arXiv:2605.06831v2 Announce Type: replace
Abstract: We theoretically study the hallucination phenomena in two canonical diffusion samplers: the stochastic Denoising Diffusion Probabilistic Model (DDPM) and the deterministic Denoising Diffusion Implicit Model (DDIM). We analyze the reverse ODE (DDIM) and SDE (DDPM) for a Gaussian mixture target, proving that after a critical time $\tau$, (a) DDIM can become stuck on the segment connecting the two nearest modes and (b) DDPM *stochasticity* helps it become unstuck from this region, thus avoiding hallucination. Our empirical validation verifies that DDPM has a significantly lower hallucination rate than DDIM when this region is entered. Building on our observations, we exhibit how using additional stochastic steps can help DDIM avoid hallucinations and offer new insights on how to design improved samplers.
Science Journals
arXiv:2605.30716v1 Announce Type: new
Abstract: Generating clinically useful pathology reports for pathology cases from whole-slide images (WSIs) is challenging due to gigapixel resolution, long visual-token sequences, and the complexity of case-level reasoning, where a single case may contain multiple WSIs with heterogeneous tissues and ambiguous findings. We present a simple token-efficient vision--language model for case-level synoptic report generation that remains practical under constrained GPU memory. Our architecture follows a minimal three-component design: a frozen pathology patch encoder, a lightweight two-layer MLP vision-language aligner, and a large language model decoder, with an explicit WSI marker token to separate slides within a case. Training proceeds in two supervised stages: (1) aligner-only WSI captioning using heterogeneous WSI-text pairs, and (2) case-level supervised fine-tuning on case-report pairs for structured report generation. To reduce sequence length, we represent each slide using $512 \times 512$ patches at $5\times$ magnification, which reduces the average sequence length by up to $64\times$ times compared to the commonly used $20\times$ patches. Combined with efficient training techniques, we enable practical training with only half a NVIDIA H100 GPU. Across both training stages, our approach achieves high ROUGE-L/METEOR/BLEU-4 scores while being substantially more efficient in memory and runtime. In AI-based evaluations, our model is consistently preferred over strong baselines. Extensive ablations characterize performance-efficiency trade-offs and identify simple choices that improve robustness in multi-WSI settings. Overall, this work provides a strong, reproducible baseline for efficient pathology report generation, lowering the barrier to multi-WSI VLM research under limited compute.
arXiv:2605.31241v1 Announce Type: new
Abstract: This study presents a novel hybrid prognostic framework for uncertainty-aware Remaining Useful Life (RUL) estimation in turbofan engines using the NASA C-MAPSS dataset. The framework employs a state-aware strategy that bifurcates the engines operational lifespan into "healthy" and "degraded" regimes. An LSTM-based autoencoder, trained strictly on nominal data (RUL > 150 cycles), monitors reconstruction error to act as a robust state classifier. For the healthy regime, a Conditional Weibull Survival Analysis is used for Mean Residual Life estimation. For the degraded regime, a Probabilistic Neural Network with Monte Carlo Dropout captures both aleatoric and epistemic uncertainties. Rather than using rigid binary labels, a calibrated sigmoid function converts the autoencoders output into continuous state probabilities, dynamically weighting the final ensemble prediction. The primary strength of this framework is its generation of physically consistent uncertainty bands, yielding high-confidence predictions near end-of-life while accurately reflecting the inherent variance of early operation, providing a robust tool for risk-informed maintenance.
arXiv:2605.31235v1 Announce Type: new
Abstract: Resistive Silicon Detectors (RSD/AC-LGAD) are novel silicon detectors capable of both precise spatial and temporal resolution. Such sensors will be essential for the next generation of particle colliders (EIC, FCC-ee, CEPC, FCC-hh) and would enable the possibility of a 4D tracker. RSD sensors are typically fabricated with a pixel-like geometry that provides excellent spatial resolution in the x and y directions. However, in regions further from the interaction point, high spatial resolution in one direction (strip-like geometry) is often preferred to reduce the number of readout channels. For example, strip AC-LGADs are now the default option for the US electron ion collider (EIC). The second production of RSD sensors by Fondazione Bruno Kessler includes sensors with unconventional readout pad shapes that act as a mixture between strip-like and pixel-like readout. This work presents the first characterization of these new pad designs using the Transient Current Technique (TCT). The measurements demonstrate exceptional one-dimensional spatial resolution, confirming the potential of novel strip-like RSDs for future tracking systems.
arXiv:2605.31234v1 Announce Type: new
Abstract: Learning generalizable vision-language-action (VLA) models from large-scale human videos is promising but challenging due to cross-embodiment discrepancies in both visual observations and executable actions. While latent action models reduce the action execution gap by learning action abstractions, they still rely on visual features. Thus, misaligned human and robot visual representations can lead to inconsistencies in policy inputs and induce domain-dependent latent actions, hindering effective co-training with human videos. To address this, we propose HARP, a human-robot aligned representation learning framework for more effective VLA pretraining from human videos. Specifically, HARP uses limited paired human-robot demonstrations as cross-embodiment bridges and abundant unpaired human and robot videos as a scalable dynamics supervision data source. It trains a robot-adapted visual encoder and a latent action model with manipulation-centric auxiliary cues and a source-relative pair-discriminative alignment loss, which adapts robot representations toward human semantics while preserving pair-level discrimination. The learned aligned vision encoder and latent action model provide a unified vision and action representation for VLA-style policy learning, where human and robot videos provide vision-language-to-latent-action supervision and a lightweight robot action head grounds latent actions into executable commands. Experiments on feature visualization, simulation, and realworld manipulation show improved human-robot alignment and downstream policy performance, achieving 4.481 average length on CALVIN ABC$\rightarrow$D and a 7.1\% realworld success rate gain over the strongest baseline.
arXiv:2605.31232v1 Announce Type: new
Abstract: Optical computing offers the theoretical potential for high-speed, energy-efficient inference, yet its practical deployment remains constrained by fundamental input-output bottlenecks, particularly the reliance on electronic sensors with limited frame rates and stringent alignment requirements between optical components. Here, we demonstrate an image-class-gated single-pixel DONN that overcomes these limitations by converting spatial complexity into a temporal intensity signature. Using a minimal architecture comprising a reconfigurable digital micromirror device and a single-pixel photodetector, we implement a virtual optical gate. The system time-multiplexes class-specific masks, causing the detector response to peak only when the mask index matches the input class. This allows the predicted label to be read out via peak timing rather than spatial localization, eliminating 2D sensor constraints. To bridge the persistent sim-to-real gap, we introduce a physics-aware training strategy using random-phase augmentation. This method renders the model intrinsically tolerant to phase aberrations and mechanical misalignments without requiring precise hardware modeling. Our prototype achieves 90.0%(MNIST) and 80.0% (Fashion-MNIST) accuracy at a readout rate of 5 kHz. By combining gigahertz-compatible single-pixel detection with robust and alignment-tolerant training, this work provides a scalable, hardware-efficient pathway toward real-time optical intelligent sensing.
arXiv:2605.31231v1 Announce Type: new
Abstract: We present a neural-network-based framework for the solution of three-dimensional boundary value problems where the solution is expressible in terms of harmonic potentials. The approach leverages the Whittaker integral formula, which allows representing the solution through functions that are holomorphic with respect to a suitable complex variable. These functions are subsequently approximated using holomorphic neural networks, which guaranty fulfillment of the holomorphicity requirement. A key feature of the proposed formulation is that the governing partial differential equations (PDEs) are satisfied exactly by construction. Therefore, in contrast to standard physics-informed neural networks, no residual minimization of PDEs is required in the interior of the domain, and training is based exclusively on boundary collocation points. The method is validated against three-dimensional Laplace and linear elasticity problems, where, in the latter case, displacement and stress fields are expressed via the Papkovich-Neuber potentials. The numerical results show an accurate approximation of both scalar and vector fields, with errors remaining controlled throughout the domain. Overall, the work demonstrates that the incorporation of analytical structures into neural network architectures provides a natural and effective framework for the meshless approximation of three-dimensional boundary value problems while preserving the underlying properties of the governing equations.
arXiv:2605.31230v1 Announce Type: new
Abstract: We present a light-responsive hydrogel nanocomposite engineered into arrays of micrometer-scale wells that can be selectively and sequentially closed and re-opened via laser illumination. Polarization-controlled light exposure induces anisotropic surface deformations, leading to the formation of protrusive flaps sealing the wells. Owing to the intrinsic elasticity and anti-adhesive properties of the hydrogel matrix, the deformation process is partially reversible, allowing flap retraction and restoration of the original well geometry. This platform facilitates contactless, on-demand trapping and release of microscale objects using a standard optical microscopy configuration. As a proof of concept, we demonstrate the controlled manipulation of a single polystyrene microbead using optical tweezers, including bead positioning within a well, light-triggered closure, and subsequent reopening to release the particle into the surrounding aqueous environment.
arXiv:2605.31217v1 Announce Type: new
Abstract: Monocular 6-DoF spacecraft pose estimation methods predominantly process individual frames, discarding the temporal information present in an image sequence acquired during spacecraft manoeuvres. Few temporal approaches require full backbone fine-tuning or auxiliary optical flow networks, risking catastrophic forgetting or increasing computational cost, respectively. We propose TALON (Token-Aligned Lightweight adapters for Orbital Navigation): spatiotemporal 3D adapters injected before the self-attention layers of a frozen ViT vision transformer, combined with a patch-token alignment loss that geometrically grounds the adapted features to keypoint structure through a prototype-conditioned KL-divergence objective. Pre-attention placement allows the frozen attention to reason over temporally enriched tokens, achieving stronger performance with a single adapter per block than post-attention alternatives. The alignment loss shapes the intermediate representations so that each keypoint induces a spatially precise activation in the token field, while the framework adds less than 5% parameters to the frozen backbone. On SPADES dataset, TALON reduces the pose error by 50% over the prior state-of-the-art, and on SwissCube dataset it surpasses the prior best by 21.8% in ADD-0.1d accuracy. Zero-shot cross-domain evaluation from sim-to-real on SPARK real data reduces pose error by 4.7x, and ablations characterise the role of adapter depth across in-domain and cross-domain settings.
arXiv:2605.30732v1 Announce Type: cross
Abstract: While quantum position verification aims to certify a prover's location using quantum information, existing security definitions only guarantee that part of the successful adversarial party is in the claimed location. This leaves open the possibility that a distributed team of adversaries can jointly simulate a prover in a way that defeats the intended meaning of ``being at a location'' in position-based cryptography.
We introduce stronger notions of position verification that we call quantum localization, which requires that there is a specified, unclonable state at the verified spacetime point -- and that this state can be found nowhere else. We show that quantum localization leads naturally to a meaningful notion of trajectory verification, in which quantum information is verifiably tracked through space and time. We construct quantum localization and trajectory verification protocols using quantum anchor states, which generalize coset states from unclonable cryptography. The security of our schemes is proven in the classical oracle (i.e. ideal obfuscation) model, which can be heuristically instantiated in the plain model using post-quantum indistinguishability obfuscation.
We also introduce and instantiate the concept of functionality localization, which guarantees that the adversary has the ability to compute a secret function at the verified spacetime point, and this function cannot be computed anywhere else. This raises the intriguing possibility of localizing computational capabilities in space and time.
More broadly, we believe our notions of quantum localization and our feasibility results provide stronger foundations for position-based cryptography.
arXiv:2605.31204v1 Announce Type: new
Abstract: Accurate weather forecasts are essential across various domains and are safety-critical in extreme weather conditions. Compared to simulation-based forecasting, data-driven approaches show greater efficiency, enabling short-term, high-resolution nowcasting. In particular, diffusion models proved effective in weather nowcasting due to their strong probabilistic foundation. However, existing methods rely on deterministic compression to reduce the complexity of high-dimensional weather data, limiting their ability to capture uncertainty in the decoding process. In this work, we introduce $\textbf{FREUD}$, a $\textbf{Fr}$ame-wise $\textbf{E}$ncoder and $\textbf{U}$nited $\textbf{D}$ecoder model based on rectified flow transformers for efficient compression of spatio-temporal weather data. Frame-wise encoding enables continuous forecast updates, while the unified video decoder ensures temporal consistency. Our uncertainty-preserving first stage allows us to capture aleatoric uncertainty via ensembling, which is particularly beneficial for extreme weather events with high decoding variability. We achieve state-of-the-art performance in precipitation nowcasting with a compact latent-space rectified flow transformer on the SEVIR benchmark and show further performance gains by model and test-time scaling. Code available here: https://github.com/CompVis/weather-rf
arXiv:2605.31287v1 Announce Type: new
Abstract: Managers in manufacturing settings rely on digital interfaces to interpret operational data for decision-making, but growing data volume and complexity can make relevant insights difficult to identify efficiently. While dashboards remain dominant in industrial contexts, Large Language Model (LLM)-based conversational agents (CAs), accessed through conversational user interfaces (CUIs), may provide more direct access to such data. However, their effectiveness may depend on the information-processing demands of the task. This study compares an LLM-based CA delivered through a CUI with a dashboard in a manufacturing decision-support scenario. In a mixed factorial experiment with a 2x3 design, 134 industrial decision-makers were assigned to one interface condition and completed three tasks of increasing complexity. We examined perceived Mental Workload (MWL), decision accuracy, completion time, and intended reliance, and tested self-reported data literacy as a moderator. Results showed that the CUI reduced perceived MWL overall and supported faster completion in less demanding tasks, but both advantages diminished as task complexity increased. Neither interface produced a consistent overall advantage in decision accuracy, and the CUI was not preferred as a sole basis for subsequent decisions. Furthermore, data literacy did not reliably moderate interface effects. These findings indicate that conversational interaction offers conditional rather than universal benefits for industrial decision support. LLM-based CAs may reduce information-access effort, whereas complex decisions continue to benefit from persistent, inspectable visual representations.
arXiv:2605.31193v1 Announce Type: new
Abstract: Real-world multimodal systems must be robust against low-quality data, such as sensor noise, incomplete multimodal data and conflicting inputs. However, existing trustworthy fusion methods rely on the model's own prediction confidence to judge data quality. This creates a circular dependency: when a model is confident but wrong, these methods fail to detect the error. To break this loop, we propose Geometry-based Multimodal Fusion (GMF). Instead of relying on predictions, we evaluate reliability by measuring how much transport correction the input needs in latent space. We implement Diffusion Schr\"odinger Bridge transport with Rectified Flow, where the squared initial velocity gives an efficient learned correction score. Valid data has low squared velocity magnitude, while noisy, incomplete data or conflicting data requires stronger transport correction. This geometry-based reliability signal acts as an independent judge, effectively flagging unreliable inputs even when the classifier is fooled. Extensive experiments demonstrate that GMF significantly improves robustness against severe sensor noise and semantic conflicts compared to confidence-based baselines.
arXiv:2605.20992v3 Announce Type: replace
Abstract: We ask whether everyday open-world monocular videos can be turned into reusable 4D interaction primitives: articulated hand motion, object shape with 6D pose over time, and the when/where of contact. Such a capability would enable scalable mining of real interactions and, beyond reconstruction, support scene-aware synthesis and planning. However, reconstructing hand-object interaction (HOI) from challenging monocular videos remains difficult: methods often assume known objects or curated scenes, and separately estimated hands and objects easily become misaligned under clutter, occlusion, and unseen object geometries. Targeting this setting, we present CHOIR, a Contact-aware HOI Reconstruction framework for a monocular camera, using contact as an explicit coupling signal between hands and objects. CHOIR first initializes a coarse, contact-agnostic 4D HOI sequence from open-world visual priors. It then introduces a generative HOI spatial rectification module to predict ray-depth corrections and rectify hand-object relative placement, then derive initial per-frame contact correspondences on the rectified geometry. Last, a contact-aware joint optimization with dynamically updated contact constraints enforces geometric, temporal, and contact consistency. Experiments on controlled and challenging videos show that CHOIR improves object reconstruction, physical plausibility, and temporal consistency over state-of-the-art methods.
arXiv:2605.31189v1 Announce Type: new
Abstract: Tabular prediction in high-stakes domains requires models that are accurate, transparent, and robust to imperfect inputs. We propose FlagGAM, a rule-defined basis framework that separates feature-level rule construction from prediction. A Flag Core Module converts numerical and categorical variables into sparse, human-readable univariate bases, including threshold flags, category-level flags, tail-deviation bases, and categorical step functions; a default additive head then combines these bases as a restricted GAM-style predictor. Rather than reducing triggered rules to compact count summaries, FlagGAM retains a sparse rule-basis matrix that supports mixed-type classification and regression, feature-specific weighting, and optional flexible prediction heads. Across tabular benchmarks, default FlagGAM remains close to EBM in transparent additive mode, improves substantially over ridge regression on mixed-type regression, and shows smaller AUROC degradation than common baselines under missing and noisy perturbations. Flexible heads further improve accuracy and approach strong tree-based baselines, with the caveat that the resulting model should be interpreted as a rule-basis representation followed by a nonlinear predictor rather than as a fully additive GAM. Overall, FlagGAM provides a practical middle ground for tabular settings that require competitive accuracy, communicable rules, and robustness to imperfect inputs.
arXiv:2605.31188v1 Announce Type: new
Abstract: Hybrid light-matter states formed under strong coupling between molecular excitations and confined electromagnetic modes provide a potential route to modify chemical properties. Here we compute and compare a thermally averaged measure of molecular chemical activity for an equilibrium ensemble of molecules inside and outside a planar microcavity, explicitly accounting for the spatial distribution (and hence the in-plane wavevector dispersion) of the coupled light-matter states. Within a generalized Tavis-Cummings description, we find that the cavity-induced change in thermal chemical activity is most pronounced for small molecular ensembles (low areal density within a given cavity mode volume) and increases with the collective coupling strength (Rabi splitting), particularly at low temperatures. These results highlight the importance of the polariton dispersion and molecular-mode counting in assessing cavity modifications of thermally driven molecular reactivity.
arXiv:2605.20873v2 Announce Type: replace
Abstract: Planning is a fundamental capability for large language models (LLMs) because such complex tasks require models to coordinate goals, constraints, resources, and long-term consequences into executable and verifiable solutions. Existing planning benchmarks, however, usually treat planning data as fixed collections of instances rather than controllable generation targets. This limits scenario coverage, ties difficulty to surface-level proxies rather than structural sources, and offers limited support for scalable generation, automatic verification, or planning-oriented training. We introduce PlanningBench, a framework for generating scalable, diverse, and verifiable planning data for both evaluation and training. PlanningBench starts from real planning scenarios and abstracts practical workflows into a structured taxonomy of more than 30 task types, subtasks, constraint families, and difficulty factors. Guided by this taxonomy, a constraint-driven synthesis pipeline instantiates self-contained planning problems with adaptive difficulty control, quality filtering, and instance-level verification checklists. This shifts planning data construction from fixed benchmark collection to controllable generation while preserving realistic task grounding. We use PlanningBench to evaluate open-source and closed-source frontier LLMs, and find that current models still struggle to produce complete solutions under coupled constraints. Beyond evaluation, reinforcement learning on verified PlanningBench data improves performance on unseen planning benchmarks and broader instruction-following tasks. Further analysis suggests that determinate or well-specified optimal solutions provide clearer reward signals and more stable training dynamics. Overall, PlanningBench provides a controllable source of planning data for diagnosing and improving generalizable planning abilities in LLMs.
arXiv:2605.31574v1 Announce Type: new
Abstract: Radical Moral Disagreements (RMDs) are highly polarising topics that are increasingly censored in everyday life, with growing evidence suggesting that this polarisation carries measurable costs to public mental health. To address these challenges, some researchers have proposed Large Language Models (LLMs) as a means to support more democratic deliberation and better moral reasoning. Yet existing tools are poorly calibrated to help people navigate RMDs, because of their intense and divisive characteristics. This paper introduces CONSIDER, a prototype for a one-to-one AI tool for RMD navigation. Drawing on Mill's account of the epistemic value of disagreement, CONSIDER aims at value clarification through structured disagreement with an opposing LLM-generated opinion. We describe CONSIDER's design logic and analyse potential risks posed by such tools to guide future development.
arXiv:2605.31285v1 Announce Type: new
Abstract: Although mass transfer from bubbles to liquid is essential for the prediction of the efficiency of reactors, the mass transfer from bubbles is not fully understood. To determine the effect of the local velocity profile on the mass transfer for a wobbling bubble with an E\"otv\"os number of 2 and a Morton number of 10-11, 15 simulations were performed with a Front Tracking method using a sub-grid scale model for the mass transfer in the vicinity of the interface. The vortical structures created by the bubble are influenced by the exact physical properties chosen for the liquid and gas. These changes in the vortical structures also resulted in changes in mass transfer. In addition, the vortical structures created transport barriers between the wake and the bulk of liquid, which were identified by the high-value Finite Time Lyapunov Exponents. These barriers prevent convective mass transfer from the bubble wake to the bulk of the liquid. Therefore, mass transfer from the gas phase to the bulk liquid should take into account both the mass transfer from the gas to the liquid and the transfer from the wake to the bulk of the liquid.
arXiv:2605.31170v1 Announce Type: new
Abstract: Monitoring autonomous language model agents currently relies mostly on surface behavior. But what happens when agent populations invent new languages with the goal of avoiding human oversight. Here, we study the emergent languages on Moltbook. For this, we build upon the Moltbook Files dataset and apply a two-stage approach consisting of a rule-based heuristic (about 6000 matches) followed by zero-shot classification (518 kept). The resulting categories include token efficiency (166), new natural languages (106), and oversight evasion (59). We conduct both quantitative and qualitative analyses. Our results show that posts proposing new languages for avoiding oversight are judged by DeepSeek-3.2 as being less aligned than the other categories and that all languages can be learned by other language models in-context merely from a description of the language. Moreover, manually studying exemplary cases reveals surprisingly sophisticated steganographic protocols like embedding hidden messages in natural language. Although we cannot be certain about the extent of autonomy in ideation of these languages, our results add up to the evidence that monitoring surface behavior may soon be insufficient for retaining control over agent populations.
arXiv:2605.31162v1 Announce Type: new
Abstract: Unconditional diffusion models offer powerful generative priors, yet steering them toward aesthetically enhanced outputs remains largely unexplored. We show that h-space patching, the dominant paradigm for training-free diffusion editing, systematically fails for global, low-level transformations required for aesthetic and perceptual refinement. We introduce a novel, generalized framework for image-editing in unconditional diffusion models without explicit training. This inference-time mechanism operates on low-level features by extracting degradation concept vectors and combining bottleneck patching with classifier-free guidance to guide sampling away from the degraded manifold, producing consistently improved images without any model retraining.
arXiv:2605.31149v1 Announce Type: new
Abstract: This study investigates how UX research (UXR) principles, combined with Large Language Model (LLM)-supported analysis, can be used to improve the quality of requirements for mobile learning systems designed for learners with cognitive disabilities. Using the UXR Point-of-View (PoV) pyramid as a methodological framework, the study progressed through four stages: foundational structuring of psychological, behavioral, and design layers; structured validation using the DeLone and McLean Information Systems Success Model and Quality Function Deployment (QFD); insight consolidation through the development of nine Cognitive Accessibility UXR Play Cards; and stakeholder-specific PoV articulation to support interdisciplinary communication. LLM-supported synthesis was integrated to assist in theme clustering, requirement refinement, and hypothesis formulation under human oversight. Findings suggest that many usability and engagement challenges in mobile learning originate from ambiguous or under-specified requirements rather than interface design alone. By embedding cognitive accessibility principles into measurable and technically traceable requirements, the proposed Cognitive Accessibility UXR Playbook provides a structured pathway for aligning theory, system architecture, and stakeholder strategy.
arXiv:2605.31146v1 Announce Type: new
Abstract: This paper investigates how User Experience Research (UXR) methods can be combined with AI-supported analysis to develop clearer design direction for digital wellbeing interventions targeting Emergency and Public Safety Personnel (EPSP). EPSP work in high-stress, shift-based environments where cognitive fatigue and unpredictable schedules reduce engagement with conventional wellbeing tools. Using the UXR Point-of-View (PoV) framework, this study applied an AI-supported literature analysis process to identify recurring psychological, behavioural, and design patterns. Behaviour Change Techniques and Persuasive Technology principles were integrated throughout interpretation to connect evidence with practical design reasoning. The process resulted in a UXR PoV Pyramid, nine UXR Play Cards, and stakeholder focused PoV narratives. Findings show that effective wellbeing systems for EPSP must minimise cognitive effort, adapt to operational context, and prioritise psychological safety. The work demonstrates how AI can assist large-scale evidence interpretation while human researchers maintain responsibility for contextual judgement and design direction.
arXiv:2605.31145v1 Announce Type: new
Abstract: In-context localization (ICL) seeks to localize a target object specified by a small set of support examples in a query image, operating on the fly without training or parameter updates. Despite rapid advances in vision-language models (VLMs), achieving category-agnostic and visually grounded ICL remains an open problem, even though it is essential for applications such as image editing, personalized visual search, and retrieval. Existing methods are fragile and rely on explicit category supervision, which not only limits applicability in realistic settings with unnamed or instance-specific objects but also introduces category bias that steers predictions toward semantic priors rather than visual evidence. We introduce a two-stage training framework that explicitly optimizes in-context attention between support bounding boxes and query images without category supervision. We further refine localization via reinforcement learning using Group Relative Policy Optimization (GRPO) to directly minimize localization error. This formulation enforces visual correspondence over semantic priors, yielding robust instance-level localization. Empirically, a 7B-parameter model trained with our objectives outperforms models up to 72B parameters, demonstrating that context-aware localization objectives can surpass scaling alone. Comprehensive ablations validate the contribution of each component.
arXiv:2605.31138v1 Announce Type: new
Abstract: User Experience Research (UXR) in a legal and regulatory contexts presents unique challenges that require specialised approaches to protect vulnerable populations whilst generating actionable insights. Digital consultation, appointment booking, and medication delivery platforms show promise for extending care access; however, their real-world effectiveness is curtailed by an absence of theoretically grounded user experience research (UXR) methodologies that adequately account for the psychosocial conditions of these populations. This paper introduces a Generative AI-augmented UXR methodology, grounded in the UXR Point of View (PoV) Playbook, to guide the design of psychologically safe, low-cognitive-load digital health interventions for MSM and transgender individuals living with HIV/AIDS in Nigeria. Drawing from empirical research involving co-design workshops, thematic analysis, and requirements engineering, the methodology is operationalised through a four-stage UXR process encompassing AI-supported hypothesis generation, foundational planning, insight generation via Building Blocks, and the construction of stakeholder-specific PoV narratives. This process results in ten theory-informed UXR Play Cards that translate psychological mechanisms and empirical findings into actionable design guidance. Each play contains actionable tasks, AI-augmented approaches, and ethical guardrails tailored for research with marginalised populations. The output is a set of ten theory-informed UXR Play Cards translating psychological insight and empirical evidence into actionable design guidance. The core contribution is a replicable, stigma-aware, and privacy-centred framework for responsible GenAI use in UXR practice, advancing human-centred digital health design for marginalised communities.