Information Theory · Cross-listed from physics.comp-ph
Accelerated S-NFC for Million-Chaff RCS Computation Using Low-Rank Compression of Concatenated Block Rows
Dong-Yeop Na, Somyeong Lee and Chung Hyun Lee
Sparsification via neglecting far-field coupling (S-NFC) enables fast full-wave radar-cross-section analysis of large-scale chaff clouds by retaining only significant local electromagnetic interactions. This letter further accelerates S-NFC by concatenating the retained off-diagonal interaction blocks associated with each receiving chaff element and applying a joint low-rank factorization with a shared receiving-side basis. Exact self interactions are preserved, while repeated chaff templates reuse precomputed lower–upper factorizations of the self-interaction blocks. The compressed formulation reduces retained-coupling storage and
matrix–vector multiplication cost and also decreases the number of iterations required by the generalized conjugate residual solver. Numerical tests with 100,000 chaff elements demonstrate sub-$1\%$ complex-far-field error for low-rank approximations in sparse regimes and identify a practical self-only limit at sufficiently large mean spacing. For a one-million-chaff plume, the proposed compressed S-NFC achieves a $6.92\times$ end-to-end speedup over uncompressed S-NFC while storing only $6.60\%$ of the retained coupling, with a complex-far-field error of $0.253\%$.
Read the full abstract ▾
Human-Computer Interaction
Graphionale: How Graph Visualizations of LLM Rationales Affect Human Decision Making
Xinru Wang, Zhexuan Ma, Ming Yin et al. (+2 more)
Large
Language Models (LLMs) are increasingly equipped with augmented
reasoning capabilities to generate rationales that support human decision-making. Yet these text-dense rationales often impose substantial cognitive burdens. Building on a formative co-design study that identified user preferences for non-linear
reasoning representations, we developed Graphionale as a testbed for empirically studying argument-map-style rationale visualization. This system transforms linear LLM rationales into interactive, multi-level graphs. It explicitly structures logical relationships (e.g., conclusions, premises, support, and objections), while further extracting entities and relations within each statement to construct condensed node-link representations. We conduct a large-scale online user study (N = 204) to examine when graphical rationales are more effective than textual ones, across varying task modality (verbal vs. visual
reasoning), rationale format (textual vs. graphical), and question difficulty (easy vs. hard). Our results show that graphical rationales do not help uniformly: they improve trust calibration for verbal
reasoning yet feel more cognitively demanding and less satisfying; for visual
reasoning, they impair calibration yet feel more engaging and helpful. In each modality, the format that better supports calibrated decisions is not the one users prefer, highlighting that matching rationale format to task modality is key to effective AI explanation design. Our findings contribute empirical design knowledge about when and how graphical rationales support human decision making, and inform the next-generation
reasoning-aware AI interfaces.
Read the full abstract ▾
All authors Xinru Wang, Zhexuan Ma, Ming Yin, Shuai Ma, Thomas W Malone
Machine Learning
TI$^2$PS: A Topology-Informed Inverse Design Framework for Stochastic Multicellular Pattern Formation
Kenji Komiya, Andrew Kailiang Jin, Ryo Nishikimi et al. (+1 more)
This study proposes a novel framework to estimate parameters for reproducing target multicellular patterns using an
agent-based model (ABM). Two major challenges in multicellular ABMs are estimating
cell-level parameters (
agent-specific variables) and quantitatively evaluating the topological characteristics of multicellular arrangements under
stochastic cell proliferation and death. To address these challenges, we integrate two approaches: Betti vectors and inverse surrogate modeling. The Betti vectors obtained through topological data analysis can consistently represent features of a wide range of multicellular spatial configurations. The inverse surrogate modeling enables direct inference of the corresponding ABM parameters from the target patterns. We validated the proposed framework using zebrafish pigment pattern formation, a representative model of pattern formation driven by multicellular interactions. The results demonstrate that our framework successfully estimates ABM parameters and outperforms conventional methods such as PointNet++. Notably, the proposed method, which used only 10% of the training data, outperformed PointNet++, which used 100% of the data, across all evaluation metrics.
Read the full abstract ▾
All authors Kenji Komiya, Andrew Kailiang Jin, Ryo Nishikimi, Kunio Kashino
Computer Vision
Training-Free Temporal Abstraction for General Video Understanding
Etienne Casanova, Sevan Brodjian and Pietro Perona
Videos are expensive to analyze frame by frame, yet many
video understanding tasks depend on knowing where relevant moments occur. A system may need to find when an action changes, locate the segment described by a sentence, or choose a few frames for a
vision-
language model. Existing methods often solve these problems separately, using task-specific training data or specialized architectures. We study whether a pretrained
video-text model can provide enough temporal structure to support several of these tasks at once. We present STITCH, a training-free method that divides a
video into semantically meaningful temporal chunks. STITCH embeds short
video windows with a frozen
video-text backbone and detects changes in the resulting
embedding sequence. These chunks are computed once per
video and reused across tasks. We evaluate STITCH on generic event boundary detection,
language-based moment
retrieval, and frame selection for long-
video VLM
reasoning. Across all three settings, STITCH remains competitive with more specialized methods while requiring no task-specific training, with especially clear gains when only a small number of frames or
tokens can be processed. These results suggest that reusable temporal abstraction is a promising direction for general
video understanding, allowing dense
video streams to be converted once into semantic units that can be localized, retrieved, sampled, or reasoned over by downstream systems.
Read the full abstract ▾
Cryptography and Security
GraftyVul: Synthesising Insecure Programs Through Real-World Vulnerability Grafting
Omri Ram, Mitchell Horner, Ron Van der Meyden et al. (+2 more)
Vulnerability
datasets underpin a wide range of security research, including vulnerability detection, automated remediation, and secure code generation. However, existing
datasets sacrifice at least one of three desirable properties: diversity (of
language or vulnerability type), reproducibility/executability, or realism. We therefore present GraftyVul, a system that constructs vulnerable programs by grafting real-world vulnerabilities into open-source projects. This grounds the
dataset in vulnerabilities observed in real-world contexts while harnessing known good build and test environments, enabling exploit-verification scripts to guarantee that an introduced vulnerability successfully alters a program's behaviour. Using GraftyVul, we generate 212 verified and exploitable vulnerable programs spanning five programming
languages (Python, TypeScript, Java, Go, and C#) across 23 CWE categories. To evaluate fidelity, we introduce a
language- and context-agnostic semantic
embedding that compares vulnerabilities by sink, mechanism and host-feature rather than surface code. This approach outperforms standard code
embeddings on cross-
language clone and CWE classification. These
embeddings demonstrate that GraftyVul samples retain a strong semantic signature to their source vulnerability. We additionally compare GraftyVul against 13 widely used
datasets, where it attains competitive diversity while being the only reproducible-exploit
dataset with broad
language and CWE coverage. Finally, we illustrate GraftyVul's practical utility through an industrial case study evaluating a production vulnerability remediation system.
Read the full abstract ▾
All authors Omri Ram, Mitchell Horner, Ron Van der Meyden, Alsharif Abuadbba, Hammond Pearce
Software Engineering
Antipatterns in AI-assisted Qualitative Data Analysis: A Catalog of Temptations and Pitfalls for Software Engineering Researchers
Rashina Hoda, Carolyn Seaman, Victoria Gomes et al. (+1 more)
AI-assisted qualitative data analysis (QDA) offers unprecedented opportunities to streamline software engineering (SE) research, yet uncritical use risks compromising analytical rigor and flooding the field with accelerated production of low-quality research. While tactical best practices will naturally evolve over time, SE researchers currently lack strategic guidance to identify and mitigate methodological risks when attempting AI-assisted QDA. Based on our decades of qualitative SE research expertise and experience combined with an understanding of the emerging landscape of AI-assisted QDA, this paper presents a catalog of antipatterns in AI-assisted QDA - a set of assumptions and practices that initially appear advantageous but ultimately undermine analytical rigor and validity. The antipatterns are grouped into three categories reflecting escalating impact: Dangerous Drivers, Operational Missteps, and Analytical Failures. As more SE researchers attempt AI-assisted QDA, these antipatterns will help them identify and avoid common temptations and pitfalls, while reviewers can be equipped with the vocabulary and criteria to call out problematic and failed practice. Ultimately, this catalog of antipatterns can serve as a stepping stone in our responsible methodological
evolution toward principled and meaningful human-AI collaboration in qualitative research.
Read the full abstract ▾
All authors Rashina Hoda, Carolyn Seaman, Victoria Gomes, Rodrigo Spinola
Numerical Analysis
Optimal error estimates for the half-way bounce-back lattice Boltzmann method for the Stokes equations
Kai Koike
We give a mathematical proof of the optimal convergence rates for the D2Q9 BGK
lattice Boltzmann method with the half-way bounce-back rule for the incompressible Stokes equations in a flat channel. The convergence rates are second-order for the velocity and first-order for the pressure as the
lattice spacing $h$ tends to zero, in agreement with formal analyses and numerical experiments, whereas the available rigorous convergence
theorems only yield an $O(h^{1/2})$ bound for the velocity error. A key step in the proof is a decomposition of the leading boundary consistency error into macroscopic and kinetic components. These components are absorbed by suitably constructed Stokes and discrete Knudsen layer correctors, respectively. Incorporating these correctors into the prediction function used in previous rigorous analyses, we obtain a refined prediction function with consistency errors of sufficiently high order. Combined with the known weighted $L^2$-stability estimate, this gives the optimal convergence rates.
Read the full abstract ▾
Computation and Language
Entity-Memory Graph Retrieval Improves Evidence Coverage in Long-Conversation Question Answering
Shumao Sun
Entity-
Memory graph
retrieval keeps dialogue turns as verbatim
Memory nodes, links repeated mentions through shared Entities, and connects adjacent
Memories with directed chronological edges. At query time the retriever moves from Entity gating through semantic fusion and one-hop chronological recovery to dense backfill. The path can keep a neighboring
Memory that dense cosine ranking would otherwise omit. A matched dense control shares the
Memory and query vectors, context budget, requested answer protocol, and evaluator, isolating graph structure from changes to the reader. On 1,986 questions from ten LoCoMo conversations, graph
retrieval raises official evidence recall at top-k 25 from 79.7468% to 84.4842%. The recall advantage is supported from top-k 5 to 50, while no matched cutoff supports an overall final-answer F1 difference. Four paper-eligible requested configurations support empirical robustness across the tested GPT-3.5 and DeepSeek extractors on both outcomes.
Embedding robustness is mixed: F1 has no supported contrast, but recall is sensitive to the
embedding artifact. The comparison isolates a
retrieval-coverage gain from graph structure. It does not establish a final-answer F1 gain, model or
embedding equivalence, or cross-
dataset generalization.
Read the full abstract ▾
Computation and Language
What Makes Agent Memory Useful for Reliable Unanswerable Question Handling?
Chuanyuan Tan, Junjie Yu, Yuxin Wang et al. (+3 more)
Reliable handling of unanswerable questions (UAQs) is critical for trustworthy LLM-based
agents. Although
memory is widely used in
agent systems, its role in reliable UAQ handling remains unclear. We present a systematic study of
agent memory for UAQ handling under a unified agentic RAG framework, evaluating four representative
memory methods across three UAQ-related
datasets and two base models. We find that
memory can improve UAQ performance in some settings, but such gains are selective rather than universal and remain fragile under
dataset shift. Interestingly, cross-model
memory reuse is often more feasible than cross-
dataset transfer, suggesting that shifts in answerability patterns pose a greater challenge to
memory reuse than changes in the base model itself. We further find that UAQ gains are more strongly preserved through decision guidance than through trajectory shaping, and that
memory effectiveness depends strongly on representation. In particular, procedural and rule-based
memories often provide the most reliable support for UAQ handling, while
memory composition is most effective when procedural guidance is combined with complementary behavioral signals. Overall, our findings suggest that reliable UAQ
memory depends less on storing larger amounts of experience and more on preserving transferable behavioral guidance.
Read the full abstract ▾
All authors Chuanyuan Tan, Junjie Yu, Yuxin Wang, Yining Zheng, Xipeng Qiu, Wenliang Chen
Computer Vision
PCBnet: A Dataset and Automatic Construction of SPICE Netlists from Schematic Images
Zhen Huang, Yuhao Gao, Yuzhi Liu et al. (+15 more)
Printed
circuit boards (PCBs) are fundamental to modern electronic systems, yet AI-driven PCB design automation remains constrained by the lack of large-scale paired schematic-netlist
datasets. PCB schematics are particularly challenging due to diverse component types, complex wiring
topologies, and noisy textual annotations. To address this gap, we present PCBnet, a large-scale PCB schematic
dataset comprising over 300 real-world designs with annotated pins and paired SPICE netlists. It contains more than 50,000 component instances, 150,000 wires, 100,000 text regions, and 400,000 characters. We further develop an automated schematic-to-netlist pipeline that combines visual recognition,
topology construction, and domain-knowledge-guided multi-
agent correction. The proposed method achieves 94.54% component detection mAP, 98.57% text recognition accuracy, and 84.47% end-to-end connectivity accuracy. PCBnet provides a
benchmark and data foundation for future AI-driven PCB design automation.
Read the full abstract ▾
All authors Zhen Huang, Yuhao Gao, Yuzhi Liu, Daian Cheng, Chengyuan Shao, Yucheng Chen, Yongjian Jia, Futing Zhang, Yichen Shi, Wenhao Wang, Zuyan He, Yangbo Wei, Zhanfei Chen, Jinlong Yan, Yu Zhang, Haoying Wu, Ting-Jung Lin, Lei He
Computer Vision
DensityKV: Density-Guided KV Cache Compression for Long Video Generation
Wenqu Zhao, Xuemin Chi, Xin Zhang et al. (+6 more)
Autoregressive
video diffusion models enable streaming generation through sliding-window
attention, but each generated block is conditioned on previously generated content, causing appearance and motion errors to propagate recursively over time. Historical key-value (KV)
memory preserves earlier subject and scene states and helps maintain long-horizon consistency. However, retaining every generated state creates a historical archive that grows continuously with the rollout, while recurrent states repeatedly add redundant coverage. To address this problem, we propose DensityKV, a training-free historical KV bank management strategy. DensityKV maintains a separate
token-level KV bank for each
attention head and measures local redundancy among the post-RoPE keys that directly parameterize
attention routing using Soft-Riesz density. By constraining neighborhood-density growth after states enter the bank, DensityKV limits repeated historical accumulation while preserving coherent states from each completed generation block. Experiments across three autoregressive
video generation backbones and multiple generation lengths show that, at the same upper bound on historical KV capacity, DensityKV improves long-horizon consistency and generation stability while keeping persistent historical storage bounded independently of rollout length.
Read the full abstract ▾
All authors Wenqu Zhao, Xuemin Chi, Xin Zhang, Guoqing Ma, Baorun Li, Jianjie Fang, Peizhi Tang, Chen Gao, Wei Wu
Artificial Intelligence
From Documents to Reasoning: A Validated Synthetic Data Pipeline and Semantic-Aware Fine-Tuning for Financial Numerical Reasoning
Lokendra Birla, Milind Savagaonkar, Visnu Srinivasan et al. (+2 more)
Financial question answering (QA) has emerged as a key
benchmark for evaluating the performance of Large
Language Models (LLMs) on domain-specific tasks involving complex data formats such as tables, charts, and rich textual narratives. While recent advancements have enabled models to reason across modalities and perform multi-step arithmetic operations, limitations remain in performance consistency, and evaluation reliability. In particular, standard evaluation metrics like Exact Match (EM) often fail to account for minor variations such as differences in units or formats, misleading performance assessments. In this work, we propose a comprehensive pipeline for improving financial QA systems through high-quality synthetic data generation and fine-tuning of smaller
language models (SLMs) using Quantized Low-Rank Adaptation (QLoRA). Our pipeline includes aggressive data validation for synthetic question answer generation to ensure the relevance and correctness of synthetic question-answer pairs. We introduce a novel evaluation metric that matches answers computed from arithmetic expressions rather than ground-truth answers; providing a more accurate reflection of model
reasoning capability. Furthermore, we propose a modified loss function that aligns predicted and reference expressions using semantic similarity, our novel evaluation metric and standard cross-
entropy, resulting in improved performance. Experimental results on
benchmark datasets, ConvFinQA demonstrate significant gains in QA accuracy after fine-tuning using synthetic
dataset and proposed loss function.
Read the full abstract ▾
All authors Lokendra Birla, Milind Savagaonkar, Visnu Srinivasan, Sowmya Rasipuram, Shubhashis Sengupta
Systems and Control
Backup Control Barrier Function Synthesis using Sum-of-Squares Reachability
Jungbae Chun, Shima Sadat Mousavi, David E. J. van Wijk et al. (+3 more)
Backup control barrier functions (bCBFs) enforce safety for input-constrained nonlinear systems using a pre-certified backup set and controller, but their performance depends strongly on this prescribed pair. This letter develops a constructive method for synthesizing a less conservative backup pair via finite horizon sum-of-squares (SOS) backward reachability. Starting from an initial backup set, we compute an SOS-certified finite horizon backward reachable set and controller that satisfy safety and input constraints while steering trajectories to the original backup set. We then provide conditions under which this certified set becomes a valid backup set for a piecewise backup controller. The resulting backup pair is integrated into the bCBF framework to certify larger safe sets.
Read the full abstract ▾
All authors Jungbae Chun, Shima Sadat Mousavi, David E. J. van Wijk, Ersin Daş, Aaron D. Ames, Felix Biertümpfel
Cryptography and Security
A User-Centric Context-Aware Permission Governance Framework for Privacy Control in Default Mobile Applications
Asmau Yetunde Adeniran, Adeniran Kolade Ademuwagun, Fatimah Adamu-Fika et al. (+3 more)
Mobile operating systems provide runtime permission controls intended to improve user control over sensitive data. However, default or pre-installed applications are deeply integrated into the system, may operate with elevated privileges, and are difficult for users to scrutinize. Existing permission models generally grant persistent or temporary access for an application session without distinguishing among individual features, leaving users uncertain about when and why data are accessed. This paper presents a context-sensitive, user-focused permission governance framework for default mobile applications. It introduces a feature-based authorization option, "Allow When Needed," that restricts access to the functionality requiring the data rather than the entire application session. A weighted scoring system estimates the
privacy implications of user choices based on permission sensitivity and authorization type. A web-based simulation platform was developed to model 30 realistic permission-request situations across six commonly used default application types and support controlled early-stage evaluation before native implementation. The exploratory assessment combined a cross-sectional survey of 104 respondents examining permission awareness and behavior with formative usability testing involving eight participants interacting with the prototype. Survey findings indicate that users do not consistently examine default-application permissions and prefer contextual explanations before granting access. The results provide preliminary evidence that context-aware permission governance can improve user understanding and decision clarity. This simulation-based study represents an initial step toward evaluating feature-level authorization and
privacy-feedback mechanisms before native mobile deployment.
Read the full abstract ▾
All authors Asmau Yetunde Adeniran, Adeniran Kolade Ademuwagun, Fatimah Adamu-Fika, Samaila Musa Abdullahi, Freeman Bitrus, Fortune Daberechi Ifeanyi
Information Retrieval
ITER: Interaction-Aware Retrieval for Agentic Search
Haodong Chen, Shuai Wang, Yu Yin et al. (+3 more)
Deep-research
agents answer complex user questions through an iterative sequence of search steps, where the
agent autonomously formulates sub-queries to retrieve the evidence needed at each stage. However, existing retriever training typically relies only on the sub-query and its corresponding search results at the current step as training signals, leaving the information accumulated from previous interactions largely underutilized. We introduce ITER, an
agent interaction-aware dense retriever trained using
agent trajectory learning signals. ITER represents each query by incorporating not only the current sub-query, but also the main question, the
agent's pre-search
reasoning, and preceding sub-queries, and is trained using trajectory-relative learning signals derived from the
agent's interactions. Across six
agent backbones from three model families, ITER consistently outperforms the existing
agent-trajectory-trained dense retriever, LRAT, achieving an average relative improvement of 6.9% on InfoSeek-Eval and 15.4% on BrowseComp-Plus. At the matched 4B scale, ITER outperforms AgentIR on InfoSeek-Eval for five of six backbones while achieving a higher visit-to-search recall ratio on BrowseComp-Plus across all six backbones. Ablations further show that structured interaction history and pre-search
reasoning provide complementary
retrieval context, while previously visited and useful documents, used as redundancy negatives in subsequent searches, provide the strongest trajectory-relative supervision.
Read the full abstract ▾
All authors Haodong Chen, Shuai Wang, Yu Yin, Shengyao Zhuang, Guido Zuccon, Teerapong Leelanupab
Machine Learning
TACIT-Switch: Cost-Aware Model Escalation for LLM Agents from Censored Supervision
Ji'an Lei and Jian Huang
Agents with smaller
language-model backbones are less expensive but can drift into persistent failure modes, whereas those with larger backbones are generally more reliable but more costly. This reliability-cost trade-off motivates routing methods that decide when to invoke an
agent with a larger backbone: before execution, after a fixed trajectory prefix, or locally at individual steps. Our method, TACIT-SWITCH, learns permanent handoff policies from accumulated trajectory evidence and Teacher-Annotated Censored Intervention Times (TACIT). It represents each annotation as an interval-censored observation on a cumulative-risk scale. The resulting mixture-cure threshold model estimates the probability that the paired Strong rollout succeeds and, conditional on success, the handoff threshold; no teacher is required at deployment. In a mechanism-based multi-step simulation, TACIT-SWITCH improves success by 7.4-11.1 percentage points over task-level, step-level, and fixed-prefix routing baselines at comparable cost. Within that controlled simulation, ablations show that task features and cumulative trajectory risk provide complementary information. With operating points selected on development data, TACIT-SWITCH achieves the highest held-out success among learned policies on both ALFWorld (48.5% with 4B Cheap; 45.5% with 9B Cheap) and DABench (73.1%).
Read the full abstract ▾
Artificial Intelligence
AI Alignment through a Game-theoretic Lens: A Survey
Yanan Cai, Zhongrui Zhao, Zhigang Lu et al. (+6 more)
As large
language models and increasingly capable AI
agents are deployed in high-risk settings, aligning them with complex human values has become a central challenge. Existing
alignment methods, while effective in improving helpfulness, harmlessness, and controllability, often struggle to capture real-world preferences that are context-dependent, non-transitive, and shaped by dynamic multi-party interactions. This survey reviews AI
alignment through a game-theoretic lens. Specifically, it organizes recent progress around key game-theoretic elements and synthesizes the literature along three challenges: preference diversity,
alignment priority, and temporal dynamics. This perspective clarifies where current
alignment methods genuinely benefit from game-theoretic analysis, where the framework is looser, and what challenges remain in building robust, adaptive, and verifiable AI systems.
Read the full abstract ▾
All authors Yanan Cai, Zhongrui Zhao, Zhigang Lu, Ickjai Lee, Wei Emma Zhang, Minhui Xue, Yihong Zhang, Shuchao Pang, Wei Xiang
Information Theory
Low-Altitude Fluid Antenna Network with Multi-Agent Reinforcement Learning
Tong Zhang, Yanfei Su, Shuai Wang et al. (+3 more)
Low-altitude wireless networks (LAWNs) integrate terrestrial and aerial platforms to provide ubiquitous communication, sensing, and localization services for unmanned aerial vehicles (
UAVs) and electric vertical takeoff and landing (eVTOL) aircraft. However, dynamic air-ground and air-air channels, abrupt blockages, and heterogeneous interference hinder the realization of this goal. Nevertheless, fluid
antenna (FA), a cutting-edge multiple-input multiple-output (
MIMO) technique, overcomes these challenges by reconfiguring
antenna positions to unlock additional spatial degrees-of-freedom. In this paper, towards bringing low-altitude FA networks into reality, we study the fast and high-performance FA reconfiguration for low-altitude FA networks with multi-
agent reinforcement learning (MARL). Specifically, we present an electromagnetic digital twin (EM-DT)-assisted MARL framework. To fill the sim-to-real gap, we introduce a two-stage transfer learning framework. Our case study shows that joint FA positions and beamforming optimization can enhance the system sum-rate by 118.5%, compared to the fixed position baseline. This gain comes from the dynamic millisecond timescale reconfiguration of FA arrays and the adaptive steering of beams toward aerial users with mobility.
Read the full abstract ▾
All authors Tong Zhang, Yanfei Su, Shuai Wang, Wanli Ni, Chengzhong Xu, Huseyin Arslan
Artificial Intelligence
Design the Feedback, Not Just the Reward: Environments for Open-Ended Reinforcement Learning
Rui Jin, Jikai Chen, Chengyue Yu et al. (+7 more)
Reinforcement learning has advanced large
language models on tasks with reliable verifiers, where checking an outcome provides a clear basis for reward. Extending this approach to open-ended tasks requires environments that can both evaluate complex, partially successful outputs and turn these judgments into effective learning guidance. We propose a reinforcement learning framework built around a training environment that integrates human domain knowledge with model
reasoning. Human domain knowledge, encoded in rubrics, anchors evaluation to task intent, while model
reasoning combined with hierarchical rewards distinguishes complex open-ended outputs and links diagnosed failures to likely responsible output regions. Furthermore, these diagnostic attributions guide
token-level weights in the GRPO objective, thereby translating the ambiguous notion of success in open-ended tasks into concrete guidance for policy optimization. We instantiate this framework in interactive web application generation, a representative open-ended generation task. The resulting model achieves an average pass rate of 41.25% on MiniAppBench and 76.19% on ArtifactsBench. Ablation studies show the contributions of individual components, while additional out-of-distribution evaluations support transferable gains without degrading performance on other evaluated tasks.
Read the full abstract ▾
All authors Rui Jin, Jikai Chen, Chengyue Yu, Yihan Chen, Hao Zhou, Demin Zhu, Kaichen Yang, Dong Wang, Linjian Mo, Chenyi Zhuang
Computation and Language
LandingAgent: A Reference-Annotated Dataset and Agentic Generation Framework for Landing Pages
Injun Baek, HyeongSeok Lee, Yearim Kim et al. (+2 more)
Landing pages are goal-oriented web interfaces that must communicate a target-specific value proposition while organizing information flow, visual hierarchy, and calls to action (CTA). Although large
language models can generate plausible webpage code from natural-
language prompts, direct generation often yields generic templates and unsupported persuasive claims. We study target-grounded, reference-guided landing-page generation, where a system must create an executable page for a new target by adapting reusable patterns from real pages without copying them. We introduce LandingBench, a reference-profile
dataset that abstracts real landing pages into section sequences, layout patterns, tone descriptors, visual emphasis, and CTA structure. Building on LandingBench, we propose LandingAgent, a three-phase agentic framework that profiles the target, constructs a reference-guided wireframe, and refines the page through critique-guided polishing. We evaluate LandingAgent against direct prompting on faithfulness, conciseness, readability, aesthetics, and structural diversity. Experiments show improved target grounding, presentation quality, and layout diversity. Code is available at https://github.com/IAURAI/LandingAgent.
Read the full abstract ▾
All authors Injun Baek, HyeongSeok Lee, Yearim Kim, Junhoo Lee, Nojun Kwak
Computation and Language
OpenStamp: A Watermark for Open-Source Language Models
Miroojin Bakshi, Saksham Rastogi and Danish Pruthi
With the growing prevalence of large
language model (LLM) generated content, watermarking is considered a promising approach for attributing text to LLMs and distinguishing it from human-written content. A prominent class of techniques embeds subtle but detectable signals in generated text by modifying
token sampling probabilities. However, such methods are unsuitable for open-source models, where users have white-box access and can easily disable watermarking during inference. In this work, we introduce OpenStamp, a watermarking technique that encodes the watermarking logic directly into the model weights by modifying only the final projection, or unembedding, layer. Through experiments across two models, we show that OpenStamp achieves superior detection performance, with minimal degradation in model capabilities compared to prior methods. The implanted watermark is explicitly designed, and empirically confirmed, to be more robust to paraphrasing attacks and harder to scrub off through post-hoc fine-tuning than prior open-source watermarks. To enable developers to watermark their models, we release our code alongside watermarked versions of 4 popular open-source models.
Read the full abstract ▾
Data Structures and Algorithms
Online Differentially Private Consistent Clustering
Edith Cohen, Vadym Doroshenko, Badih Ghazi et al. (+7 more)
We study differentially private (DP) $k$-means and $k$-median clustering in the online streaming setting. In this model, points arrive sequentially, and at each time step, we need to output a set of $k$ centers that optimizes the clustering objective for all points seen so far. We give a generic reduction that transforms the (sensitive) input stream into a private stream, which is a semi-coreset of the input stream. This implies that any (non-private) online clustering
algorithm, run as a post-processing step, can achieve good utility for the original clustering objective. Our
algorithm matches or improves upon the approximation ratio, space usage, and running time of existing
algorithms [Epasto et al., 2026, Dupré la Tour et al., 2024]. A key aspect of our reduction is that it inherits desirable properties of the underlying non-private clustering
algorithm, such as consistency [Lattanzi and Vassilvitskii, 2017]–a property not satisfied by previous DP
algorithms.
Read the full abstract ▾
All authors Edith Cohen, Vadym Doroshenko, Badih Ghazi, Pritish Kamath, Alexander Knop, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Adam Sealfon, Marika Swanberg
Computer Vision
CommerceVibe: Learning to Design E-Commerce Creatives as Executable Visual Code via Dual-Feedback Reinforcement Learning
Yajiao Xu, Jin Zhang, Jiangbo Ai et al. (+4 more)
High-quality e-commerce creatives are essential for presenting products and conveying marketing messages. Recent
diffusion models enable scalable creative generation and produce visually compelling images, but their flattened raster outputs often contain distorted text and inconsistent product details, requiring refinement before deployment. Moreover, without explicit structure, the resulting creatives are difficult to edit and reuse, while complex design requirements remain challenging to encode as verifiable training signals. To address these challenges, we present CommerceVibe, which represents creatives as executable visual code and formulates generation as conditional HTML/CSS program synthesis. Given product images, design requirements, and product information, it produces renderable, editable, and reusable creatives. We further introduce dual-feedback reinforcement learning, in which rule-based feedback evaluates rendered programs for text readability, product visibility, and layout validity, while visual feedback from a
vision-
language model (VLM) assesses rendered creatives against input specifications across six perceptual and commercial dimensions. Together, these complementary feedback signals improve both constraint satisfaction and perception-dependent quality. We perform supervised fine-tuning (SFT) of Qwen3.5-9B on over 28,000 e-commerce examples, followed by dual-feedback reinforcement learning. On a 1,300-case
benchmark, the optimized CommerceVibe model achieves a weighted score of 94.0/100, compared with 87.3 for the SFT-only variant, and outperforms strong external models. Blind evaluations by five e-commerce design experts further validate these improvements. CommerceVibe supports controllable, editable, and scalable e-commerce creative production.
Read the full abstract ▾
All authors Yajiao Xu, Jin Zhang, Jiangbo Ai, Tao Jiang, Mo Xu, Lina Huang, Chengfu Huo
Systems and Control
AutoDRI: Bridging the Semantic Gap for Automated Design Rule Integration in CP-SAT-Based Cell Synthesis under Multi-Patterning
Yuhao Ren, Yucheng Wang, Zihao Chen et al. (+2 more)
Design-rule integration (DRI) remains a major bottleneck for scalable (Constraint Programming with SAT) CP-SAT-based standard
cell synthesis and rapid technology enablement at advanced nodes. It still depends heavily on manual effort and domain expertise. Moreover, existing low-level rule encodings are not expressive enough for emerging constraints such as cut-based rules under multi-patterning technology. This paper presents AutoDRI, a multi-
agent framework for automated design-rule integration in standard
cell synthesis. AutoDRI combines a
geometric semantic library, a standardized conflict-set encoding, a constructive multicolor-cut modeling method, and a feedback-driven multi-
agent flow to bridge the semantic gap between natural-
language design rules and executable CP-SAT constraints. In the reported experiments, AutoDRI achieves near-perfect rule-integration correctness across 41
cell benchmarks under 10+ complex rules, including colored cut-mask spacing rules, reaching 33/33 correct integrations with Gemini-3-pro and 32/33 with GPT-5.4, while maintaining runtime comparable to manual hard-coding and passing KLayout DRC and Cadence LVS.
Read the full abstract ▾
All authors Yuhao Ren, Yucheng Wang, Zihao Chen, Chung-Kuan Cheng, Zhiang Wang
Software Engineering
Decoupling is a Necessity: Transformation-Agnostic Decompiled Code Recovery under Optimization and Obfuscation
Zhiping Zhou, Xiaohong Li, Ruitao Feng et al. (+3 more)
Reverse engineering is essential for software security analysis and vulnerability detection. Decompilation, the process of lifting binaries to high-level pseudocode, is central to this task. However, production binaries are hostile environments: aggressive compiler optimizations and
adversarial obfuscation jointly mangle control structures, obscure variable intents, and disguise high-level program logic. Consequently, existing LLM-based decompilation tools frequently suffer from structural collapse and semantic
hallucinations. We present ReSource, the first multi-phase LLM framework designed for transformation-agnostic source recovery. To tackle these intertwined distortions, ReSource conceptualizes the binary-to-source discrepancies into three orthogonal tiers, namely lexical, syntactic, and semantic, and decouples the recovery process accordingly. First, to ground the LLM and prevent logic drift, it retrieves empirical priors from a curated Semantic Distortion Database. Second, to resolve control-flow flattening, it integrates a lightweight predictor to reconstruct the source-level structural skeleton. Finally, a contextual lexical deduction stage refines identifiers to restore human readability. Evaluated on a massive
benchmark of over 80,000 decompiled-source function pairs across three optimization levels and four obfuscation techniques, ReSource achieves an 83% Top-5 source
retrieval accuracy and an average similarity score of 0.66. By maintaining robust semantic identifiability where state-of-the-art baselines (DeGPT, LLM4Decompile, and FidelityGPT) severely overfit or degrade, ReSource provides a scalable and reliable foundation for downstream security analysis.
Read the full abstract ▾
All authors Zhiping Zhou, Xiaohong Li, Ruitao Feng, Yao Zhang, Yuekang Li, Wenbu Feng
Computer Vision
Thread-Efficient Decoding for Neural Texture Compression
Janarbek Matai, Sho Ikeda, Lukasz Lipski et al. (+1 more)
Neural texture compression (NTC) achieves higher compression ratios than BCn formats but suffers from GPU thread divergence, which significantly reduces runtime performance. In this work, we propose a shared decoder MLP architecture – trained with a gradual decoder freezing schedule – combined with texture clustering to reduce thread divergence by 25%-52% while preserving rendering quality. We evaluate our method on over 500 textures and multiple real rendering scenes, demonstrating up to 8.48x speedup on the Radeon RX 9070 XT GPU compared to non-shared baselines. Our key contributions include: (1) a unified shared decoder architecture that reduces divergence by grouping textures; (2) a training recipe with gradual decoder freezing that improves stability and reconstruction accuracy; (3) a semantic clustering strategy using CLIP
embeddings that groups similar textures for effective decoder sharing; and (4) comprehensive performance and ablation studies validating our approach.
Read the full abstract ▾
All authors Janarbek Matai, Sho Ikeda, Lukasz Lipski, Takahiro Harada
Artificial Intelligence
Resource Constraints and Performance in Agentic AI Systems
Amaz Salman, Malka Halgamuge and Teo Susnjak
Progress toward more autonomous AI increasingly depends on agentic systems that combine a
language model with tools,
memory, state management, and multi-step execution. These mechanisms shape both task capability and operational burden. We compare OpenClaw and NanoBot as complete agentic systems using a paired primary
benchmark and a more detailed instrumented subset of paired
prompts. In the primary
benchmark, the rate of full task completion was 31% for OpenClaw and 25% for NanoBot, a six-percentage-point difference with a 95% task-bootstrap interval from -3 to 15 percentage points, providing no statistically established full-completion advantage for either system. In the instrumented layer, both systems achieved 26% full completion, while NanoBot reached at least partial completion on 43% of
prompts compared with 26% for OpenClaw. OpenClaw took longer on 83% of
prompts and had a higher recorded peak-
memory value on every
prompt, with
geometric mean ratios of 2.98 for wall time and 19.44 for peak
memory. Among the ten detailed-layer
prompts on which at least one system achieved partial or full completion, NanoBot weakly dominated on eight; across all 23
prompts, however, ten of its eighteen dominance cases were cheaper joint failures. Outcome labels differ across the two evidence layers, showing why
agent-system evaluation should connect capability and resource measurements to attempt-level execution and scoring provenance. These findings show that progress toward more autonomous AI should be evaluated through verified task completion, observed resource use and records linking each result to the execution that produced it.
Read the full abstract ▾
Machine Learning
There and Back Again: Bidirectional Diffusion Bridges for Multimodality Translation
Gabe Guo, Elon Litman, Thanawat Sornwanee et al. (+2 more)
Multimodality translation (e.g., text-to-image) is a core generative AI task. However, existing approaches (1) follow generative paths that do not directly represent the source modality, limiting the flexibility of some sampling
algorithms; and (2) are unidirectional, preventing inversion (e.g., image-to-text). We propose BIT: Bidirectional Image-Text
Diffusion Bridges. In contrast to previous approaches, BIT starts directly from text and interpolates into images, providing (1) a source-aware generative path that enables diverse and flexible sampling
algorithms; and (2) an endpoint-conditioned process that can be traversed from image to text, providing a unified, bidirectional generative framework. BIT is derived through
stochastic calculus, yielding SDE forms amenable to simulation and tractable loss functions that scale to high dimensions. Our experiments show that BIT is competitive with denoising-
diffusion and deterministic-flow baselines, and outperforms them on several
vision–
language and natural-science evaluations.
Read the full abstract ▾
All authors Gabe Guo, Elon Litman, Thanawat Sornwanee, Jose Blanchet, Stefano Ermon
Machine Learning
Beyond Pairwise Graphs in Science: Hypergraph Adaptive Wavelet Operators for Parametric PDEs
Rajat Sarkar, Venkataramana Runkana and Souvik Chakraborty
Physical systems are often modeled by solution operators that map input fields, parameters, geometries, or past states to steady or future physical states. Learning these maps is difficult, especially for time-dependent systems that must assimilate history and remain stable under autoregressive rollout. Many neural operators work best on regular, structured grids, while realistic simulations often require unstructured meshes or point clouds to resolve complex geometries; in such settings, grid-centric representations can lose accuracy. Graph neural operators handle these domains through message passing or spectral graph filtering, but pairwise edges do not directly capture group-wise couplings among mesh
cells, local neighborhoods, or conservation volumes. We introduce the Hypergraph Adaptive waveLet Operator (
HALO), which lifts the domain to a hypergraph and learns in its spectral wavelet domain.
HALO avoids explicit hypergraph-
Laplacian eigendecomposition through Chebyshev
polynomial wavelet filters, giving localized spectral kernels at linear sparse-
matrix cost. Its trainable dyadic wavelet scales are regularized toward tight-frame coverage, allowing the frequency response to adapt to each PDE while encouraging stable multi-scale spectral coverage. Across 2D and 3D
benchmarks on structured and unstructured discretizations,
HALO achieves best or near-best accuracy among frequency-,
transformer-, DeepONet-, state-space-, and graph-based baselines and sustains stable multi-step rollouts. The same model scales to industrial aerodynamic geometries: on meshes of a few hundred thousand points it is on par with, or better than, the strongest fixed-discretization
transformers, while remaining resolution-equivariant.
Read the full abstract ▾
Machine Learning
SOMTab: Set-Order Mamba for Efficient Tabular In-Context Learning
Hao Wang, Siyu Zhang and Wei Ma
Tabular foundation models based on in-context learning have recently emerged as strong alternatives to task-specific model fitting. However, the current performance frontier remains dominated by
attention-heavy architectures, where
attention is used throughout the modeling pipeline. This raises a natural question: is
attention necessary at every stage of tabular in-context learning? We introduce SOMTab, a Set-Order Mamba architecture for efficient tabular in-context learning. SOMTab separates representation construction from query-conditioned
retrieval. For row and column representations, it maps unordered table
tokens into stable latent slots and applies Mamba-based state-space mixing to construct compact representations. For final prediction, it retains
attention-based in-context learning to preserve query-conditioned
retrieval from labeled context examples. We further introduce DCH-TailMix, a synthetic prior that combines degree-corrected graph heterogeneity with mixed heavy-tailed regimes to diversify synthetic dependency structures. Across tabular
benchmarks, SOMTab approaches the performance of strong
Transformer-based tabular foundation models while achieving faster inference and lower GPU
memory usage, yielding a favorable efficiency–accuracy trade-off.
Read the full abstract ▾