Papers

Vision foundation models (VFMs) provide transferable visual representations, but their inference cost limits deployment in many settings. Fine-tuning specializes a VFM without shrinking it; distillation shrinks it, but through expensive teacher-guided training. Structured pruning offers a more direct route by extracting a compact subnetwork from the VFM. However, as compression gets aggressive, existing methods fail because they treat subnetwork selection and recovery as separate axes. Across layers, capacity must follow task sensitivity rather than spread uniformly. Within a layer, a removal cannot be judged by importance alone; its impact also depends on how well the lost contribution can be recovered from what remains. Selection and recovery must therefore be decided jointly. We introduce Carve VFM, which resolves this interdependence. Given a VFM, a calibration set, and a parameter budget, it (i) searches for task-specific capacity allocations across layers; (ii) guides the search via an adaptive recovery-aware fitness criterion; and (iii) reconstructs removed behavior through iterative closed-form low-rank corrections merged into the surviving weights. The result is a dense encoder produced in minutes on a single GPU without backbone retraining. Across twelve benchmarks and four models from DINOv3 and MetaCLIP-2, Carve VFM achieves the highest reported mean accuracy in seven of eight backbone-budget configurations among the evaluated dense structured-pruning methods. Further fine-tuning surpasses the strongest evaluated edge model (88.1% vs. 85.8%), and carved models cut compute and memory while delivering 1.3-2.0x higher GPU throughput than the uncompressed one. These results show that the compact model you need is inside the VFM; it only has to be carved out.

Symbolic regression (SR) aims to discover interpretable mathematical expressions from data and plays a key role in scientific discovery. However, existing methods face a common bottleneck: the enormous search space and severe combinatorial explosion make it difficult to achieve a favorable trade-off between accuracy and algorithmic efficiency. We argue that, in addition to designing increasingly complex solver-specific SR strategies, an equally promising direction is to equip them with a shareable auxiliary strategy that can provide reliable search guidance. To this end, we propose DASS, a solver-adaptable Dynamic Auxiliary Search Strategy that improves SR by constructing and refining a high-potential auxiliary search subspace. DASS represents the auxiliary search space as a functional subspace spanned by a set of high-potential basis function terms. It estimates term utility through multi-environment evaluation, filters unstable guidance, and updates term potential scores with a Gibbs posterior, thereby calibrating the subspace to provide more reliable guidance for downstream solvers. The high-quality solutions produced by the solver are used to update the set of basis terms. This forms a virtuous closed-loop optimization process: the subspace guides the downstream solver, and the solver feedback reshapes the subspace for subsequent exploration. DASS can be easily integrated with various types of SR solvers. Extensive experiments on LLM-SRBench show that DASS significantly improves the accuracy of original solvers with a manageable increase in runtime.

Chest X-ray (CXR) interpretation often requires integrating visual findings with task-specific evidence rather than relying on direct visual recognition alone. While tool-augmented medical agents can supply such evidence via external modules, they often lack explicit mechanisms for learning when auxiliary evidence is needed and for preventing inapplicable quantitative evidence from entering diagnostic reasoning. To address this, we propose X-Ragent, a post-training framework for tool-augmented reinforcement learning that decouples learned auxiliary-evidence seeking from validity-gated quantitative measurement acquisition for evidence-grounded CXR reasoning. We construct Rad-CoT, a 7.7K-sample corpus combining causally ordered tool-augmented trajectories with report-style diagnostic reasoning, and use it to initialize Qwen3-VL-8B via agentic supervised fine-tuning (SFT). We then optimize the policy with Group Relative Policy Optimization (GRPO) using an accuracy-gated reward that applies process-level terms for measurement consistency and auxiliary-tool cost only to correct trajectories, preventing plausible process behavior from compensating for an incorrect diagnosis. Across three CXR benchmarks, X-Ragent achieves the strongest results, including an 8.6-point improvement on the fully held-out ChestAgentBench. By seeking evidence selectively and admitting only valid measurements, X-Ragent supports more faithful and evidence-grounded CXR reasoning.

This study addresses the prediction of audio popularity on an online sharing platform by leveraging both metadata and acoustic feature representations. Two distinct categories of audio content are considered: music and sound effects. Popularity is formulated as a supervised classification task based on two target variables: the number of downloads and the average user rating. We conduct a comparative evaluation of multiple machine learning models, including Random Forest, XGBoost, and a Neural Network model. Experiments are performed across different feature sets, including metadata, platform-provided descriptors, and eGeMAPS acoustic features. Results indicate that metadata consistently provide the most informative representation for predicting popularity. Nevertheless, acoustic features alone achieve performance significantly above chance level, demonstrating that intrinsic properties of the audio signal contribute to popularity prediction.

Driven by the scientific value of Venusian atmospheric studies, numerous missions, such as Magellan and Venus Express, have relied on single-spacecraft radio occultation (RO) experiments. Despite their proven success, data throughput is inherently limited by the use of a single transmitter and its relative geometry with respect to Earth-based receivers. Therefore, the literature proposes leveraging a constellation of spacecraft to increase RO measurement opportunities and improve spatial and temporal coverage; however, current efforts impose strict simplifying assumptions that limit their applicability and responsiveness to complex mission narratives. Beyond initial constellation design, evolving mission objectives may require event-based constellation reconfiguration during operations. To address both design and operational needs, we propose two problems formulated as integer linear programs: the RO Constellation Configuration Design Problem and the RO Constellation Reconfiguration Problem. Further, we address the programs' solution-space explosion with a Benders decomposition approach. Numerical experiments show the applicability of our problems for constellation configuration design, tackle the full mission pipeline, transitioning from global atmospheric profiling to on-demand regional profiling above areas of volcanic interest, and show that the Benders decomposition approach efficiently obtains high-quality solutions to large-scale instances.

We study the vehicle routing problem (VRP) with stochastic demands, where each client has an independent demand with a known distribution, and its realized demand is observed only on the first visit. We consider a priori and restocking policies that fix the client order before observing demands and serve each client's entire demand before first visiting the next. Gupta, Nagarajan, and Ravi (Oper. Res., 2012) developed randomized a priori $(\alpha+1)$-approximation and $(\alpha+2)$-approximation algorithms for splittable and unsplittable deliveries, respectively, where $\alpha$ is the approximation ratio of a metric traveling salesman problem (TSP) algorithm. We improve these approximation ratios to $2$ and $3$ by using their replenishment rules with a TSP tour constructed via matroid parity. We also obtain deterministic a priori $(2+\varepsilon)$-approximation and $(3+\varepsilon)$-approximation algorithms by compressing the distributions of cumulative demands to select an initial stock in polynomial time. All guarantees are relative to the general adaptive optimum. We then establish matching lower bounds of $2$ and $3$ that hold even for the more general class of randomized restocking policies. Finally, we apply our matroid-parity construction to improve approximation ratios for several VRP variants with deterministic demands.

Tabular foundation models (TFMs) achieve state-of-the-art performance on IID benchmarks, but how do they respond to repeated measurements at the same inputs? Across six TFMs, synthetic and semi-synthetic experiments show that additional measurements can improve predictions at measured inputs while degrading them elsewhere. Harm is most frequent at low noise, and irrelevant features amplify it in several models; real repeated-measurement datasets show similar patterns. Statistically, the IID rule targeted by PFN pretraining treats each repeated input as fresh evidence about the input distribution. When the prior links this distribution to the response function, the resulting protocol mismatch can outweigh the benefit of additional measurements, even under exact inference. Computationally, interventions identify row-count dependence in TabPFN-v3's attention scaling as a contributor to harm. Resetting the count largely reverses distortion in a noiseless linear diagnostic and attenuates amplification by irrelevant features. Finally, we evaluate ways to retain the benefits of repeated measurements while limiting their harm. Averaging measurements usually outperforms supplying them separately at larger repetition counts, whereas count reset can suppress both harm and useful gains. Code, saved results and reproduction instructions are available at https://github.com/drizmiz/PFN-Repeated-Measurement-Supp

Chain-of-Thought (CoT) enables transformers to solve complex reasoning tasks by generating intermediate reasoning steps. Despite strong empirical success, the mechanisms by which such reasoning abilities emerge during training remain poorly understood, particularly from a theoretical perspective. In this work, we study this question in a stylized yet fully analyzable setting: in-context $\mathrm{K}$-nearest-neighbor ($\mathrm{K}$-NN) prediction with a one-layer transformer. Earlier work has demonstrated that one-layer transformers can be trained to perform $1$-NN without CoT (Li et al., 2024a) by having the softmax attention attend to the nearest neighbor in context. However, this result on $1$-NN cannot be extended to $\mathrm{K}$-NN for $K>1$, as softmax attention is much less naturally suited to attending to the 2nd through $K$-th nearest neighbors. We first give a rigorous negative result showing that this limitation already appears on a well-separated class of binary classification tasks for odd $K>1$. We then give an explicit construction of a one-layer transformer, and show that it can solve $\mathrm{K}$-NN via CoT reasoning. We further prove that, under a stylized training setup, gradient descent can recover this construction, thereby showing that transformers can acquire the capability to solve $\mathrm{K}$-NN through training. In addition, we show that the resulting trained model applies to a broader test class than that assumed in the training analysis. Our results shed light on how CoT expands the ability of transformers to learn and solve tasks that are otherwise hard to solve.

We study the information-theoretic limits of inference in rectangular rank-one spiked matrix models with additive rotationally invariant noise, thereby going beyond the standard assumption of independent noise entries. Using the replica method from statistical physics, we derive a variational formula for the mutual information between the signal and the data, together with a system of saddle point equations predicting the minimum mean squared error in estimating the rank-one spike. We further show that, in the Bayes-optimal setting, these saddle point equations coincide with the fixed point equations of the state evolution of a recently proposed orthogonal approximate message passing algorithm with Bayes-optimal denoisers. This equivalence provides an algorithmic interpretation of the replica prediction and supports the Bayes-optimality of orthogonal approximate message passing whenever the relevant fixed point is unique. Numerical evaluations of the saddle point equations for several rotationally invariant noise ensembles and signal priors, together with finite-size simulations of the algorithm, confirm the asymptotic predictions. They illustrate both regimes with a unique informative fixed point, where orthogonal approximate message passing is predicted to attain the minimum mean squared error, and regimes with multiple fixed points, where a statistical-to-computational gap exists.

Existing deep-learning-based channel state information (CSI) feedback methods reduce feedback overhead by compressing high-dimensional CSI into low-dimensional representations and/or exploiting historical CSI to predict future CSI. However, these methods may become unreliable when user equipment (UE) suddenly changes its motion. To address this issue, we propose a prediction-aided coding (PAC) framework for generative CSI feedback, which adaptively encodes CSI based on predicted channel/CSI distributions and the observed CSI in real time. Each CSI frame is represented by multiple CSI tokens obtained without using historical CSI, making token generation robust to abrupt UE motion. In the first stage, the conditional distribution, instead of a deterministic value, of the next-frame CSI tokens is predicted based on historical tokens. In the second stage, once the next frame arrives, the predicted distribution is used for variable-length entropy coding of its CSI tokens. To further reduce feedback overhead and inference latency, we propose efficient designs for both stages. For the first stage, a customized causal Transformer with a new positional embedding strategy accurately predicts next-frame token probabilities. For the second stage, a parallel causal decoding strategy reduces the inference latency caused by sequential token decoding. Extensive experiments show that, compared with existing history-aware baselines, PAC reduces feedback overhead by approximately 72% to 84% while achieving higher reconstruction accuracy. Additionally, PAC maintains CSI reconstruction accuracy under random-walk trajectories, whereas existing history-aware baselines suffer sharp degradation in reconstruction accuracy.

Established interpolation-based methods efficiently compute visibility from one source to every grid cell using values computed closer to the source. Interpolation yields fractional values even on binary grids of free or fully blocking cells. Two-dimensional path-counting theory interprets these values as fractions of unobstructed grid paths, but three-dimensional methods use different predecessor structures. Interpreting these values consistently across dimensions and on nonbinary grids remains unresolved. We provide a unified mathematical account that gives every visibility value a precise meaning in any dimension. We establish when grid refinement yields eventual agreement with continuous visibility, implement parallel solvers, and compare four three-dimensional methods in accuracy and throughput. We define cell transmission: zero blocks visibility, one preserves it, and intermediate values attenuate it proportionally. We prove each computed value equals the uniform finite-path average of transmission products over finitely many source-to-cell grid paths. It is the fraction of clear paths on binary grids and the mean path transmission on nonbinary grids. For a source–target query, the fractions of paths passing through cells at each step form a hypergeometric distribution in 2D, which we call the hypergeometric bridge. On the last step into the target, these probabilities equal the interpolation weights. Higher-dimensional interpolation weights arise from products of hypergeometric bridges. For any fixed dimension, the full-field algorithm remains linear in grid size. Exact path enumeration reproduces every checked visibility value. NumPy, OpenMP, and CUDA agree numerically, and our OpenMP solver achieves the highest throughput in the four-method CPU comparison at every tested resolution.

Proximal Policy Optimization (PPO) is widely used in reinforcement learning with verifiable rewards for language-model reasoning. While value evolution along trajectory characterizes relative token-level credit, yet standard critics often fail to track it under sparse terminal rewards. To model this evolution, we analyze the relation between successive prefix values and show that they admit a Bayesian decomposition with additive updates in log-odds space. We use this additive structure to construct Tracking-Value PPO (\method), a cumulative value parameterization that sums position-wise scalar outputs into value logits. These outputs are learned through terminal-outcome supervision on the reconstructed values. \method improves aggregate mathematical reasoning scores over PPO by 7.0 and 8.4 points on Qwen3-4B-Base and Qwen3-8B-Base, respectively, while improving out-of-distribution generalization. Gains extend to Qwen3-4B, Qwen2.5-Math-1.5B, Qwen3.5-9B and to countdown, and scientific coding tasks. Further analysis shows more accurate tracking of value evolution and more reliable advantage estimates. Our code is publicly available in https://github.com/LINs-lab/TPPO.

Interacting with unfamiliar objects requires understanding how their parts connect and move. We introduce ViewStruct, a framework for jointly predicting connectivity and articulation in objects and scenes. Given an RGB image with aligned part segmentation and depth, optionally supplemented by images or video, ViewStruct predicts rigid-body groupings, attachments, and joint parameters. Its view-grounded representation links predictions to observed regions and expresses joint geometry in a gravity-aligned, view-relative frame, without requiring category-specific canonical orientations. A pretrained vision–language model is adapted to predict structure in seconds, without requiring observed articulation motion or per-instance optimisation. Experiments demonstrate improved structural prediction over evaluated baselines and transfer to unseen categories, asset sources, and real-world human-interaction videos, despite task-specific training exclusively on synthetic data. Simulated manipulation experiments further demonstrate the utility of predicted joints for generating robot motion trajectories.

Adaptive optimization methods have received considerable attention in recent years due to their strong empirical performance. However, they generally require maintaining a preconditioning matrix, which incurs prohibitive computational overhead in large-scale applications. To address these limitations, we investigate the acceleration of preconditioned optimization methods through frequent directions (FD), a widely used matrix sketching technique. We first propose FTSL by integrating FD with adaptive subgradient methods under the primal-dual framework and adding back the cumulative information discarded by FD. FTSL obtains a tighter regret bound than existing state-of-the-art results. We then apply a doubling trick that further reduces the time complexity of FTSL, while maintaining the same regret guarantee. We also consider optimization over matrix-valued decision variables and exploit their structural properties to construct sketched preconditioners. We develop FTSL-Shampoo by adapting FD to Shampoo and give a novel analysis under the primal-dual framework. To further mitigate its computational complexity, we design one-sided variants of FTSL-Shampoo under both mirror descent and primal-dual frameworks. Our algorithms not only reduce the computational cost of FTSL-Shampoo, but also achieve tighter regret bounds. We extend our methods to offline stochastic convex optimization and exploit smoothness to achieve faster convergence rates. Finally, we introduce practical variants of our algorithms and empirically demonstrate their efficiency and effectiveness across a broad range of tasks.

Language model APIs can expose token-specific biases while withholding logits and token probabilities. Existing bias-based extraction recovers relative logits, leaving a common additive component undetermined in ideal arithmetic. We identify a numerical side channel in floating-point bias addition that exposes information about this component through token identities alone. The channel distinguishes score vectors with identical complete unperturbed log probabilities. Our method exploits changes in representable spacing at binary exponent boundaries. Under the stated binary32 arithmetic assumptions and a known reachable score interval, it recovers a logit pair and its unknown tie-breaking priority exactly in at most 52 token queries. Given complete relative logits, one recovered anchor determines the original logit vector. We evaluate recovery across 11 public checkpoints from seven model families and extend the local method with adaptive interval search and anchor selection. In end-to-end experiments with vLLM, SGLang, and llama.cpp, adaptive recovery succeeds on all 128 Qwen3-0.6B inputs per system, including 64 held-out inputs. A separate token-only experiment extracts a pretrained small model's complete output-head representation up to an invertible hidden-basis transformation. We also establish a sufficient condition for suppressing common-shift disclosure by subtracting the maximum before bias addition. In controlled experiments, this mitigation eliminates all observed distinctions between common-shift variants and preserves token decisions under the tested random biases.

We present new algorithms for approximate shortest path computation in weighted undirected graphs within the Massively Parallel Computation (MPC) model. Specifically, we construct an $a$-approximate Single-Source Shortest Path (SSSP) oracle: Given a query consisting of a source vertex $u \in V$, the oracle returns $a$-approximate distances $\delta(u,v)$ for all $v \in V$. Fix an $n$-vertex weighted undirected graph. We consider two regimes of the MPC model: the near-linear regime, where each machine has $\tilde{\Theta}(n)$ memory, and the heterogeneous regime, where all machines have $\Theta(n^\gamma)$ memory for some constant $\gamma\in (0,1]$, except for a single machine with $\tilde{\Theta}(n)$ memory. We develop randomised algorithms that construct $O(1)$-approximate SSSP oracles in $O(\log\log n)$ rounds in the near-linear regime and in $O(\log^2\log n)$ rounds in the heterogeneous regime. These oracles answer distance queries in $O(1)$ rounds. Our results improve upon the recent work of Dory and Matar (SPAA 2024) which, for the same total memory, requires $\left(\log\log n\right)^{2+O(1/\gamma)}$ rounds and applies only to unweighted graphs in the heterogeneous setting. We say that $\tilde N_k(u)$ is the approximate $k$-nearest neighbourhood of a vertex $u$ if there exists an approximate distance estimate $\delta$ such that $\tilde N_k(u)$ consists of the $k$ vertices closest to $u$ according to $\delta$, breaking ties by vertex ID. The main technical ingredient is a new method for efficiently computing approximate $n^{O(\gamma)}$-nearest neighbourhoods in the heterogeneous MPC model in $O(\log^2\log n)$ rounds.

Submodular maximization arises in a wide range of combinatorial optimization problems and has been extensively studied from the perspective of approximation algorithms. For maximizing nonnegative, non-monotone submodular functions subject to a matroid constraint, randomized algorithms achieve a $0.401$-approximation, whereas obtaining comparable deterministic guarantees remains challenging. In this paper, we present a deterministic $0.401$-approximation algorithm in the exact value and independence oracle model, improving upon the previous deterministic guarantee of $(0.385-\varepsilon)$ \cite{ChenGLSZ2026}. Our algorithm builds on the extended multilinear extension and provides a deterministic implementation of the recursive guided framework underlying the randomized $0.401$-approximation algorithm. The main technical ingredient is a direction oracle supported on at most two partitioned matroid bases. This oracle simultaneously satisfies the growth condition required by the extended-multilinear update and an approximate stationarity condition needed to construct the recursive guides. The resulting finite-support representation enables exact evaluation of the relevant expectations and marginal values without random sampling. The algorithm uses polynomially many value- and independence-oracle queries.

Generating and editing presentation slides requires models to combine accurate text rendering, instruction following, visual grounding, aesthetic design, and precise editing within one canvas. Existing work covers only subsets of these capabilities and lacks large-scale slide-native supervision and diagnostic evaluation. We formulate four slide-centric tasks and build a scalable data engine with over 13M continual-pretraining records and 1.9M supervised fine-tuning records. We also introduce VisSlideBench, a benchmark of 1,527 manually screened instances that covers all four tasks with task-specific, multidimensional evaluation. Its automatic rankings agree with blinded, dimension-wise human rankings. Using these resources, we train InfoVis, a unified 9B slide generation and editing model. On VisSlideBench, InfoVis leads every evaluated open-source model on all eleven metrics and scores 7.94 overall against 7.99 for Nano-Banana-2. Starting from FLUX.2-klein-base-9B, slide-specific post-training adds 1.6 points overall, with the largest generation gains in content faithfulness; the remaining gap to proprietary models is smallest in content faithfulness and largest in aesthetic quality. Built on InfoVis, our document-to-slide workflow achieves the second-highest Aesthetics score on the external SlidesGen-Bench. We will release the model, code, data, and benchmark.

Industrial manipulation in flexible manufacturing, e.g., high-mix, low-volume (HMLV) electronics assembly, requires robot policies to adapt to changing products and production conditions. Such settings impose industrial process constraints, including product variants, moving material flows, finite execution windows, and tight geometric tolerances. However, existing evaluation frameworks do not systematically capture these constraints when assessing generalist robot policies. To address this gap, we introduce LIBERO-Industry, a novel benchmark built on the widely used robot learning benchmark LIBERO, that translates the aforementioned industrial constraints into controllable task conditions and measurable success criteria. Specifically, LIBERO-Industry comprises three classic task scenarios: Static-to-Dynamic (S2D) loading, Dynamic-to-Static (D2S) unloading, and Dynamic-to-Dynamic (D2D) transfer. The suites contain 216 tasks in total that systematically vary object geometry, conveyor speed, interaction-window duration, and geometric acceptance region size. Extensive experiments across five generalist robot policies (including vision-language-action models and world-action models) show that performance progressively degrades as industrial constraints are introduced and combined. Under a shared fine-tuning and evaluation protocol, the LIBERO-Industry co-training condition achieved higher observed target-transfer completion than the original-LIBERO condition.

Parallel token proposals need a joint law, not merely accurate token marginals. We construct coordinate-Bethe-ansatz laws from the periodic XXZ chain and compare them with their maximum-entropy pairwise projections at identical one- and two-site moments. In an eight-site, three-excitation sector, symmetry makes the full probability-law difference one-dimensional, determined by a contiguous three-site moment $\delta$. Along the Bethe branch, this gap changes sign and vanishes exactly at $\Delta=(3+\sqrt3)/2$, where the eigenstate law becomes pairwise. A nonlinear two-token readout preserves separate token marginals yet exposes a distance $2|\delta|$; a direct three-token readout preserves all one- and two-token marginals yet exposes $4|\delta|$. At $\Delta=1.5$ these deterministic binary distances are $0.02654573$ and $0.05309145$. We give an exact target-alignment formula and prove a strict speculative accepted-prefix advantage throughout an unrestricted open neighborhood of a constructed target. These are finite-law existence results, not measured language-model or wall-clock gains.

Cloud graphical user interface (GUI) agents send instructions and screenshots to remote planners, exposing personally identifiable information (PII). Existing placeholder defenses mask detected spans and reuse exact strings. Fragmented or changed forms can expose PII or break entity continuity across turns. PrivacyGuard addresses this private reference problem with source-linked sanitization (SAN) and a structured reference lifecycle (REF). SAN reconstructs fragmented or overlapping evidence and rewrites the complete source extent. REF links changed appearances to session entities and supports locally resolvable references without returning raw values to the upload path. In five-turn sessions scored against common gold, PrivacyGuard reduces audited source-value leakage by 33.55%–82.60% relative to the closest prior full-pipeline system in all four reader–language combinations. REF raises strict cross-form continuity from 0.04 under exact-value reuse to 0.81. In reference-required Android tasks, verified completion rises from 8/30 and 7/30 to 17/30 and 20/30. On AndroidLab, PrivacyGuard achieves the highest or tied-highest task-success point estimate among protection pipelines for all four planners. On PrivScreen, it reduces fixed-reader field exposure by 62.72%–62.84% relative to the same baseline. PrivacyGuard lowers upload exposure while preserving a locally resolvable task path.

Transmission switching is an effective approach for restoring operational flexibility and improving the economic performance of AC/multi-terminal DC (MTDC) grids following DC-side faults. Its practical implementation requires that the faulted branch be safely isolated and that the associated switching commands be successfully delivered through the communication network. However, conventional transmission switching models generally represent switching actions using binary variables, without considering the availability of communication resources or whether the corresponding DC circuit breakers (DCCBs) can interrupt the fault current affected by time delay. To address these issues, this paper develops an explicit optimal info–power flow (OIPF) formulation that incorporates information transmission into the post-fault transmission-switching optimization for AC/MTDC grids. The switching status of each DC branch is determined by the availability of its communication path and associated communication resources. In addition, binary switching decisions are supplemented by a DCCB feasibility constraint that limits the estimated delayed-interruption current to the DCCB breaking capability. The resulting problem is formulated as a mixed-integer second-order cone programming (MISOCP) model that can be efficiently solved using off-the-shelf optimization solvers. Numerical results reveal that limited communication capacity and additional routing costs may render electrically beneficial switching actions infeasible or uneconomical, while delay-aware DCCB interruption constraints may favor lower-delay communication routes despite their higher costs.

Game-Creation-Agents (GCA) turns a natural-language request into a runnable Phaser 4 browser game. The pipeline first builds a multimodal game design document that couples mechanics and scene contracts to grounded visual references. It then projects that document into a runtime scaffold, machine-readable contracts, and deterministic tests. Eight specialized agents next carry out production: scenes are implemented serially, assets are produced in parallel, and one reduced manifest joins the two branches into a single build. Build-linked real-UI checks and a code-blind critic then verify that build and decide whether the game may ship. Each blocker returns to the agent that owns the affected artifact for a bounded repair, and the game is released once all the gates pass. We evaluate finished games separately, through their rendered interfaces alone, over prompt-matched tasks run under a common protocol. GCA achieves stronger requirement satisfaction, core mechanics, content depth, and functional visuals than a comparable open pipeline. In a side-by-side human study, raters also score GCA's games higher on every dimension and prefer them overall.

Digital Twin (DT) combined with reinforcement learning (RL) can support adaptive resource allocation and security-aware decision-making by comparing expected and observed network behavior. This paper presents a simulation-based DT reference and a belief-guided Q-learning (BGQL) for joint jammer identification and beam-power control in a site-specific 28-GHz network. For each action, the same channel simulator is evaluated under an attack-free and an attacked configuration. Receiver-level residuals are combined with spatial jamming footprints and accumulated to form a normalized suspicion vector. BGQL incorporates this vector into an aggregated state, a belief-concentration reward, and exploratory beam-selection rule. The BGQL scheme is compared with SARSA, Greedy, and Random under matched attacker sets. Across 30 paired Monte Carlo runs in four configurations, with the number of active jammers supplied to every method, BGQL achieves mean aggregate full-band link-rate scores of approximately 437.4–564.2~Mbit/s and rate-to-device-power scores of 60.37–76.79~Mbit/J. Its detection accuracy is 100% in one-jammer configurations and approximately 78%–81% in two-jammer configurations. BGQL requires approximately 80–130~s per run, compared with 5–14~s for SARSA, reflecting evaluation of 625 beam pairs during exploratory steps. These findings provide a matched-model simulation proof of concept for DT-referenced belief-guided learning for security-aware beam-power control in 6G networks.

Geospatial reasoning links VLMs to real-world action and decision making. Reliable reasoning requires accurate spatial information and effective spatial representations. However, current VLMs obtain this information mainly from language and vision. At larger geographic scales, limited visual observations make it difficult to establish accurate spatial references and recover precise spatial relations. This leads to a bottleneck for VLM spatial perception and reasoning. This paper proposes that geospatial vector geometry can become a native spatial modality within a VLM and introduces GeoVec-VLM. First, we develop a structured geometry representation that preserves the spatial structure and arrangement of vector objects, building an explicit spatial basis. Second, we introduce a geometry interaction strategy that brings this basis into multimodal computation, where it interacts with visual content and language references according to the queried spatial relations. Together, these designs allow perception and reasoning to operate on shared geometric references. Across five spatial reasoning tasks, GeoVec-VLM improves mean accuracy by about 11% relative to the strongest baseline, maintains its gains under geographic transfer, and shows greater geometric consistency. Our results show that geospatial vector geometry offers a promising internal spatial basis for VLM spatial reasoning. https://github.com/TXFR/GeoVector-VLM

In this short note, we prove that any closed interval in a well-ordered and discrete space is finite. The coincidence between finiteness and boundedness can then be established for transition systems where the state space is well-ordered and discrete. Finally, this result is also proven when the state space is a Cartesian product of $d$ discrete and well-ordered sets.

Relational learning typically predicts from a database state, but decision making asks a different question: how will that state change under an action? In operational systems, the answer depends on system-specific dynamics that may not be visible in the database itself. We view each such system as a relational "world" and ask whether a model can infer how it behaves from observed executions. We introduce TabWM (Tabular World Model) and WorldRel, a generator of executable relational worlds for pretraining. Given executions from an unseen world, TabWM uses them as context to predict the sparse structured edits caused by a new action without parameter updates. Across 512 held-out worlds, complete-edit F1 rises from 0.016 with no observed executions to 0.685 with 64, where a correct edit must match its operation, relational location, and value. Because these predictions are explicit relational edits, they can be applied recursively to imagine candidate futures and compare actions before they are taken. Broader search over these predicted futures improves the realized return of selected action sequences. Together, these results suggest that relational dynamics can be learned in context, broadening relational learning from modeling system state to modeling how that state changes under action.

Keypoint detection plays a central role in geometric vision pipelines. Existing detectors exhibit complementary strengths across different scene structures and keypoint budgets, and reliance on a single detector often results in suboptimal keypoint distributions. Motivated by this observation, we propose Mixture of Detectors (MoD) for dense matching pipelines, a unified framework for complementary keypoint detection through the adaptive composition of heterogeneous detectors. MoD first distills heterogeneous detectors into a unified model, allowing diverse detection maps to be predicted efficiently within a single forward pass. Detector selection is subsequently formulated as a patch-wise, budget-conditioned decision process, in which a lightweight router assigns the most suitable detector to each local region. To avoid heuristic supervision, the router is trained with task-driven rewards derived from downstream matching quality, jointly capturing both keypoint quantity and precision. Extensive experiments on MegaDepth, ScanNet, and HPatches demonstrate that MoD consistently outperforms strong baselines across a wide range of keypoint budgets, demonstrating its effectiveness in improving keypoint distribution and downstream geometric performance.

LLM-based information systems need safety guardrails. Most guardrails classify the prompt alone. If the prompt looks harmful, the system rejects it before any answer is generated. This is costly. Many rejected prompts would have received a safe response. Users lose help they should have received from the information system. This cost grows as conversational and generative search becomes common. Prompt-level labels treat harm as a property of the query. But harm depends on what the model actually writes. Existing input-output guards do look at responses. But they judge a finished response, so the decision comes after full generation. However, we observe that safety of model interaction with the input prompt can be inferred early with only partial output. So the system can start generating, watch the partial response, and stop only if it turns harmful. We test this idea in three steps. First, we build a dataset of 41,944 prompt-response pairs with seven open weights LLMs from three families: Llama, Gemma, and Qwen. Second, we show that prompt harmfulness and interaction safety differ. Prompt labels and response labels agree on only 50.46% of items (Cohen's $\kappa$ = 0.06). Of the prompts that make any model respond harmfully, only 3.5% do so for all seven LLMs. Third, we show that partial responses carry most of the signal. Fine-tuned classifiers predict response-level harm well (best AUPRC 0.885, F1 0.807). About one third of the response tokens recover almost full-response AUPRC.

Latent diffusion models generate images as codes of an image tokenizer, whose decoder turns them into the pixel image. Recent tokenizers improve how well these codes reconstruct an image and how easily a generator learns them. Yet a generator does not reproduce the codes of training images, and when a generated code lands outside what the decoder expects, the decoded image contains imperfections. Current methods make the decoder more robust to generated codes by adding noise during training. However, generated codes lie between the training codes and resemble their mixture more than one of them plus noise. To improve generated images, decoders should therefore be trained on codes in the space between training samples. We propose InterpTok, which fine-tunes MAETok to decode mixtures of image codes into natural images. Since no target image exists between two training samples, a discriminator judges whether each decoded mixture looks as natural as its two sources. A mixing ratio loss requires the decoded mixture to keep the mixing ratio of the two codes. Together, they prevent collapse to a trivial solution and yield a sharp and natural composition of both images. InterpTok keeps MAETok's reconstruction quality and improves interpolation quality more than threefold, the best of all tokenizers in a recent benchmark. Beyond interpolation, InterpTok improves the generation FID of a matched diffusion transformer from 11.61 to 8.48 without guidance, and even reaches 8.11 at an eighth of the sampling steps, where the generator on MAETok's codes worsens. The generator trained on our tokenizer also reaches the final result of the one trained on MAETok at half the training steps. Our findings show that the space between image codes can and should be explicitly supervised rather than ignored.