arXiv:2607.01365v1 Announce Type: new Abstract: Given one or more images of a railway crossing, can we leverage visual cues that allow us to robustly estimate how safe it is? Can we improve our ability to do so by introducing structured data (such as official accident reports) about the accident history of that crossing into our models? In this work, we explore how to best answer those questions towards building an AI system that can ingest multi-modal data for railway crossings and provide safety assessment and scores that align with expert opinion and with safety scoring used by the Federal Railroad Administration (FRA). To that end, we propose a proof-of-concept pipeline that delivers on that goal, while at the same time exploring and tackling a number of critical research challenges that pertain to different parts of the pipeline, from data preparation to different learning paradigms that can allow us to realize such a system. Indicatively, our proposed system identifies HIGH-RISK and LOW-RISK crossings with a macro F1 score of 0.757 and estimates FRA-based safety scores with an RMSE of 0.078 and correlation of 0.492 using a routed fine-tuned compact VLM pipeline, while producing qualitative results that align with domain-expert assessment.
Science Journals
arXiv:2607.01900v1 Announce Type: new Abstract: Dual-pixel (DP) imaging enables metric depth estimation from a single camera using sub-aperture disparity. However, the extremely small effective baseline limits disparity observability, leading to structural degradation and depth failure in textureless, low-contrast, or downsampled regions. Existing DP-based methods rely primarily on local disparity cues and therefore become unreliable when disparity signals are weak or ambiguous. To address this limitation, we propose \emph{FoundDP}, a unified framework that integrates metric DP depth with global structural priors from a monocular depth foundation model. Our method preserves metric scale through DP-derived depth and leverages Vision Transformer (ViT) features to restore structural consistency in weak-disparity regions. To ensure reliable metric guidance under DP imaging conditions, we identify and mitigate ViT representation degradation induced by DP defocus blur via ViT feature alignment, enabling stable metric-guided depth estimation. Extensive experiments on synthetic and real-world DP benchmarks show that FoundDP delivers superior performance, with consistent gains in structural fidelity and metric accuracy, especially under reduced disparity observability. Code will be available at: https://github.com/EchoLighting/FoundDP
arXiv:2607.01547v1 Announce Type: cross Abstract: We investigate fluid mixing induced by microswimmers using mutual information as a global, information-theoretic measure of mixing efficiency. For a two-dimensional squirmer model in a confined domain, we compute numerically the swimmer-generated flows and solve the advection-diffusion equation for the transport of tracer particles in the fluid. We show that the spatial distribution of swimmers strongly affects mixing, which is suppressed by swimmer aggregation and enhanced by positional and orientational disorder. At fixed energy dissipation, mixing efficiency depends non-monotonically on the squirmer parameter, with an optimal finite value arising from the balance between swimmer translation and dipolar flow generation. When hydrodynamic interactions are included, pushers outperform pullers. The mutual information as a function of time decays in three stages: an initial diffusion-dominated stage, an intermediate advection enhanced regime, and a final relaxation stage controlled by system size. Our results demonstrate that mutual information, previously validated as a measure of mixing efficiency only in simplified model systems, can equally be used in complex flows. Its application reveals that mixing by microswimmers is subject to a trade-off between the generation of strong shear flows and achieving optimal dispersion across the fluid domain.
arXiv:2312.09365v3 Announce Type: replace Abstract: In this paper, we propose a novel variational active contour model based on I-divergence-TV model to segment Synthetic aperture radar (SAR) images with multiplicative gamma noise, which hybrides edge-based model with region-based model. The proposed model can efficiently stop the contours at weak or blurred edges, and can automatically detect the exterior and interior boundaries of images. We further transform the proposed model into a general ROF model by adding a proximity term ,and it can be solved by a fast denoising algorithm proposed by Jia-Zhao or soved by BM3D and NLM denoising algorithm, which also provide a unified solution framework for formally generalized-ROF-like subproblems arising in multivariate splitting algorithms[25]. [25] was submitted on 29-Aug-2013, and our early edition was ever submitted to TGRS on 12-Jun-2012, Venkatakrishnan et al. [26] proposed their PnP algorithm on 29-May-2013, so Venkatakrishnan and we proposed the PnP algorithm almost simultaneously.
arXiv:2401.10083v3 Announce Type: replace Abstract: In this paper, we propose a novel locally statistical variational active contour model based on I-divergence-TV denoising model, which hybrides geodesic active contour (GAC) model with active contours without edges (ACWE) model, and can be used to segment images corrupted by multiplicative gamma noise. By adding a diffusion term into the level set evolution (LSE) equation of the proposed model, we construct a reaction-diffusion (RD) equation, which can gradually regularize the level set function (LSF) to be piecewise constant in each segment domain and gain the stable solution. We further transform the proposed model into a general ROF model by adding a proximity term ,and it can be solved by a fast denoising algorithm proposed by Jia-Zhao or soved by BM3D and NLM denoising algorithm, which also provide a unified solution framework for formally generalized-ROF-like subproblems arising in multivariate splitting algorithms.
arXiv:2607.01520v1 Announce Type: new Abstract: Transformer inference on long sequences is expensive because softmax attention repeatedly reads from a large KV cache. The prevalent approach to this bottleneck is KV cache compression, which replaces the full cache with a compact summary. Despite its practical importance, the design of such summaries is largely driven by empirical experimentation. On the theoretical side, existing results show that KV cache compression can be impossible in the worst case, but offer little systematic guidance for designing algorithms in regimes where accurate compression is possible. We bridge this gap by characterizing the minimax risk of KV cache compression in terms of the intrinsic compressibility of a cache, revealing when and how accurate compression is possible. These results yield novel design principles for KV cache compression under causal masking that map efficiently to prefill and autoregressive decoding while achieving minimax-optimal risk. We instantiate these principles in a practical algorithm and report promising performance on LongBench in targeted experiments. Overall, our results provide a principled avenue for practical KV cache compression with theoretical guarantees.
arXiv:2607.01522v1 Announce Type: new Abstract: Mode shape recognition is a fundamental task in automotive NVH development, yet it remains dependent on manual visual inspection by experienced engineers. Existing approaches based on engineering heuristics, Modal Assurance Criterion (MAC), or geometry-dependent AI representations often exhibit limited robustness across different vehicle architectures, finite element (FE) meshes, and experimental measurement layouts, restricting their industrial applicability. This paper presents a Canonical Engineering Graph Representation and region-aware graph learning framework for robust and explainable 3D mode shape recognition. Rather than learning directly from vehicle-specific FE meshes, heterogeneous FE models and experimental measurements are transformed into a common graph whose nodes represent semantically meaningful structural regions connected through engineering-informed relationships. Geometry-independent regional descriptors are combined with graph attention learning and region-aware pooling to capture structural interactions while preserving engineering semantics and enabling physically interpretable predictions. The resulting representation decouples engineering knowledge from numerical discretization, allowing transfer across different vehicle programs without requiring identical mesh topology or sensor configurations. The proposed framework is validated using FE and experimental datasets from four vehicle programs under severe label scarcity. Results demonstrate high classification accuracy, cross-vehicle transferability, and physically meaningful explanations by directly relating predictions to engineering-defined structural regions used in NVH analysis. Beyond mode shape recognition, the proposed Canonical Engineering Graph Representation provides a reusable engineering abstraction for trustworthy and transferable AI across heterogeneous simulation and experimental workflows.
Quantifying the Uncertainty of Blindly Estimated Room Embeddings Using a Dispersion-Calibrated Score
arXiv:2607.01527v1 Announce Type: new Abstract: Room embeddings derived from reverberant speech are often unreliable: speech content and recording degradation can alter the representation even when speaker, room, and source-receiver geometry remain unchanged, degrading downstream task performance. We propose a framework that learns room embeddings robust to speech-content variation and a representation-level uncertainty score from reverberant speech without downstream-task supervision. The embedding is anchored to a structured room impulse response (RIR) latent space and trained using a multi-view data structure with Kullback-Leibler (KL)-based alignment; a multi-positive contrastive term further refines robustness. A lightweight uncertainty head is calibrated using the dispersion of corruption-induced embeddings and optimized with a rank-based objective. Across waveform- and spectrogram-level corruptions, the score is consistent with representation dispersion and enables effective selective prediction while requiring only a single utterance at inference.
arXiv:2607.01528v1 Announce Type: new Abstract: Small multirotor aircraft are increasingly tasked with operations in the atmospheric boundary layer, where turbulent winds comparable to the vehicle's airspeed degrade trajectory tracking and can defeat conventional feedback control. This work illustrates a two-stage learning pipeline that first estimates the local wind from onboard kinematics and dynamics and then exploits that estimate inside a reinforcement learning (RL) flight controller. The wind estimator, an attention-augmented gated recurrent network trained on thousands of simulated flights through von Karman turbulence with power-law shear and veer, recovers the horizontal wind vector with a per-flight root-mean-square error of 0.40 m/s and a direction error of 3.2 degrees on unseen wind regimes, an accuracy near the floor imposed by unresolved turbulence, and generalizes to vertical ascent profiles with a skill score of 0.861 over a constant-wind reference. A proximal policy optimization controller receiving the frozen estimator's output reduces horizontal trajectory tracking error by 48% relative to a wind-blind proportional-derivative baseline across mean winds of 4 m/s to 12 m/s, winning on 100% of evaluation episodes. A three-way ablation decomposes this improvement into a kinematic component, available without wind information, and a wind-perception component; the perception share rises with wind speed, from small in light winds toward roughly half the total benefit in strong winds, consistent with the quadratic scaling of aerodynamic drag. The controller degrades gracefully on out-of-distribution winds of 13 m/s to 15 m/s, where the baseline fails catastrophically.
arXiv:2607.01533v1 Announce Type: new Abstract: We study hydrodynamic spin coupling in a two-rotor corral using DNS of 2D incompressible viscous fluid flow. An active rotor is driven at angular velocity W, and a nearby torque-free passive rotor selects an angular velocity w through hydrodynamic torque balance. The signed gear ratio Gamma=w/W distinguishes corotation from counterrotation, with Reynolds number Re=|\Omega|r^2/\nu. Motivated by a recent quasi-two-dimensional experiment, we use a DLM/FD method to compute planar phase diagrams of $\Gamma(G,Re)$ at corral sizes C=3, 4.5, and 6. The planar model recovers the benchmark gap route at Re=20: an intermediate counterrotation band, a wide-gap transition to corotation, gear-ratio magnitudes of order 10^{-2}, and the observed sequence of vortex attachment, detachment, and merger. It also produces a reentrant-like gap structure with a small-gap corotation region whose relation to the experimental close-range geometric state remains unresolved. The main discrepancy is the high-Re boundary. At the experimental mid-gap transect G about 0.3, the planar gear ratio approaches zero from the counterrotating side but does not cross through Re=400; at the narrower gap G=0.22, by contrast, the planar terminal spin reverses near Re=44. Wall-traction diagnostics show that this crossing is not the experimental shear-competition mechanism: the gap-facing counterrotating arc narrows but does not collapse or deflect as in the experiment, and the reversal at G=0.22 occurs by redistribution of the integrated planar torque. The strictly planar model therefore captures the broad gap-route architecture and the existence of a Reynolds-driven spin boundary, but displaces that boundary in gap and alters its surface-stress mechanism. The remaining mismatch points to finite-depth secondary motion, end-wall stresses, and apparatus geometry as plausible contributors to the experimental shear balance.
arXiv:2607.01535v1 Announce Type: new Abstract: Despite the intense engagement surrounding low-level vision generalist models, their effectiveness in zero/few-shot scenarios beyond learned tasks remains unverified. The primary challenge of developing an ideal generalist lies in achieving the ability to generalize from new unseen tasks, which also can be assessed by matched quantitative criteria. Existing methods have made some progress in prompt engineering but have not systematically explored this gap across a wide range of low-level visual tasks. Stimulated by the problem, we propose Hidden-Shot, an implicit prompt mechanism aimed at exploring low-level task adaptation in a vision generalist model. Specifically, the method extracts implicit visual task-based information, utilizes a global task-aware textural prompt, and selectively merges implicit information with in-task processing information to enhance one-shot capabilities in new tasks. The overall design performs direct injection in a cost-effective manner, while minimally altering the architecture of the original generalist model. Additionally, we introduce a data-driven evaluation framework termed C/U assessment to cover two basic scenarios, 3C4U (3 conventional and 4 unconventional tasks) for retraining existing models and 3C7U (3 conventional and 7 unconventional tasks) for training from scratch, as a comprehensive assessment to systematically test the generalization ability of low-level generalist models. Experiments on seven and ten datasets outperform the state-of-the-art vision generalist model, respectively verified by 3C4U and 3C7U framework. Our presented Hidden-Shot approach demonstrates superior performance on one-shot new tasks while maintaining consistent performance on existing tasks.
arXiv:2607.01548v1 Announce Type: new Abstract: Large language models are increasingly used as open-ended search operators in evolutionary optimization. We introduce Evolutionary Feature Engineering (EFE), a framework for using LLM-based evolution to discover preprocessing transformations for structured data. EFE represents transformations as Python programs with a standardized fit/transform interface, allowing them to be inserted directly into existing machine learning pipelines. During evolution, candidate programs are refined using dataset context, summary statistics, and downstream performance feedback on validation set. We instantiate EFE in two settings. For time-series forecasting, EFE-Time learns invertible, dataset-specific normalizations that improve off-the-shelf time-series foundation models. It reduces forecasting errors (MASE, WQL, MAE) 3% or more when averaged across datasets and improvements are as much as 19% on the COVID-Deaths dataset. Notably, these improvements occur with recent TSFMs such as Chronos-2. For tabular prediction, EFE-Tab evolves compact feature programs that add useful interpretable features and remove redundant ones, improving or matching existing LLM-based feature-engineering methods. We found EFE-Tab to be particularly effective on classical decision trees, where small sets of evolved features yield competitive accuracy while preserving interpretability. Overall, EFE demonstrates that LLM-based evolution can improve both accuracy and interpretability when automatically tackling structured data.
arXiv:2607.01581v1 Announce Type: new Abstract: The capacity of Large Language Models (LLMs) to reason about pedagogical intent within instructional communication remains underexplored, particularly in educational domains such as translation pedagogy. To address this, we propose the \textbf{Adaptive Pedagogical Vigilance (APV)} framework, a novel computational formalism that reframes communicative vigilance as an adaptive mechanism for optimizing learning through intent inference. APV formalizes the problem via a Bayesian Pedagogical Intent Inference Engine (PIIE), which models how instructors select content to maximize pedagogical utility and how vigilant learners should inversely reason about latent instructional configurations -- encompassing genre, stance, and incentives. We evaluate APV through a three-tier hierarchy: distinguishing instructional genre, reasoning about structured pedagogical setups, and generalizing to authentic educational discourse. Experiments on leading LLMs (e.g., GPT-4o, Claude 3.5) show that APV substantially improves model vigilance. It achieves the strongest discrimination between pedagogical and exposure-based content, correlates highly with human judgments ($r=0.958$), and maintains robust performance on naturalistic data where baseline methods degrade. This work establishes a unified framework for assessing and enhancing LLMs' understanding of pedagogical motives, advancing the development of more reliable AI-assisted learning systems.
arXiv:2607.01588v1 Announce Type: new Abstract: Extended Reality (XR) has become an important interaction paradigm in Human-Computer Interaction (HCI). XR studies are used to investigate interaction, perception, and user behavior in immersive environments, and typically involve experimental tasks, 3D scenes, and interactive logic. However, turning an initial XR study idea into a runnable prototype remains fragmented across study design, scene construction, and interaction implementation. We present OrchestrXR, a multi-agent human-AI workflow for early-stage idea-to-prototype XR study authoring. Rather than treating XR study creation as one-shot generation, OrchestrXR supports a controllable workflow across study design, scene generation, and interaction generation through structured schemas, multi-agent orchestration, and interactive human-agent interfaces, producing a Unity-based prototype from a researcher's idea. A user study with 12 XR researchers suggests that OrchestrXR provides effective support for early-stage XR study authoring with strong intent preservation across stages.
arXiv:2607.01597v1 Announce Type: new Abstract: Modern LLM coding agents are commonly evaluated using pass@k, but developers typically apply a single final patch in real-world settings. This pass@k-to-pass@1 gap is a post-generation problem: a candidate patch pool may contain a correct patch, but the system must decide which one to suggest to developers. Existing post-generation approaches mainly rank whole candidates, filter them with tests, or query an LLM judge, but none deterministically reuse shared edit-atom evidence to both select and construct the final patch. Thus, we propose PatchFusion, a deterministic atomic evidence fusion approach for candidate patches that consults no test outcome at decision time. PatchFusion first fuses whole-diff agreement into a repair neighborhood, selects an auditable representative, and then applies evidence-constrained fusion (ECF) to retain repeated edit atoms and prune unsupported parts. To evaluate this setting, we build PatchFuseBench, a fixed-pool benchmark covering SWE-bench Verified, SWE-bench Multilingual, and Defects4J candidate patches. On PatchFuseBench, PatchFusion solves 426/500 bugs on SWE-bench Verified and 236/300 on SWE-bench Multilingual, and reaches 87/371 plausible patches on Defects4J, outperforming every matched candidate-pool selector on all three. PatchFusion recovers 41 and 27 bugs that no single source solves (30 and 18 more over the best single source). Ablation studies show that ECF adds +5/+6/+9 solved bugs by recovering in-pool repairs that selection misses, with no observed regression, and that PatchFusion's gains remain stable as candidate pools are resampled. On these complementary multi-source pools, cross-candidate evidence recovers more correct patches than the test-based and LLM-based selectors we evaluate, at orders-of-magnitude lower cost, reaching within 96.2% and 89.7% of the candidate-reachable ceiling on the two SWE-bench benchmarks.
arXiv:2607.01616v1 Announce Type: new Abstract: This paper proposes a novel unified control framework for achieving hybrid grid-forming (GFM) and grid-following (GFL) inverter operation by integrating dispatchable virtual oscillator control with reference-following synchronization. The proposed inverter control method supports multiple operating modes within a unified structure, including voltage- and frequency-following (PQ mode), voltage-forming and frequency-following (PV mode), voltage-following and frequency-forming (Qf mode), voltage- and frequency-forming (Vf mode), and a hybrid mode with mixed GFM and GFL behaviors. In particular, the proposed method achieves smooth pre-synchronization and enables seamless transitions across a spectrum of inverter operating modes by tuning a small set of continuous control parameters, rather than relying on discrete controller switching. This framework provides a flexible and physically interpretable approach for adapting inverter dynamics to varying grid conditions and operational requirements. The small-signal stability and input-output frequency-domain characteristics are further analyzed under different control parameter settings. The effectiveness and robustness of the proposed unified control method are demonstrated through extensive electromagnetic transient (EMT) simulations and hardware-in-the-loop (HIL) experiments.
arXiv:2607.02458v1 Announce Type: new Abstract: This paper studies source seeking for a torque-controlled nonholonomic vehicle with a laterally displaced scalar sensor. The vehicle has constant forward speed, while its yaw motion is controlled by torque input with unknown inertia and damping. The objective is to steer the vehicle to a source-centered circular motion so that the lateral sensor approaches the unknown source, without using position, heading, source-location, gradient, or source-value information. The proposed torque law combines a fast oscillatory component, which generates averaged steering through symmetric-product approximation, with a slowly tuned bias component, which selects the desired orbit. Two bias-tuning designs are developed. The first is an output-feedback design using only the scalar measurement; it applies a Lie-bracket extremum-seeking update and yields local practical stability. The second is a velocity-assisted design using forward-speed and yaw-rate measurements; it tunes the bias through the yaw-rate tracking error and yields a globally asymptotically stable averaged system, implying semi-global practical stability of the original system. Simulations illustrate the proposed designs.
arXiv:2503.21796v2 Announce Type: replace Abstract: Self-supervised learning has become an increasingly important paradigm in the domain of machine intelligence. Furthermore, evidence for self-supervised adaptation, such as contrastive formulations, has emerged in recent computational neuroscience and brain-inspired research. Nevertheless, current work on self-supervised learning relies on biologically implausible credit assignment -- in the form of backpropagation of errors -- and feedforward inference, typically a forward-locked pass. Predictive coding, in its mechanistic form, offers a biologically plausible means to sidestep these backprop-specific limitations. However, unsupervised predictive coding rests on learning a generative model of raw input (akin to "generative AI" approaches), which entails predicting a potentially high dimensional input; on the other hand, supervised predictive coding, which learns a mapping between inputs to target labels, requires human annotation, and thus incurs the drawbacks of supervised learning. In this work, we present a scheme for self-supervised learning, specifically for an emerging research sub-domain that we label as neuroscience-informed self-supervised learning (NeuroSSL), within a neurobiologically plausible framework that appeals to the free energy principle, constructing a new form of predictive coding that we call meta-representational predictive coding (MPC). MPC sidesteps the need for learning a generative model of sensory input (e.g., pixel-level features) by learning to predict representations of the input across parallel streams, resulting in an encoder-only learning and inference scheme. This formulation notably rests on active inference (in the form of sensory glimpsing) to drive the learning of representations, i.e., the representational dynamics are driven by sequences of decisions made by the model to sample informative portions of its sensorium.
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.
arXiv:2607.02504v1 Announce Type: new Abstract: Long-form TV dramas present a formidable challenge for comprehensive video understanding, where deciphering complex storyline often relies on \textbf{speaker recognition}, the task of accurately attributing each spoken utterance to its respective character. In this paper, we advance this field through two primary contributions. (1) We introduce \textbf{DramaSR-532K}, a large-scale benchmark comprising 532K annotated dialogue lines across more than 900 unique characters, necessitating the integration of auditory, linguistic, and visual cues for speaker recognition. (2) We propose \textbf{DramaSR-LRM}, a robust approach built upon a large reasoning model (LRM). DramaSR-LRM is designed to autonomously aggregate contextual evidence via multimodal tool-use, synthesizing diverse inputs to achieve high-fidelity attribution. Experimental results demonstrate that DramaSR-LRM significantly outperforms existing baselines, particularly on short utterances where acoustic biometrics are inherently unreliable. \textit{All the data and code will be made publicly available at the project page: https://www.github.com/198808xc/DramaSR-LRM.}
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:2607.01819v1 Announce Type: new Abstract: The Koopman operator has gained considerable attention due to its ability to provide a global linear representation of highly complex dynamical systems. The operator describes nonlinear dynamics in a linear way through the lens of real- or complex-valued observable functions. Recently proposed data-driven techniques, like extended dynamic mode decomposition (EDMD), its kernelized variant, and machine-learning methods, can be used to generate finite-dimensional approximations accompanied by finite-data error bounds. In this tutorial paper, we provide a concise introduction into Koopman operator theory and its use in systems and control. A particular focus is put on data-driven surrogate models, their extension to systems with inputs, and controller design using Koopman operator theory. Moreover, we demonstrate the key techniques, i.e., EDMD and Koopman MPC. To this end, we provide simulation studies including source code on GitHub to enable the interested reader to experience the Koopman operator in systems and control step by step.
arXiv:2503.24009v3 Announce Type: replace Abstract: Realistic simulation is critical for applications ranging from robotics to animation. Learned simulators have emerged as a possibility to capture real world physics directly from video data, but very often require privileged information such as depth information, particle tracks and hand-engineered features to maintain spatial and temporal consistency. These strong inductive biases or ground truth 3D information help in domains where data is sparse but limit scalability and generalization in data rich regimes. To overcome the key limitations, we propose 3DGSim, a learned 3D simulator that directly learns physical interactions from multi-view RGB videos. 3DGSim unifies 3D scene reconstruction, particle dynamics prediction and video synthesis into an end-to-end trained framework. It adopts MVSplat to learn a latent particle-based representation of 3D scenes, a Point Transformer for particle dynamics, a Temporal Merging module for consistent temporal aggregation and Gaussian Splatting to produce novel view renderings. By jointly training inverse rendering and dynamics forecasting, 3DGSim embeds the physical properties into point-wise latent features. This enables the model to capture diverse physical behaviors, from rigid to elastic, cloth-like dynamics, and boundary conditions (e.g. fixed cloth corner), along with realistic lighting effects that also generalize to unseen multibody interactions and novel scene edits.