arXiv:2607.01663v1 Announce Type: new Abstract: 4D scene synthesis from monocular videos has made significant progress in recent years. However, existing methods are typically constrained by view interpolation. As a result, they struggle to infer unseen regions beyond the observed views. In this paper, we reformulate the task as 4D scene synthesis with unseen regions, which extends beyond traditional interpolation settings. Camera-conditioned video generation enables unseen region synthesis by guiding generation along specified cameras. However, these methods lack explicit 3D priors and are optimized with random camera trajectories. This design leads to severe inconsistencies under large trajectory deviations. To address this limitation, we build a unified training and inference framework with panoramic trajectory guidance. While this design improves cross-view consistency, the panoramic representation alone fails to model dynamic content effectively. Object motion in panoramic space introduces scale and shape distortions. To address this, we propose PanoGaussian, a unified Panoramic-Gaussian representation that distills the panoramic representation into an explicit dynamic Gaussian representation to capture dynamic physical priors of the 4D scene. Experiments demonstrate that PanoGaussian achieves consistent 4D scene synthesis even under large viewpoint variations.
Science Journals
arXiv:2607.02041v1 Announce Type: new Abstract: We present NLF (Nonlinear Laplacian Flow), a unified framework and linear-time solver for convex network-flow equilibria. Congestion routing, minimum-delay routing, and maximum flow share one form: the nonlinear graph Laplacian $B\rho(B^T\phi)=\alpha d$, where a monotone edge law $\rho_e$ encodes the physics (undirected graphs; directed variants are future work). NLF solves it by a damped chord-Newton iteration whose frozen linearization -- a weighted graph Laplacian -- is inverted by a near-linear Laplacian solver (default: approximate Cholesky, LAMG+ interchangeable). The nonlinear solve costs $2$--$4$ linear Laplacian solves, making the wall-clock empirically $O(m)$ in the edge count $m$ (not a proved bound). On single-commodity congestion (BPR cost), NLF converges on all 2,003 SuiteSparse corpus graphs up to $1.8\times10^7$ edges. Against a state-of-the-art interior-point method, NLF is a median $2.6\times$ faster where both converge and $>45\times$ on poorly-separable graphs where the IPM's direct core is superlinear; against L-BFGS, a median $4.2\times$ faster and the only solver to finish on the 90 hardest instances. A multicommodity extension routes $K$ commodities through one shared hierarchy at $O(Km)$ per step. The same machinery recovers the exact max-flow as a short sequence of Laplacian solves, with the cut potential as a by-product. Code: https://github.com/orenlivne/nlf
arXiv:2607.01363v1 Announce Type: new Abstract: When runtime verification is used to monitor safety-critical systems, it is essential that monitoring code behaves correctly. The Copilot runtime verification framework pursues this goal by automatically generating C monitor programs from a high-level DSL embedded in Haskell. In safety-critical domains, every piece of deployed code must be accompanied by an assurance argument that is convincing to human auditors. However, it is difficult for auditors to determine with confidence that a compiled monitor cannot crash and implements the behavior required by the Copilot semantics. In this paper we describe CopilotVerifier, which runs alongside the Copilot compiler, generating a proof of correctness for the compiled output. The proof establishes that a given Copilot monitor and its compiled form produce equivalent outputs on equivalent inputs, and that they either crash in identical circumstances or cannot crash. The proof takes the form of a bisimulation broken down into a set of verification conditions. We leverage two pieces of SMT-backed technology: the Crucible symbolic execution library for LLVM and the What4 solver interface library. Our results demonstrate that dramatically increased compiler assurance can be achieved at moderate cost by building on existing tools. This paves the way to our ultimate goal of generating formal assurance arguments that are convincing to human auditors.
arXiv:2607.01953v1 Announce Type: new Abstract: Large Language Models (LLMs) have become increasingly effective at generating code when task descriptions are clear and precise. Yet, in practice, user-provided task descriptions are often ambiguous, incomplete, or contradictory, leaving critical aspects of the intended program behavior underspecified. In such cases, multiple behaviorally distinct interpretations may satisfy the description equally well, yet semantically differ in ways that matter/affect the user intent. A natural expectation, often assumed by researchers, is that prompt underspecification manifests as incoherence: When asked multiple times, an LLM produces multiple semantically distinct implementations reflecting the ambiguity of the task description. In this paper, we challenge this assumption. We find that LLMs frequently collapse onto a single incorrect interpretation of the task description, consistently generating coherent but behaviorally misaligned code. We term this failure mode detrimental semantic collapse and find that it affects over 10% of tasks in MBPP, 3% in HumanEval, and 32% of LiveCodeBench, all benchmarks assumed to be well-specified. By deliberately injecting underspecification issues in the benchmark prompts, the rate rises to over 5 times, exposing a fundamental blind spot in disambiguation and correctness estimation techniques that rely on incoherence as a proxy for prompt underspecification.
arXiv:2607.01814v1 Announce Type: new Abstract: Traditional Chinese Medicine (TCM) diagnosis, particularly through tongue inspection, faces persistent challenges in subjectivity and reproducibility. The application of multimodal artificial intelligence to TCM clinical tasks, such as syndrome differentiation and prescription generation, is significantly hampered by the semantic gap between visual tongue features and textual reasoning, as well as the lack of large-scale, standardized datasets. To address these challenges, we introduce MMIR-TCM, a novel framework that emulates the diagnostic process of TCM experts by integrating multimodal large language model(MLLM) with memory-augmented segmentation and retrieval-augmented generation (RAG). Employing a three-stage architecture, MMIR-TCM integrates a training-free Memory-SAM module for robust tongue extraction, a fine-tuned Qwen3-VL model for structured tongue diagnosis generation, and a Qwen3-based RAG component for evidence-grounded clinical decision support generation. The framework was developed and validated using MedTCM, a new large-scale multimodal dataset that we introduce specifically for advanced TCM research. To properly evaluate our framework's clinical accuracy, which existing metrics fail to capture, we also developed TDEU, a domain-specific evaluation metric incorporating semantic understanding and diagnostic importance. Our comprehensive experiments demonstrate that MMIR-TCM significantly outperforms leading models, including GPT-4o and Gemini 2.5 Flash.
arXiv:2606.10822v3 Announce Type: replace Abstract: Aerial search and rescue missions require fast and reliable victim detection under uncertain and rapidly changing environments. Deterministic deep learning models can produce overconfident false positives, forcing unmanned aircraft systems to perform costly verification maneuvers that reduce search coverage and increase rescue delay. Bayesian neural networks provide uncertainty-aware detection, but their sampling overhead is challenging for battery-constrained edge platforms. This work presents a FeFET-based Bayesian inference engine with a write-free central limit theorem Gaussian random number generator embedded in a compute-in-memory macro. By summing currents from a randomly selected subset of minimum-sized, programmed-once FeFETs, the proposed architecture eliminates energy- and endurance-intensive write operations during inference while maintaining scalable Gaussian sampling. The CLT-GRNG consumes 640 aJ per sample, providing a 560x energy-efficiency improvement over prior BNN accelerators, while the CIM tile achieves 185 TOPS/W/mm2. Evaluated on aerial search and rescue detection, the Bayesian model improves uncertainty calibration and robustness under environmental corruption, reducing risk and enabling low-confidence detections to be filtered before costly verification. These results demonstrate an energy-efficient and uncertainty-aware edge AI engine for autonomous search and rescue systems.
arXiv:2606.11326v2 Announce Type: replace Abstract: Recent feed-forward 3D reconstruction methods have demonstrated strong performance and flexibility in efficient end-to-end scene geometry estimation from image streams. However, their reliance on visible-light appearance makes them vulnerable in dark and low-visibility environments, where RGB cues are severely degraded and geometric evidence becomes ambiguous. To address this challenge, we propose DarkVGGT, an RGB-T feed-forward geometry framework that uses physics-aware thermal modeling for robust 3D estimation in low-light scenes. DarkVGGT introduces two complementary modules. First, physics-inspired thermal factorization extracts emissive-dominant, geometry-consistent thermal cues while isolating sparse reflective residuals that may introduce geometric ambiguity. Second, geometry-shared thermal routing isolates modality-invariant geometric structures from thermal-specific patterns, selectively injecting reliability-aware structural guidance into the RGB stream. Together, these components enable accurate thermal-informed geometry estimation under degraded RGB conditions while largely preserving performance in well-lit environments. Experiments on low-visibility RGB-T benchmarks demonstrate consistent improvements in both depth and camera pose estimation over existing feed-forward geometry baselines.
arXiv:2606.13501v2 Announce Type: replace Abstract: Diffusion Transformers (DiTs) have become the dominant architecture for image and video generation, creating growing demand for efficient DiT serving. Existing systems assign each request a fixed parallel configuration throughout its lifetime. However, DiT workloads exhibit substantial heterogeneity across requests, execution stages, and system conditions, making static parallelism inefficient and often leading to poor GPU utilization and degraded service quality. This paper argues that DiT serving should treat GPU parallelism as a first-class schedulable resource. We present GF-DiT, a policy-programmable runtime for elastic DiT serving that dynamically adapts the parallelism of running requests according to workload demands and service objectives. GF-DiT introduces an asynchronous execution abstraction that decomposes requests into independently schedulable trajectory tasks and enables online GPU reallocation. To make elastic parallelism practical, GF-DiT further proposes group-free collectives, a lightweight communication abstraction that supports low-overhead online formation and reconfiguration of arbitrary execution groups. We implement GF-DiT in vLLM-Omni and evaluate it on representative image and video diffusion workloads. Compared with fixed-pipeline execution with static parallelism, GF-DiT improves throughput by up to 6.01$\times$, reduces mean latency by up to 95%, lowers SLO violation rates by up to 90%, and reduces communication-group setup overhead from 778 ms to approximately 60 $\mu$s. Our code is available at https://github.com/SJTU-Liquid/GF-DiT.
arXiv:2607.01546v1 Announce Type: new Abstract: Rankings derived from weighted scoring functions are widely used in settings such as university rankings and employment candidate evaluations. Since ranking weights are often chosen by organizations or analysts, ranking stability asks whether a reported ranking persists under reasonable weight changes. Prior work on stable rankings formalizes this idea through volume-based stability, which measures the fraction of the weight space that induces the target ranking exactly. This exact-match requirement can be too blunt: once a perturbed weight vector produces a different ranking, exact stability gives it no credit, whether the change replaces the top-ranked item or only swaps two nearly tied lower-ranked items. We propose general stability, a distance-based generalization that aggregates ranking regions according to a user-defined distance from the target ranking. This lets users specify which ranking changes matter in the application, while recovering exact stability as a special case. Our algorithmic focus is stability computation: given a reported or user-specified ranking and a distance function, estimate its general-stability score. We give a two-dimensional sweep algorithm and an unbiased multidimensional sampler that extend exact-stability methods, and analyze why sampling can scale poorly as the dimension grows. Motivated by this scaling challenge, we identify quasiconvex distance functions as a tractable subclass and introduce Conv-SC, which reduces stability computation for this subclass to convex-volume approximation, where randomized polynomial-time methods are available. Experiments on eight real datasets and generated instances show that distance-sensitive stability gives informative real-data results, that our estimators are accurate and practical, and that Conv-SC improves scaling with dimension for quasiconvex distance functions.
arXiv:2607.01708v1 Announce Type: new Abstract: Reliable instance-level scene understanding is a fundamental prerequisite for object-level interactions and high-fidelity 3D representations. While current methods often leverage 2D foundation segmentation models to obtain these priors, their 2D-centric design typically yields fragmented masks and inconsistent predictions across different views. To address these issues, we propose a novel framework that produces consistent 2D instance masks to guide the optimization of 3D Gaussian Splatting (3DGS) feature fields. Our framework consists of three main stages. (1) Multi-Cue Extraction that generates synergistic semantic, geometric, and structural priors from input images. (2) Multi-Cue-Guided Mask Merging process that consolidates fragmented masks using a composite merge score derived from semantic, depth, and edge cues. (3) Cross-View Mask Matching that establishes globally consistent identity assignments across all viewpoints. By transforming viewpoint-specific segments into coherent 3D primitives, our approach enables stable 3D instance segmentation and effective downstream editing tasks. Experiments demonstrate that our method significantly improves cross-view consistency and segmentation stability over existing baselines while maintaining high-fidelity photometric reconstruction.
arXiv:2607.01709v1 Announce Type: new Abstract: Agents are increasingly used to construct workflows and assist humans in completing recurring tasks more efficiently. As these workflows become repeated and domain-specific, agent memory and reusable skills become increasingly important: agents should be able to recall workflow patterns, execution constraints, and user preferences from previous runs. We study this problem in workflow-based image generation and introduce COMFYCLAW, an agentic skill evolution harness for controlling ComfyUI workflows. COMFYCLAW formulates workflow construction as typed graph editing, exposes tools organized by construction stage, automatically reverts invalid edits, and uses a region-level vision-language model (VLM) verifier to translate visual failures into actionable repair suggestions. The framework further evolves a progressively disclosed skill library, where trajectories, execution errors, and verifier feedback from previous runs are distilled into reusable Agent Skills. Across four benchmark splits, three agent models, and two image backbones, COMFYCLAW achieves the best average image-generation evaluation score across all six agent configurations, outperforming a verifier-only baseline without skill evolution. Human annotations further show that annotators prefer COMFYCLAW over variants without skill evolution. Our results suggest that skill evolution is an effective mechanism for improving agent reliability and performance in recurring visual workflow construction.
arXiv:2607.01721v1 Announce Type: new Abstract: Reward design remains a central challenge in reinforcement learning (RL). Hand-crafted rewards are often difficult to specify and may lead to suboptimal policies, while learned rewards from preferences can suffer from inefficiency and unstable training. Inspired by the dual nature of human learning explored in cognitive science, we decompose rewards into two complementary components: Formal Rewards (FR), explicitly designed based on task knowledge, and Residual Rewards (RR), learned from observations to capture implicit and nuanced preferences. Based on this decomposition, we propose CoRe, a hybrid framework that integrates FR and RR with vision-language models (VLMs) feedback to achieve preference-aligned policies without human involvement. Our contributions are twofold: (1) We propose a Formal Reward Module (FRM) that leverages VLMs to iteratively design and optimize FR based on task knowledge and preference feedback, enabling the continual improvement of policy during training; (2) We introduce a Residual Reward Module (RRM) that learns RR from video-level preference by employing VLMs to generate preference labels and capturing nuanced rewards that complement FR, ensuring alignment with human intent. Through the synergy of FRM and RRM, CoRe enables the automatic construction of reliable rewards that are efficient and preference-aligned. Extensive experiments demonstrate that CoRe outperforms existing approaches in terms of policy learning effectiveness and efficiency on ten robotic manipulation tasks in simulation and five real-worlds. Videos can be found on our project website: https://core-2026.github.io/
arXiv:2607.01727v1 Announce Type: new Abstract: Synthetic data can be scaled along two routes: Source Expansion (SE), which enlarges the source by adding seed materials or generators, and Fixed-Source Synthesis (FSS), which holds the source fixed and scales the generation budget. Existing scaling studies typically expand the source as the data grows, conflating SE with FSS and leaving FSS underexplored. We isolate FSS by holding the seed-question pool and teacher model fixed, varying only the per-question response budget under Rejection Sampling (RS). We adapt the rectified scaling law to FSS, deriving it from how repeated sampling covers a fixed source. Empirically, the derived form, fit on low budgets, predicts performance at the held-out highest budget for every evaluated teacher--student pair. At matched total-sample budgets, SE and FSS are comparable at small budgets; at large budgets, adding seed questions outperforms spending the same budget on more responses. Within FSS, however, neither synthesizing additional questions from the existing seeds nor varying the synthesis protocol outperforms plain RS at matched budgets. FSS is thus a bounded scaling axis and a controlled setting for comparing synthesis protocols. We will release our code and data to facilitate further research.
arXiv:2605.30295v3 Announce Type: replace Abstract: Large language models (LLMs) show promise for clinical reasoning and decision support, but evaluation in structured, electronic health record-congruent settings remains limited. Existing benchmarks often rely on static datasets or unstructured inputs that do not reflect the interoperable data formats used in clinical systems. We introduce a reusable pipeline for generating terminology-grounded HL7 FHIR R4 bundles from unstructured text, enabling controllable evaluation of clinical decision support systems over structured inputs. The pipeline combines staged LLM generation with terminology-grounded validation and repair to eliminate hallucinated codes and enforce structural and semantic consistency. Applying this approach to MedCaseReasoning, we construct MedCase-Structured, a synthetic dataset of 1,732 FHIR bundles derived from clinician-authored diagnostic cases, producing complete, valid bundles for 97.1% of attempted cases. Evaluation on MedCase-Structured reveals consistently lower diagnostic accuracy for LLMs on structured FHIR inputs than with plain text, highlighting the importance of deployment-aligned benchmarking.
arXiv:2607.02259v1 Announce Type: new Abstract: In this paper, we introduce BamiBERT, a new BERT-based pre-trained language model for Vietnamese that addresses key limitations of PhoBERT -- the current de facto Vietnamese text encoder. Trained from scratch on a 129GB corpus of general-domain Vietnamese text for 20 epochs, BamiBERT supports an extended context length of up to 2048 tokens and operates directly on raw input, eliminating the need for external word segmentation. Across 8 Vietnamese benchmarks, it achieves the best score on 11 of 15 metrics and the second-best on 3 others, setting a new state of the art among "base"-sized Vietnamese encoders and demonstrating strong cross-domain generalization. We release BamiBERT at: https://huggingface.co/Qualcomm-AI-Research/BamiBERT
arXiv:2607.01781v1 Announce Type: new Abstract: The limited predictive skill of forecasts makes it difficult for decision-makers to act decisively. Advance assessment of real-time forecast credibility can strengthen decision-makers' resolve and confidence to act. Such an assessment can draw on real-time observations of large-scale background signals. This study evaluates how credible the 2026 East Asia summer temperature forecast is. Enhanced predictability of East Asia summer temperature can be indicated by the synergistic forcing of sea surface temperature anomalies (SSTAs) across three key oceanic regions: the tropical western Pacific, the Japan Sea-Kuroshio-Kuroshio Extension (K-KE), and the North Atlantic. Based on the latest observational data and model predictions, the SSTAs in these three regions maintain positive anomalies, which suggests that East Asia's summer temperature forecast skill will stay at a relatively high level in the coming summer. Based on the predictions, the following summer is expected to feature pronounced positive temperature anomalies over central and eastern China, the Korean Peninsula, and Japan, which may trigger regional droughts and place severe strain on power supply networks.
arXiv:2607.01784v1 Announce Type: new Abstract: Visual-spatial understanding, defined as the ability to infer object relationships and scene layouts from visual inputs, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, pre-trained vision-language models (VLMs) remain constrained by spatial uncertainty stemming from inherently 2D observations and by the scarcity of data for 3D spatial understanding. To address these limitations, we proposed a novel framework, SpaceEra, in the NeurIPS 2025 Spotlight paper. Although it achieved significant performance gains, we further observed that its effectiveness is hindered by insufficient input from scanning videos and weak reasoning constraints. To tackle these newly emerged challenges, we extend the original framework into a comprehensive system, termed SpaceEra++, which spans data construction, model design, training optimization, and prompting inference. Specifically, to alleviate input insufficiency, we introduce ScenePick, a frame sampling strategy that balances spatial coverage with object semantics to produce compact yet comprehensive scene representations. In addition, to enhance spatial reasoning, we develop SpaceAlign, which enforces pairwise object constraints by jointly exploiting absolute coordinates and relative spatial relations, thereby aligning optimization with spatial accuracy. Extensive experiments across multiple benchmarks demonstrate consistent improvements over strong baselines, while ablation studies validate both the individual and joint contributions of each component, and further analyses provide guidance for future research.
arXiv:2607.01735v1 Announce Type: new Abstract: Gauss-Seidel is a well-established iterative method for the solution of linear systems, and multicoloring has been widely used to increase parallelism in iterative solution techniques. Implementing multi-color Gauss-Seidel with conventional divide-and-conquer parallelization strategies, however, may be inefficient due to global synchronization requirements and load imbalances. Task-based programming models can mitigate these issues by enabling fine-grained parallelism, removing global barriers and allowing updates of different colors to partially overlap in time. In this work, we implement the red-black Gauss-Seidel method using two task-based programming models and compare them with a classical divide-and-conquer parallel implementation to evaluate the impact of fine-grained parallelism on execution efficiency. The red-black scheme serves as a representative example, as task-based approaches naturally extend to more general multi-color schemes arising from unstructured grids and wider stencils. Using the solve of the 2D Poisson equation as benchmark, our results show that task-based implementations can achieve performance comparable to conventional divide-and-conquer parallelization while providing greater resilience to hardware-level asynchronicity.
arXiv:2607.01771v1 Announce Type: new Abstract: In the present paper, we provide an explicit construction for generators of a $\lambda$-constacyclic code $\mathcal{C}$ of arbitrary length $\ell$ over a finite chain ring(FCR) $\mathcal{R}$ in terms of certain minimum degree polynomials of the ring $\mathcal{R}[x]/ \langle x^{\ell}-\lambda \rangle$. Moreover, the proposed construction achieves the minimum possible number of generators. We prove certain properties of this set of generators, using which we obtain a minimal spanning set of $\mathcal{C}$. We also obtain that the rank of $\mathcal{C}$ is $\ell-n_0$, where $n_0$ is the degree of the minimal degree polynomial in $\mathcal{C}$. Finally, we derive necessary and sufficient conditions under which an arbitrary length $\lambda$-constacyclic code $\mathcal{C}$ over $\mathcal{R}$ is Maximum Hamming Distance with respect to Rank(MHDR) as well as Maximum Distance Separable(MDS) in terms of a torsion code of $\mathcal{C}$ over the residue field $\mathbb{F}_q$ of $\mathcal{R}$. We further determine the exact values for $n_0$ for which $\mathcal{C}$ over $\mathcal{R}$ is MHDR.
arXiv:2606.13723v2 Announce Type: replace Abstract: Intersection-over-Union (IoU), as a pivotal metric for evaluating the spatial alignment between candidate proposals and ground-truth annotations, directly determines the quality of positive sample sets and the training efficacy of visual detection models. Through theoretical modeling and analysis, we uncover a non-sensitive region on the IoU response curve, within which samples yield nearly identical IoU scores despite distinct geometric overlaps. To overcome this limitation, we introduce a set of morphological similarity metrics covering area, shape, and aspect ratio, to refine the positive sample assignment process, thereby ensuring more discriminative and reliable matching. A supplementary matching score is derived via mean-based aggregation of these multidimensional similarities, compensating for the intrinsic limitation of IoU in representing structural correspondence. Theoretically, incorporating morphological similarity reshapes the response distribution of the matching function, yielding both effective directional gradients and polygon-like iso-response contours, which tightly confine high-response regions around each ground-truth instance and substantially enhance the precision of positive sample selection. Experiments based on the YOLOv9 framework demonstrate consistent performance gains on both NEUDET and GC10- DET datasets. Notably, the proposed approach is fully plug-and-play and incurs zero additional inference overhead, thereby ensuring deployment efficiency for industrial visual inspection.
arXiv:2606.13732v2 Announce Type: replace Abstract: The proliferation of recursive training on synthetic data can alleviate data scarcity but risks model collapse, where repeated training erodes distributional tails and homogenizes outputs. Data selection is widely viewed as a remedy, yet its reliability depends critically on the reference distribution used by the verifier. We show that in low-resource verification regimes, where each verifier observes only a small, fragmented, and biased slice of the target manifold, selection itself becomes biased. This situation naturally arises in low-resource data silos such as healthcare consortia or proprietary financial institutions, where raw data cannot be pooled and local references are inherently incomplete. As a result, selection preferentially retains samples aligned with the local manifold while pruning globally relevant tail modes, turning from a safeguard against collapse into a mechanism that precipitates it. We theoretically prove that such siloed selection accelerates collapse and induces power-law diversity decay. As an initial mitigation, we construct Wasserstein proxy references from multiple silos without sharing raw data. Empirical results confirm that local-reference selection fails on skewed distributions, whereas collaborative proxy references mitigate diversity degradation, suggesting that recursive synthetic-data pipelines require particular caution when real-data coverage is fragmented or scarce.
arXiv:2606.17793v2 Announce Type: replace Abstract: We introduce AIriskEval-gaming, an open platform and dataset to evaluate social engineering risks in LLM-mediated multimodal interaction through controlled games. It supports human-human, human-AI and AI-AI settings, combining configurable game templates, role-conditioned LLM agents, psychology-informed participant profiling, structured interaction trees, and synchronized behavioral and biometric acquisition, filtering, and deep-learning-based feature extraction. The dataset (AIriskEval-gaming-db) was collected from 15 participants who interacted with a role-conditioned GPT-5.4 agent in two concatenated games: an adapted Prisoner's Dilemma and an Ultimatum Game. It comprises 340 GB of raw and processed multimodal data across six streams: interaction logs, video, screen recordings, gaze logs, smartwatch signals, and game/questionnaire metadata. These data include interaction paths, written justifications, psychological profiles, subjective feedback, perceived counterpart identity, game outcomes, and derived behavioral, facial, and gaze features. Alongside the dataset, we provide descriptive analyses characterizing the resulting multimodal data. Rigorous risk evaluation is essential for the deployment of secure AI systems, as it enables the identification and mitigation of vulnerabilities, ensures the protection of sensitive data, and supports compliance with evolving regulatory and ethical standards in society. The dataset and related code are available on GitHub.
arXiv:2606.23041v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in visual understanding but remain constrained in visual generation due to the fundamental feature discrepancy between semantic perception and pixel-level reconstruction. Bridging this gap requires overcoming two core challenges: endowing semantic encoders with high-fidelity reconstruction capabilities, and effectively aligning generative models with semantic spaces without relying on external teachers. To this end, we propose a novel unified multimodal framework featuring \textbf{S}emantic-\textbf{P}ixel self-alignment and \textbf{A}daptive \textbf{R}outing (\textbf{SPAR}). First, to reconcile semantic perception with pixel-level reconstruction, we introduce an asymmetric dual-stream unified tokenizer. A lightweight semantic stream anchors discriminative features, while a Transformer-augmented pixel stream recovers fine-grained visual details into a unified compact latent space. Second, to eliminate external dependencies, we propose a self-aligned generation paradigm that natively leverages this optimized tokenizer as an internal alignment teacher for the diffusion model. Furthermore, to facilitate flexible multimodal interaction within this unified space, we introduce Dynamic Token Routing, which enables each token to adaptively aggregate multi-layer MLLM features based on its distinct semantic demands. Extensive experiments demonstrate that SPAR establishes the state-of-the-art for unified architectures, achieving exceptional generation and reconstruction quality while preserving foundational visual understanding capabilities.
arXiv:2607.01795v1 Announce Type: new Abstract: Monitoring cognitive load during online learning could help instructors identify content that learners find difficult, but remote settings remove the visual cues that support this judgement in a classroom. We study whether a single-channel, consumer-grade EEG device (the NeuroSky MindWave Mobile 2) can distinguish easy from difficult educational-video content, using the publicly available dataset of Wang et al. [24] (ten learners, one excluded for excessive noise, leaving nine). We implement a hybrid CNN+LSTM+Attention model that combines the raw waveform with band-power features. In a within-subject setting, the model reaches up to 78.5% accuracy, compared with 55% for conventional feature-based classifiers; regularization (dropout and L2) closes the large gap between training and validation accuracy that we observe without it, keeping validation accuracy stable at roughly 68-73%. We are deliberately cautious about these numbers: with only nine subjects, within-subject evaluation is optimistic, and we argue that subject-independent evaluation -- in which no learner appears in both training and test data -- should be the standard for this task. To that end we release a reproducible evaluation pipeline. We frame the work as a feasibility study rather than a deployable system, and pair it with an open, notebook-based tool that records EEG, runs inference, and visualizes estimated cognitive load as a heatmap over the video timeline to help educators locate potentially challenging segments.
arXiv:2607.01801v1 Announce Type: new Abstract: Static and frequency-dependent polarizabilities were computed for 41 molecules using RPA, RPA(D), HRPA, HRPA(D), SOPPA, SOPPA(CC2), and SOPPA(CCSD) with the aug-cc-pVTZ basis set and benchmarked against CCSD reference values and available experimental data. The analysis reveals a pronounced distinction between the performance of these methods for aromatic versus non-aromatic molecules. Across all frequencies, HRPA consistently yields substantially larger deviations from CCSD than the other approaches, whereas HRPA(D) and SOPPA(CCSD) provide the most accurate results overall. For static polarizabilities, HRPA(D) performs best for non-aromatic systems, followed by SOPPA(CCSD) and RPA(D), while SOPPA(CCSD) is most accurate for aromatic molecules. In the frequency-dependent regime, HRPA(D) remains the most accurate method for non-aromatic molecules, although RPA(D) shows greater consistency. For aromatic molecules, SOPPA(CCSD) performs best at low frequencies, with RPA offering intermediate accuracy but higher consistency than most other methods; at higher frequencies, RPA becomes the most accurate approach, followed by RPA(D), while SOPPA(CCSD) deteriorates. These trends highlight the importance of doubles corrections in RPA(D) and HRPA(D), which achieve accuracy comparable to or better than SOPPA(CCSD) at lower computational cost. The strong performance of RPA for aromatic molecules is attributed to its characteristic overestimation of the lowest electronic excitation energy. Comparison with experimental data confirms SOPPA(CCSD) as the most reliable method for static polarizabilities, while RPA and HRPA(D) provide the best agreement for frequency-dependent polarizabilities of aromatic systems.