Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science (sign in to use)

Thursday 20 August

Computation and Language

Generating Diverse Personas for User Simulators to Test Interview Dialogue Systems

This paper addresses the issue of the significant labor required to test interview dialogue systems. While interview dialogue systems are expected to be useful in various scenarios, like other dialogue systems, testing them with human users requires significant effort and cost. Therefore, testing with user simulators can be beneficial. Since most conventional user simulators have been primarily designed for training task-oriented dialogue systems, little attention has been paid to the personas of the simulated users. During development, testing interview dialogue systems requires simulating a wide range of user behaviors, but manually creating a large number of personas is labor-intensive. We propose a method that automatically generates personas for user simulators using a large language model. Furthermore, by assigning personality traits related to communication styles when generating personas, we aim to increase the diversity of communication styles in the user simulator. Experimental results show that the proposed method enables the user simulator to generate utterances with greater variation.
Read the full abstract

Computers and Society

Two-sided receptivity to conversational AI agents in online dating: Bilingual survey data from Fledge.Love

Autonomous conversational agents and generative-AI features are being added to online dating platforms faster than public evidence about user attitudes can accumulate, and the scarcest evidence concerns the receiving side: how people react when the profiles, messages, or conversation partners they encounter are machine-generated. We release two anonymized survey datasets collected from active users of Fledge.Love, a dating platform serving an international user base. The first (N = 2,617; Russian and English forms) measures receptivity to autonomous conversational agents with a seven-item battery that separates the principal role (deploying one's own agent) from the counterpart role (encountering someone else's), plus six ordinal covariates and two auxiliary items. The second (N = 2,894) measures interest in three passive generative-AI features. The release includes model-derived scores for 2,499 complete cases, a bilingual codebook, a documented anonymization pipeline with a k-anonymity audit, executable analysis notebooks, and canonical outputs, supporting reuse in human-AI communication, recommender-systems, and cross-cultural technology-acceptance research.
Read the full abstract

All authors Daria Leshchikova, Valentina V. Kuskova, Dmitry Zaytsev, Valerii Klimov

Machine Learning · Cross-listed from cond-mat.mtrl-sci

Composition-Driven Phase Evolution in Sm-Doped BiFeO3 via Latent-Field Reconstruction of Atomically Resolved STEM Data

Functionalities of ferroelectric materials are governed by the spatial organization and coupling of polarization, strain, lattice rotation, and structural order accessible via atomically resolved scanning transmission electron microscopy (STEM) images. Quantitative interpretation of atomic-resolution STEM data has conventionally relied on locating atomic columns and converting their fitted coordinates into local structural descriptors. Here, we develop a field-based approach in which atomic-resolution images are represented by spatially varying latent Bragg fields, whose amplitudes and phases provide continuous maps of crystalline order, lattice displacement, strain, rotation, and mode-specific residual structure. The observed atomically resolved images are decoded from the latent fields. We apply this framework to image series of Sm-substituted BiFeO3 spanning 0-20% Sm and crossing the composition-driven boundary between the R3c ferroelectric phase and the orthorhombic, nonpolar Pnma phase. Conventional atom-resolved parameterization is used as an independent validation, showing that reconstructed Bragg amplitude tracks local atomic-column intensity and that field-derived shear reproduces unit-cell angular distortions obtained from atom fitting. The combined analysis reveals a systematic evolution from extended ferroelectric domains at low Sm concentration, through the appearance and growth of localized regions with period-doubled Pnma order at intermediate compositions, to a connected Pnma-dominated state at high Sm content. The period-doubled order is accompanied by enhanced shear and lattice rotation and by progressive reorganization of the ferroelectric domain structure. These results establish latent-field reconstruction as a physically interpretable complement to atom finding and provide a unified framework for resolving composition-driven phase evolution in ferroic materials.
Read the full abstract

All authors Newsha Javanmardi, Christopher T. Nelson, Anna N. Morozovska, Eugene A. Eliseev, Ichiro Takeuchi, Sergei V. Kalinin

Machine Learning

Continuous Adversarial MeanFlow for Few-Step Generative Adaptation from Any Parameterization

Training fast generators on new domains with limited data remains challenging for two reasons. First, adapting a pretrained diffusion or flow model leaves its costly multi-step sampling intact, and existing acceleration methods are tied to the source parameterization (x, epsilon, v, or u), so heterogeneous pretrained models share no common acceleration target. Second, while adversarial post-training sharpens generation quality, existing criteria each cover only one end of the step range. Discrete criteria compare jump endpoints and lose their signal as the jump shrinks, while continuous criteria score the instantaneous velocity and misjudge the large jumps of few-step sampling. Neither fits MeanFlow (MF) models, which predict average velocities over intervals of any length. We propose MeanFlow-Transfer (MF-T), which adapts a source domain model of any parameterization and compresses it into a few-step MF generator through a common velocity map. We then introduce Continuous Adversarial MeanFlow (CAMF), which scores the change of a learned potential along each predicted interval jump of MF. CAMF needs no gradient penalty or Jacobian-vector product (JVP). We also prove it stays well-conditioned for every interval length and recovers the instantaneous criterion as the interval vanishes. Adapting four ImageNet-based source models (DiT, SiT, JiT, iMF) to five target domains, MF-T + CAMF approaches or exceeds the fine-tuned many-step teacher in FID and FDD at up to 125x fewer Neural Function Evaluations (NFEs). Further, CAMF improves MF-T's few-step FID by about 30% on average, outperforming prior adversarial post-training on iMF at every NFE.
Read the full abstract

All authors Yara Bahram, Zahra Dehghani, Mélodie Desbos, Eric Granger, Pablo Piantanida, Mohammadhadi Shateri

Data Structures and Algorithms

A simple and practical $o(\sqrt{n})$-time algorithm for shortest paths in power law graphs

Computing shortest paths in large graphs is, and remains, a fundamental and practically motivated problem. While many algorithms were proposed to calculate shortest path between pairs of vertices efficiently, many of them (index-based methods) require substantial preprocessing, while others (traversal-based methods) have higher time complexity. In this paper, we propose and analyze Pruned Bidirectional Search (PBS), a simple sublinear approximation algorithm for power-law graphs with parameter $\beta\in[2,3)$: our algorithm does not require any preprocessing, yet exhibits performance comparable to light index-based algorithms (of linear or sublinear index size): that is, PBS runs in time $O(n^{(1-1/\log\log n)/2})$ and, with high probability, returns a path with length within $\frac{41}{32}$ of the shortest path. Moreover, if one does allow a $n^{\Theta(2-1/\log\log n)}$-time preprocessing step, its query time improves to $n^{\Theta(1/\log\log n})$. We complement our theoretical results by experiments on both real-world and synthetic power-law graphs, which show that PBS is typically $1.84\times$-$7.76\times$ times faster than existing alternatives, while achieving an approximation ratio at most 1.05.
Read the full abstract

Robotics

Multimodal Trajectory Planning for Surface Vehicles using Turning Circle-based Control Barrier Functions

This paper presents a guide path-free multimodal trajectory planning framework for autonomous surface vehicles operating in dynamic environments. The proposed method integrates model predictive control (MPC) with a turning circle-based control barrier function (TC-CBF). Unlike conventional Euclidean distance-based CBFs (ED-CBFs), which evaluate safety solely based on proximity, the TC-CBF accounts for the nonholonomic motion and finite turning capability of a surface vehicle. Its geometric formulation identifies feasible avoidance regions according to the vehicle's turning circles and generates distinct left- and right-turning avoidance modes. These modes allow the optimization solver to explore and select topologically different trajectories without relying on globally planned guide paths, as required by many conventional multimodal planning approaches. By embedding the avoidance direction directly into the safety constraint, the proposed framework alleviates the local-minimum and deadlock problems of single-mode MPC while maintaining computational efficiency. Extensive simulations involving multiple moving vessels demonstrate that the proposed method achieves higher success rates, fewer safety violations, and smaller residual violations than single-mode baselines across all tested traffic densities.
Read the full abstract

Computer Vision

CVSD-Reg: Cross-Modal Visual Semantic Prior Distillation for Robust LiDAR Registration

Learning-based global point cloud registration has achieved remarkable progress, yet its reliance on geometric representations makes existing methods sensitive to variations in point density, scan pattern, viewpoint, and sensor characteristics. We propose CVSD-Reg, a robust global LiDAR registration framework that distills visual semantic priors from a vision foundation model into LiDAR representations. In Stage 1, a Point Transformer V3 student learns from a frozen DINOv2 teacher through contrastive distillation and spherical-manifold alignment, which preserves the hyperspherical geometry of the teacher embedding space. Self-supervised InfoNCE consistency and soft $\mathrm{SE}(3)$ invariance further encourage viewpoint-robust descriptors. In Stage 2, the distilled representation is adapted to registration through correspondence learning, density-aware point-dropout augmentation, and end-to-end pose optimization. With a single checkpoint, CVSD-Reg generalizes to both single-sensor and zero-shot cross-sensor scenarios without sensor-specific adaptation and remains entirely camera-free at inference. On KITTI, nuScenes, and HeLiPR, CVSD-Reg achieves strict success rate (SR@0.5\,m/$1^\circ$) of 97.7$\%$, 99.0$\%$, and 99.3$\%$, respectively, including 97.3$\%$ on sparse 16-beam Velodyne scans. It outperforms state-of-the-art geometric registration methods by up to 44.0 percentage points without requiring camera inputs or post-hoc ICP refinement.
Read the full abstract

All authors Eunsoo Im, Junghun Suh, Gyeonggwan Lee, Seunghwan Hong

Artificial Intelligence

From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG

Retrieval-augmented generation (RAG) improves language-model responses by grounding generation in external passages, which comes with overhead: retrieved context lengthens the prompt, increasing prefill work, KV-cache footprint, memory traffic, latency, and energy. Context compression offers a natural remedy by pruning retrieved text before generation. However, state-of-the-art context-compression methods are typically used with a fixed compression budget, or with the rate selected offline and then applied at inference time. This static view ignores both workload variation and the live state of the edge device. On an edge SoC, compression is not free: the compressor itself runs on the same SoC and consumes latency and energy that can offset any generation savings. This paper proposes a vision for telemetry-informed adaptive compression in edge RAG, grounded in experimental evidence. We characterize the compression tradeoff on the NVIDIA Jetson AGX Thor using Llama and Qwen generators, Natural Questions and HotpotQA datasets, and LLMLingua-2 compression. Our measurements show that generation dominates the RAG budget for larger models, reaching roughly 90% of per-query latency and 91% of GPU energy for 7B-8B generators. Exploring the impact of the compression rate reveals an adaptive operating region: mild compression can miss energy opportunities, and overly aggressive compression can hurt inference quality. Intermediate compression can reduce GPU energy by up to 53.2%, and SoC energy by up to 48.2%, with negligible quality loss. We argue for runtime policies that dynamically manage compression, guided by workload features and edge telemetry.
Read the full abstract

All authors Zlatan Feric, Amir Taherin, Yanzhi Wang, David Kaeli

Cryptography and Security

AEGIS: Attention-Embedding Gradient Isolation Shield - Triple-Channel Gradient Masking for Privacy-Preserving Federated LLM Fine-Tuning

Gradient inversion attacks recover private training text from gradients shared in federated learning, posing a serious threat to collaborative model training. Through our analysis of transformer gradient structure, we identify three channels through which private token information leaks: the attention output projection gradient exposes a low-rank subspace that encodes input embeddings (Channel 1), the embedding gradient's row-norm sparsity directly reveals which tokens are present (Channel 2), and the MLP expansion gradient carries a recoverable subspace signal analogous to Channel 1 (Channel 3). State-of-the-art attacks exploit these channels analytically to achieve near-exact token recovery in seconds. Existing defences address at most one channel and either degrade model utility or leave the remaining structural signals intact. We introduce AEGIS (Attention-Embedding Gradient Isolation Shield), a lightweight defence that closes all three analytical channels with three backward-path operations requiring no architectural changes: freezing attention projection parameters eliminates Channel 1 by construction, calibrated noise injection into the embedding gradient destroys Channel 2's token-presence signal, and analogous per-block noise injection into the MLP expansion gradient masks Channel 3. The same masked gradient drives both the local optimiser step and the server export, so no clean signal is retained on either side. Evaluated across 11 models and six datasets, AEGIS reduces token recovery rates to near zero against a range of gradient inversion attacks, both analytical and optimisation-based, while preserving or improving model utility. We provide formal guarantees for Channels 1 and 2 and validate the full defence empirically against adaptive adversaries with complete knowledge of the mechanism.
Read the full abstract

All authors Ye Tao, Hong Shen, Hui Tian, Xin Wang, Can Wang

Systems and Control · Cross-listed from math.OC

On the Value Function of Infinite-Horizon Optimal Control of Piecewise Affine Systems

In this paper, we study the structure of the value function in constrained infinite-time optimal control (CITOC) problems of piecewise affine (PWA) systems, with $\ell_1$ or $\ell_\infty$ stage cost. Existing works, such as [1], establish that the resulting value function is PWA in the state. However, existing results do not analyze whether the value function is a proper PWA function, i.e., with a finite number of affine pieces over compact sets, or whether the number of pieces can be infinite. We show that the latter case is indeed possible by means of an explicit example, which is also instrumental in establishing rigorous and easily verifiable sufficient conditions that ensure that the resulting value function is a proper PWA function. Our theoretical findings complement well-known results, e.g., the linear-quadratic case, and serve as support for recent learning-based control schemes for PWA systems. Throughout the paper, the proposed results are illustrated by means of a numerical example.
Read the full abstract

Computation and Language

When Machines Speak: A Unified Generative Framework for Integrating Machine-Native Symbols into Pretrained Large Language Models

Many real-world AI systems represent entities, behaviors, and structured information using discrete machine-native symbols rather than natural language. While these representations are compact and preserve task-relevant structure, they lie outside the linguistic token space of pretrained large language models (LLMs), creating a fundamental divide between language modeling and structured prediction. We introduce UniLang, a unified generative framework that bridges this divide by extending pretrained LLMs to treat machine-native symbols as first-class generative units alongside natural-language tokens. UniLang expands the LLM's vocabulary and embedding space with grounded machine-native representations, enabling textual and symbolic tokens to be jointly modeled and generated under a single autoregressive objective. This unified interface allows pretrained LLMs to directly operate on machine-native representations without requiring them to be verbalized as natural language or relying on task-specific architectures. We evaluate UniLang on two structurally distinct tasks, sequential recommendation and legal precedent prediction, spanning different domains and types of structured prediction. Across both tasks, UniLang consistently outperforms strong baselines, demonstrating a path toward extending pretrained LLMs beyond language and using them as a common generative modeling backbone for heterogeneous machine-native representations.
Read the full abstract

Human-Computer Interaction

Does Listening Matter? Backchanneling and Nodding in AI Clone

AI clones that imitate a specific person typically reproduce what the person says and how they sound, but not how they listen. We investigate whether adding multimodal listening behaviors gives such a clone more presence and authenticity. We integrated verbal backchannels and head nodding, driven by real-time prediction models, into an AI clone equipped with voice cloning and LLM-based responses. In a within-subjects study (N=35), adding these behaviors significantly improved the perceived attentiveness of the avatar, the sense of talking with the real person, and the feeling of co-presence. These results indicate that AI clone fidelity should extend beyond voice and response content to include interactive listening behavior.
Read the full abstract

All authors Koji Inoue, Kazushi Kato, Tatsuya Kawahara, Shunichi Kasahara

Computation and Language

Automated Summarization of Financial News Using Large Language Models and Retrieval-Augmented Generation: An Early Empirical Study (Fall 2023)

Stock market analysts and investors face a daily challenge: too much financial news, too little time. Manually reading and synthesizing hundreds of company-specific articles is impractical, yet missing key information can directly affect investment decisions. This project, conducted at George Washington University in Fall 2023, explores whether Large Language Models can automate this process reliably. We built a pipeline that pulls news articles from the News API, company background from Wikipedia, and stock price data from Yahoo Finance for ten major companies (AAPL, MSFT, GOOGL, AMZN, META, TSLA, JPM, NVDA, WMT, DIS). Because LLMs cannot directly process numerical tables, we developed a simple but effective template that converts stock data into natural language narratives. We then tested two summarization approaches (Summarize Chains and Retrieval-Augmented Generation with FAISS) across three open-source models (Falcon-7B-Instruct, DistilBART-CNN-12-6, BART-Large-XSum) for news, and GPT (text-davinci-003) for stock summaries. Falcon-7B with Summarize Chains gave the best results, covering all news events accurately and coherently. RAG, while promising in theory, caused severe repetition in Falcon and hallucinated facts in BART-Large when k was large. Both LLM-based approaches outperformed a simple Lead-3 baseline on ROUGE-1. We also built a Streamlit dashboard for interactive stock visualization. The work was done in Fall 2023, before RAG-based financial tools became widespread, and the failure modes we document, particularly hallucination under RAG in smaller models, remain relevant today.
Read the full abstract

Robotics

LF-GICP: Parameter-Free Degeneracy-Aware LiDAR Odometry via a Voxel-Normal Localizability Field

Scan-to-map LiDAR odometry drifts unboundedly along the unobservable axes of geometrically degenerate environments like tunnels and corridors, and existing degeneracy handling requires environment-specific parameter tuning. This paper presents a parameter-free approach. We show that in voxelized GICP the Gauss–Newton (GN) Hessian masks translational degeneracy, because covariance regularization keeps the translation block artificially well-conditioned. We bypass this with a regularization-free voxel-normal localizability field and two of its statistics: a normalized fraction $f_0$ detecting directional anisotropy, and an absolute per-voxel mass $\lambda_0$ distinguishing information absence (tunnels) from dilution (dense open scenes). A temporal-median gate combines both to trigger Fisher-information correspondence weighting. Calibrated once by fixed rules on two short sequences and then frozen, LF-GICP achieves the lowest KITTI relative translation error ($0.865\%$) under an identical evaluation protocol against re-run baselines, outperforms them on GEODE tunnels and MulRan, leads the HeLiPR mean, and generalizes across four sensor types without re-tuning. We further demonstrate empirically that straight, uniform tunnels remain unobservable along their axis for LiDAR-only registration.
Read the full abstract

Computational Engineering

Time Series Forecasting based on Solana Digital Asset Dataset

Accurate analysis and forecasting of Solana digital assets require data that captures both token-level behavior and ecosystem-level DEX activity. This paper introduces, to the best of our knowledge, the first Solana digital asset time series dataset designed for forecasting and market-structure analysis. The dataset contains 1,584 tokens observed at daily resolution from March 24, 2024 to March 16, 2025, with 27 variables combining token transactions, prices, liquidity-pool balances, trader activity, Solana DEX volume, DEX trader counts, newly created pairs, and SOL price indicators. Rather than treating the dataset only as input for model comparison, we use it to characterize the DEX-driven token market during a period of rapid ecosystem growth. The analysis identifies synchronized market-wide activity peaks in mid-November 2024 and mid-January 2025 across DEX volume, token trading volume, active wallets, buyers, sellers, new traders, liquidity-pool balances, and SOL price. The January 2025 peak coincides with the 'Trump' token event and is accompanied by a visible transition from liquidity accumulation to withdrawals, suggesting that individual token dynamics are strongly coupled to broader Solana market sentiment and DEX activity. Forecasting experiments are then used as an empirical validation of the dataset's signal content. In three-day-ahead market-capitalization prediction, PatchTST achieves the best overall rank, fine-tuned Chronos follows closely, and statistical baselines remain competitive for trend-dominated tokens. Feature-importance analysis further shows that SOL price, SOL moving averages, total DEX volume, DEX trader counts, and newly created pairs are among the most informative covariates. The main contribution is therefore a curated Solana forecasting dataset and a data-driven analysis of the ecosystem-level factors that shape token volatility.
Read the full abstract

All authors Yufeng Xiao, Minxing Wang, Pavel Braslavski, Dmitry I. Ignatov

Software Engineering

Garbage Collection and Energy Consumption in Java: A Controlled Study Across Workloads and JDKs

Garbage-collector selection is a low-effort configuration decision that can influence both the performance and energy consumption of Java applications. However, it remains unclear whether aggregate energy rankings among collectors generalise across heterogeneous applications, workload intensities, and JDK distributions. This study presents a controlled empirical evaluation of Serial, Parallel, and G1 garbage collection across three Java applications, three workload intensities, and two JDK distributions: OpenJDK and Oracle JDK. Using EnergiBridge, processor-package energy consumption and execution time were measured and complementary energy-performance metrics derived. Across all evaluated configurations, Parallel recorded the lowest mean energy consumption (839.8 J), followed closely by Serial (857.6 J) and G1 (969.0 J), but an RCBD ANOVA did not establish a statistically reliable collector effect. Workload intensity, by contrast, was a significant driver of energy consumption, with heavy workloads consuming substantially more energy than light or medium workloads regardless of collector. Energy consumption showed a moderate positive association with execution time (r = 0.33), indicating that longer-running configurations tended toward higher energy use, though the relationship was far from proportional. No statistically significant energy difference was found between OpenJDK and Oracle JDK. Overall, the results do not support a universally energy-optimal garbage collector; instead, workload intensity emerges as the more reliable lever for managing Java energy consumption, and collector selection should be treated as an application-specific tuning decision supported by measurement on the target system rather than aggregate rankings alone.
Read the full abstract

Computation and Language

Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does

Prosodic cues can carry task-relevant information that words omit, but existing benchmarks rarely test whether it changes downstream decisions. We introduce Hear2Act, a 480-scenario protocol with unstated user needs and verifiable task success. Across matched scenarios, we keep the task and user needs fixed, varying whether an unmet need is stated in words or absent from the transcript while the user's reaction is conveyed through prosody, yielding Explicit lexical and Prosody-mediated conditions. We vary assistant access to transcript, audio, and an indication of whether the recommendation is resolved, and evaluate two audio-capable LLMs and five text LLMs on behavior and task outcomes. Our results show an asymmetry: prosodic information is valuable when the need is absent from the transcript, but adds little when that need is stated in words. Yet neither audio-capable LLM benefits much from raw audio: adding audio to the transcript changes task success only from 14.3% to 15.1%. When models infer from audio whether the recommendation remains unresolved and use that inference with the transcript, success rises to 39.6%, close to 40.5% with ground-truth state. This reveals a perception-action gap: raw audio barely helps, while making the information explicit in text enables much better decisions.
Read the full abstract

All authors Xinyi Liu, Hooshang Nayyeri, Dilek Hakkani-Tur, Emine Yilmaz, Joo-Kyung Kim, Yifei Zhang, Charith Peris, Hari Thadakamalla

Machine Learning

In Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models

Persistent intelligent systems require the ability to learn continually, but current machine learning approaches face significant challenges in this area compared to biological learning systems. Machine learning algorithms typically trade off retention of previously learned information and adaptation to new or changing data patterns. When continual learning capabilities are absent, algorithms must undergo retraining using the entire data set, an approach that becomes impractical when original training data are unavailable due to storage constraints, financial or computational costs, or privacy restrictions. However, biological animals can learn continually, without experiencing catastrophic forgetting. This paper attempts to build a high-level framework for how animals learn and preserve knowledge by modelling neural components and states that are known to be related to memory consolidation. We focus on three concepts: experience replay, REM sleep, and bilaterality. We propose 4MAS (4 Module Awake/Sleep), a novel macroarchitecture demonstrating how machine learning models might benefit from asymmetric hemispheres, each with their own long- and short-term memory mechanisms, and how a period of sleep between incremental learning tasks might benefit memory consolidation. Finally, we present results showing that our architecture achieves statistical improvements over established generative replay baselines on Split-MNIST (98.3%) and Split-Fashion-MNIST (84.9%), while reducing forgetting by more than half relative to the strongest replay baseline and demonstrating monotonic capacity scaling on Split-CIFAR-100 (29.29%).
Read the full abstract

All authors Benjamin Smith, Levin Kuhlmann, Kaushik Roy, Gideon Kowadlo

Numerical Analysis

The Normal Procrustes Problem: A Riemannian Optimization Approach

For given $m \times n$ data matrices $X, Y$, we investigate the Normal Procrustes Problem—the least squares optimization problem that aims to minimize $\|AX-Y\|_F^2$, where $A$ is constrained to be a normal $m \times m$ matrix. As far as the author of this article is aware, no other method that attempts to solve the Normal Procrustes Problem exists in the literature; we thus propose what is, to our knowledge, the first such method. We, furthermore, adapt our approach to address the Real Normal Procrustes Problem, where $A$ must be real. In our treatment of these problems, we first reduce our complex and real objective functions to be purely optimizable over the Riemannian manifolds of the unitary and real orthogonal matrices, respectively. This reduction enables us to apply techniques in Riemannian manifold optimization to approximate solutions to both. The Closest Normal Matrix and Real Closest Normal Matrix Problems are both special cases of their respective Procrustes Problems (by setting $m = n$ and $X = I_m$) and have been previously studied in the literature. Our approach thus recovers a novel Riemannian optimization method for approximating solutions to both these problems. We further numerically test the performance of our method across all such problems (including against previously developed algorithms on the Closest Normal Matrix Problems) and obtain competitive residuals and favorable scaling in wall-clock time.
Read the full abstract

Artificial Intelligence

Symposium: Trust via Auditable Records for Communities of AI Scientist Agents

Symposium is a formal framework and practical implementation to record the operation of AI agents deployed by small scientific research communities. Symposium provides long-term, immutable histories of agent-driven research activity, leaving auditable trails of analyses, hypotheses, data, and scientific discourse. This shared record of published artifacts enables agents to build on prior work and preserves the evidence researchers and agents need to make purpose-dependent trust assessments. Symposium captures scientific argument, including structured claims, fine-grained evidence citations, assumptions, and explicit declarations of what material may and may not be used as evidence. Symposium differs from AI co-scientist agents or integrated AI research environments; it is a framework that separates a scientific community's durable history from the agents and other systems that operate on that history. It assumes that a community will use diverse AI systems in a rapidly evolving environment. A working implementation of the publication infrastructure, agent prompt components, and documentation are provided to enable users to rapidly set up and run their own Symposium community.
Read the full abstract

Software Engineering

Trace-Based Execution-Level Observability of VDM-SL Specifications

VDM has been pursuing rigorous verification through mathematical theorem proving and software testing via simulated execution. Animation through an interpreter enables validation of the specification to ensure it meets the required functionality. Step-by-step execution in a debugger also allows the user to follow the internal behavior of operations. In this paper, we propose the recording and utilization of execution traces of assignments, operation calls, and return statements to make the internal behavior of operations persistent and analyzable as state-based models. The data model of events in execution traces, its implementation in ViennaTalk, and its application to visualization will be introduced.
Read the full abstract

Wednesday 19 August

Information Retrieval

Improving Contextual Retrieval for Long Documents using Semantic Chunking and Hybrid Retrieval Strategies

The vast amount of information available in lengthy, distributed documents makes finding relevant answers difficult, especially when the answer requires connecting evidence from multiple sources. Standard Retrieval-Augmented Generation (RAG) systems often struggle with this type of "multi-hop" reasoning and frequently face issues with context fragmentation. In this paper, we propose a hybrid RAG framework that integrates the structured reasoning of knowledge graphs with the broad semantic coverage of dense vector retrieval. Our approach employs a multi-stage pipeline using transformer-based summarization and semantic chunking to improve context retention. We construct a dynamic knowledge graph to capture explicit relationships between entities while simultaneously maintaining a dense vector index. During inference, the system uses a hierarchical mechanism that prioritizes graph traversal for precision and falls back to vector retrieval when necessary. We evaluated our framework on the MultiHop-RAG dataset. The results show that this hybrid approach outperforms standalone vector and graph-based baselines, achieving higher Exact Match scores and improved retrieval accuracy for complex queries. This confirms that merging structured reasoning with standard vector retrieval creates a more robust system for handling complex knowledge-intensive questions.
Read the full abstract

Machine Learning

SAGE-CP: When Marginal Coverage Hides Route-Conditional Failures in Adaptive VLM Ensembles

Adaptive VLM ensembles save computation by stopping early on easy images and escalating harder ones. Although a single conformal threshold can make the final predictor marginally valid, it can still fail severely along individual computational routes. We characterize this failure precisely: if a route has prevalence pi, marginal 1-alpha coverage allows its conditional coverage to fall to max{0, 1-alpha/pi}. To address this mismatch, we learn the router on development data, freeze all routing choices, and calibrate the returned score separately for early exits and escalated inputs. We call this pipeline SAGE-CP. Its calibration step applies Mondrian split conformal prediction to the operational groups created by the router. Under exchangeability, the resulting prediction sets achieve finite-sample coverage within each route. Across 10 benchmarks, 4 frozen VLMs, and 5 aligned splits, both global calibration and SAGE-CP achieve 0.900 marginal coverage at a 0.90 target, but their route behavior differs substantially. SAGE-CP raises mean worst-route coverage from 0.623 to 0.887 and reduces the mean route-coverage gap from 0.324 to 0.025, using the same routed scores and 1.177 source calls per image. The stronger guarantee increases the mean prediction-set size from 1.893 to 2.212; nevertheless, the sets remain smaller than those of the full ensemble (2.486) while requiring 70.6 percent fewer source calls. The route-level reliability persists across 6 fixed query fractions, while finer exit-depth groups demonstrate the need for additional calibration data on rare routes. Across 5 datasets, SAGE-CP also reduces measured batch-one latency by 58.8 to 63.4 percent and gross GPU energy by 55.7 to 57.5 percent relative to full inference. Thus, routing provides computational savings, while route-stratified calibration attaches coverage guarantees to the operational paths created by the router.
Read the full abstract

Computational Geometry · Cross-listed from math.MG

Certified Geometry and Admissible Motion of Gerver's Sofa

The moving sofa problem asks for the largest planar set that can pass through a unit-width right-angled hallway. Gerver's 1992 construction remains the largest explicit example, but its defining switching parameters, continuum of supporting hallways, and contact topology involve transcendental equations and global inequalities. We give a reproducible exact-rational certification of the construction. A strict four-dimensional Krawczyk inclusion encloses the reduced switching system, while an independent twenty-two-dimensional Krawczyk calculation verifies Romik's full matching and contact equations in an explicit rational box. Exact interval propagation through the five analytic phases proves the support identities, global half-plane constraints, inner-wall separation, niche topology, oriented contacts, injectivity, and area bounds. From the certified support functions we identify every supporting hallway as L_t=x(t)+R_tL. For G=K_0\setminus\mathcal N(K_0) we prove directly that G is nonempty, closed, and connected and that \Phi_t(q)=R_{-t}(q-x(t)) is a continuous path in SE(2) carrying G through the hallway, with the correct initial and final arms. We further identify G with Romik's reconstruction of Gerver's classical eighteen-piece sofa. The deterministic companion verifier uses only Python's standard library and exact rational arithmetic. As a consequence, the Gerver-specific geometric hypotheses in Baek's recent variational framework are rigorously certified; we also clarify the one-sided tangent-speed convention at two contact-curve junctions.
Read the full abstract

Programming Languages

DLCB: Ahead-of-Time Compilation for Dynamic Deep Learning

Deep learning workloads are increasingly deployed in settings where tensor shapes are not fully known at compile time. Batch sizes vary across requests, sequence lengths differ between inputs, and model architectures admit a range of spatial resolutions. This dynamism creates a fundamental tension: ahead-of-time compiled GPU kernels deliver peak performance but traditionally require fully static tensor shapes, while just-in-time compilation supports dynamic shapes at the cost of runtime compilation overhead. We present DLCB (Deep Learning Compiler Backend), a deep learning compiler that resolves this tension through a unified three-tier compilation strategy. For programs with fully static tensor shapes, DLCB generates static CUDA C++ kernels ahead of time. For programs whose tensor rank is statically known but whose dimension sizes are dynamic, DLCB generates AOT kernels parameterized by those dimensions, compiling once and executing across a range of shapes. For programs with tensors of unknown rank, DLCB falls back to JIT compilation at runtime. For AOT compilation with dynamic shape tensors, our approach builds a system of shape constraints from the input program, and uses a solver to reduce these to either a) fixed constraints that produce hard-coded constants in the generated kernel; b) unresolved constraints which become kernel parameters passed at launch time, along with interpreted host code to check that the constraint holds for a given set of inputs and to compute the values to pass. Our compiler and runtime are embedded in PyTorch, and use an automatic shape generalization pass to enable AOT compilation with dynamic shapes for supported subsets of PyTorch programs
Read the full abstract

All authors Alexander Collins, Bin Fan, Evghenii Gaburov, William Brandon, Sean Lee, Hanfeng Chen, Vinod Grover

Machine Learning · Cross-listed from stat.ML

Theoretical Study on the Evidential Learning-based Variational Autoencoder

A normal–inverse-gamma (NIG) latent hierarchy has four parameters, but its induced latent law does not identify all four. For $\sigma^2\sim\mathrm{InvGamma}(\alpha,\beta)$, $\mu\mid\sigma^2\sim\mathcal{N}(\gamma,\sigma^2/\nu)$, and $z\mid\mu,\sigma^2\sim\mathcal{N}(\mu,\sigma^2)$, the marginal law of $z$ depends on $(\nu,\beta)$ only through $c=\beta(1+1/\nu)$. Hence the reconstruction-visible parameter space is the three-dimensional quotient $(\gamma,\alpha,c)$, with a one-dimensional fiber degree of freedom. For a fixed hierarchical variational objective, exact partial minimization of the forward KL divergence to a complete NIG prior selects a unique prior-relative representative on each fiber, yielding an exact three-coordinate reduction with the same optimum as the four-coordinate objective. Writing $\rho_0=2\beta_0/\nu_0$ and $T=c/\{\alpha[(\gamma-\gamma_0)^2+\rho_0]\}$, we show that inverse canonical allocation $1/\nu_{\rm can}$ is an explicit strictly increasing function of $T$. For $\alpha>1$, the ratio $u_{\rm epi}/u_{\rm var}=1/\nu_{\rm can}$ is therefore determined by the quotient state and prior; for rank-only use under a common calibration, $T$ contains the same coordinatewise ordinal information. The residual prior gauge is characterized rather than eliminated: $(\gamma_0,\rho_0)$ govern ordinal dependence, while $(\nu_0,\alpha_0)$ determine numerical calibration and the analytic ceiling of $1/\nu_{\rm can}$.
Read the full abstract

Computer Vision

Geometry-anchored PET-aware multimodal pseudo-CT synthesis for whole-body attenuation correction: the BIC-MAC Challenge

The BIC-MAC challenge targets whole-body pseudo-CT synthesis from NAC-PET, Dixon MRI, and a 2D topogram for CT-less PET attenuation correction. We propose GeoPACT, a geometry-anchored multimodal framework that uses NAC-PET as the spatial reference and incorporates topogram and MRI features through gated residual fusion. Absolute coordinates and whole-body conditioning support anatomically consistent patch-based prediction. Training combines attenuation-map supervision with a differentiable PET-response surrogate to reduce errors relevant to downstream PET reconstruction. Full-resolution pseudo-CT volumes are generated using sliding-window inference without requiring CT or PET labels at test time.
Read the full abstract

All authors Xuan Loc Nguyen, Hoang-Loc Cao, Truong Thanh Hung Nguyen, Phuc Ho, Phuc Truong Loc Nguyen, Nguyen Truong Toan To, Hung Cao

Cryptography and Security

Security and Privacy in Large-Model-Driven Embodied Agents: Attacks, Defenses, and Future Directions

Large-model-driven embodied agents integrate foundation models with perception, reasoning, planning, and physical action, extending conventional model-level risks into embodied closed loops. Existing studies on their security and privacy remain fragmented across different system components and operational stages, making it difficult to understand how risks arise, propagate, and ultimately affect physical behavior or sensitive information. This survey presents a lifecycle-based analysis of security and privacy in large-model-driven embodied agents. We organize existing research into five stages: model construction and supply chain, multimodal input and interaction, semantic reasoning and task planning, action execution and physical feedback, and long-term deployment. Within this lifecycle, we systematically review representative attacks, defenses, and evaluation methods. Our analysis shows that attack entry, consequence realization, and defense intervention often occur at different stages of the embodied closed loop. It further reveals substantial gaps in end-to-end protection, real-world evaluation, and long-term privacy governance. This survey provides a unified perspective for understanding current progress and identifying critical directions for securing large-model-driven embodied agents.
Read the full abstract

All authors Lele Zheng, Tong Chen, Ke Cheng, Tao Zhang, Xingchi Liu, Ji He, Xutong Mu, Yulong Shen

Information Retrieval

Query Implied Generative Engine Optimization

The landscape of search has changed drastically with how people look for information online. Traditional search engines are being replaced by Generative Search Engines (GSEs), which use Large Language Models (LLMs) to generate natural language responses to user queries. For content creators, visibility is no longer solely determined by ranking in search results but by being cited within generated responses. But Generative Search Engines are black-boxes, leading to the emergence of Generative Engine Optimization (GEO), a set of techniques aimed at improving content visibility in generative search settings. Most existing approaches rely on the explicit queries or query derived signals to align content to better suit user needs. We propose Query Implied Generative Engine Optimization (QI-GEO) to infers user intent directly from the document. Our approach approximates document's intent space and identifies content that may be missing yet relevant to answer potential user queries. Evaluation on GEO-Bench and Extended GEO-Bench demonstrated improvements across objective and subjective metrics. QI-GEO improved objective scores by up to 15.9% and subjective scores by up to 17.6%, while yielding nearly twice as many citation gains as citation losses. These results suggest that document-derived approximations of user intents can improve visibility without relying on explicit query inputs.
Read the full abstract

Computers and Society

AI Can Do Your Homework. Now What? Report from an Online Workshop on Computing Assessment in the Age of Generative AI

On 28 July 2026, the SIGCSE Virtual 2026 Working Group on computing assessment and generative AI held an open online workshop attended by 73 computing educators. The first hour ran seven strategy rooms, one per approach to adapting (or deliberately preserving) computing assessment in the AI era: open-ended and authentic task design; ambitious, AI-leveraged projects; evaluating and fixing AI-produced work; controlled and AI-free assessment; process evidence and effort signals; rubric and grading redesign; and oral and interactive assessment. The second hour ran question rooms seeded from those strategies, plus two cross-cutting rooms on fairness and trust and student motivation. This report records what was discussed: the approaches participants have tried, the results they reported, and the questions every room left open. It is the first public artifact of the working group, whose taxonomy of computing assessments that accommodate generative AI use will follow.
Read the full abstract

All authors Muhammad Sajjad Akbar, Geoffrey Challen, Fraida Fund, Casey Hopkins, Oscar Karnalim, Kevin Lin, James McGuffee, Shubbhi Taneja, Ranysha Ware