arXiv:2607.12234v1 Announce Type: new
Abstract: Current analog complexity theory, built on the General-Purpose Analog Computer (GPAC) model and polynomial ODEs, allows unbounded state variables -- an assumption that is physically unrealistic for chemical reaction networks and other laboratory-scale analog computers. We develop a bounded analog complexity theory in which all state variables remain in compact intervals and physical time (wall-clock time) is the only diverging resource.
Our main technical contribution is bounded surrogate compilation, a compilation framework that transforms unbounded polynomial ODE systems into bounded ones while preserving computational limits and time-to-precision guarantees. We prove that if a system is compiled into a bounded system through our algorithm, the wall-clock time of the compiled system is polynomial in the arc length and physical time of the original system.
We exhibit concrete constructions demonstrating fine-grained bounded time complexity -- a tunable polynomial-degree family, a Lambert-$W$-based system achieving $\Theta(r\log r)$ time-to-precision (where $r$ is the desired precision parameter, in nats: $|x(t)-\alpha|<e^{-r}$), and an iterated-logarithm tower realizing arbitrarily high complexity classes -- all for the task of computing the constant 1. We show that bounded GPACs are closed under exponentiation ($\alpha^\beta$) with time complexity equal to the harder input, and that the full GPAC-to-CRN compilation pipeline preserves time complexity class via a low-pass filter analysis of readout modules.
Science Journals
arXiv:2607.12958v1 Announce Type: new
Abstract: Digital objects express emotions through different modalities. For example, a movie may include visual scenes, audio, dialogue, and facial expressions, while a song may contain melody, rhythm, lyrics, and vocal tone. Because existing emotion recognition models are usually modality-specific, it is difficult to compare such objects directly. This paper proposes CD-MED, a Cross-Domain Multimodal Emotion Descriptor for representing heterogeneous digital objects in a common emotional space. Each modality can be processed by its own emotion recognition model, and the resulting emotional outputs are transformed into a shared descriptor. The descriptor preserves information from individual modalities while also allowing an integrated emotional profile of the object. For interpretation, CD-MED is visualized in the valence-arousal space: position represents affective coordinates, color denotes emotion category, size indicates intensity, and shape shows the modality. This unified representation enables emotion-based comparison, retrieval, recommendation, and visualization across different domains such as movies, songs, images, and books.
arXiv:2607.12242v1 Announce Type: new
Abstract: We introduce a Jordan-canonical-form framework for constructing $q$-ary quantum stabilizer codes from arbitrary classical linear codes over $\F_{q^2}$. The framework does not require the classical linear code $\mathcal{C}$ to satisfy the dual-containing condition (i.e., self-orthogonality). Given a classical code $\mathcal{C}=[n,k,d]_{q^2}$ with parity-check matrix $H$, we measure the obstruction to Hermitian self-orthogonality by the rank $r=(n-k)-\dim_{\F_{q^2}}(\mathcal{C}^{\perp_h}\cap \mathcal{C})$. The ingredient code $\mathcal{C}$ is $r$-nearly dual containing, or, equivalently, $\mathcal{C}^{\perp_h}$ is $r$-nearly self-orthogonal, by which we mean that $r=\Rank(HH^{\dagger})=\dim_{\F_{q^2}}(\mathcal{C}^{\perp_h})-\dim_{\F_{q^2}}(\mathcal{C}^{\perp_h}\cap \mathcal{C})$. By systematically reducing the rank of the Hermitian inner-product matrix $A=HH^{\dagger}$ through rank-one perturbations along the Jordan basis $W=P^{-1}$ of the decomposition $A=PJ_AP^{-1}$, we construct an explicit Hermitian self-orthogonal code $\mathcal{C}_{\mathrm{so}}=[n+r,n-k]_{q^2}$. A sufficient distance-preservation criterion guarantees that the resulting $q$-ary quantum code has parameters $[[n+r,2k-n+r,\geq d]]_q$. Applying this construction to classical codes produces several record quantum codes that improve or supplement the best-known parameters in Grassl's tables.
arXiv:2607.12244v1 Announce Type: new
Abstract: Memory inference remains a significant challenge in turnkey ASIC design flows. Inferring flip-flops from RTL can create thousands of densely interconnected instances which dramatically slow down design flows and impede performance. Memory compilers address this issue, although they are third-party tools which are often PDK-specific and may require specialized cells not in the base PDK.
To address these shortcomings, we present ORRAM, a standard-cell-based memory generator built as a native module within OpenROAD. Given a standard cell library, ORRAM produces a fully placed and routed RAM block requiring no custom bitcells or external tooling, with timing verification via OpenSTA rather than SPICE simulation. ORRAM supports arbitrary word sizes, word counts, mask granularities, multi-port read configurations, column muxing, latch-based storage, and automatic PDK-agnostic cell selection, making it compatible with most standard cell libraries including sky130hd and NanGate45. Evaluated on SkyWater 130nm, ORRAM matches the bit density of historical DFFRAM results while offering a significantly expanded feature set. The source code is available as part of the OpenROAD project.
arXiv:2607.12318v1 Announce Type: cross
Abstract: Interior-point methods (IPMs) are widely adopted due to their high practical efficiency in solving linear, convex, and nonconvex optimization problems. For convex optimization, this performance is theoretically well-supported: there are strong complexity guarantees for self-concordant barrier setups \cite{nesterov1994interior}, which cover linear and conic optimization. On the other hand, unconstrained convex optimization is well-studied. However, there is limited analysis of constrained convex optimization methods without the self-concordance assumption. We develop and analyze a regularized Newton method with line search applied to the log barrier function in the setting that the objective and constraints are thrice differentiable and have Lipschitz continuous first and second derivatives. Starting from a strictly feasible point, our method finds an $\epsilon$-approximately optimal solution in $\tilde{O}(\epsilon^{-2/3})$ iterations.
arXiv:2601.10609v5 Announce Type: replace
Abstract: Addressing itinerary modification is crucial for enhancing the travel experience as it is a frequent requirement during traveling. However, existing research mainly focuses on fixed itinerary planning, leaving modification underexplored due to the scarcity of need-to-modify itinerary data. To bridge this gap, we formally define the itinerary modification task and propose a general pipeline to construct the corresponding dataset, namely iTIMO. This pipeline frames the generation of need-to-modify itinerary data as an intent-driven perturbation task. It instructs large language models to perturb real-world itineraries using three operations: REPLACE, ADD, and DELETE. Each perturbation is grounded in three intents: disruptions of popularity, spatial distance, and category diversity. Furthermore, hybrid evaluation metrics are introduced to ensure perturbation effectiveness. We conduct comprehensive benchmarking on iTIMO to analyze the capabilities and limitations of state-of-the-art LLMs. Overall, iTIMO provides a comprehensive testbed for the modification task, and empowers the evolution of traditional travel recommender systems into adaptive frameworks capable of handling dynamic travel needs. Dataset, code and supplementary materials are available at https://github.com/zelo2/iTIMO.
arXiv:2601.14776v3 Announce Type: replace
Abstract: Recent advances in multi-modal detection have significantly improved detection accuracy in challenging environments (e.g., low light, overexposure). By integrating RGB with modalities such as thermal and depth, multi-modal fusion increases data redundancy and system robustness. However, significant challenges remain in effectively extracting task-relevant information both within and across modalities, as well as in achieving precise cross-modal alignment. While CNNs excel at feature extraction, they are limited by constrained receptive fields, strong inductive biases, and difficulty in capturing long-range dependencies. Transformer-based models offer global context but suffer from quadratic computational complexity and are confined to pairwise correlation modeling. Mamba and other State Space Models (SSMs), on the other hand, are hindered by their sequential scanning mechanism, which flattens 2D spatial structures into 1D sequences, disrupting topological relationships and limiting the modeling of complex higher-order dependencies. To address these issues, we propose a multi-modal perception network based on hypergraph theory called M2I2HA. Our architecture includes an Intra-Hypergraph Enhancement module to capture global many-to-many high-order relationships within each modality, and an Inter-Hypergraph Fusion module to align, enhance, and fuse cross-modal features by bridging configuration and spatial gaps between data sources. We further introduce a M2-FullPAD module to enable adaptive multi-level fusion of multi-modal enhanced features within the network, meanwhile enhancing data distribution and flow across the architecture. Extensive object detection experiments on multiple public datasets against baselines demonstrate that M2I2HA achieves state-of-the-art performance in multi-modal object detection tasks.
arXiv:2607.13008v1 Announce Type: new
Abstract: In quantum information systems made of optical tweezer arrays of ultracold molecules, thermal motion of molecules degrades the coherence of their interactions, which limits entanglement fidelity and the concomitant scientific applicability of these systems. We show that by controlling the geometry of the dipolar interaction, even when a molecule occupies many motional states in the tweezer, coherence can be preserved. We characterize several geometries that suppress sensitivity to thermal fluctuations. We further use programmable, coherence-preserving motion of the molecules during entanglement to refocus dephasing from relative positional jitter of the tweezers, which is relevant even on the 10 nm scale. These methods yield substantially improved dipolar coherence and enable generation of two-molecule entanglement with a Bell state fidelity of $\mathcal{F}= 0.976^{+0.008}_{-0.011}$ in directly laser-cooled molecules.
arXiv:2607.13015v1 Announce Type: new
Abstract: The stable marriage problem appears in many privacy-sensitive domains, for example in the National Resident Matching Program in the US. In such applications, preserving the privacy of users' preference lists is essential to prevent strategic manipulation, discourage misreporting, and comply with data protection regulations.
In this work, we investigate privacy attacks on stable marriage algorithms. Assuming that the attacker (e.g., the hospitals) can repeatedly interact with the stable marriage algorithm, we demonstrate how such interactions can reveal private preferences of the non-malicious side (e.g., the residents). We show that the widely applied Gale-Shapley Matching Algorithm, where the proposers' side is malicious, is vulnerable to privacy attacks and all honest agents' preferences can be revealed. We further investigate which preference distributions of the honest, non-malicious side are susceptible to privacy attacks and show that the Gale-Shapley Matching Algorithm where the honest side proposes can preserve privacy in non-susceptible preference distributions. We extend our results to the decentralized setting and show that the attacker's side can infer all preference orderings. In an experimental evaluation, we test privacy attacks on synthetic and real-world data and show that real-world data is indeed susceptible to privacy attacks. This work underlines a need for new privacy-preserving stable marriage algorithms.
arXiv:2607.12336v1 Announce Type: new
Abstract: Artificial Intelligence (AI) technologies, while serving as a foundational enabler for modern social media and digital health services, exert a bivalent effect by simultaneously acting as a combatant against and a spread vector for misinformation. A prevalent challenge in mitigating this issue arises in non-English contexts and low socioeconomic classes, where limited data hinders the training of AI models for effective detection. Consequently, culturally and linguistically diverse (CALD) communities struggle to access trustworthy health information through AI-driven tools. Current AI tools underperform due to a lack of training data and are largely unable to consider language nuances and traditions in non-English contexts. This research addresses these gaps by proposing a CALD-friendly AI-based health misinformation detector and providing a dashboard for medical professionals to analyse this misinformation, a critical step toward mitigating a growing concern among CALD populations. To this end, we conduct a series of experiments using a Bangla-translated health misinformation dataset to evaluate the performance of various Small Language Models (SLMs). SLMs are particularly relevant in this context given the frequent underperformance of Large Language Models (LLMs), which often stems from insufficient domain-specific knowledge and the prohibitive costs of resource-intensive fine-tuning. The results demonstrate that Phi-4 is the superior model, achieving an ideal balance between precision and recall in claim extraction. Then, to mitigate the limitations of SLMs, we design and test a novel health misinformation detection framework grounded in Responsible Natural Language Processing (NLP), which incorporates cultural sensitivity, potential for harm, and communication quality, thereby providing a holistic lens for evaluating misinformation in low-resource languages.
arXiv:2607.13033v1 Announce Type: new
Abstract: Reinforcement learning holds great promise for improving robot policies beyond the limits of imitation learning. However, its practical adoption remains bottlenecked by the lack of reliable vision-language reward models that provide dense and informative feedback. Two key challenges remain: acquiring diverse failure data at scale and obtaining fine-grained reward signals beyond sparse trajectory-level success labels. Collecting failure trajectories typically requires laborious human effort, while pseudo-failures constructed by relabeling successful demonstrations fail to capture the diverse physical failure modes that arise during robot execution. Meanwhile, existing reward models often predict sparse binary or trajectory-level rewards, which provide limited guidance for efficient policy optimization. We introduce DenseReward, a dense robotic reward model that addresses both challenges. To train DenseReward, we develop an automated failure data generation pipeline that synthesizes physically realistic failure trajectories in simulation without human labeling, covering diverse failure modes such as collisions, missed grasps, object drops, and recovery behaviors. DenseReward predicts dense frame-level reward scores from visual observations and language instructions, enabling fine-grained estimation of task progress throughout an episode. Experiments show that DenseReward outperforms general-purpose VLMs and existing robotic reward models in dense reward prediction across both simulated and real-world manipulation. We further demonstrate that DenseReward provides effective reward guidance for downstream model predictive control and reinforcement learning. We release the dataset, trained reward models, and evaluation suite to support the development of failure-aware dense reward modeling for robot learning.
arXiv:2601.17434v2 Announce Type: replace
Abstract: Artificial intelligence (AI) and large language models (LLMs) are reshaping education, with virtual avatars emerging as digital teachers capable of enhancing engagement, sustaining attention, and addressing instructor shortages. Aligned with the Sustainable Development Goals (SDGs) for equitable quality education, these technologies hold promise yet lack clear guidelines for effective design and implementation in online learning. To fill this gap, we introduce a framework specifying when, what, and how digital teachers should be integrated. Our study combines (1) a design space analysis of 87 works across AI, educational technology, design, and HCI, (2) a survey of 132 learners' practices and preferences, and (3) three co-design workshops with 18 experts from pedagogy, design, and AI. It provides actionable guidance for educators, designers, and HCI researchers, advancing opportunities to build more engaging, equitable, and effective online learning environments powered by digital teachers.
arXiv:2607.12282v1 Announce Type: new
Abstract: Recent work has developed many techniques for formally verifying probabilistic programs. However, existing verification frameworks for probabilistic programs are restricted to idealized languages designed for verification. As a result, they cannot be used to verify off-the-shelf probabilistic programs written in standard languages. In contrast, for non-probabilistic programs, a number of verification tools now support verifying realistic code written in widely used languages such as Go, C, and Rust. To verify probabilistic programs written in these languages, it would be useful to be able to reuse, as much as possible, the extensive development work that has gone into such tools.
This paper presents Alerus, a framework for verifying probabilistic Rust programs. Alerus is based on Verus, a verification tool for Rust that supports SMT-based automation and separation-logic-inspired reasoning features. Alerus extends Verus with support for probabilistic reasoning while retaining these expressive features. To do so, Alerus uses a lightweight encoding of probabilistic error credits, a form of ghost state for randomized reasoning introduced in the Eris program logic. By deriving an appropriate specification using error credits, Alerus supports verifying the correctness of randomized sampling algorithms. We use this technique to verify several sampling routines for discrete distributions, including samplers for the discrete Gaussian distributions, the alias method, and the fast loaded dice roller.
We establish the soundness of our error credit extension by adapting VerusBelt, a recently developed logical relations model of Verus that encodes its features in terms of the Iris separation logic. To do so, we replace the use of Iris's standard weakest precondition in this model with Eris's probabilistic weakest precondition instead. The resulting soundness proof is fully mechanized in Rocq.
arXiv:2607.12295v1 Announce Type: new
Abstract: The rapid integration of artificial intelligence (AI) and generative AI (GenAI) into education presents significant opportunities to enhance teaching and learning, while raising ethical concerns about the responsible use of these technologies in educational settings. Understanding how the public perceives and debates these issues is increasingly important for educators, institutions, and policymakers seeking to integrate AI responsibly and equitably. Social media platforms, where such debates unfold frequently and at scale, offer a valuable lens for capturing large-scale, real-time public reactions to key developments as they emerge. In this study, we analyse five years (2019-2024) of discourse on Twitter (now X) to trace the evolving public conversation around AI ethics in education, paying particular attention to the release of ChatGPT as a pivotal moment that reshaped the nature and tone of that discourse. Using BERT-based topic modelling and SetFit sentiment analysis to identify dominant themes and track sentiment over time, we find that the discourse has been predominantly positive across the observation period, with negative sentiment concentrated around specific ethical controversies. More recently, anxieties about academic integrity and the broader implications of generative AI have come to dominate the conversation. Rather than reflecting a polarized debate, public discourse appears pragmatic and largely receptive to AI integration, though accompanied by growing calls for ethical oversight and institutional accountability. By providing a longitudinal account of public sentiment surrounding AI ethics in education, this study informs educators, institutions, and policymakers an empirically grounded understanding of public expectations, informing the development of responsible, transparent, and equitable approaches to AI integration across educational contexts.
arXiv:2607.12296v1 Announce Type: new
Abstract: With the increased use of generative AI (GenAI) applications such as ChatGPT, higher education institutions (HEIs) have released a range of guidelines and policies to direct adoption within their institutions. In computer science (CS) courses GenAI adoption is especially high and the implications for student learning are significant. At the same time, instructors have also been forced to address the use of GenAI as students have started to use it for a range of functions. Currently, comparative analysis of guidance provided by institutions and its uptake in instruction is lacking. In this paper we bridge this gap by comparing institutional and computing course level guidance to better understand this terrain. We utilize secondary analysis of institutional and course syllabi guidelines from higher education institutions in the U.S. classified as research-intensive. Our findings reveal that although institutional guidance is more pro-use, at the course-level the uptake is still guarded. We discuss the implications and propose an instructor-centered framework to guide future adoption of GenAI.
arXiv:2607.12297v1 Announce Type: new
Abstract: The recent large video foundation model, SAM2, enables segment anything in both images and videos, serving as a powerful base model for various applications. However, many of such use cases require to operate on resource-constrained devices like mobile phones and laptops. In this work, we aim to make SAM2 more mobile-friendly by distilling the heavyweight SAM2 into a lightweight model, facilitating segment anything in both images and videos on mobile devices. To this end, we propose Hypergraphical Knowledge Distill (HyperKD), which introduces the idea of hypergraph into knowledge distillation, aiming to effectively model and transfer SAM2's generalizable and comprehensive knowledge. HyperKD consists of Temporal HyperKD and Granularity HyperKD that construct hypergraphs to explicitly model and extract the generalizable temporal knowledge and the comprehensive multi-granularity knowledge from SAM2 respectively, which are then distilled into the lightweight student model by aligning it with the constructed hypergraphs. Besides, we present MobileSAM2, a new family of lightweight SAM2 that balances efficiency and effectiveness via searching the best model architectures with HyperKD during model size reduction. Extensive experiments validate MobileSAM2 across multiple benchmarks and show promising generalization performance on embodied AI tasks.
arXiv:2607.13003v1 Announce Type: new
Abstract: A watermark in a generative model's output is usually asked only whether a text is machine-made. The same mark can do more: attribute it to the user who produced it, extract a hidden payload, or localize the part that survives editing. These form a forensic ladder, and we ask what each rung costs in the sample length $n$.
One object organizes the answers. Let $S$ be the secret the mark carries (a user's identity or payload), and let the information profile $\nu(t)=I(S;X_t\mid X_{<t})$ record how much the $t$-th token reveals about $S$ given the earlier ones. Its total mass pays for attribution and extraction; how that mass is spread pays for localization; and detection alone is paid for not by information but by presence, the distance from the marked to the unmarked distribution. The literature's two quality models, a mark subtle on every token and one that stamps a few tokens loudly, are two incomparable ways of capping this profile.
Our main theorem settles the ladder's entropy column. For statistically distortion-free schemes, attributing a text to one of $N$ users costs $\Theta(\log N/h)$ tokens over every stationary-ergodic source of entropy rate $h$, sharp to a $(1+o(1))$ factor: to our knowledge the first tight entropy-rate law for multi-user attribution (via exact alignment). The natural collision-counting analysis overcharges without bound; only a decoder thresholding each candidate by its own realized surprisal attains the rate while almost never implicating an innocent user. A matching converse makes the law two-sided, and extraction of an $\ell$-bit payload costs $\Theta(\ell/h)$. Two gaps are real, not modeling artifacts: a $\Theta(\log N)$-token window in which a text is provably machine-made yet unattributable, and a footprint-resolution uncertainty principle. Experiments on GPT-2, Pythia-410M, and Qwen2.5 recover the predicted constants.
arXiv:2604.26052v4 Announce Type: replace
Abstract: Safety evaluations of large language models (LLMs) typically report binary outcomes, i.e. attack success rate (ASR), refusal rate, or harmful versus safe classification, which hide how risk changes between prompt and response. We present a paired analysis over human labeled prompt and response records across four harm categories (Sexual, Self harm, Hate and Violence) and ordinal severity levels (Safe, Low, Medium, High). 61% of responses reduce harm relative to the prompt, 36% preserve severity, and 3% escalate. The escalation splits into two mechanisms: benign prompts triggering unrequested harmful detail, and answers that stay on task at higher severity than the prompt. Category decomposition shows that Sexual content exhibits the highest harm persistence in this sample, driven by compliance at the same severity rather than drift from benign inputs. Joint relevance analysis exposes a helpfulness versus harmlessness tradeoff: compliance escalations remain highly relevant, whereas safe responses include generic refusals with low relevance. A public supporting evaluation over 600 prompts and six models reproduces the framework's measurements and two directional signals, while few-shot LLM graders exhibit a prompt/response detection asymmetry that data calibration does not close. Grader prompts, public-evaluation artifacts, and analysis code are shared at https://github.com/microsoft/PairedSafety.
Improved SINR Approximation for Downlink RSMA-based Networks with Outdated Channel State Information
arXiv:2508.09020v3 Announce Type: replace-cross
Abstract: Understanding the performance of multi-user multiple-input multiple-output (MU-MIMO) systems under imperfect channel state information at the transmitter (CSIT) remains a critical challenge in next-generation wireless networks. In this context, accurate statistical modeling of the signal-to-interference-plus-noise ratio (SINR) is essential for enabling tractable performance analysis of multi-user systems. This paper presents an improved statistical approximation of the SINR for downlink (DL) MU-MIMO systems with imperfect CSIT. The proposed model retains the analytical simplicity of existing approaches (e.g., Gamma-based approximations) while overcoming their limitations, particularly the underestimation of SINR variance. We evaluate the proposed approximation in the context of Rate-Splitting Multiple Access (RSMA)-enabled MIMO DL systems with outdated CSIT. The results demonstrate excellent accuracy across a wide range of system configurations, including varying numbers of users, antennas, and degrees of CSIT staleness.
arXiv:2607.13007v1 Announce Type: new
Abstract: Simulation-based algorithms are especially suited for high-uncertainty environments such as adversarial board games with significant elements of randomness and hidden information. In particular, several Monte Carlo Tree Search (MCTS) variants are commonly used in such domains. In this paper, we propose a series of enhancements for Ensemble Determinization MCTS, introducing two axes for dynamic resource allocation. First, Dynamic Number of Determinizations, increases or decreases the number of currently used determinization trees depending on the behavior of so-far search. Second, Dynamic Simulation Allocation, splits the simulation budget nonuniformly across the determinization trees, using simulation-to-simulation decisions to choose the tree with potentially the best knowledge gain. As benchmark domains, we used three popular tabletop games: Jaipur, Lost Cities, and Splendor. Testing our proposed enhancements in iteration- and time-based settings showed that particular configurations yield a statistically significant increase in the algorithm's strength.
arXiv:2607.12352v1 Announce Type: new
Abstract: Filtering noise is a fundamental part of data preparation that enhances image quality for applications such as object segmentation, detection, and recognition. Various noise reduction techniques are proposed in the literature, including the use of median, Gaussian, and bilateral filters. Convolutional neural networks (CNNs) have gained popularity in image denoising owing to their ability to extract complex patterns and features from data. CNNs are highly adaptable, making them effective tools for various image-denoising tasks. One drawback of CNN-based techniques is that they require an appropriate training dataset and all images to be resized. Another notable drawback of all these filtering techniques is that they work for certain types of environmental and camera noises. To bridge this research gap, in this paper, for the first time, instead of denoising, we propose an approach that filters out poor-quality images for various environmental and camera impacts. In our approach, quality is assessed using an image quality assessment metric and an optimum threshold is used to filter out poor-quality images. We also ensure that a sufficient number of images remain to develop the deep learning (DL) model. The results produced using real and simulated traffic and object recognition data demonstrate the performance supremacy of the proposed approach compared with the state-of-the-art approaches. The average recognition accuracy for our proposed approach is 93.8% for the traffic sign recognition dataset and 84.9% for the object recognition dataset. This indicates our model's potential for real-life applications such as autonomous vehicles.
arXiv:2607.12419v1 Announce Type: new
Abstract: In autonomous driving perception, the fusion of LiDAR and camera modalities has become the dominant paradigm for 3D object detection. However, current multi-modal frameworks heavily rely on massive visual backbones pretrained on 2D semantic tasks. This reliance introduces substantial parameter redundancy and a structural misalignment, as 2D priors are ill-equipped to handle the extreme sparsity of LiDAR projections required for Bird's-Eye-View geometry. To address this, we present DeGuNet, an ultra-compact and plug-and-play image backbone explicitly designed for depth-guided representation learning. By incorporating sparsity-aware feature extraction mechanisms, DeGuNet effectively aligns multi-view images with unstructured LiDAR depth while strictly preventing invalid-region contamination. Extensive experiments on the nuScenes dataset demonstrate DeGuNet's broad plug-and-play applicability and superior efficiency. When integrated into established baselines, it fundamentally eliminates architectural redundancy, reducing GPU memory consumption by up to 66.5% and achieving a 1.16x inference speedup. Concurrently, DeGuNet delivers up to a 6.20 absolute mAP gain, establishing a new paradigm for parameter-efficient multi-modal 3D perception.
arXiv:2604.04241v2 Announce Type: replace
Abstract: Risk scoring systems are widely used in high-stakes domains to assist decision-making. However, existing approaches often focus on optimizing predictive accuracy or likelihood-based criteria, which may not align with the main goal of maximizing utility. In this paper, we propose a novel risk scoring system that directly optimizes net benefit over a range of decision thresholds. The model is formulated as a sparse integer linear programming problem which enables the construction of a transparent scoring system with integer coefficients, and hence, facilitates interpretation and practical application. We also establish fundamental relationships among net benefit, discrimination, and calibration. Our analysis proves that optimizing net benefit also guarantees conventional performance measures. We evaluated our method on multiple public datasets as well as on a large-scale credit risk dataset. This computational study demonstrated that our interpretable method can effectively achieve high net benefit while maintaining competitive discrimination and calibration performance.
arXiv:2607.12364v1 Announce Type: new
Abstract: EEG-to-image evaluation should distinguish visual fidelity from recoverable meaning. Yet EEG-derived reconstructions are blurry, distorted, and low-detail, causing SSIM, LPIPS, and CLIP to penalize semantically recoverable outputs or reward plausible but incorrect ones. We analyze 6,855 ground-truth/reconstruction pairs from ATM, ENIGMA, BrainVis, and DreamDiffusion using semantic probes, caption harshness and blind-spot rates, and controlled degradations. Pixel metrics show near-zero correlation with semantic consistency, while representation metrics conflate perceptual and semantic errors. We therefore introduce a BCI-aware framework in which four VLMs assess image pairs through structured questions, producing Tolerant Perceptual Alignment Scores (T-PAS) and Tolerant Semantic Alignment Scores (T-SAS). Their consensus is distilled into the BCI-Coherence Score (BCS), a compact evaluator achieving a T-PAS MAE of 0.079 (r = 0.700) and a T-SAS MAE of 0.082 (r = 0.850) on our data. Human validation shows highly reliable joint coherence judgments, with Cohen's kappa = 0.882 +/- 0.174 and Krippendorff's alpha = 0.882, supporting perceptual-semantic recoverability over generic visual similarity. Code and resources are available at https://sukt03.github.io/BCS/.
arXiv:2607.12421v1 Announce Type: new
Abstract: In $k$-clustering problems, we are given a metric space $(\mathcal{C}, d)$, and must choose a set $S$ of $k$ centers to open. Each client $j \in \mathcal{C}$ incurs an assignment cost, which is the distance between $j$ and center in $S$ that it has been assigned to. In this work, we study the \emph{minimum-norm $k$-clustering problem}, where we are given an arbitrary monotone symmetric norm $f$, and wish to open $k$ centers so as to minimize $f$(assignment-cost vector). This is a powerful generalization, encompassing many classical $k$-clustering problems including the $k$-median, $k$-means, and $k$-center problems.
A simple and efficient algorithmic idea is that of \emph{adaptive sampling}, wherein we randomly choose the location of the next center to open with probability proportional to its ``cost" under the currently chosen set. While this has yielded fast algorithms for some $k$-clustering problem, little is known for settings \emph{without} ``min-sum" objectives.
We devise the first adaptive-sampling-based bicriteria constant-factor approximation algorithm for general minimum-norm $k$-clustering, vastly expanding the scope of problems handled by adaptive sampling. For the special case of $\text{Top}_\ell$ norms, which form a building block of monotone symmetric norms, we show that adaptive sampling yields an $O(\log k)$-approximation algorithm.