while cleanup increases both speed and recorded reach. Classification infrastructure may therefore change when relevant objects are found even when overall recorded
attention is unchanged, and greater classificatory detail need not improve search efficiency.
Read the full abstract ▾
Data Structures and Algorithms
Collision Detection is Instance $\widetilde{O}$ptimal Under the Birthday Threshold
Omri Ben-Eliezer, Tomer Grossman, Václav Rozhoň et al. (+1 more)
Can structural knowledge about a hash function help accelerate the (black box) detection of collisions in it? This question is fundamental to cryptography theory given the importance of collision-resistant hash functions, and in this paper we tackle it from the angle of instance optimality, an ultimate notion of beyond worst case
algorithm analysis that has gained significant traction in recent years. Instance optimality asks for a single
algorithm that, on every input, performs nearly as well as the best correct
algorithm that “knows the structure” of that specific input. Here we measure
algorithms by the number of queries they make to the hash function $f\colon [n]\to [n]$, and we say that an
algorithm “knows the structure” of the input if, in addition to query access to $f$, it has free access to an unlabeled copy $\pi^{-1}\circ f\circ\pi$ of $f$, for an unknown permutation $\pi$ on $[n]$. We prove the existence of an (almost) instance-optimal
algorithm for collision detection in the regime most interesting from a cryptographic perspective: among functions where finding a collision takes significantly less than $\sqrt{n}$ queries. Specifically, we prove the existence of a single
algorithm $A$ that, for any input $f$ in which a structure-aware
algorithm can find a collision using $q\leq O(\sqrt{n/\log n})$ queries in expectation, $A$ can find a collision in at most $O(q\log n)$ queries. The $O(\log n)$ multiplicative overhead is tight, matching a lower bound of Ben-Eliezer, Grossman, and Naor [ICALP'25], and partially resolving their main open question. Our result implies, in particular, that it is impossible for a cryptographic designer to plant purely structural
backdoors for collision finding (for this unlabeled notion of structure): whatever collisions the designer's secret knowledge finds, the public can find with a multiplicative overhead of $O(\log n)$.
Read the full abstract ▾
All authors Omri Ben-Eliezer, Tomer Grossman, Václav Rozhoň, Jakub Tětek
Dynamical Systems
Baker domains with arbitrarily slow controlled rate of escape
Benjamin Handsaker-Whetton
Rempe and Rippon gave a general result which enables the construction of a transcendental entire function with a Baker domain, in which the iterates tend to infinity at a prescribed arbitrarily slow rate. Here we construct a transcendental entire function with a Baker domain, in which the iterates are controlled from both above and below in a prescribed arbitrarily slow but regular manner. The proof uses distortion
theorems for conformal mappings due to Ahlfors and Warschawski, and an approximation
theorem due to Rempe and Rippon.
Read the full abstract ▾
Computer Vision
HyperSAM: A Promptable Foundation Model for Hyperspectral Remote Sensing
Li Pang, Xinqiao Wu, Jing Yao et al. (+5 more)
Hyperspectral remote sensing provides dense spectral measurements that are indispensable for material-level Earth observation, yet the construction of a general-purpose hyperspectral foundation model remains difficult. Two bottlenecks are especially limiting. First, large hyperspectral corpora rarely provide high spatial resolution together with reliable dense annotations. Second, many hyperspectral models are still trained almost from scratch, so the
geometric and interactive priors learned by modern
vision foundation models are not fully reused. To alleviate these issues, we \highlight{present} HyperSAM, a promptable hyperspectral foundation model that couples a data-centric hyperspectral synthesis pipeline with a spectral adaptation architecture based on Segment Anything Model 3 (SAM3). On the data side, HyperSAM synthesizes full-spectrum hyperspectral cubes from high-resolution SpaceNet multispectral imagery through a physics-informed abundance-transfer generator, while SAM3-derived pseudo-masks provide object-centric supervision. On the model side, the latest implementation uses a frozen SAM3 RGB image branch, a trainable hyperspectral side encoder initialized from the RGB
vision transformer (ViT), ControlNet-style zero-initialized feature injection, and a lightweight mixture-of-experts mask refiner. To enhance training robustness against noisy pseudo-labels, Cross-modal Sample Selection (CromSS)-style confidence selection is incorporated for noisy-label weighting. Extensive experiments show that HyperSAM obtains strong generalization on diverse hyperspectral tasks (e.g., classification, anomaly detection, change detection, target detection, and airborne oil-spill mapping) and that high-quality synthetic hyperspectral data can be more effective than simply scaling noisy hyperspectral supervision.
Read the full abstract ▾
All authors Li Pang, Xinqiao Wu, Jing Yao, Pedram Ghamisi, Jun Zhou, Zhengchao Chen, Deyu Meng, Xiangyong Cao
Computer Vision
UGO: Unified Architecture for General Multi-Object Tracking by Segmentation
Jer Pelhan, Alan Lukezic and Matej Kristan
General multi-object tracking (GMOT) tracks all instances of a user-specified category from a single first-frame exemplar. Prior work relies on bounding boxes and surrogate training, and struggles with non-rigid objects, crowded scenes, and distractors. We introduce UGO, a unified GMOT tracker that pairs a pretrained exemplar-conditioned detection head with an instance-propagation head in a common architecture. A novel training-free, energy-minimization consolidation method converts overlapping proposals into exclusive pixel-wise masks and detections, resolving over-
segmentation, duplicates, and conflicts. A hierarchical
memory spanning global and instance levels improves recall and per-instance
segmentation accuracy using a new
memory management protocol. UGO sets a new state-of-the-art on GMOT
benchmarks and
video object counting, and is competitive with specialist MOT methods, establishing a strong paradigm for unified, open-category multi-object tracking.
Read the full abstract ▾
Information Theory
Rotatable Antenna-Enabled Space-Air-Ground Integrated Networks: Opportunities and Challenges
Yanhua Tan, Beixiong Zheng, Tiantian Ma et al. (+6 more)
Space-air-ground integrated networks (SAGINs) are expected to support ubiquitous three-dimensional (3D) communication and sensing services in future sixth-generation (6G) wireless networks. However, heterogeneous mobility and service requirements across the space, air, and ground segments challenge fixed-boresight or fixed-sector
antennas in supporting wide-area coverage, maintaining directional
alignment over time-varying communication links, and flexibly adjusting observation directions for sensing tasks. To address these limitations, non-fixed flexible
antenna architectures, such as fluid
antenna system (FAS), movable
antenna (MA), and pinching
antenna, have garnered significant interest in recent years. Among them, rotatable
antenna (RA) technology has emerged as a promising solution by enabling mechanical or electronic boresight adjustment while keeping the
antenna positions fixed. This article investigates the roles of RA technology in enabling communication and sensing in SAGINs. Specifically, we first explain how RA boresight control complements platform mobility and supports wide-area coverage, dynamic directional transmission, cross-segment cooperative operation, and cooperative sensing. We then discuss the main design challenges, potential approaches, and future research directions, including channel acquisition and predictive tracking, joint orientation control and access/handover coordination, cross-segment coordination and resource management, as well as deployment tradeoffs and practical implementation. Finally, an RA array prototype and two representative simulation studies are presented to illustrate the feasibility and potential performance gains of RA-enabled SAGINs.
Read the full abstract ▾
All authors Yanhua Tan, Beixiong Zheng, Tiantian Ma, Qingjie Wu, Lipeng Zhu, Wenyan Ma, Cheng-Xiang Wang, Robert Schober, Rui Zhang
Logic in Computer Science
A Rank-Preserving Gaifman Normal Form for First-Order Logic on Weighted Structures
Steffen van Bergerem, Martin Grohe, Charlotte Lenz et al. (+1 more)
We prove a rank-preserving version of Gaifman's
Theorem. Compared to earlier rank-preserving locality
theorems (in particular, [Grohe, Kreutzer, Siebertz, JACM 2017]), our
theorem is much simpler and yields formulas in exactly the same normal form as Gaifman's original
theorem. Furthermore, it holds not only for first-order logic, but also for first-order logic with modulo-counting quantifiers and, more generally, for the first-order logic on weighted structures ngFOW+ that is introduced in this article. As an application of our
theorem, we give a simplified proof of the algorithmic meta-
theorem of [Grohe, Kreutzer, Siebertz, JACM 2017] stating that first-order properties of nowhere dense structures can be decided in almost-linear time. Our locality
theorem for the weight logic ngFOW+ can be seen as an essential step toward such a meta-
theorem for this logic.
Read the full abstract ▾
All authors Steffen van Bergerem, Martin Grohe, Charlotte Lenz, Nicole Schweikardt