A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation

AI-based Visually Impaired Assistance (VIA) remains challenging, largely due to the high cost of human evaluation. The VLM-as-a-Judge paradigm may offer a promising alternative, although it has mostly been studied in general domains. We therefore ask whether such judges can be trusted for VIA tasks. To investigate this question, we introduce VIABLE (Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation), the first benchmark for VLM-as-a-Judge evaluation in VIA. VIABLE contains over 300K judgment samples across three scenarios and introduces an Effectiveness--Impartiality--Stability framework with a 12-mode failure taxonomy. Based on VIABLE, our systematic study of seven judges across different model scales shows that existing models are largely unreliable across all evaluation axes. The strongest judge, GPT-5.4, achieves only 52.6% single-failure diagnostic accuracy, yet exhibits the highest self-preference rate at 94.2%; while open-source judges are strongly biased and adversarially fragile. To address these issues, we propose VIA-Judge-Agent, a model-agnostic inference-time harness that augments judges with visual evidence extraction and a taxonomy-guided workflow. It enables positive improvements in diagnostic accuracy and downstream VIA responses more preferred by BLV users. Data and code are available at: https://github.com/YiyiyiZhao/VIABLE

RoHIL: Robust Human-in-the-Loop Robotic Reinforcement Learning Against Illumination Variations

Human-in-the-loop reinforcement learning systems achieve near-perfect success on the workstation where they are trained, but collapse when the same robot is moved to a workstation a few meters away due to shifts in the visual input distribution caused by new lamp positions and window light. Re-collecting demonstrations and re-running HIL on every workstation is incompatible with deployment, and naively fine-tuning on shifted-light data triggers catastrophic forgetting of the source workstation. To close this cross-domain gap, we present RoHIL, an offline fine-tuning framework that uses no extra real-robot interaction. RoHIL combines (i) a world-model-based image relighter that re-synthesises the visual stream of source-workstation trajectories under multiple virtual HDRI environments, leaving actions and rewards real; (ii) Illumination-Retention Replay (IRR), a data-level anti-forgetting mechanism that interleaves relit adaptation transitions with original-light retention transitions to preserve source-workstation Bellman coverage; and (iii) an anchored Bellman-actor regulariser that constrains representation and policy drift from the original source-workstation policy. Across four real-robot manipulation tasks under significant cross-workstation illumination variations, RoHIL substantially improves shifted-light performance where standard HIL-RL collapses, while preserving source-workstation performance, eliminating the need to re-collect data and retrain for every new workstation and environment. Project page: https://anonymous4365.github.io/RoHIL/

An evaluation framework for sparse 4D (3D + time) imaging reconstruction via bootstrapped cross-validation

Four-dimensional (4D; 3D + time) microscopic imaging has emerged as a powerful technique for investigating dynamic phenomena in complex systems, enabling direct visualization of structural evolution in space and time. However, when pushing the limits of spatiotemporal resolution, most time-resolved imaging techniques yield inherently sparse 4D datasets. While deep learning-based reconstruction methods have shown promise in reconstructing 4D from sparse spatiotemporal measurements, a practical approach for evaluating their performance in the absence of a 4D reference has, to the best of our knowledge, been lacking. Here, we present a bootstrapped cross-validation framework that estimates reconstruction performance by quantifying correlations between reconstructions generated from independently sampled subsets of the acquired data, as inspired by the 3D validation strategy in cryo-electron microscopy, where reconstructions from split datasets are compared to assess resolutions. This enables both qualitative and quantitative assessment in the absence of ground truth. We investigate two representative scenarios with sparse and ultra-sparse X-ray datasets and validate this approach using 4D-ONIX, a 4D deep-learning reconstruction method, on simulated water droplet collision experiments. The proposed approach provides a reference-free framework for performance estimation and support for better-informed experimental strategies across a wide range of ultrafast imaging applications.

Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models

Vision-Language-Action (VLA) models achieve remarkable flexibility and generalization beyond classical control paradigms. However, most prevailing VLAs are trained under a single-frame observation paradigm, which leaves them structurally blind to temporal dynamics. Consequently, these models degrade severely in non-stationary scenarios, even when trained or finetuned on dynamic datasets. Existing approaches either require expensive retraining or suffer from latency bottlenecks and poor temporal consistency across action chunks. We propose Pace-and-Path Correction, a training-free, closed-form inference-time operator that wraps any chunked-action VLA. From a single quadratic cost, joint minimization yields a unified solution that decomposes orthogonally into two distinct channels. The pace channel compresses execution along the planned direction, while the path channel applies an orthogonal spatial offset, jointly absorbing the perceived dynamics within the chunk window. We evaluate our approach on a comprehensive diagnostic benchmark MoveBench designed to isolate motion as the sole controlled variable. Empirical results demonstrate that our framework consistently outperforms state-of-the-art training-free wrappers and dynamic-adaptive methods and improves success rates by up to 28.8% and 25.9% in absolute terms over foundational VLA models in dynamic-only and static-dynamic mixed environments, respectively.

Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection

Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on limited observation windows and end-to-end action prediction, which makes them brittle in long-horizon, memory-dependent tasks with partial observability, occlusions, and multi-stage dependencies. Such tasks require not only precise visuomotor control, but also persistent memory, adaptive task decomposition, and explicit recovery from execution failures. To address these limitations, we propose a dual-system framework for long-horizon embodied manipulation. Our framework explicitly separates high-level semantic reasoning from low-level motor execution. A high-level planner, implemented as a VLM-based agentic module, maintains structured task memory and performs goal decomposition, outcome verification, and error-driven correction. A low-level executor, instantiated as a VLA-based visuomotor controller, carries out each sub-task through diffusion-based action generation conditioned on geometry-preserving filtered observations. Together, the two systems form a closed loop between planning and execution, enabling memory-aware reasoning, adaptive replanning, and robust online recovery. Experiments on representative RMBench tasks show that the proposed framework substantially outperforms representative baselines, achieving a 32.4% average success rate compared with 9.8% for the strongest baseline. Ablation studies further confirm the importance of structured memory and closed-loop recovery for long-horizon manipulation.

4D reconstruction of alumina laser melt pools at 25 kHz via operando X-ray multi-projection imaging

Advancing additive manufacturing, e.g., laser powder-bed fusion (LPBF), requires resolving rapid processes such as melt-pool dynamics and keyhole evolution in 4D (3D + time). Operando X-ray tomography is a state-of-the-art approach for 4D characterization, but its temporal resolution is fundamentally constrained by the sample rotation speed, limiting achievable 4D imaging rates and preventing the resolution of these fast phenomena. Here we present rotation-enabled X-ray Multi-Projection Imaging (rotation-XMPI), which captures three angularly resolved projections per time step and thereby decouples temporal resolution from the sample rotation speed. Combined with a self-supervised deep-learning reconstruction framework for multi-angle inputs, rotation-XMPI enables high-fidelity 4D imaging at unprecedented speed. We demonstrate the approach in an operando alumina laser-remelting experiment at MAX IV using three beamlets combined with 25 Hz sample rotation. Rotation-XMPI resolves melt-pool morphology and keyhole evolution; in contrast, conventional and limited-angle tomography remain rotation-limited, and motion blur prevents resolving these dynamics. Overall, rotation-XMPI delivers a 250-fold increase relative to state-of-the-art melt-pool imaging, effectively achieving 25,000 reconstructed volumes per second. This method establishes a practical route to scalable ultrafast 4D imaging for additive manufacturing and other materials processes.

Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding

Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts, especially those describing complex sound events. We uncover a surprising capability in AR audio generators: their early prefix tokens implicitly encode global semantic attributes of the final output, such as event count and sound-object category, revealing a form of implicit planning. Building on this insight, we propose Plan-Critic, a lightweight auxiliary model trained with a Generalized Advantage Estimation (GAE)-inspired objective to predict final instruction-following quality from partial generations. At inference time, Plan-Critic enables guided exploration: it evaluates candidate prefixes early, prunes low-fidelity trajectories, and reallocates computation to high-potential planning seeds. Our Plan-Critic-guided sampling achieves up to a 10-point improvement in CLAP score over the AR baseline-establishing a new state of the art in AR text-to-audio generation-while maintaining computational parity with standard best-of-N decoding. This work bridges the gap between causal generation and global semantic alignment, demonstrating that even strictly autoregressive models can plan ahead.

Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization

Crowd localization plays a crucial role in visual scene understanding towards predicting each pedestrian location in a crowd, thus being applicable to various downstream tasks. However, existing approaches suffer from significant performance degradation due to discrepancies in head scale distributions (scale shift) between training and testing data, a challenge known as domain generalization (DG). This paper aims to comprehend the nature of scale shift within the context of domain generalization for crowd localization models. To this end, we address four critical questions: (i) How does scale shift influence crowd localization in a DG scenario? (ii) How can we quantify this influence? (iii) What causes this influence? (iv) How to mitigate the influence? Initially, we conduct a systematic examination of how crowd localization performance varies with different levels of scale shift. Then, we establish a benchmark, ScaleBench, and reproduce 20 advanced DG algorithms to quantify the influence. Through extensive experiments, we demonstrate the limitations of existing algorithms and underscore the importance and complexity of scale shift, a topic that remains insufficiently explored. To deepen our understanding, we provide a rigorous theoretical analysis on scale shift. Building on these insights, we further propose an effective algorithm called Causal Feature Decomposition and Anisotropic Processing (Catto) to mitigate the influence of scale shift in DG settings. Later, we also provide extensive analytical experiments, revealing four significant insights for future research. Our results emphasize the importance of this novel and applicable research direction, which we term Scale Shift Domain Generalization.

Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers

While language models (LMs) paired with residual vector quantization (RVQ) tokenizers have shown promise in text-to-audio (T2A) generation, they still lag behind diffusion-based models by a non-trivial margin. We identify a critical dilemma underpinning this gap: incorporating more RVQ layers improves audio reconstruction fidelity but exceeds the generation capacity of conventional LMs. To address this, we first analyze RVQ dynamics and uncover two key limitations: 1) orthogonality of features across RVQ layers hinders effective LMs training, and 2) descending semantic richness in tokens from deeper RVQ layers exacerbates exposure bias during autoregressive decoding. Based on these insights, we propose Siren, a novel LM-based framework that employs multiple isolated transformers with causal conditioning and anti-causal alignment via reinforcement learning. Extensive experiments demonstrate that Siren outperforms both existing LM-based and diffusion-based T2A systems, achieving state-of-the-art results. By bridging the representational strengths of LMs with the fidelity demands of audio synthesis, our approach repositions LMs as competitive contenders against diffusion models in T2A tasks. Moreover, by aligning audio representations with linguistic structures, Siren facilitates a promising pathway toward unified multi-modal generation frameworks.

Physics-informed 4D X-ray image reconstruction from ultra-sparse spatiotemporal data

The unprecedented X-ray flux density provided by modern X-ray sources offers new spatiotemporal possibilities for X-ray imaging of fast dynamic processes. Approaches to exploit such possibilities often result in either i) a limited number of projections or spatial information due to limited scanning speed, as in time-resolved tomography, or ii) a limited number of time points, as in stroboscopic imaging, making the reconstruction problem ill-posed and unlikely to be solved by classical reconstruction approaches. 4D reconstruction from such data requires sample priors, which can be included via deep learning (DL). State-of-the-art 4D reconstruction methods for X-ray imaging combine the power of AI and the physics of X-ray propagation to tackle the challenge of sparse views. However, most approaches do not constrain the physics of the studied process, i.e., a full physical model. Here we present 4D physics-informed optimized neural implicit X-ray imaging (4D-PIONIX), a novel physics-informed 4D X-ray image reconstruction method combining the full physical model and a state-of-the-art DL-based reconstruction method for 4D X-ray imaging from sparse views. We demonstrate and evaluate the potential of our approach by retrieving 4D information from ultra-sparse spatiotemporal acquisitions of simulated binary droplet collisions, a relevant fluid dynamic process. We envision that this work will open new spatiotemporal possibilities for various 4D X-ray imaging modalities, such as time-resolved X-ray tomography and more novel sparse acquisition approaches like X-ray multi-projection imaging, which will pave the way for investigations of various rapid 4D dynamics, such as fluid dynamics and composite testing.