Papers

A routing node on the Lightning Network holds its liquidity in separate channels, so a payment can fail at a channel whose outbound balance is exhausted while the node's other channels still hold balance. Pooling the channels into one reserve fixes this only if the node's draws across all channels stay within the reserve: a global invariant that each counterparty must enforce from its own channel, with no shared counter that off-chain draws can update. A node must therefore split the reserve into per-channel quotas in advance or coordinate every draw with every counterparty. On three Lightning snapshots the advance split forfeits $16$ to $67\%$ of the pooling gain over unpooled channels, and the loss grows with channel count. Sluice recovers $19$ to $65\%$ of that loss with a nested reservation: each channel keeps an exclusive base that its counterparty checks alone, and the rest is a shared overflow drawn on with certificates from a capacity-weighted quorum of the node's counterparties. Two conflicting certificates share an honest signer, so over-drawing is prevented without a slashable stake, under a stated bound on the capacity the node controls in the signing set. Sluice loses at most $1.3$ points of payment success to coordination where deployed coin movers lose up to $10.3$, and improves them in eleven of twelve cells when stacked on them. Re-creating every base output each epoch costs $2.8$ to $5.1$ times Lightning's on-chain bytes; re-creating only those that overflowed costs $0.5$ to $1.2$ times and keeps part of the gain.

Predicting heterogeneous causal effects supports informed decision-making, yet suitable inductive biases vary with treatment overlap, covariate imbalance, prognostic structure, and sample size. The Geometry-Diverse Anchor–Correction Expert Ensemble (GeoACE) addresses this variation through five complementary experts whose predictions are combined using weights estimated from validation data. Compared with ensemble designs that derive diversity primarily from sample or feature subsets, reweighting, or feature transformations, its central contribution is the coordinated design of training objectives and anchor geometries that target different prognostic and overlap structures. Following validation, each expert is refitted on the combined training and validation data, while retaining its distinctive structure. The shared architecture couples a structured outcome anchor with a learned neural correction. ACE serves as the reference estimator, while OW-ACE emphasizes well-supported covariate regions through overlap-weighted factual training. G$\Phi$-ACE constructs a global outcome-guided geometry from pooled prognostic associations, whereas A$\Phi$-ACE incorporates arm-specific outcome associations and penalties for treatment-group imbalance. O$\Phi$-ACE complements these approaches with an outcome-free, overlap-aware projection that replaces the anchor input with a lower-dimensional representation. GeoACE is evaluated against 11 comparators on eight benchmark protocols, alongside comparisons of weighting rules and aggregation controls. It achieves the lowest mean $\sqrt{\mathrm{PEHE}}$ and absolute average treatment effect error on all three IHDP protocols and closely approaches the best comparator on NEWS, although performance varies across the remaining benchmarks. The aggregation analyses show similar observed performance for inverse-DR weighting and equal averaging.

Generative recommendation reformulates item retrieval as sequence generation, allowing a unified model to directly generate the next item from a user's interaction history. Semantic IDs further make this paradigm effective and scalable by representing each item as discrete codes, enabling knowledge sharing among semantically related items. Recent studies introduce explicit reasoning before Semantic-ID generation, helping models summarize user interests and infer possible preference transitions. However, reasoning is not inherently beneficial: Inaccurate or uninformative reasoning may mislead subsequent item generation and ultimately degrade recommendation performance. This raises a central challenge: how can a recommender select and learn effective reasoning traces and progressively evolve toward better reasoning from its own generations? In this work, we propose Evo-Rec, a three-stage framework for learning better reasoning and further enhancing it through reinforcement learning. First, we align Semantic IDs with their textual and behavioral contexts, enabling the model to understand and generate item identifiers. Second, we sample multiple candidate reasoning traces and retain those that improve the prediction of the ground-truth item, providing a stronger reasoning initialization through supervised fine-tuning. Third, we further optimize the reasoning policy through reinforcement learning with catalog-constrained item generation and ranking-aware recommendation feedback. Experiments on three Amazon Review benchmarks show that Evo-Rec consistently outperforms discriminative, generative, and reasoning-enhanced recommenders across all evaluation metrics. These results demonstrate the effectiveness of our framework in learning better reasoning for SID-based generative recommendation.

Zero Forcing (ZF) and Power Dominating Set (PDS) mark vertices in a graph based on a common forcing process starting from a problem-specific set of initially marked vertices. ZF initially marks the selected vertices while PDS additionally marks their neighbors. In the forcing process, a marked vertex with only one unmarked neighbor may force that neighbor which then becomes marked, too. A solution marks the entire graph by exhaustive application of this rule. One variant generalizes the forcing threshold; vertices may force when they have a fixed number of $k$ unmarked neighbors. Another variant limits propagation to a fixed number of rounds. We classify the parameterized complexity of the problem variants obtained by combining these choices of initialization, round limit and forcing threshold. We show that with appropriate choices, these variants range in parameterized complexity from fixed-parameter tractable to complete for every even layer $W[2\ell]$ of the $W$-hierarchy, and up to $W[P]$-complete. Our results demonstrate that small changes in any one of these three dimensions can lead to a sharp change in problem complexity.

Standard-cell libraries form the critical interface between transistor-level circuit design and automated digital design flows, yet their design and characterization are rarely covered in depth in digital VLSI courses. This paper presents VLSI 5, a graduate-level course at ETH Zurich in which students design, lay out, characterize, and integrate their own standard cells using IHP's open-source 130nm SG13G2 process design kit. In the first course offering, 19 students developed EZ130 8T, an open-source eight-track standard-cell library comprising 220 cells. We evaluate successive library versions using eight synthesis benchmarks, across which EZ130 8T achieves significant area reduction compared to the SG13G2 library at competitive timing. For a postlayout 8x8 matrix-vector multiplier, EZ130 8T reduces cell area by 35% and energy by 39% while maintaining virtually the same clock period. The library has already been adopted in other ETH Zurich VLSI courses, enabling the creation of chips entirely designed by students down to the transistor level.

General-purpose vision-language models (VLMs) bring broad knowledge and spatial reasoning to robot manipulation, yet existing systems either use them indirectly, to predict constraints or write programs, or give them a view of the scene rather than a world in which to act. We present World Action Agent (WAA), a multi-agent harness through which VLMs pilot robots with basic tools, making every decision within a visual action workspace. The workspace has three properties. Contact views, selected automatically from the scene geometry, present the scene around the current interaction. Action rehearsal turns each action into an editable proposal that the agent, alone or through an Imagination Agent, previews and revises against planning feedback before execution. In-view correction closes the loop between observation, rehearsal, and low-level execution, letting the agent remove residual offsets in the view where it observes them. Through the same workspace, WAA acquires embodied procedural knowledge in two ways: it evolves multimodal skills from expert videos and human teaching under evidence-based review and consults them through a Skill Agent, and its interaction traces train smaller VLMs to pilot the same harness. On LIBERO-Pro, WAA with skills evolved only from LIBERO-90 reaches a state-of-the-art 75.6% average success, outperforming end-to-end VLAs, code-as-policy agents, and a visual-harness baseline with the same backbone; the same skills remain effective on robosuite without further learning. Fine-tuning Qwen3.5-9B on harness traces raises its out-of-domain success from 1.7% to 43.3%.

Textured Gaussians improve local appearance capacity, but assigning the same texture resolution to every primitive wastes storage on low-detail or weakly visible regions. We introduce AdaTex4D, an adaptive texture-capacity module for deformation-based 4D Gaussian Splatting. Each Gaussian carries packed RGBA triplanes whose two axes grow independently according to visibility normalized screen-space gradients and deformed local scales. Experiments on N3DV and PanopticSports show that AdaTex4D reduces texture storage by more than half while preserving reconstruction quality. Under fixed memory budgets, adaptive allocation also improves quality over uniform texture assignment and reduces overall model and peak memory. These results show that dynamic, anisotropic texture allocation provides a more efficient way to distribute local appearance capacity in 4D Gaussian representations.

Formal verification tools commonly rely on SMT solvers to automatically reason about programs, leveraging a range of logical theories, e.g., linear integer arithmetic, arrays, or strings, to encode program constructs and verification conditions. Despite recent advances, such solvers still struggle when reasoning about recursive data structures such as lists, which are pervasive in modern functional languages. Additionally, lists are commonly used in conjunction with higher-order combinators to, e.g., generically apply a function to all elements of the list. In this work, we provide first-class support for reasoning about lists within SMT solvers. We focus on lists of arbitrary size that, following the map-reduce paradigm, can be manipulated exclusively through a set of abstract combinators. To this end, we introduce DueList, an abstraction-refinement approach geared towards list reasoning, which we implement on top of off-the-shelf SMT solvers. To evaluate the efficiency of our approach, we assemble a diverse set of 752 benchmarks curated from previous works and real-world programs, and compare DueList against state-of-the-art solvers such as Z3 and CVC5. Our experimental evaluation shows that DueList extends reasoning facilities of existing solvers, allowing to conclude about the (un)satisfiability of a larger range of problems, while outperforming existing solvers in the vast majority of previously supported cases.

Many iterative algorithms rely on bootstrapping. A variable is updated using a second, frozen copy as a target, which is periodically replaced with the updated variable. Majorize-minimize and inexact proximal-point methods share this structure, as does temporal-difference (TD) learning. However, existing convergence guarantees for scenarios that combine sampled updates with targets refreshed only every $K$ steps rely on the specific structure of the update, such as linear approximation or gradient-based inner steps, and on uniformly bounded sampling error. We instead model the sampled update as a stochastic operator on the parameter space, which reduces the analysis to a contraction argument that needs no gradient structure and allows the sampling error to grow with the iterates. Within this framework, we derive a finite-time bound for i.i.d. samples and any target-update period $K$. We show that the iterates converge geometrically in root mean square to a ball around the fixed point, provided the sensitivity to the frozen target is smaller than the contraction slack of the inner map. Existing deterministic frozen-target contraction and stochastic-gradient-type bounds follow as special cases of our framework, and simulations of TD learning reproduce the predicted contraction rate and scaling of the error floor with the step size.

Fine-tuning large language models on new objectives can improve helpfulness, instruction following, or domain-specific performance, but it can also induce regressions on safety-critical prompts. Existing safety-preserving fine-tuning methods typically control average safety loss or use weighted auxiliary penalties, which can obscure rare but severe failures. We propose a chance-constrained formulation for safety-preserving fine-tuning that limits the fraction of safety examples whose degradation relative to a reference model exceeds a prescribed threshold. Because the resulting empirical chance constraint contains a discontinuous indicator, we introduce a differentiable majorization of the violation rate, yielding a tractable conservative constraint. We then develop a constraint-aware gradient descent method that treats the majorized constraint as a safe set in parameter space and minimally modifies the fine-tuning direction to preserve feasibility. The resulting update admits a closed form and produces a tail-aware safety correction that emphasizes examples near or above the degradation threshold. We conduct an extensive set of experiments on harmful fine-tuning across three different tasks and three models and show that our approach consistently outperforms the baselines that exist in the literature. These results suggest that safety preservation in LLM fine-tuning is better viewed as a reliability-constrained optimization problem than as average-risk regularization.

Fine-grained object detectors are commonly evaluated with confusion matrices, which show where the model is confused but not why, nor whether the confusion can be reduced. We argue that confusion can be attributed to distinct, separable sources, each quantitatively measurable, turning a passive measurement into actionable guidance. We present $A^2E^2$, a diagnostic tool that decomposes the sources of confusion along two axes, $\{$aleatoric, epistemic$\} \times \{$within-class, between-class$\}$, giving a $2\times2$ taxonomy that enumerates the source types. Each quadrant is measured by its own quantity, computed in one of three places (input geometry, output-space disagreement, and the bias-parameter posterior), so the two epistemic sources are separated by construction rather than by an empirical correlation. On fine-grained aircraft detection, the four quadrants become four named sources with their own remedy verdict: affinity (geometric similarity, irreducible from size alone), heterogeneity (geometrically heterogeneous sub-variants, pointing to re-labeling rather than more data), contested (an insufficiently trained but learnable boundary, improvable), and collapsed (a class starved of data, reducible). After attributing the confusion to a specific reducible source, we apply a targeted intervention and verify experimentally that it reduces the diagnosed source specifically while leaving the irreducible sources unchanged. $A^2E^2$ thus turns confusion measurement into a concrete, validatable and actionable "diagnosis" in which the same off-diagonal mass can carry opposite causes and opposite remedies. We also state this framework's limits, including which sources are only partially identifiable on this specific dataset and why.

We study a matching mechanism where agents and objects are described by features rather than complete rankings. A single spectral projection reduces the problem to a one-dimensional sort, computable in O(N log N) time. We prove that on descaled features and preferences, our algorithm obtains the exact Nash Social Welfare (NSW) optimum within the projected space, with an unconditional utilitarian-welfare guarantee and a conditional NSW guarantee. The proposed mechanism is stable against exogenous noise but not strategy-proof; we provide an explicit profitable misreport. On an agentic AI shopping application, the diagnostics correctly anticipate both a success and a failure case. A 100-instance robustness study confirms the findings.

Before a product or policy change ships, the question that matters is how people will react to it. Augur rehearses that reaction offline: it builds a typed knowledge graph from the change documents, populates a grounded persona market, simulates the interaction, and returns an auditable decision memo recommending one of five actions. We assemble Gold-50, fifty real product and policy episodes whose real-world outcome is known, adjudicated against the public record, and score the five-way release verdict against it. Our central finding is methodological and negative: most of the measured gap between frontier cloud models and open-weight models we fine-tune and serve offline is attributable to an under-specified evaluation, not a difference in capability. We show this three ways. First, the prompt envelope alone can dominate the score: holding weights, cases and scorer fixed, one system – a LoRA-SFT adapter on Qwen3-32B – swings from 0% to 73%. Second, in a matched 2x2 ablation, defining the decision taxonomy in the prompt – with no model change – lifts every frontier model by +24 to +34pp; under the under-specified prompt, Qwen3-32B LoRA-SFT served offline beats all three frontier models (paired McNemar, Holm-corrected), and once the prompt is fair no significant difference from any of them is detected. Third, agreement with the distillation teacher rises without accuracy following, and the full pipeline amplifies a systematic "over-doom" bias rather than improving the verdict. Separately, we validate the reaction layer on its own terms: blind judges across four model families find the synthetic reaction recovers 67-90% of the concerns the public actually raised, and a pre-registered ablation locates its value – largest where the decision is hardest, redundant near ceiling. The pipeline that regenerates every number and figure here is available from the authors.

State tracking requires composing a sequence of updates, but accuracy alone does not reveal what a model has learned. We study neural networks trained to predict the running product of group elements. We identify quotient solutions in Transformers, where models recover the quotient class while predicting nearly uniformly among its members. The reciprocal of class size predicts partial accuracy without a fitted parameter, extending parity-based accounts to non-parity quotients. Our baseline Transformers' predictions change little under prefix reordering beyond the exact-tracking frontier. We prove that, for finite groups under uniform i.i.d. full-group inputs, optimal order-blind exact accuracy converges to the reciprocal of abelianization class size as prefix length grows, consistent with the observed abelianization plateaus. Sequential updates permit more: any partition into right cosets of a subgroup, normal or not, survives sequential updates. In our census of standard Transformers, every recovered coset partition comes from a normal subgroup, whereas parameter-matched recurrent networks pass through both normal and non-normal right-coset stages during training. On $A_5$, we identify low-dimensional subspaces of the recurrent state that encode non-normal cosets. In the three-dimensional cases, coset mean vectors form approximate dodecahedra, and swapping the state components in these subspaces transfers the donor's coset state through a shared input suffix. Our results connect partial accuracy, learning stages, and internal computation through the subgroup cosets that models learn to track.

We consider a class of SPDEs driven by a standard real-valued Brownian motion, with drift and diffusion coefficients such that there exists a unique mild solution taking values in the interval $[-1,1]$ almost surely. To preserve this qualitative property of the exact solution, we propose a domain preserving Lie–Trotter splitting scheme: for any choice of the time-step size, the numerical solution takes values in the interval $[-1,1]$ almost surely. Furthermore, we prove mean-square convergence with rate $1/2-$ for the domain preserving Lie–Trotter scheme. These theoretical results are illustrated with numerical experiments.

Prompt injection can degrade benign task performance without eliciting harmful content. Yet many attack objectives depend on task labels or predefined target responses. We present ENDOPROMPT, a white-box method that learns utility-degrading prefixes from unlabeled instructions. Its generator takes the request text as input. Clean victim continuations serve as pseudo-references: local search identifies prefixes that reduce continuation likelihood, and preference fitting on comparisons within the same instruction, followed by reward refinement, distills this signal into a generator. At deployment, the generator produces one prefix per request without further victim-side search. Across four instruction-tuned models and the complete splits of seven benign benchmarks, ENDOPROMPT yields a mean utility change of -26.8 percentage points; 27 of 28 cells are negative. Failure analysis reveals output expansion and prefix reuse; the controls do not establish a degradation advantage from request matching. Victim-derived supervision can reveal utility weaknesses without benchmark feedback or prescribed failure responses. The code will be released upon acceptance.

Large Language Models (LLMs) have shown impressive performance on a wide range of generative tasks. Yet their probabilistic nature makes them, in isolation, fundamentally unsuited for industrial product configuration, where outputs must be syntactically valid, semantically consistent with a knowledge base of hundreds of features and rules, and producible by an existing manufacturing chain. We argue that Neuro-symbolic (NeSy) AI methods lay out a promising path towards industrial-grade configurators that are reliable by design, explainable, and trustworthy. This paper describes a taxonomy of three NeSy integration strategies, namely hybrid inference, hybrid fine-tuning, and hybrid training, exploring their usage in the configuration domain. We report our effort to operationalize NeSy concepts in an industrial configuration copilot and derive a set of practical design choices for deploying trustworthy AI in engineering environments. We close with a discussion of open research challenges we consider most pressing, in particular how to scale NeSy methods from small academic demonstrators to the size of industrial configurators.

Robust control under delayed sensory feedback remains a key challenge in both robotics and neuroscience. Classical cerebellar models explain delay compensation through forward prediction but fail to account for fast online corrections and rapid adaptation observed in biological systems. We propose a cerebellum-inspired control framework that combines multiplexed predictive representations with internal feedback. By jointly encoding kinematic variables and task-relevant error signals, the model enables accurate online correction despite delayed feedback. Furthermore, incorporating feedback within the cerebellar loop significantly accelerates adaptation, reducing learning time by an order of magnitude. Our results show that single-signal predictions are insufficient under delay, while multiplexing and feedback together provide a unified mechanism for online control and rapid learning.

Many real-world optimization problems rely on expensive simulations or experiments, making the efficient use of available data essential. Multi-fidelity optimization of high-dimensional black-box functions subject to black-box constraints is increasingly relevant as the cost of objective evaluations continues to rise in applications such as machine learning, engineering, and control. To our knowledge, no existing method simultaneously addresses high-dimensionality, black-box constraints, an arbitrary number of fidelity levels, and non-nested sampling. In this work, we extend the Scalable Constrained Bayesian Optimization method to the multi-fidelity setting, resulting in the MF-SCBO method. The proposed approach is evaluated on standard benchmark functions as well as challenging problems. The experimental results demonstrate that MF-SCBO generally achieves better convergence than both the single-fidelity SCBO and the other multi-fidelity method considered in this high-dimensional and constrained settings.

Multimodal large language models (MLLMs) achieve strong performance on visual reasoning tasks, yet remain prone to hallucinations and over-reliance on language priors, often generating answers without adequately using task-relevant visual evidence. Existing approaches primarily improve reasoning through reasoning-oriented supervision or inference-time strategies. In this work, we study a complementary question: can multimodal reasoning be improved by strengthening implicit visual grounding without directly supervising the reasoning process? Motivated by the functional specialization of attention heads, we investigate whether reasoning can be improved by guiding only the heads most responsive to visual evidence grounding. We propose Selective Probability Mass Concentration (sPMC), a training framework that identifies grounding-responsive heads and selectively regularizes their text-to-image attention. sPMC treats normalized attention over visual tokens as a spatial probability distribution and encourages the probability mass to be assigned to semantically relevant regions using segmentation-derived spatial priors. Adaptive Head Selection restricts this guidance to visually responsive heads while leaving the remaining heads unconstrained to preserve their complementary functions. Across 6 multimodal benchmark suites, sPMC achieves an average zero-shot improvement of 3% and gains of up to 11.3% across multiple MLLMs while regularizing only 3%-15% of their attention heads. These results demonstrate that targeted guidance of sparse and implicit visual evidence pathways can directly improve multimodal reasoning.

We address the formation control problem for open multi-robot systems (OMRS), i.e., systems in which robots may join or leave the team during operation and new interaction links are established over time, subject to inter-robot collision-avoidance and connectivity-maintenance constraints. The robots are modeled by double integrators, and interact over a dynamic undirected graph. We design a distributed controller based on the gradient of a barrier-Lyapunov function. To enable team reconfiguration, we introduce a formation manager that coordinates robot additions and removals and establishes prospective edges whenever needed, either to connect a joining robot to the team or to preserve connectivity before a robot departs. The upper-distance constraints of prospective edges are temporarily relaxed through auxiliary dynamics that preserve feasibility while progressively recovering the nominal interaction range. The resulting open-team dynamics are modeled as a switched system, for which we establish uniform practical stability for almost all initial conditions under a transition-dependent average dwell-time condition. Finally, the proposed approach is validated in realistic Gazebo simulations with dynamically simulated quadrotors undergoing repeated joining and departure maneuvers.

A central goal when designing treatment policies is often to "do no harm", that is, to avoid interventions that improve average outcomes while worsening outcomes for some individuals. A widely used notion for harm is the fraction of negatively affected (FNA), defined as the probability that an intervention decreases an individual's outcome. However, in many applications, treatments operate through mediators, and a single "total" FNA can obscure whether harm arises primarily through direct pathways or indirect (mediator-induced) pathways. In this work, we introduce a path-specific analogue of the FNA. For this, we disentangle total harm into direct and indirect harm in causal mediation settings. However, these quantities depend on joint distributions of potential outcomes that are not point-identified even in randomised controlled trials. As a remedy, we develop a novel partial identification framework for direct and indirect FNA. In our framework, we (i) derive sharp Makarov bounds for the FNA, and (ii) propose a semiparametrically efficient estimator with valid confidence intervals for these bounds under mild margin conditions. We demonstrate our framework across various numerical experiments. To the best of our knowledge, we are the first to study path-specific decomposition of causal harm and to develop an orthogonal inference framework for its analysis.

Wearable human-activity recognition (HAR) models operate across sensors, subjects, and backbones, yet a smooth waveform may appear temporal while exploiting a persistent sensor offset primarily. We introduce SpectrumAudit, a label-sealed audit that fits a phase-randomized full-window stimulus on calibration windows from subjects held out from training and testing. After selection, it replays its exact DC projection and budget-constrained zero-mean residual on the same frozen victim without refitting. Across 27 victims from three datasets and three backbones, the selected waveforms cause 2.87-40.83-point three-phase robust accuracy losses. Under this replay budget, DC is more damaging than AC on 24/27 victims and recovers at least 90% of the full drop on 22/27; all 5 failures occur on WISDM. In a held-out UTD-MHAD check, the selected waveform causes 13.49-pp accuracy and 11.68-pp macro-F1 losses, versus -0.66 pp for matched random changes. The audit diagnoses offset versus zero-mean variation under a common peak-budget cap. The code will be released upon acceptance.

We study the detection of LLM-generated text under editing and contamination. Modeling human and machine text as finite-order Markov processes with Huber contamination, we characterize an exact boundary for reliable detection under our assumptions. Detection is impossible when contamination is sufficiently large relative to clean-source separation. Below this boundary, a collection of clipped likelihood-ratio tests achieves vanishing worst-case errors. This construction motivates clipping as a simple modification of existing statistical detectors. For a broad class of additive scores, we identify conditions under which the clipped test is consistent while the raw test's worst-case power tends to zero. We evaluate seven detectors across three datasets and three generation models, and on the RAID benchmark. Clipping improves robustness in both studies, with gains varying across detectors and contamination settings. For example, at a target false-positive rate of 5%, clipping improves the log-likelihood–log-rank ratio (LRR) detector's true-positive rate by a median of 8.3 percentage points in the controlled study and 2.1 and 4.3 points in rate- and attack-specific RAID evaluations, respectively.

Does progress on spatial reasoning benchmarks translate into better navigation? Existing benchmarks test isolated inferences from images or videos, with little connection to downstream navigation. Our analysis reveals a gap between benchmark-oriented spatial specialization and navigation performance, and shows how aligning spatial supervision with navigation goals, phases, and decision learning improves navigation. Guided by these findings, we build Spatial-Nav-100K and fine-tune in two stages, i.e. first learning a shared spatial-navigation foundation, and then specializing each phase with the abilities it relies on. We further introduce Spatial-NPD, where a teacher conditioned on spatial priors produces grounded action preferences and distills them into a student policy, so no explicit spatial reasoning is needed at inference. With 45 A100 GPU-hours of policy training, our 8B model reaches SR/SPL of 77.4/35.4 on HM3D-v0.2, 60.2/30.5 on HM3D-v0.1, and 47.9/20.6 on train-unseen MP3D. It outperforms several systems that rely on closed-source models or thousands of GPU-hours of training, at 148 ms per action step. All code and datasets will be publicly available at https://github.com/ylwhxht/Spatial-Nav.

Vision-Language Models (VLMs) are increasingly used for long-document processing, where the inputs combine text with charts, tables, figures, and complex layouts. Deploying them means choosing how to feed the document to the model, which retriever to use when only a subset of pages is sent, and whether to run the model agentically or as a static pipeline. We study these choices on two long-document QA benchmarks with both frontier API and open-weight VLMs. First, on MMLongBench-Doc our six-tool agent with page, table, figure, and search calls pays off only once the answering VLM is large enough: with Qwen3.5-4B and 9B it trails static page input, with Qwen3.5-27B it draws level, and with Sonnet 4.5 it leads. On LongDocURL it is level with or ahead of static input at every reader. Its lead over the strongest static pipeline is clearest with the frontier reader on MMLongBench-Doc and narrows to within noise on LongDocURL. Second, retrieval modality matters more than the specific retriever: the strongest image retriever leads the strongest text pipeline, and on the text side a single off-the-shelf cross-encoder rerank essentially matches a much heavier multi-stage LLM pipeline. Top-k image retrieval is also the most token-efficient input at every reader we paired it with, at roughly a seventh to a quarter of the tokens of sending every page. Third, cutting across all three choices, three of our strongest pipelines succeed on different questions, and an oracle that picks the best pipeline per question gains roughly thirteen points over the best single pipeline, though evidence-type routing recovers almost none of it.

Resting-state functional connectivity (FC) is widely used to classify brain phenotypes and disorders. Most pipelines use the full connectome and seek gains through model design. We instead examine how FC geometry constrains classification and cross-site transfer. Across-subject FC variation concentrates in a small effective subspace, suggesting substantial redundancy in nominal dimensions. Across cohorts, these subspaces may differ in orientation even when their effective ranks are comparable, potentially limiting transfer. Across 2,330 subjects from HCP, ABIDE, and ADHD-200, effective-rank analysis reveals strong spectral concentration. Projection onto leading components at the effective-rank scale recovers most of the full-FC classification performance. In ABIDE, site-specific effective subspaces are weakly aligned, and their principal-angle overlap predicts pairwise transfer after covariate adjustment despite comparable per-site effective ranks. Controlled rotations that alter subspace orientation while preserving the mean and covariance spectrum drive transfer toward chance, whereas displacement-matched label-orthogonal rotations do not. These results identify subspace orientation as a key factor in transfer degradation under controlled perturbations. This study offers a geometric diagnostic of FC generalization and suggests evaluating cross-site harmonization by its ability to align effective subspaces alongside classification accuracy.

Radiology AI systems increasingly inform clinical decisions such as triage, follow-up imaging, and treatment planning. For these decisions to be made safely, model outputs must be well calibrated, meaning predicted probabilities accurately reflect true risk. Many standard techniques for improving calibration, such as MC Dropout and Deep Ensembles, require access to model parameters or retraining. However, proprietary clinical AI systems operate as black boxes, preventing access to the model's internals. To that end, we propose a model-agnostic framework for improving calibration of black-box models using clinically grounded test-time augmentation (TTA). Our framework applies geometric and physics-inspired 3D CT perturbations and learns probability-level aggregation strategies without access to model internals or the original training data. Across pulmonary embolism and intracranial hemorrhage detection tasks, DualTTA achieved the strongest overall calibration among TTA methods, reducing the Expected Calibration Error by 54% (0.239 -> 0.109) and 43% (0.051 -> 0.029), respectively, while requiring only input-output access. Additionally, DualTTA outperformed uncertainty estimation techniques that require access to model internals, such as Temperature Scaling, MC Dropout, and Deep Ensembles, in most calibration metrics. These results demonstrate that learned TTA aggregation can improve the calibration of clinical AI systems, providing a practical approach for improving the reliability of black-box medical AI.

WCE produces large-scale gastrointestinal image data yet pathological findings remain significantly underrepresented limiting the generalization performance of deep-learning based abnormality detection systems. SDG methods offer a practical solution to mitigate this imbalance. However their training directly on scarce abnormal samples often results in instability overfitting and structural distortions. Addressing these challenges requires controlled adaptation mechanisms that preserve anatomical priors while enabling realistic pathological variation. This paper presents EndoFSA a GAN-based model for Endoscopic Few-Shot image generation by Adaptation in WCE imaging. EndoFSA leverages a generator pretrained on abundant normal data and adapts it to abnormal domains using limited number of training samples through a rank-constrained parameter adaptation where only a small number of modulation parameters is updated while the pretrained weights remain frozen. By restricting parameter updates to a low dimensional subspace and incorporating perceptual boundary regularization and cluster-wise diversity control EndoFSA enables efficient model adaptation under limited data conditions and mitigates mode collapse while preserving the anatomical priors learned from normal data. Importantly EndoFSA operates without requiring pixel-level annotations, masks or bounding box supervision. Evaluation on publicly available WCE benchmark datasets spanning various abnormal categories demonstrates that EndoFSA generates abnormal images reproducing real lesions morphology. Moreover in a downstream classification task training an image classifier solely on synthetic abnormal images generated by EndoFSA yields performance comparable to that obtained with real images.

Multi-robot coordination methods often score a joint plan from singleton and pairwise terms, leaving out the terms that involve three or more robots. We measure the plan-selection regret of two pairwise approximations to delivered coverage using frozen multi-robot trajectories. For each four-robot plan on an indoor exploration benchmark, replaying all 16 robot subsets gives the exact delivered-coverage set function $F$. From the same subset values we compute two pairwise scores: the exact order-2 Möbius truncation $F_2$, which depends only on the singleton and pair values, and an equal-weight least-squares two-additive fit $G$. Ranking by $F_2$ instead of $F$ changes the selected plan on six of seven maps at the 15 m candidate-generation range in each of two candidate families, with regret up to 0.337 of map coverage. Switching to $G$ reduces the regret but still changes the selection on three of seven maps in each family. The additive score $F_1$, which keeps only the singleton terms, selects the exact winner on six of seven maps in one family and four of seven in the other, against one of seven for $F_2$. We also find that lower average reconstruction error does not guarantee lower selection regret.