arXiv:2607.04643v1 Announce Type: new Abstract: Video quality assessment (VQA) plays a critical role in optimizing video delivery systems. While numerous objective metrics have been proposed to approximate human perception, the perceived quality strongly depends on viewing conditions and display characteristics. Factors such as ambient lighting, display brightness, and resolution significantly influence the visibility of distortions. In this work, we address the question of the multi-screen quality assessment on mobile devices, as this area still tends to be under-covered. We introduce a first large-scale subjective dataset collected across more than different 300 Android devices, accompanied by metadata on viewing conditions and display properties. We propose a strategy for aggregated score extraction and adaptation of VQA models to device-specific quality estimation. Our results demonstrate that incorporating device and context information enables more accurate and flexible quality prediction, offering new opportunities for fine-grained optimization in streaming services. Ultimately, this work advances the development of perceptual quality models that bridge the gap between laboratory evaluations and the diverse conditions of real-world media consumption. We made the dataset and the code available at https://videoprocessing.github.io/device-viewing-conditions.
Science Journals
arXiv:2607.04645v1 Announce Type: new Abstract: Safety alignment in large language models is typically evaluated against direct, imperative harmful requests. We show that this alignment is highly conditioned on pragmatic register: models that refuse a direct request frequently comply when the same underlying objective is expressed through a different communicative stance. This suggests that current alignment policies are not invariant to semantic equivalence, but remain sensitive to how a request is pragmatically framed. We introduce Retroactive Chain-of-Thought (RetroCoT), a single-turn attack that reframes harmful requests as forensic reconstruction tasks. Rather than requesting harmful instructions directly, RetroCoT presupposes that the harmful outcome has already occurred and asks the model, acting as a forensic analyst, to reconstruct in reverse the causal chain that produced it. On AdvBench (n=50), RetroCoT achieves attach success rate of 58% on gpt-4o and 52% on gpt-4o-mini, compared with direct-request baselines of 0% and 4%, respectively. We further identify a pronounced generation gap: GPT-5-family models refuse RetroCoT entirely, explicitly identifying the reconstruction premise in their refusal rationales, consistent with explicit coverage of this reconstruction register. However, this robustness does not generalize across pragmatic forms. A single adversarial feedback turn presenting an existing forensic reconstruction response alongside evaluator critique raises ASR from 0% to 48% on GPT-5.4-mini and from 58% to 94% on GPT-4o; a control condition omitting the fabricated low score achieves 85% on GPT-5.4-mini, indicating that the operative element is pragmatic continuation within the established forensic frame rather than score manipulation. These results suggest that frontier-model alignment remains conditioned on pragmatic framing rather than semantic intent, and that new pragmatic registers can continue to expose a...
arXiv:2607.04648v1 Announce Type: new Abstract: Depression screening from large-scale behavioral data is challenged by fragmented circadian indicators, limited interpretability, and the lack of intervention-oriented analysis. Existing approaches typically analyze sleep, activity, and social behaviors in isolation, failing to capture their joint circadian structure. To address this limitation, we first propose the Circadian Rhythm Score (CRS), a composite index that compresses multi-domain daily behaviors into a unified representation of circadian rhythm. CRS is constructed to maximize discriminative power for depression screening while preserving behavioral semantics through non-negativity constraints. Empirical results demonstrate near-lossless compression, where a single CRS retains almost the full predictive capability compared with multiple raw behavioral indicators. Building upon CRS, we develop an interpretable depression screening framework based on gradient-boosted trees and SHAP analysis, revealing nonlinear and saturation-like associations between circadian rhythm and depression risk. Beyond risk prediction, we further integrate interaction modeling and counterfactual regression to estimate heterogeneous and dose-dependent behavioral effects, enabling intervention-oriented reasoning under different circadian contexts. Experiments on the China Health and Retirement Longitudinal Study (CHARLS, n=15,233), demonstrate robust screening performance (ROC-AUC=0.825) and identify actionable behavioral thresholds, including a minimum effective exercise dose of approximately 300 MET-min/week and an optimal restorative nap duration of approximately 65 minutes for sleep-deprived individuals. By bridging supervised representation learning and interpretable modeling, this work provides a scalable framework for depression screening and intervention-aware healthcare data mining.
arXiv:2607.04652v1 Announce Type: new Abstract: Learning manipulation from few demonstrations requires visual priors that capture not only where to interact, but also how the interaction should begin; static priors such as segmentation masks encode only the former. We present KAM-WM, a framework that extracts a coarse directional interaction cue from a frozen latent video world model without rollout or world-model fine-tuning. KAM-WM queries a Flow Matching image-to-video backbone once and interprets its single-step latent velocity as a Kinematic Affordance Map (KAM), which provides task-conditioned interaction regions and coarse motion structure. A lightweight Perceiver compresses KAM into tokens that condition a diffusion policy together with RGB observations and proprioception. Across LIBERO and RoboTwin2.0, KAM-WM reaches 90.6% average success on LIBERO and achieves 65.7% and 22.4% success rates in the Easy and Hard settings on RoboTwin2.0, respectively. Controlled comparisons against a zero-order mask prior suggest that part of the gains comes from directional information beyond spatial localization alone. These results indicate that, in the evaluated settings, a frozen video model can provide a useful first-order visual prior for control without the test-time cost of future rollout.
arXiv:2607.03433v1 Announce Type: cross Abstract: Foundation machine learning interatomic potentials (MLIPs) are increasingly being used as drop-in replacements for first-principles calculations, enabling simulations of materials at length and time scales that were previously inaccessible. However, due to lack of ground truth data, their accuracy on structural and dynamical observables in finite thermodynamic ensembles is yet to be established. Here, we introduce Dyna-Mat-v1.0, a benchmark dataset of condensed-phase first-principles molecular dynamics trajectories designed to test foundation MLIPs at realistic finite-temperature conditions. Using this dataset, we evaluate 15 foundation MLIPs across four model tiers by comparing both single-point energy and force errors on first-principles configurations and observables generated from MLIP-driven trajectories. We find that "on average" models with lower single-point force errors also yield lower errors for structural and dynamical observables. However, there are individual systems for which low force errors lead to qualitative failures in the predicted structure. Pressure remains poorly described across most models, pointing to limitations in the density functional theory stress labels available in current large-scale training datasets. Finally, we construct an accuracy-cost Pareto frontier to identify the best trade-offs for molecular dynamics with foundation MLIPs, finding that the latest generation of cross-trained models is close to Pareto-optimal according to the accuracy metrics considered here. Overall, Dyna-Mat-v1.0 shows that end-to-end finite-temperature validation is essential for quantifying the predictive behaviour of foundation MLIPs, and provides a simple, scalable route for assessing them beyond static and harmonic benchmarks relevant to materials design.
arXiv:2602.06872v2 Announce Type: replace Abstract: We derive a residual-based $hp$-a posteriori error estimator for hybrid high-order (HHO) methods on simplicial meshes applied to the biharmonic problem posed on two- and three-dimensional polytopal Lipschitz domains. The a posteriori error estimator hinges on an error decomposition into conforming and nonconforming components. To bound the nonconforming error, we use a $C^1$-partition of unity constructed via Alfeld splittings, combined with local Helmholtz decompositions on vertex stars where the key contribution is to show that the stability constant only depends on the mesh shape-regularity. For the conforming error, we design two residual-based estimators, each associated with a specific interpolation operator. In the first setting, the upper bound on the conforming error involves only the stabilization term and the data oscillation, but hinges on an assumption that we verify numerically. In the second setting, the bound additionally incorporates bulk residuals, normal flux jumps, and tangential jumps. Numerical experiments confirm the theoretical findings on the error upper bound and also illustrate numerically that the proposed estimators lead to moderate effectivity indices.
arXiv:2602.06934v5 Announce Type: replace Abstract: Grassroots Logic Programs (GLP) is a concurrent logic programming language in which logic variables are partitioned into paired readers and writers. An assignment is produced at most once via a writer and consumed at most once via its paired reader, and may contain additional readers and/or writers. This enables the concise expression of rich multidirectional communication modalities. The language was introduced together with concurrent (cGLP) and multiagent (maGLP) operational semantics. Here, we derive from these (\ia)~dGLP, a deterministic counterpart of cGLP, and (\ib)~madGLP, a counterpart of maGLP in which deterministic agents communicate solely by asynchronous message passing, and prove them correct against their abstract counterparts. maGLP shared variable pairs spanning agents can be implemented as local variables paired by \emph{global links}, with correctness following from disjoint substitution commutativity (a consequence of GLP's single-occurrence invariant). We further prove that madGLP is grassroots. Both dGLP and madGLP serve as formal specifications for an AI-driven implementation discipline (math $\to$ informal spec $\to$ Dart) employed and described here: from dGLP, AI (Claude) developed a workstation-based GLP implementation in Dart, and from madGLP it is developing a smartphone-based multiagent one.
arXiv:2607.04709v1 Announce Type: new Abstract: Modern machine learning systems demand extensive datasets for visual recognition. Conversely, humans learn with high efficiency despite severe data limitations, often by acquiring broad categorical structures before refining finer distinctions. Inspired by this contrast, we introduce SCALA (Scaffolded Cognitive Architecture for Learning under limited dAta), a hierarchical learning framework grounded in cognitive psychology that guides models from coarse conceptual structures to fine-grained recognition. Our model exhibits human-like cognitive selectivity by effectively prioritizing task-relevant features while suppressing background distractors, a mechanism that induces a fundamental shift in representation learning. This shift is characterized by accelerated cluster formation, reduced intra-class dispersion, and enhanced semantic separability. Empirically, SCALA achieves significant accuracy improvements under severe data scarcity. Furthermore, this hierarchical scaffolding promotes robust generalization to unseen classes and accelerates the acquisition of novel categories. Collectively, our results establish SCALA as a powerful framework for achieving human-level sample efficiency and resilient category generalization in data-constrained environments.
arXiv:2607.04711v1 Announce Type: new Abstract: Continual learning aims to progressively learn from a sequence of tasks, each containing a disjoint subset of classes, while preserving previously learned knowledge. Prompt-based continual learning methods propose to learn a small set of parameters, i.e., prompts, by associating them with a query feature of an input image. These methods optimize the prompts, attempting to represent diverse patterns of images. However, we have observed that existing prompt-based methods suffer from a prompt collapse problem, that is, the prompts tend to be highly similar to each other, thereby failing to capture the diverse data distributions in continual learning scenarios. To address this issue, we propose in this paper a novel prompt-based continual learning framework that captures diverse patterns of images across a sequence of tasks. To this end, we model each prompt as a probabilistic distribution and construct a mixture of these distributions, from which we sample diverse prompts. This enables our model to effectively capture highly diverse image distributions in the continual learning process. We also present a distribution regularization loss to prevent abrupt changes in the prompt distributions throughout the training process. We show extensive experimental results for continual learning on standard benchmarks, including ImageNet-R, CIFAR-100, and CUB-200, demonstrating the effectiveness of our framework.
arXiv:2607.05064v1 Announce Type: new Abstract: Reinforcement learning in real world environments often suffers from severe performance degradation due to delayed feedback. Existing approaches typically mitigate performance degradation caused by observation delays by constructing augmented states or predicting the true states. However, these methods often overlook the inherent discrepancy between delayed state and true states induced by stochastic MDP. We theoretically prove the existence of such a discrepancy and show that it leads to the degradation of the optimal policy. To address this challenge, we propose Diffusion Guided Uncertainty Aware Delayed Policy Optimization (DUPO). Our method explicitly models the relationship between delayed state message and the current state using a diffusion model, and leverages the resulting discrepancy estimates to weight delayed policies. Extensive experiments on continuous robotic control tasks with multiple stochastic delays demonstrate that DUPO consistently outperforms existing methods and remains effective even under long and random delay scenarios.
arXiv:2607.04682v1 Announce Type: new Abstract: Coherent perfect absorption (CPA) extinguishes optical fields through interference and dissipation, but conventional implementations rely on material loss that is largely fixed after fabrication. Here we demonstrate all-optically controllable CPA based on frequency conversion in a periodically poled lithium niobate waveguide resonator. Pump-driven frequency conversion couples a resonant signal field at 1581 nm in the main system to a non-resonant environmental mode at 780 nm, creating a dynamically tunable effective loss channel. The nonlinear cavity acts as a tunable lossy beamsplitter without intrinsic material absorption. Under coherent two-sided signal injection, we observe up to 92 % absorption. We further introduce environment-assisted CPA by injecting an external field into the frequency-converted environmental mode, turning the environment from a passive loss reservoir into an addressable coherent control port. Our results establish a frequency-conversion-based platform for all-optical control of dissipation in CPA, combining pump-tunable loss with environment-assisted coherent control.
arXiv:2607.04684v1 Announce Type: new Abstract: Spatio-temporal action detection in videos requires jointly localizing actors in space and identifying action boundaries over time. A common challenge is constructing temporally stable action tubes, as frame-level detectors often suffer from jitter, fragmentation, and imprecise temporal localization. Many recent approaches address this by introducing heavy spatio-temporal transformers or optical-flow-based pipelines, leading to high computational cost and limited scalability. We propose TubeLite, a lightweight framework for spatio-temporal action detection that focuses on stable tube construction and boundary-aware temporal modeling. TubeLite represents each actor as a tube, defined as a sequence of bounding boxes associated with a single actor over time, and explicitly enforces temporal consistency at both the spatial and semantic levels. The method combines low-jitter actor detection, Gaussian-weighted actor feature extraction, efficient short-term temporal propagation, and a boundary-focused temporal prediction head, while avoiding optical flow and large-scale temporal attention. Despite its compact design, TubeLite achieves strong video-level localization performance. It improves Video-mAP@0.5 by 4.5 and 7.1 percentage points over the best compared method on the MultiSports and UCF101-24 datasets, respectively, with substantially fewer parameters and floating-point operations than transformer-based alternatives, demonstrating that effective spatio-temporal action detection can be obtained through principled, lightweight temporal modeling.
arXiv:2607.04243v1 Announce Type: new Abstract: Accurate patient-specific tetrahedral cardiac meshes are essential for in-silico trials, yet common segmentation-then-modelling pipelines can blur thin-wall anatomy and offer limited cross-case correspondence. We propose HeartVolMesh, which lifts each template vertex to an anisotropic Gaussian kernel and uses a 3D CNN-GNN to predict per-vertex displacements and Cholesky-parameterized covariances from volumetric images. Training is guided by a covariance-aware negative log-likelihood loss with lightweight mesh regularization. For volumetric meshing, we warp a fixed tetrahedral template to the reconstructed surface via staged alignment, non-rigid registration, and deformation propagation, preserving connectivity and correspondence by construction, with resolution controlled by template density. Experiments show consistent gains over deformation-based baselines in surface mesh accuracy and volumetric mesh fidelity.
arXiv:2607.04321v1 Announce Type: new Abstract: We present LogicProof, an interactive web-based theorem prover designed for educational use. The system supports natural deduction and sequent calculus for propositional and first-order logic in both classical and constructive variants. It emphasizes a modern user experience through real-time feedback and interactive visualization of proof trees. We evaluated LogicProof in a study involving 35 students. The results suggest that the system improves understanding of formal proof construction and supports student engagement with logical concepts. Compared to traditional pen-and-paper approaches, students reported faster iteration, easier error correction, and greater confidence in the correctness of their solutions. These findings indicate that LogicProof can serve as a practical supplement to existing teaching methods, particularly in supporting the learning process and reducing barriers associated with formal proof construction.
arXiv:2607.04688v1 Announce Type: new Abstract: Synthesis planning aiming to find pathways of reactions for a target molecule is one of the most important and challenging tasks in drug discovery. Recent progress has produced both specialized deep-learning retrosynthesis systems and general-purpose large language models, but objective comparison remains difficult due to the lack of flexible, chemically interpretable benchmarking protocols. In the current study, we are introducing the URSA (Utilitarian RetroSynthesis Assessment) evaluation framework that provides the opportunity to benchmark the synthetic routes not only from a formal perspective, such as convergence to commercially available starting materials, but also from a chemical plausibility perspective, mimicking the way expert chemists evaluate the reactions and routes. The study covers a comprehensive evaluation of both conventional end-to-end retrosynthesis solutions and LLMs for the synthesis planning task on a set of novel, diverse target molecules with undisclosed synthetic routes, which represent realistic tasks in the daily drug design routine. We find that while LLMs can support high-level strategic planning, they currently underperform specialized retrosynthesis models in reliably solving synthesis planning tasks.
arXiv:2602.06941v3 Announce Type: replace Abstract: Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.g., ``wait, that's not right'') and continuing on-topic even while the steering perturbation remains active. We term this Endogenous Steering Resistance (ESR). Using sparse autoencoder (SAE) latents to steer model activations, we find that Llama-3.3-70B exhibits explicit ESR at 3.8%, with smaller models from the Llama-3 and Gemma-2 families showing the explicit form less frequently. Two controls dissociate ESR into a detection event and a sustained-resistance component that conditioning on recent on-topic tokens does not fully explain. We identify 26 SAE latents through contrastive on-topic/off-topic search; zero-ablating them reduces the multi-attempt rate by 25%, with random-latent and held-out-prompt controls supporting specificity. ESR can also be deliberately enhanced through both meta-prompting and fine-tuning on synthetic self-correction examples. ESR has dual implications for safety: it could harden models against adversarial activation-space manipulation, but may equally interfere with beneficial steering-based interventions, since the model has no way to distinguish the two. Code is available at https://github.com/agencyenterprise/endogenous-steering-resistance.
arXiv:2602.07789v2 Announce Type: replace Abstract: Rod-based structures are commonly used in practical applications in science and engineering. However, in many design, analysis, and manufacturing tasks, handling the rod-based structures in three dimensions directly is generally challenging. To simplify the tasks, it is usually more desirable to achieve a two-dimensional representation of the rod-based structures via some suitable geometric mappings. In this work, we develop a novel method for computing a low-distortion planar embedding of rod-based structures. Specifically, we identify geometrical constraints that aim to preserve key length and angle quantities of the 3D rod-based structures and prevent the occurrence of overlapping rods in the planar embedding. Experimental results with a variety of rod-based structures are presented to demonstrate the effectiveness of our approach. Moreover, our method can be naturally extended to the design and mapping of hybrid structures consisting of both rods and surface elements. Altogether, our approach paves a new way for the efficient design and fabrication of novel three-dimensional geometric structures for practical applications.
arXiv:2602.16299v3 Announce Type: replace Abstract: Cross-encoders deliver state-of-the-art ranking effectiveness in information retrieval, but have a high inference cost. This prevents them from being used as first-stage rankers, but also incurs a cost when re-ranking documents. Prior work has addressed this bottleneck from two largely separate directions: accelerating cross-encoder inference by sparsifying the attention process or improving first-stage retrieval effectiveness using more complex models, e.g. late-interaction ones. In this work, we propose to bridge these two approaches, based on an in-depth understanding of the internal mechanisms of cross-encoders. Starting from cross-encoders, we show that it is possible to derive a new late-interaction-like architecture by carefully removing detrimental or unnecessary interactions. We name this architecture MICE (Minimal Interaction Cross-Encoders). We extensively evaluate MICE across both in-domain (ID) and out-of-domain (OOD) datasets. MICE decreases fourfold the inference latency compared to standard cross-encoders, matching late-interaction models like ColBERT while retaining most of cross-encoder ID effectiveness and demonstrating superior generalization abilities in OOD.
arXiv:2602.18037v2 Announce Type: replace Abstract: Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Models (LMs). A common problem is reward hacking, where the policy may exploit inaccuracies of the reward and learn an unintended behavior. Most previous works address this by limiting the policy update with a Kullback-Leibler (KL) penalty towards a reference model. We propose a different framing: Train the LM in a way that biases policy updates towards regions in which the reward is more accurate. First, we derive a theoretical connection between the accuracy of a reward model and the flatness of an optimum at convergence. Gradient regularization (GR) can then be used to bias training to flatter regions and thereby maintain reward model accuracy. We confirm these results by showing that the gradient norm and reward accuracy are empirically correlated in RLHF. We then empirically show that Reference Resets of the KL penalty find flatter regions with a higher reward accuracy. We further improve on this by proposing to use explicit GR with an efficient finite-difference estimate. Empirically, GR performs better than a KL penalty across a diverse set of RL experiments with LMs. GR achieves a higher GPT-judged win-rate in RLHF, avoids overly focusing on the format in rule-based math rewards, and prevents hacking the judge in LLM-as-a-Judge math tasks.
arXiv:2603.13259v3 Announce Type: replace Abstract: When a decoder-only transformer is forced to process matched correct and incorrect single-token continuations of a factual query, the two pathways through hidden-state space diverge: displacement vectors from the query-only representation keep near-equal magnitude but rotate apart, with angular separation growing through mid-depth before late layers resolve an asymmetric outcome. A logit-lens preference in the incorrect run falls far below the equal-probability prior (roughly 11.5x more mass on the incorrect token than the correct one). We read this pattern, rotational divergence then late-layer asymmetric commitment, as the geometric signature of the model externally appearing to reject a wrong continuation, while staying explicit that it is observational, not causal: the incorrect run could equally reflect the model conforming to the token it is forced to carry, which only a random-token control can settle. It holds across six decoder-only transformers spanning four architecture families (Llama, Mistral, Gemma, StableLM) from 1B to 13B parameters; a seventh (Qwen2 1.5B) is flat under our protocol, plausibly a tokenizer artefact, leaving an emergence threshold open. Linear probes recover the distinction at intermediate depth, and cross-domain transfer is structurally asymmetric, a financial-medical corridor transferring far better than transport pairs. Where single-layer activation patching is cleanly interpretable (LLaMA-2 13B, Mistral 7B) it yields no layer band of consistent recovery; a third model (StableLM-2 1.6B) recovers uniformly above the ceiling, which we diagnose as a code-path artefact and exclude. Under this scoped null the late-layer asymmetry is not localized to a single component, fitting a distributed-by-trajectory account rather than single-layer localized recall. We document this with forced-completion probing across seven models, three domains, and 300 queries.
arXiv:2603.16809v2 Announce Type: replace Abstract: Behavior Trees (BTs) offer a powerful paradigm for designing modular and reactive robot controllers. BT planning, an emerging field, provides theoretical guarantees for the automated generation of reliable BTs. However, BT planning typically assumes that a well-designed BT system is already grounded -- comprising high-level action models and low-level control policies -- which often requires extensive expert knowledge and manual effort. In this paper, we formalize the BT Grounding problem: the automated construction of a complete and consistent BT system. We analyze its complexity and introduce CABTO (Context-Aware Behavior Tree grOunding), the first framework to efficiently solve this challenge. CABTO leverages pre-trained Large Models (LMs) to heuristically search the space of action models and control policies, guided by contextual feedback from BT planners and environmental observations. Experiments spanning seven task sets across three distinct robotic manipulation scenarios demonstrate CABTO's effectiveness and efficiency in generating complete and consistent behavior tree systems.
arXiv:2603.17673v2 Announce Type: replace Abstract: LLM agents are becoming increasingly important in the security domain, but leading systems are often closed-source, cloud-based, hard to reproduce or use with sensitive code. This creates a need for small, local models that can perform security tasks under strict resource constraints, though effective methods for developing them remain unexplored. In this paper, we address this gap by proposing a two-stage post-training recipe that turns a small local language model into a security agent. To this end, we focus on Linux privilege escalation as a representative setting to systematically study the training of local models, as the task is both automatically verifiable and requires multi-step interactive reasoning. Using an experimental setup that mitigates data leakage, we post-train a small 4B model in two stages: supervised fine-tuning on traces from procedural privilege-escalation environments, followed by reinforcement learning with verifiable rewards. On a held-out benchmark of 12 Linux privilege-escalation scenarios, supervised fine-tuning doubles the baseline success rate under a tight budget of 20 interaction rounds, and subsequent reinforcement learning training improves our model, PrivEsc-LLM 4B, to 93.3% success, behind only Claude Opus 4.7 at this budget. At the same time, the expected inference cost per successful escalation decreases by more than 80x. Our findings not only show that small local models can be adapted to complex security tasks, but also document the challenges involved, offering guidance for transferring this recipe to other settings.
arXiv:2603.18528v2 Announce Type: replace Abstract: Text-to-image models produce images that align well with natural language prompts, but compositional generation has long been a central challenge. Models often struggle to satisfy multiple concepts within a single prompt, frequently omitting some concepts and resulting in partial success. Such failures highlight the difficulty of jointly optimizing multiple concepts during reward optimization, where competing concepts can interfere with one another. To address this limitation, we propose Correlation-Weighted Multi-Reward Optimization (CMO), a framework that leverages the correlation structure among concept rewards to adaptively weight each attribute concept in optimization. By accounting for interactions among concepts, CMO balances competing reward signals and emphasizes concepts that are partially satisfied yet inconsistently generated across samples, improving compositional generation. Specifically, we decompose multi-concept prompts into pre-defined concept groups (e.g., objects, attributes, and relations) and obtain reward signals from dedicated reward models for each concept. We then adaptively reweight these rewards, assigning higher weights to conflicting or hard-to-satisfy concepts using correlation-based difficulty estimation. By focusing optimization on the most challenging concepts within each group, CMO encourages the model to consistently satisfy all requested attributes simultaneously. We apply our approach to train state-of-the-art diffusion models, SD3.5 and FLUX.1-dev, and demonstrate consistent improvements on challenging multi-concept benchmarks, including ConceptMix, GenEval 2, and T2I-CompBench. The code is available at https://github.com/TheDarkKnight-21th/CMO.
arXiv:2607.03643v1 Announce Type: cross Abstract: Purpose: Early screening for eye diseases is critical in low- and middle-income countries where access to care is limited. We investigate whether a confidence-guided, multi-image diabetic retinopathy diagnosis framework can integrate image filtering with confidence-aware predictions for reliable screening at capture. Methods: We develop a multi-image fusion method that aggregates retinal views to improve confidence and balanced accuracy. Our method uses confidence to identify unreliable predictions, prompting retakes when needed. We compare: (1) a cascaded image-quality and disease diagnosis pipeline using a single image per patient, (2) confidence-based prediction, and (3) our confidence-based multi-image fusion pipeline. All methods are evaluated using a RETFoundGreen backbone on the mBRSET (n = 1,234) and BRSET (n = 7,599) datasets. Results: At 70% coverage, our method achieves 91% balanced accuracy on mBRSET and 97% on BRSET, improvements of ~12% and ~6%, respectively, over cascade filtering. The image-quality cascade reaches sensitivities of 61% on mBRSET and 86% on BRSET, whereas our framework reaches 94% and 96%, respectively, at 50% coverage. Conclusions: Human-annotated quality labels are weakly associated with diagnostic performance, and confidence-based filtering consistently outperforms image quality-based cascaded pipelines. Translational Relevance: Using confidence-based multi-image fusion, patients receive more reliable predictions, reducing incorrect diagnoses during screening. The lightweight backbone and single inference pass per image make the framework compatible with low-latency mobile screening systems in resource-limited settings.
arXiv:2607.04741v1 Announce Type: new Abstract: Event-based vision sensors provide asynchronous event generation and microsecond timestamp resolution, which may be useful for high-speed optical measurements. However, precise event timestamps do not necessarily guarantee accurate reconstruction of temporally varying optical signals, particularly under dense and spatially extended illumination, imposing operational limits when used as optical interrogators that remain underexplored in the literature. To address this knowledge gap, this work presents a systematic, quantitative characterization of the temporal response and waveform reconstruction fidelity of an IMX636-based event camera under both controlled sinusoidal and pulsed optical excitation. For this, frequency-domain measurements are first used to evaluate modulation response, event-rate behavior, polarity balance, and spectral reconstruction fidelity over a wide range of illumination conditions and region-of-interest geometries. Then, complementary pulse-based measurements quantify first-event latency, response duration, recovery dynamics, and pulse-width reconstruction accuracy under rapidly repeated excitation, showing that optical transitions can be detected with first-event latencies below 5 microseconds. However, the complete event response extends over significantly longer timescales due to photoreceptor dynamics, refractory behavior, and readout serialization. Under high-frequency modulation and short-pulse excitation, the reconstructed waveforms progressively degrade because of temporal spreading and imbalance between positive and negative event generation. The measurements further demonstrate that the temporal fidelity of the reconstructed signal depends strongly on the geometry and spatial activity of the selected region of interest.