arXiv:2607.17243v1 Announce Type: new
Abstract: Multi-view spatial reasoning requires vision-language models to compare visual evidence across images, align object correspondences, and infer spatial relations over long visual contexts, a setting where chain-of-thought reasoning tends to grow verbose without becoming more accurate. Reinforcement learning with verifiable rewards is a natural fit for this task, but standard GRPO reward relies on sparse outcome-level feedback and gives no signal about where a reasoning trajectory goes wrong, nor any control over its length. We propose LenGuard-GPC, a dense reward framework that addresses both problems together. For each sampled trajectory, it compares the token-wise predictive distributions under a standard prompt and a guided prompt, and uses the resulting token-sum KL divergence as a dense reward signal. Since this KL penalty accumulates over tokens and would otherwise reward shorter responses regardless of their quality, we introduce a staged length bonus that keeps reasoning length within a controlled range without simply encouraging brevity. On six multi-view spatial reasoning benchmarks, LenGuard-GPC improves accuracy over vanilla GRPO while reducing average response length.
Science Journals
arXiv:2607.16320v1 Announce Type: new
Abstract: In this paper, we reveal an important yet overlooked problem in image denoising: under signal-dependent camera noise models, dark regions suffer from inherently low Signal-to-Noise Ratio (SNR), as signal intensity decays far faster than noise variance diminishes, making detail recovery in dark areas fundamentally challenging. Yet rather than compensating for this difficulty, MSE-trained denoisers exacerbate it -- reconstructing dark pixels up to 6x worse relative to their per-band noise floor. This bias stems from two compounding factors: signal-dependent noise inflates bright-pixel residuals, and the network's Jacobian norm increases monotonically with brightness. Together, these cause bright regions to chronically dominate gradient updates at the expense of dark ones. To this end, we propose Brightness Bias-Robust Denoising (BBRD), a drop-in replacement for MSE loss that partitions pixels into brightness bands, normalizes per-band error by empirical noise variance, and applies Group Distributionally Robust Optimization (Group-DRO) to dynamically upweight whichever band is currently worst, with zero additional parameters or inference cost. Across 8 architectures and 2 datasets in our experiments, BBRD is the only method among 13 tested alternatives that improves each brightness band simultaneously, achieving up to +0.45 dB on dark bands, +0.32 dB on bright bands, and +0.65 dB aggregate Peak Signal-to-Noise Ratio (PSNR) on SIDD, with the largest per-band gains in the darkest regions where detail recovery matters most. Code is available at https://github.com/xmed-lab/BBRD
arXiv:2607.17469v1 Announce Type: new
Abstract: A randomized algorithm may terminate almost surely even though exceptional random tapes make it run forever. This paper studies the survival tail, the Kolmogorov complexity of one such tape, and the Hausdorff dimension of all of them. For each $s>0$ at which the powered repair matrices commute, the main theorem bounds $\sum_wP[w]^s$ over surviving prefixes $w$, uniformly over deterministic nonanticipating selectors. The case $s=1$ controls termination; the full family gives weak-source and dimension bounds.
The source powers contain information absent even from the ordinary repair kernel and the complete stopping-time law. Under one common finite tape source, two overlapping disagreement-repair rules on a four-vertex path have the same ordinary kernels and the same stopping-time law for every selector, yet their nontermination dimensions can be arbitrarily close to zero and one. At one common source-power level, the same dominated tape source makes one rule run forever but gives the other an exponential stopping tail. The separation is caused by action labels that produce the same state transition and are therefore invisible at power one. For bounded-dependence $k$-SAT, conditional block min-entropy above the trace-growth threshold gives exponential termination, and the effective dimension of an individual infinite run is bounded by the trace growth induced by the clauses repaired infinitely often. Tree formulas asymptotically attain the maximum-degree dimension and global source bounds, while clique formulas attain the graph-specific one-step threshold in the stated regime. An exact backward likelihood identity complements these setwise results with tail and coding bounds for each run.
arXiv:2607.17689v1 Announce Type: new
Abstract: Multilingual language models rely on shared subword vocabularies to represent multiple languages within a limited number of token units. While such sharing is often useful, it can also create cases in which identical surface forms are treated too uniformly across languages, even when their meanings or usage differ. We investigate this limitation through cross-lingual homographs and false friends, and examine whether introducing language information earlier in the tokenization process can improve their treatment. We propose a simple tokenizer-level intervention based on language cues: language-specific characters replacing initial characters of shared-vocabulary words, reducing common identity during vocabulary construction. In intrinsic analysis, we find through tokenizer-level statistics that BPE and UnigramLM often treat cross-lingual homographs in a largely language agnostic way, whereas the context-sensitive SaGe tokenizer diverges more strongly; our intervention removes this gap. In downstream English-to-X machine translation, our cues yield modest improvements in several settings, especially under BPE, although the effect is not consistent across all languages and evaluation sets. Overall, the findings suggest that adding lightweight language information at the tokenizer level is a promising direction for further exploration.
arXiv:2607.16947v1 Announce Type: new
Abstract: Text-to-video (T2V) generation models have achieved strong visual realism, but improving physical plausibility can come at the cost of semantic consistency with the input text. This tension arises because physical preference is typically determined by comparing dynamics between two videos, without accounting for whether either video faithfully depicts the scene specified by the prompt, making physical-semantic conflict a systematic tendency under this supervision paradigm. We formulate this challenge as a constrained preference optimization problem and propose Physical and Semantic Direct Preference Optimization (PSDPO), which modulates each preference pair's contribution based on the agreement between its physical and semantic signals. A gradient-level analysis shows that PSDPO bounds the semantic drift from conflicting pairs to a controllable residual, and further motivates a staged optimization protocol that provably reduces cumulative drift. The resulting method operates entirely within the standard DPO framework, requiring no auxiliary models or additional loss terms. Experiments show that PSDPO improves physical plausibility by up to $2\times$ over the baseline on VideoPhy-2, while maintaining strong semantic consistency on VBench, achieving a more reliable balance than existing preference-based methods.
arXiv:2607.16780v1 Announce Type: new
Abstract: Artificial intelligence (AI) is increasingly embedded in scientific research, but its scientific value is unlikely to be distributed evenly. This study examines how AI knowledge integration is associated with scientific impact and asks who benefits from AI-related knowledge in science. Using large-scale bibliographic data, we measure AI integration through references to papers in the OpenAlex Artificial intelligence subfield and link it to five-year citation impact. The results show that AI references are generally associated with higher citation impact, but the returns vary substantially across scientific fields. Career stage also matters: senior scholars benefit more from the extensive margin of AI referencing, whereas junior scholars benefit more from intensive AI referencing and tend to cite newer and higher-impact AI papers. At the institutional level, returns are non-monotonic: institutions with intermediate AI capability achieve the largest proportional gains, while leading AI institutions are more deeply embedded in AI-centered knowledge spaces, attract more AI-related audiences, and more often become substitute citation gateways to cited AI sources. These findings suggest that the value of AI knowledge depends not only on technical capability, but also on translational capacity: the ability to make AI knowledge meaningful, legitimate, and useful across scientific communities.
arXiv:2607.17553v1 Announce Type: new
Abstract: This paper proposes a novel on-off division multiple access (ODMA) transmission scheme that enables efficient joint multi-user channel estimation and iterative decoding by inserting a small number of frozen symbols into the codewords. Functionally analogous to pilots, these symbols are sparsely distributed within the codeword. Unlike conventional pilot-based methods, our approach requires only a minimal number of frozen symbols (e.g., $5\sim20$ symbols per user in a 300-user system), which serve dual purposes as both estimation references and decoding aids. By employing low-complexity single-user channel estimation and decoding, combined with simple iterative interference cancellation, the scheme achieves performance equivalent to that with perfectly known user channels, even when accounting for the additional energy and bandwidth costs of the frozen symbols. Furthermore, for the large-scale ODMA sparse multiple access system, this paper proposes a fixed-point analysis method, which can accurately estimate the iterative convergence performance over multi-user block fading channels by only leveraging the decoding functions under the single-user AWGN channel. This method is applicable to performance analysis for arbitrary code lengths, code rates, and decoding algorithms. It eliminates the need for extensive Monte Carlo simulation time, and provides an efficient tool for the design of multi-user codes.
arXiv:2607.16321v1 Announce Type: new
Abstract: Understanding a painting is never a single act. Art historians may analyze the same work through concepts of style, iconography, or historical context, dimensions that are not interchangeable, and each carries distinct semantic relationships between the visual and the textual. Vision-Language Models (VLMs) like CLIP, which learn a single shared embedding space, collapse this richness into a single homogeneous alignment, thereby losing the multi-relational structure that defines art-historical reasoning. We introduce CANVAS (Contrastive Art-aware Network for Vision-Language Alignment with Sheaves), a framework for learning relation-aware multimodal representations inspired by sheaf theory. Each artwork is projected into multiple embeddings conditioned on the type of relation (i.e., the context), and a novel contrastive loss encodes contextual information during training, with no dependency on external data at inference. We evaluate on three newly introduced benchmarks of artworks for multi-relational art understanding: WikiArt+, derived from WikiArt and Wikipedia, HertzianaDP, from the Bibliotheca Hertziana collection, and SemArt+, refined from the SemArt dataset. In multimodal retrieval and art understanding, CANVAS outperforms the baselines, supporting the view that multi-relational alignment is not just theoretically motivated but also practically essential.
arXiv:2607.16784v1 Announce Type: new
Abstract: As demand for DNN inference grows, GPU capacity is increasingly oversubscribed, forcing operators to colocate multiple models on the same device in both cloud and edge deployments. Whether colocation succeeds or violates SLOs depends on the temporal overlap of kernels from concurrently executing models -- an effect that existing serving systems either ignore or approximate using aggregate resource profiles that fail to capture temporal dynamics. This paper presents Roomie, a model serving orchestration architecture that predicts and avoids kernel-level interference between colocated DNNs. Roomie decouples offline kernel profiling from online interference prediction. It uses profiling only to extract per-kernel resource configurations, and predicts interference with an occupancy-based analytical model immune to profiler-induced timing distortion. A pairwise greedy heuristic then approximates multi-model interference in polynomial rather than exponential time, and an online placement algorithm then uses these estimates to assign each incoming model to the GPU that minimizes predicted slowdown. Our experimental evaluation compares Roomie against state-of-the-art solutions across both cloud-grade server clusters and embedded edge devices, demonstrating that Roomie reduces SLO violations (i.e., inference latency) by up to 3x, while maintaining comparable, and in many cases superior, goodput relative to existing approaches.
arXiv:2607.17555v1 Announce Type: new
Abstract: Predicting extreme price movements in high-frequency financial markets is a challenging task due to non-stationarity, heavy-tailed return distributions, and severe class imbalance. In particular, rare but impactful events are often difficult to detect using conventional modeling approaches, which typically treat extreme movements as isolated observations. This study proposes a volatility-aware approach for extreme event detection using high-frequency Bitcoin limit order book (LOB) data. Motivated by empirical evidence of volatility clustering, the target formulation is extended to incorporate both large future returns and high-volatility regimes. This redefinition increases the proportion of informative samples and aligns the learning objective with the underlying market dynamics. Using a tree-based model (XGBoost) with time-series cross-validation and imbalance-aware evaluation, the proposed method achieves a Precision-Recall AUC of approximately 0.40, significantly outperforming the baseline formulation with a PR-AUC of around 0.06. This represents more than a sixfold improvement in detecting rare events. The results highlight that target design plays a critical role in financial machine learning, often exceeding the impact of model complexity. By incorporating volatility structure into the labeling process, the proposed approach provides a more effective and realistic framework for extreme event detection in high-frequency cryptocurrency markets.
arXiv:2607.17693v1 Announce Type: new
Abstract: Test-time adaptation (TTA) aims to mitigate distribution shifts by adapting models with unlabeled target data at inference time. While TTA with vision-language models (VLMs) has shown promising results in classification, extending it to medical image segmentation remains challenging. In this setting, the adaptation gains from optimizing on VLM-generated predictions are often outweighed by the degradation to the VLM's strong pretrained features caused by noisy, update-driven learning, resulting in limited and unstable improvements. We therefore propose Memory-Supported Synergistic Adaptation (MSSA), a novel training-free TTA framework for medical image segmentation. Without updating model parameters, MSSA dynamically selects reliable image-text predictions to construct an online memory, uses them as text-guided semantic priors, and couples them with cross-image structural alignment for robust adaptation. Specifically, MSSA consists of (i) a noise-aware memory construction module that filters and stabilizes cross-modal predictions, and (ii) a relevance-driven prototype alignment module that aligns the target sample with structurally consistent memory samples and their reliable predictions to improve adaptation. Extensive experiments on multiple medical segmentation benchmarks demonstrate that MSSA consistently improves VLM-based segmentation models and outperforms existing fine-tuning-based TTA methods by a clear margin, with gains of up to 12.2% DSC and 11.7% mIoU. Project page: https://lingrayy.github.io/MSSA/ .
arXiv:2607.17818v1 Announce Type: new
Abstract: Efficient, collision-free, and time-optimal motion planning is a fundamental requirement for autonomous forestry cranes operating under hydraulic pump-flow constraints. The Via-Point-based Stochastic Trajectory Optimization (VP-STO) algorithm has demonstrated near-time-optimal hybrid motion planning in this domain, but requires a fixed terminal joint configuration specified prior to optimization. For kinematically redundant manipulators such as forestry cranes, this pre-commitment to a single inverse kinematics solution restricts the planner's ability to exploit redundancy, particularly under the nonlinear, globally coupled pump-flow constraint where admissible joint velocities depend on their combined hydraulic demand. This paper presents TSC-VP-STO, a task-space-constrained extension of VP-STO that replaces the strict terminal joint-space constraint with a task-space constraint, jointly optimizing the trajectory and the redundant degrees of freedom of the terminal configuration. This enables the planner to adapt end configurations to the environment-dependent motion and hydraulic flow allocation, yielding more balanced pump utilization and shorter trajectory durations. We formalize the approach through a configuration space decomposition and derive a concrete reachability constraint for the forestry crane kinematics. Experimental evaluations across multiple planning targets and via-point configurations demonstrates a reduction on trajectory durations by 12-15% on average and improved pump-flow utilization compared to the baseline VP-STO. The practical applicability of TSC-VP-STO is validated through real-world deployment on a forestry crane, including a full log-loading cycle.
arXiv:2607.17247v1 Announce Type: new
Abstract: Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL) and on-policy distillation (OPD). However, RL relies on coarse-grained outcome supervision, resulting in difficult credit assignment and limited capability to acquire new knowledge. OPD, meanwhile, unconditionally matches teacher logits through KL divergence, which creates a dilemma: similar teachers provide little new knowledge, while substantially different teachers often yield ineffective guidance, largely restricting OPD to within-family distillation. We propose Distilled Reinforcement Learning (Distilled RL), which integrates teacher supervision into the RL objective to provide fine-grained guidance, selectively transfer new knowledge and avoid unconditional imitation. Distilled RL contains three components: reverse importance sampling with clipping, negative sample reset, and sequence-level geometric normalization. Through a concise and interpretable case study, we demonstrate that Distilled RL can effectively transfer previously unavailable knowledge from a teacher model to a student model. Extensive experiments across both within-family and cross-family distillation settings show that Distilled RL substantially outperforms standard RL and OPD in terms of both pass@1 and pass@k. Our code is available at https://github.com/597358816/Distilled-RL.
arXiv:2607.17256v1 Announce Type: cross
Abstract: Optical spectroscopy underpins material characterization, chemical sensing, and astronomy, but conventional instruments face a rigid trade-off between footprint, spectral range, and resolution. We demonstrate a content-adaptive spectrometer that overcomes this by co-designing dispersive Moir\'e meta-optics with a recursive sampling algorithm. Instead of using Moir\'e metalenses solely for varifocal tuning, we harness the strong chromatic aberration arising from phase-wrapping in their subwavelength metasurface architecture. This hyperchromaticity enables a deterministic, one-to-one mapping between the metasurfaces' mutual rotation angle and the sharply focused wavelength, repurposing the pair as a high-resolution spectral scanner. To accelerate data acquisition, we introduce a content-adaptive recursive sampling protocol that exploits the structural sparsity of physical spectra: a fast coarse sweep identifies high-information regions, followed by successively finer angular refinement only where needed. Using a laboratory prototype spanning 405-980 nm, we reconstruct diverse spectra -- from smooth broadband to sparse multi-line laser emissions -- with nearly 3x fewer measurements on average at matched fidelity (up to 7x for sparse line spectra), achieving 30 dB reconstruction 6.7x faster than conventional uniform sampling. This establishes a framework for intelligent, task-adaptive meta-optical sensors that tightly integrate physical dispersion with computational signal processing for real-time spectrometry.
arXiv:2607.16325v1 Announce Type: new
Abstract: Foundation models provide powerful representations for brain MRI analysis, but their predictions remain difficult to interpret in anatomically meaningful terms. Clinical assessment of brain MRI is commonly organized around anatomically defined structures and regional abnormalities, whereas conventional explanation methods typically produce voxel- or patch-level importance maps that do not explicitly quantify the contributions of individual brain regions. To address this mismatch, we propose RegionFM, an interpretable framework that integrates anatomical segmentation with brain MRI foundation-model embeddings. RegionFM first divides each MRI scan into anatomical regions and constructs a separate MRI volume for each region. A frozen foundation model then encodes each region into an embedding, and a region-additive logistic model combines these embeddings such that every anatomical region contributes an explicit scalar term to the final prediction. This formulation supports both subject-level and cohort-level analyses of regional contributions. We evaluate RegionFM on cognitive-impairment classification using embeddings from multiple pretrained brain MRI foundation models. The results show that RegionFM maintains performance comparable to less interpretable fine-tuning approaches while providing anatomically grounded explanations. Randomized embedding ablations yield near-chance performance, indicating that the predictions rely on meaningful structure captured by the foundation-model embeddings rather than simple feature statistics. Overall, RegionFM better aligns model explanations with anatomy-based clinical reasoning while maintaining competitive predictive performance.
arXiv:2607.17260v1 Announce Type: cross
Abstract: We consider the uniform exponential stability analysis of infinite-dimensional impulsive systems defined on a Banach or Hilbert space, whose flow is governed by a fixed $C_0$-semigroup generator and whose jumps occur at a prescribed time sequence. While the flow and jump maps are themselves time-invariant, the time-triggered impulses render the propagator a genuinely time-varying evolution family, which is the source of the analysis difficulty addressed here. We combine ideas from hybrid systems theory and infinite-dimensional systems to produce operator-based stability conditions, which can be analytically or numerically checked via convex programming. Necessary and sufficient conditions for the uniform exponential stability of impulsive systems on Banach spaces are obtained in the context of a fixed impulse-times sequence but also of arbitrary, constant, minimum, and range dwell-times using both non-coercive and coercive Lyapunov functionals. Some of those results are then adapted to systems on a Hilbert space and quadratic Lyapunov functionals. As an application, linear switched systems are shown to be an exact special case: reformulated as impulsive systems with unit-norm selector jumps, they inherit non-coercive and clock-dependent dwell-time stability conditions on both Banach and Hilbert spaces. Theoretical and numerical examples are given for illustration, notably on the sampled-data control of time-delay systems.
arXiv:2607.16959v1 Announce Type: new
Abstract: Blockchain platforms have grown into an ecosystem of independent networks, and a growing class of applications now requires smart contracts on separate chains to act as one. Such operations must be atomic, yet immutability makes this fundamentally harder: a confirmed transaction cannot be reversed, so the rollback on which classical atomic commitment protocols depend is unavailable. Two challenges follow. Contract state must be held across an operation whose outcome is not yet known, and each chain's execution outcome must be established even though no chain can observe another. In response, we introduce a framework that achieves atomicity through forward-only correction, resolving incomplete operations with new on-chain transactions rather than reversal. The framework bounds how long contract state is held and confines contention to the state an operation touches, and it establishes outcomes from an on-chain record of what each chain executed, without relying on any single coordinating party. This work lays the foundation for atomic coordination of general smart contract operations across heterogeneous blockchains.
arXiv:2607.17698v1 Announce Type: new
Abstract: Optical phased arrays (OPAs) are key components for solid-state beam steering in emerging photonic technologies such as LiDAR, optical communication, and adaptive optics. However, conventional integrated OPA designs face trade-offs between bandwidth, steering range, and fabrication complexity. Here we designed and numerically analyzed a novel three-dimensional end-firing antenna array compatible with fabrication using two-photon polymerization (2PP) directly on a thin-film lithium niobate (TFLN) platform. By elevating the polymer antennas above the chip surface, the design enables two-dimensional beam steering while maintaining the broadband advantages of end-fire emission. Full-wave electromagnetic simulations demonstrate transmission efficiencies up to 89.5\% over the \SIrange{1.4}{1.6}{\micro\meter} wavelength range, achieving a field of view of \ang{24.9} $\times$ \ang{22.8} with beamwidths of approximately \ang{1.7}. The architecture's compatibility with electro-optic phase control and advanced array configurations suggests significant potential for high-speed, low-loss beam steering systems. This work establishes a foundation for scalable 3D photonic phased arrays that bridge integrated optics with free-space beam manipulation.
arXiv:2607.17321v1 Announce Type: cross
Abstract: We formulate a loss-tolerant extension of entanglement-assisted long-baseline optical interferometry in which the astronomical optical coherence is first mapped coherently to distributed quantum memories and is subsequently protected by local scrambling encoders. The proposal must be distinguished from existing memory-assisted Gottesman--Jennewein--Croke (GJC) interferometers, in which quantum memories store an ancillary single-photon-entangled reference rather than the astronomical state itself. We derive the weak-thermal-light model, its two-parameter quantum Fisher information (QFI) matrix, the GJC measurement probabilities, and the associated classical Fisher information (CFI). We then prove that exact local correction of flagged erasures restores the complete complex visibility, its QFI matrix, and the operational GJC CFI. The relevant protection criterion is reference--environment decoupling, not volume-law entanglement alone. We state, as conjectures, quantitative decoupling bounds for local random encoders and finite-depth scramblers, and derive the expected threshold of fewer than one half of the physical memories erased per node. Finally, we formulate the phase-covariance and superselection-rule constraints required for a physically meaningful distributed protocol.
arXiv:2607.16961v1 Announce Type: new
Abstract: Existing tool-use benchmarks report a single success rate for complex, multistep tasks. Inspired by ideas from cognitive science, we distinguish tool use from tool discovery and decompose the latter into curiosity (the model's ability to discover the parts needed to build the tool), recognition (the model's ability to discover the process of creating the tool), and efficiency (the model's use of the tool after creation). We show that this framework can be applied to existing discovery tasks, such as Voyager. In addition, we provide evidence that recognition inversely scales with model size, and we introduce and analyze a class of combinatorial games that demonstrates this. We further observe inverse scaling in a separate environment designed to emulate real-world tasks.
arXiv:2607.17700v1 Announce Type: new
Abstract: Threshold, aggregate, and multi-signatures -- which we collectively call quorum signatures -- certify that a quorum of nodes endorsed a statement, with a certificate as small as a single signature. No constant-size post-quantum quorum signature is known: all candidates grow with the number of signers and are slow to aggregate, making quorum signatures the hardest obstacle to migrating byzantine fault-tolerant systems to post-quantum security.
In this paper, we sidestep this open cryptographic problem by changing how the protocol communicates. We introduce a primitive we call Distributed Quorum Signature (DQS), built solely from ordinary digital signatures and a Bracha-style approval broadcast. DQS turns certificates from network messages into local events. Two event types divide the roles certificates play: weak certificates capture safety, strong certificates capture liveness. In DQS every message is constant size, fitting a single datagram regardless of the number of nodes. The total communication is quadratic, and no security assumptions change. In a large distributed system, the overhead of post-quantum DQS is competitive with the canonical pre-quantum BLS scheme.
arXiv:2607.18043v1 Announce Type: new
Abstract: Accurately solving partial differential equations (PDEs) on arbitrary geometries and a variety of meshes is an important task in science and engineering applications. In this paper, we propose Adaptive Mamba Neural Operators (AMO), which integrates reproducing kernels for state-space models (SSMs) rather than the kernel integral formulation of SSMs. This is achieved by constructing Takenaka-Malmquist systems for the PDEs. AMO offers new representations that align well with the adaptive Fourier decomposition (AFD) theory and can approximate the solution manifold of PDEs on a wide range of geometries and meshes. In several challenging benchmark PDE problems in the fields of fluid physics, solid physics, and finance on point clouds, structured meshes, regular grids, and irregular domains, AMO consistently outperforms state-of-the-art solvers in terms of relative $L^2$ error. Overall, this work presents a new paradigm for designing explainable neural operator frameworks.
arXiv:2607.16253v1 Announce Type: new
Abstract: Machine learning-based Type 2 diabetes risk prediction models obtain good internal validation results but lose effectiveness in real-world applications due to deficient external testing and fairness assessment. We developed a multi-dimensional framework evaluating discrimination, calibration, interpretability, and algorithmic fairness on nationally representative populations. An XGBoost model was trained on NHANES 2015-2020 (n=15,685) using eight non-laboratory predictors: age, sex, race/ethnicity, BMI, smoking status, physical activity, history of heart attack, and history of stroke. External validation was performed on BRFSS 2020-2022 (n=1,285,783) under realistic distribution shift. Internal validation showed good discrimination (AUC=0.794, 95% CI 0.788-0.800), with performance loss on external validation (AUC=0.717, relative decrease: -9.7%, p<0.001). Fairness analysis revealed severe bias: elderly adults (>=60) showed AUC=0.607 vs 0.742 for young adults (difference=0.135, p<0.001); obese individuals showed AUC=0.698 vs 0.735 for normal weight (difference=0.037, p<0.001). Gender showed comparable performance (male=0.723 vs female=0.712, p=0.142). Calibration revealed risk overestimation (Brier score=0.123). SHAP analysis identified age, BMI, and physical activity as primary risk drivers. Populations with highest diabetes risk receive the worst algorithmic performance, underscoring the need for fairness-aware, age-stratified deployment strategies before clinical use.
arXiv:2607.16326v1 Announce Type: new
Abstract: Large Vision-Language Models (LVLMs) typically require processing hundreds to thousands of visual tokens, leading to substantial inference overhead. Existing visual token pruning methods either operate before the LLM using text-agnostic heuristics or prune inside the LLM at the cost of efficiency and noisy cross-modal attention. To address these limitations, we propose CRISP, a pre-LLM yet text-driven visual token pruning framework that preserves both instruction-relevant evidence and essential scene context. CRISP works in a two-stage pipeline: Stage 1 first identifies text-aligned visual tokens, and Stage 2 enhances contextual completeness through semantic diversity. Extensive experiments on LLaVA-1.5 and LLaVA-NeXT demonstrate that CRISP achieves superior performance retention under aggressive pruning ratios, maintaining up to 99.5% accuracy while reducing inference cost and latency by more than 2 times. CRISP serves as a practical solution for efficient LVLM inference, especially in resource-constrained scenarios.
arXiv:2607.16648v1 Announce Type: new
Abstract: Large Language Models (LLMs) have created an urgent need for reliable watermarking methods that enable attribution of generated text while remaining robust to editing and paraphrasing. We propose a novel synchronization-free watermarking scheme in which every watermark consists of a single binary congruence generated from a pair of neighbouring tokens. For each token pair, a cryptographic hash determines an evaluation point of a Reed--Solomon polynomial representing the secret identity, while the parity of the polynomial evaluation determines the watermark bit embedded into the second token of the pair. Since each congruence is self-contained and depends only on the local token pair, the proposed construction is naturally resistant to insertions, deletions, and token reordering. We analyse the recovery problem from an algebraic perspective, discuss several decoding algorithms suitable for different identity sizes, and model watermark corruption as a Binary Symmetric Channel. The analysis shows that reliable recovery requires only a small redundancy even for relatively high token corruption rates. Unlike existing block-based watermarking schemes, the proposed method avoids synchronization problems while providing a flexible framework for embedding both short and long secret identities.