Computer Science (arXiv)

Geometric Data Perturbation (GDP) enables one-shot, privacy-preserving collaborative learning: each participant applies a distance-preserving transformation to its private data and uploads only the resulting representation to a central analyst. We study GDP under analyst-participant collusion, in which the analyst combines all uploaded representations with the private data and transformations disclosed by colluding participants to recover a non-colluding participant's private data. Participant-specific independent transformations resist this attack but map participants' data into incompatible representation spaces, degrading downstream model performance. Shared-anchor alignment from Data Collaboration (DC) analysis restores compatibility and improves utility, but we show that disclosing the DC anchor matrix enables exact recovery of non-colluding participants' private data even in the presence of collusion. Adding noise directly to the private-data representations mitigates this vulnerability but substantially reduces utility. We propose adding noise to the anchor representations instead. Each participant independently transforms its private data and the shared anchor matrix, perturbs only the resulting anchor representation, and uploads both representations in a single round. Using the noisy anchor representations, the analyst aligns the private-data representations by solving a Generalized Orthogonal Procrustes Problem. We characterize alignment and recovery errors, specialize a conservative sufficient condition for convergence of the alignment to our setting, and analyze three recovery attacks. Experiments on MNIST and CelebA show that, across the evaluated attacks and deployment settings, anchor noise achieves higher learning accuracy than private-data noise at comparable measured leakage, yielding a more favorable privacy-utility trade-off under the specified collusion model.

Biological and artificial systems offer complementary forms of adaptation, learning, and computation, with advances in in-vitro neurotechnology increasingly enabling bidirectional coupling between them. As these systems become more tightly integrated, a key architectural question is how task-relevant computation should be distributed across both substrates. Yet existing biohybrid solutions optimise the biological substrate, the AI model, or their interface without explicitly addressing how such computation is allocated, reassigned, and evaluated. We introduce Biological-Hybrid Intelligence (BHI), a conceptual framework for distributing computation across adaptive biological and artificial substrates coupled through a bioelectronic interface and coordinated by an orchestrator. BHI treats both substrates as computational entities whose computational responsibilities may change during operation. BHI requires reciprocal co-adaptation and differs from systems that merely decode biological activity, stimulate a living substrate, or adapt a single component. BHI further defines three operating modes: adversarial, collaborative, and codependent, distinguished by whether the substrates compete, divide computational labour, or become mutually necessary for task performance. BHI provides a common basis for comparing computational frameworks, defining benchmarks for latency, viability, interface bandwidth, learning efficiency, and reproducibility. It also highlights governance considerations arising from reciprocal stimulation, adaptation, and data exchange. More broadly, BHI invites computer scientists to consider biological substrates as active computational resources and to ask not only how a task should be computed, but where its computation should reside. BHI therefore reframes biological-artificial integration as a system-level problem of computational allocation, coordination, and control.

JEPA-style latent world models can use Euclidean distance to a goal latent as the cost for model-predictive control (MPC). Strong decoding of task variables, however, does not guarantee that this particular cost ranks candidate action sequences by real task progress. We call the latter property \emph{decision-metric alignment}. We introduce Plan-Real Spearman, which measures latent--real rank agreement on random plans, and CEM-stage Spearman, which measures the same agreement as cross-entropy-method (CEM) search concentrates its proposal. We analyze sufficient conditions under which latent distance preserves real-cost rankings, identifying encoder distortion, terminal rollout error, and candidate margins as the controlling quantities. Guided by the observed empirical alignment gap, DA-LeWM augments LeWM with inverse-dynamics and demonstration-conditioned goal-action heads. Across all our experiments, DA-LeWM accelerates convergence and achieves higher online success than LeWM, while probe scores remain similar. These results show that action-conditioned objectives improve the geometry used by Euclidean-cost, CEM-based latent MPC.

Agents improve quickly against a reliable automatic metric and stall without one, and the applications that need them most, report generation among them, are the ones nobody knows how to score. Can the metric write itself? Saying what makes an answer good is hard; pointing at something wrong with one is easier, so the metric we evolve is a pool of small Python operators that each flag a candidate for one named defect, or abstain, and vote. Asking a model for operators directly does not work: 183 candidates realise only 96 distinct behaviours, from one narrow region of an enormous space. EvalCEGAR instead borrows counterexample-guided abstraction refinement from program verification. It reads the pool as an abstraction and searches for a collision, two answers the operators score identically, one correct and one not. That pair, not a prompt, is the authoring request, and when a collision defeats every attempt the loop widens what an operator may read rather than resampling. On MBPP+ and HumanEval+, a sandbox whose hidden unit tests give exact ground truth, the loop writes a 55-line operator that closes 15.4% of the gap between flagging nothing and a perfect filter on 428 unseen tasks (+0.0065, p=0.0010) at a quarter of our best hand-written operator's flags. On the benchmark it never saw it matches that operator's effect exactly on a third of the flags. Six of eight runs admit such an operator and all six help out of sample; our 15 hand-written operators applied together as one filter lose accuracy. An LLM judge on the same information ties that delta on a nearly disjoint set of candidates, and charges a model call per candidate forever where the operator charges none.

In some fields currently dominated by empirical approaches, such as state of health (SoH) prediction for lithium-ion batteries, phenomenological models motivated by quasi-physical thinking contain parameters to be estimated from experimental data. Often the structure of such models yields fully or partially confounded parameters, which are difficult or even impossible to estimate reliably. To preserve the desired model formulation and simultaneously improve the numerical conditioning for the problem we introduce a ridge regression scheme. An automated method is provided, based on information theoretic measures of model performance, which optimises the ridge regression hyper-parameter at each iteration. The formulae presented require fixed point iteration to solve for the hyper-parameter. Given a suitable starting value, analysis demonstrates convergence is very rapid. The optimal hyper-parameter selection mechanism is incorporated within an efficient regularised iterative generalised least squares mechanism, capable of fitting both heteroscedastic and serially correlated data as required. Simulation confirms the efficacy of the overall method.

This paper proposes a multi-agent framework built on CrewAI [1] for conversational business intelligence. Five specialized AI agents operate in a sequential pipeline to process natural language queries, retrieve and analyze data, generate visualizations via the Model Context Protocol (MCP) [2], and deliver actionable insights. The platform features a defense-in-depth security architecture for multi-tenant data isolation and a query parameterization mechanism for transforming conversational insights into reusable dashboard components. Evaluation across 300 end-to-end test cases spanning synthetic and production enterprise datasets demonstrates 95.3% functional accuracy, a mean response latency of 24 seconds, and a response quality score of 4.52/5.0 as assessed by an LLM-as-a-Judge framework, with a 93.0% hallucination-free rate, representing a 22.6 percentage point accuracy improvement and 20.2% quality gain over a single-agent baseline. Cross-model evaluation across four LLM backends and human expert validation confirm architectural generalizability and evaluator reliability. An ablation study confirms that the Data Analysis and Report Aggregation agents are the primary drivers of output quality.

Federated training enables language models to learn from distributed private text, but the server cannot directly verify the local supervision or optimization process that produces each client update. A malicious client can therefore train on corrupted targets, introduce incorrect context-token associations, and degrade the global model through repeated aggregation. Such degradation can also increase the risk of unreliable or hallucinatory generation. We propose Federated Learning with Normalization Signatures (FedLNS), a server-side framework for lightweight malicious-update screening. FedLNS represents each client update through changes in trainable normalization-layer parameters and screens suspicious updates against a robust, history-aware cross-client reference. Because the signatures are extracted at the server from the returned local models, FedLNS requires no additional client-to-server parameter or metadata exchange compared to standard federated learning (FL) methods. After screening, the retained full-model updates can be aggregated using standard FL or another compatible aggregation rule. FedLNS requires no raw client data, trusted server dataset, labeled attack examples, or separately trained detector. Experiments on GPT-style, BERT-style, and LLaMA-style models trained from scratch with 200 clients show that, under 40% population-level target manipulation, FedLNS achieves lower test perplexity than the strongest of six baselines for all three architectures under both IID (independently and identically distributed) and non-IID data partitions.

4D understanding and reasoning is a fundamental capability for embodied AI agents operating in dynamic physical environments. However, existing vision encoders are largely limited to static 2D images or 3D point clouds without temporal modeling, or to 2D videos that lack accurate geometric depth reasoning. Consequently, current approaches fail to jointly capture spatial structure and motion evolution in dynamic scenes. We present CL4D, the first foundational 4D vision encoder that directly operates on dynamic point clouds, trained with a contrastive learning objective to align spatio-temporal geometric representations with natural language descriptions. By learning a shared embedding space between text and 4D scene dynamics, CL4D enables zero-shot motion-to-text and text-to-motion retrieval in dynamic environments and serves as a foundational 4D vision encoder for downstream 4D vision-language tasks. Building on this encoder, we introduce 4DVLM, a 4D vision-language model that conditions language generation on dynamic geometric representations. 4DVLM is the first VLM designed to operate directly on 4D point clouds without relying on 2D images, 2D videos, or static 3D point clouds. We train CL4D and subsequently 4DVLM on a newly constructed dataset termed DynAction4D capturing diverse human motions across varying object interactions and scene environments. Extensive experiments across multiple 4D human action benchmarks demonstrate that CL4D achieves state-of-the-art performance, with improvements of approximately ~16.75% over prior methods. Furthermore, 4DVLM outperforms frontier video VLMs such as Gemini and GPT-5 even when these models are provided with RGB video sequences corresponding to the same scenes represented as 4D point clouds for 4DVLM.

We present Flama, an open-source Python framework for developing and deploying production-ready web APIs, machine learning services, and large-language-model (LLM) applications. Built on the Asynchronous Server Gateway Interface (ASGI), Flama offers a type-driven, async-first programming model that unifies REST API development, predictive model serving, and generative AI inference in one architecture. It is organised around seven subsystems: a component-based dependency injection system resolving handler parameters from type annotations at startup; a pluggable schema layer supporting Pydantic, Marshmallow and Typesystem behind a single adapter; an automatic CRUD generator turning a SQLAlchemy table and a schema class into REST endpoints backed by the Repository and Unit of Work patterns; a portable binary format (.flm) packaging models from scikit-learn, TensorFlow, PyTorch and Hugging Face Transformers with their metadata for zero-code deployment; a multi-backend LLM server running vLLM (Linux/CUDA) or MLX (Apple Silicon) and exposing four wire protocols (OpenAI, Anthropic, Ollama, and a native streaming dialect) through a shared codec; a Rust-accelerated core compiled via Maturin for routing, JSON encoding, compression and parsing; and a Model Context Protocol module turning any application into an MCP server over JSON-RPC 2.0. Built-in capabilities include JWT authentication, two pagination strategies, background tasks in threads or processes, WebSocket endpoints, Server-Sent Event and NDJSON streaming, OpenAPI 3.2.0 generation from handler signatures, and a command-line interface for running applications and for serving, packaging and inspecting models. We describe the architecture, present the programming model through worked examples, and compare Flama with existing frameworks, model serving platforms and LLM inference engines.

Medical image segmentation is essential for clinical workflows such as treatment planning and disease assessment. While specialist tools like TotalSegmentator and MRSegmentator achieve strong performance, they require large annotated datasets for training. Medical foundation models offer a promising alternative through large-scale pretraining that reduces the annotation burden for new tasks, but zero-shot performance remains limited. Parameter-efficient adaptation via Low-Rank Adaptation (LoRA) enables efficient specialization with few trainable parameters, but a key question remains: how many expert-annotated cases are needed to achieve clinically useful segmentation performance? We address this by adapting MedSAM3 with LoRA for five abdominal organs (liver, kidneys, spleen, gallbladder, and pancreas) in CT and MRI using only 1, 2, 5, and 10 annotated cases, evaluating on AMOS22 dataset. With just 10 cases, models achieve performance competitive with specialist systems trained on orders of magnitude more data. Notably, this includes reliable gallbladder segmentation (Dice 0.68 CT, 0.59 MRI) where existing tools fail almost completely (Dice 0.0004), while remaining within 5--10% of MRSegmentator for liver, kidneys, and spleen using over 100 times fewer annotations. Furthermore, external validation on the Whole Heart Segmentation dataset shows that the approach extends to cardiac segmentation, a use case beyond the scope of TotalSegmentator (MRI) and MRSegmentator, achieving competitive left ventricle (LV) performance with only 10 annotated cases. Training requires only3--5,hours per organ on a single GPU, approximately 2--3 times faster than nnU-Net. These findings suggest that ten annotated cases are sufficient for clinically useful segmentation, effectively reducing bottlenecks for both image annotation and training time.

Applying machine learning to web pages is challenging due to the need to interpret HTML together with associated resources and perform rendering to obtain a meaningful visual and layout-aware representation. As a result, machine learning over web content remains comparatively underexplored. In this paper, we present a platform for visual-aware representation and machine learning over web pages based on the open-source rendering tool FitLayout. The platform provides a server capable of rendering web pages, explicitly capturing their visual and structural properties in an RDF-based representation, and persisting the rendered documents in an integrated storage. The processing pipeline is controlled via a REST API, while SPARQL queries are used to retrieve structured data suitable as input for machine learning algorithms. By explicitly modeling rendered web pages, including fine-grained layout details, the platform enables dataset sharing and supports the reproducibility of experimental results. The architecture supports the complete dataset preparation workflow, from web page collection and rendering through preprocessing and annotation of content elements to downstream learning tasks. We further provide a Python client library that integrates the platform with standard machine learning workflows. As a demonstration, we show how rendered web pages can be transformed into graph-based representations and used to train graph neural networks for recognizing key content elements, illustrating both the applicability of the approach and the reproducibility of the results.

Large language models are increasingly used for quantitative work in the environmental sciences, yet existing evaluations score only final answers, leaving calculation process unobserved. Here we introduce AtmosCoder-Bench, an execution-grounded benchmark that makes the calculation process visible. Built through a transferable semi-automated pipeline (436 problems, 3,910 variants, 7,029 graded quantities), every problem is validated to be unambiguous and human-solvable, with uniquely verifiable answers. We find that (i) multiple-choice formats inflate measured accuracy by at least 12 percentage points; (ii) many failures arise not from missing knowledge but from models failing to apply known formulas and constraints consistently throughout multi-step computation; and (iii) even frontier models remain weak when task-specific conditions invalidate familiar methods, often reverting to canonical solution patterns rather than adapting methods to the relevant physical regime, leaving expert oversight essential.

Telecom operators traditionally offer predefined tariff grids, forcing users to choose from a limited set of plans. This paper proposes BFTR (Budget-First Tariff Recommendation), a complete algorithmic framework integrating eight Budget-First strategies, including two original hybrid approaches: Recursive Hybrid (conditional interpolation) and Knapsack-First Hybrid (priority knapsack). Unlike existing approaches that adjust prices upward to guarantee a minimum margin, BFTR guarantees the absence of overcharging by systematically aligning the final price with the catalog reference price. We mathematically formalize each strategy, prove the existence of an offer for any positive budget, and prove that the price deviation (surcharge) is zero for all strategies that do not use interpolation with correction. A detailed comparative analysis confronts BFTR to ten main existing tariff models on ten dimensions. Experiments on a dataset of 974 customers inspired by the Nigerian MTN market show that: (i) Recursive Hybrid is optimal for the customer (100% budget used, 29.9 GB volume, utility 0.946, 0% overcharging), (ii) Piecewise offers the highest volume (39.7 GB) with 0% overcharging, (iii) Power Law provides an excellent compromise (99.9% budget, 38.1 GB, 0% overcharging). All strategies achieve a zero surcharge, confirming the theoretical guarantees. A sensitivity analysis on the weighting parameter alpha (0.2 - volume priority, 0.5 - balance, 0.8 - budget priority) shows that utility rankings evolve logically. Execution times (< 10 ms) and very low failure rates (0% for robust strategies) confirm the operational viability of the system. The formal proof of the absence of overcharging constitutes a major theoretical contribution.

Understanding and enhancing visual analytics (VA) performance is important for maximizing their impact. Existing studies have successfully applied well-established summative evaluation methods from information visualization to the VA context, yet the recent emphasis on an extra data analysis/modeling stage in the VA pipeline poses an additional challenge. Inspired by the modern concept of visualization literacy, this paper examines model literacy, namely users' knowledge of the analysis model used in a VA technique, as an additional factor for VA performance. Results from a controlled study on the visual analysis of multidimensional data with two dimensionality-reduction models indicate a positive correlation between model-task accuracy and VA-task accuracy. The study involves two common dimensionality-reduction models, PCA and t-SNE. The correlation is stronger for PCA than for t-SNE in the current task design, a pattern consistent with the possibility that VA effectiveness is more closely associated with model literacy when model outputs are less directly readable from the visualization. Completion-time evidence does not show a stable efficiency gain, suggesting that differences in model intuitiveness may help explain when model knowledge shortens task completion and when it involves additional interpretive effort. The findings of this study suggest ways to further enrich VA evaluation methods and provide directions for developing more rigorous model-literacy assessment instruments.

Text-space skill optimization adapts a frozen agent by evolving a natural-language skill document, accepting each candidate through a validation gate. Existing gates rely on verifiable rewards, confining these methods to tasks with an automatic verifier. Replacing the verifier with an LLM-judge gate would lift that restriction, but whether such a gate carries usable signal is untested. We ask a prior question: can we tell, before placing a judge in the loop, whether its scores separate correct from incorrect answers at all? We formalize a reference-free judge as a latent solver -- its verdict rests on agreement with whatever it would itself conclude, so its capacity to evaluate is bounded by its capacity to solve. The model yields a closed-form bound on discriminability (ROC-AUC) in the judge's competence $c$ and answer-space size $k$, a necessary condition $c > 1/k$, and the result that the marginal AUC is confounded by item difficulty while a within-question estimator is not. A non-intervening probe records judge scores on genuine optimization runs without altering any decision. We find discriminability at chance where competence sits near the floor and usable above it; that a judge's benchmark accuracy overstates the competence that matters; and, in a closed-loop study, that the screen predicts which kind of gating error occurs. The result is a cheap pre-deployment diagnostic for judge gates.

Diagnosing faults in rotating machinery is essential for ensuring the reliability of industrial processes. Random convolutional kernel-based Time Series Classification (TSC) methods, such as ROCKET and its variants, provide an attractive trade-off between predictive performance and computational efficiency. In this work, we evaluate SelF-Rocket for the multi-class diagnosis of both mechanical and electrical faults and introduce, as a new contribution, a multivariate extension of the original method. The proposed approach is compared with leading ROCKET-based methods on two public benchmark datasets, MaFaulDa (mechanical faults) and ITSC-UDG (stator inter-turn short circuits), under both univariate and multivariate settings. Experimental results show that SelF-Rocket achieves the best overall accuracy-latency trade-off among the evaluated methods, obtaining the highest classification performance on MaFaulDa while remaining highly competitive on the more challenging ITSC-UDG dataset.

Ensuring not only high accuracy but also reliable and robust predictions is critical for the deployment of semantic segmentation models in safety-critical applications such as autonomous driving. Despite the widespread use of CutMix - a simple yet powerful data augmentation strategy - its effect on the reliability and robustness in dense predictions tasks remains unexplored. Motivated by recent findings that semi-supervised segmentation methods, where CutMix is a core component, can severely degrade reliability, this study isolates and systematically analyzes the influence of CutMix on segmentation accuracy, calibration, and uncertainty quality. We evaluate two representative architectures, the CNN-based DeepLabV3+ and the transformer-based SegFormer, across both in-domain and out-of-domain scenarios. Our results show that CutMix has only a minor impact on segmentation accuracy but consistently improves the reliability, particularly under distribution shifts. These improvements indicate that CutMix primarily enhances the trustworthiness of the model's calibration and uncertainty rather than the raw segmentation prediction itself. This distinction is crucial for safety-critical deployment, where reliable confidence estimates are as important as raw performance.

Machine-learned models are replacing first-principles calculations across materials discovery, and physical symmetry is the central guarantee built into them. The debate over how much symmetry to hard-wire rather than learn has run on rotations, where a symmetry error is an approximation error. Some constraints are exact: symmetry forces certain property tensors to exactly zero, so a nonzero prediction is physically impossible rather than inaccurate. Here we show that whether a model can make such predictions is decided before training by one rarely reported design bit, whether its features carry parity labels, and derive a criterion, the parity gap, that computes from group theory alone which properties and crystals are exposed. Across matched architecture pairs differing only in that bit, evaluated on two thousand centrosymmetric crystals whose piezoelectric tensor must vanish, parity-labelled arms sit at the floating-point floor while rotation-only arms predict forbidden responses on 90-96% of crystals, six orders of magnitude apart, at no accuracy cost. Training on explicit zeros does not recover exactness, and a head on a frozen universal potential inherits its backbone's symmetry group. One reflection at random initialization verifies the label in seconds.

Stacked intelligent metasurfaces (SIM) provide an efficient architecture for integrated sensing and communication (ISAC) with few radio-frequency (RF) chains. However, diagonal SIM provide only element-wise phase control, so balancing multiuser communication and sensing performance may require additional layers. In this letter, we propose a beyond-diagonal SIM (BD-SIM) architecture for ISAC, enabling controllable intra-layer coupling through reconfigurable impedance networks, thereby enhancing wave-domain processing flexibility. We develop a unified alternating optimization framework applicable to fully-connected, group-connected, and diagonal SIM architectures. Within this framework, we derive a closed-form power allocation rule and propose an effective variable separation algorithm for multi-layer phase-shift design. Simulation results show that the proposed BD-SIM achieve a better communication-sensing trade-off and require fewer layers to attain performance comparable to conventional SIM.

Egocentric vision systems capture human behavior from visible cues, but overlook physiological indicators of autonomic states such as stress, engagement, and attention. Heart rate variability (HRV) is a widely used noninvasive marker of autonomic regulation under stress. HRV reflects small timing differences between successive heartbeats and has so far been out of reach for egocentric platforms, where motion and noise in gaze video mask exactly this fine-grained timing. We propose EgoHRV, a method that estimates HRV as well as heart rate (HR) from the gaze cameras that are already integrated into egocentric headsets. Our pipeline combines a 3D backbone with a novel low--high decomposition module that extracts the blood volume pulse (BVP) signal from gaze video. Our cross-domain pretraining aligns the frequency-domain representations of contact-based and camera-derived signals. This alignment gives EgoHRV the temporal precision to recover HRV from the subtle fluctuations in gaze video. EgoHRV achieves state-of-the-art accuracy for HR and HRV estimation from egocentric video, and its uncertainty-aware design improves downstream behavioral modeling. Integrating our HRV estimates and confidence measures into EgoExo4D's proficiency estimator raises accuracy by 17.8%. Beyond skill, continuous HRV estimation also opens egocentric systems to stress- and arousal-aware estimation tasks. Code: https://github.com/eth-siplab/EgoHRV

Recent advances in generative video models have enabled camera-controlled world video generation, allowing models to synthesize videos under user-defined camera trajectories. However, existing video quality assessment (VQA) methods are mainly developed for natural videos and fail to capture the unique perceptual characteristics of camera-controlled generation, such as viewpoint consistency, motion coherence, and content preservation. In this work, we introduce CamWorldQA, the first benchmark for perceptual quality assessment of camera-controlled world video generation. CamWorldQA contains 720 generated videos produced by 6 representative generation methods from 20 diverse source videos under 6 camera trajectories, where each video is annotated with a human-rated perceptual quality score through subjective experiments. Furthermore, we propose CWQA, a no-reference quality assessment network with three complementary branches that extract spatial features, temporal motion features and optical flow features to jointly predict quality scores. Extensive experiments demonstrate that CWQA achieves superior performance over existing quality assessment methods on the CamWorldQA dataset.

Foundation models are increasingly breaking what seemed to be impossible not long ago by enabling unprecedented accuracy and cross-domain generalization. Yet their lack of interpretability, tendency to be overconfident, and sensitivity to real-world domain shifts pose critical challenges for safety- and mission-critical applications. Uncertainty quantification (UQ) offers a principled way to address these issues, but its integration into segmentation foundation models has yet to be explored. In this paper we present the first systematic evaluation of UQ methods applied to a foundation model for semantic segmentation. We fine-tune a lightweight DPT decoder on top of the pretrained SAM2 encoder to establish a simple yet competitive baseline and benchmark four representative UQ approaches - Monte Carlo Dropout, Deep Sub-Ensemble, Test-Time Augmentation, and Evidential Deep Learning - across Cityscapes, NYUv2, and two challenging out-of-domain settings. Our analysis compares segmentation accuracy, calibration, uncertainty quality, and inference time, revealing clear trade-offs between predictive performance, reliability, and computational cost. These results highlight both the promise and the current limitations of uncertainty-aware foundation models, pointing to the need for future work that jointly optimizes accuracy, robustness, and efficiency for real-world deployment.

Long-term memory is essential for agents that operate across extended interactions, yet existing memory systems and benchmarks predominantly focus on single-source textual histories. In realistic settings, however, relevant information is often fragmented across applications and devices, as well as across users and time, requiring agents to integrate dispersed observations into coherent episodic memories while preserving their source provenance. To address these gaps, we introduce **MemFuseBench**, a benchmark for *multi-source memory fusion*. MemFuseBench is built with a Scene-to-Sensor pipeline that synthesizes controllable scenarios into source-tagged observations, evidence-grounded questions, and adversarial distractors. It enables systematic evaluation of temporal reasoning, cross-source evidence fusion, and robustness to noise. We further propose **MemFuse**, a structured memory system that preserves source-level evidence in event-layer atomic memory and organizes related atomic events into cluster-layer fused memory within a causal fusion graph. During retrieval, MemFuse retrieves and organizes related evidence fragments while maintaining traceability to original source events. Experiments on MemFuseBench show that MemFuse achieves the best overall performance among the evaluated memory systems under all three LLM settings and consistently improves performance on questions requiring cross-source evidence fusion.

We study the classical and parameterized complexity of efficient connected allocation problems on graphs, where efficiency is measured by egalitarian and utilitarian welfare maximization. We first establish a sharp complexity dichotomy in the classical setting: both problems are NP-hard in general and remain hard even on very restricted graph classes such as paths, and consequently trees and cycles. In contrast, they are polynomial-time solvable on stars, but this tractability does not extend even to the case of two disjoint stars. Motivated by these boundaries, we move to the parameterized complexity framework, where we study the problem with respect to the number of agents. We obtain fixed-parameter tractability (FPT) on trees and, more generally, identify a robust phenomenon whereby tractability on a connected graph class extends to disjoint unions of graphs from that class. We further investigate the parameters treewidth and treedepth, showing that the utilitarian version is FPT for both, whereas the egalitarian version remains para-NP-hard even on graphs of treedepth two. Finally, we analyze the number of connected components and show that except for the collection of stars, the problems remain hard. For the collection of stars,while we obtain para-NP-hardness for the egalitarian case, the utilitarian case gives W[2]-hardness together with an XP algorithm.

Physical interaction quality is central to deformable-object manipulation, yet most benchmarks evaluate task success alone. A policy may complete the task while allowing slip or causing excessive compression. A primary bottleneck is the absence of visuo-tactile datasets that pair policy-visible contact observations with independent physical ground truth over complete tasks. We introduce SoftVTBench, a visuo-tactile dataset for physical-interaction-aware deformable-object manipulation. It contains 4,000 expert demonstrations and more than 50 assets, including volumetric deformable objects and visually matched rigid twins. At 20 Hz, each episode synchronizes multi-view RGB, dual-finger tactile RGB and marker motion, proprioception, language, and binary and continuous gripper actions, alongside evaluator-only finite-element (FEM) states. Building upon this dataset, we establish a closed-loop benchmark that uses fixed object-specific calibration to define the Deformation-aware Success Rate (DSR), which counts a rollout as successful only when it completes the task and keeps peak normalized deformation within tolerance. Across Diffusion Policy, $π_{0.5}$, and FastWAM, all 12 in-distribution configurations contain successful rollouts that violate the deformation tolerance, accounting for 0.7--24% of each configuration's successes. Under distribution shift, visuo-tactile variants achieve higher task success in all six policy--suite comparisons and higher DSR in five, whereas their in-distribution benefits are mixed. These results show that making touch available does not by itself ensure effective multimodal fusion. SoftVTBench therefore provides a common visuo-tactile resource for studying not only whether a policy succeeds, but how it physically interacts with deformable objects and when touch improves that interaction.