Computers and Society
Dataset repurposing and disruptive AI research
Yulin Yu, Yong-Yeol Ahn and Daniel M. Romero
Technological advancements are enabling increasingly systematic and large-scale data collection across all areas of science, driving scientific innovation. In particular, AI research exemplifies this trend, having advanced rapidly through the assembly of massive
datasets used to train and evaluate machine learning models. However, the escalating demand for data, the difficulty of creating high-quality
datasets, and the exhaustion of easily accessible data sources in AI research raise important questions about how to maximize the value of existing
datasets through recombination and repurposing. Here, we draw on two theoretical frameworks—recombinational novelty and transformational creativity—to examine the practice of data repurposing and its scientific impact. Focusing on AI, we analyze scientific outcomes associated with data repurposing across more than 10,000 machine learning papers. First, we find that although most repurposed
datasets do not achieve broad visibility in the short term, data repurposing is associated with greater disruption. Second, when repurposed data is adopted by subsequent research, the repurposing paper is associated with higher disruption and increased citation impact. Third, repurposing teams tend to be more experienced, more institutionally prestigious, and involve academic–industry collaboration. However, team characteristics poorly predict which repurposed
datasets will be adopted by the community. These findings suggest that data repurposing may be an important approach to scientific discovery, and that its successful adoption is more common among larger teams and collaborations spanning academia and industry.
Read the full abstract ▾
Cryptography and Security
When Agents See Differently: Exposing UI Desynchronization Threats in Mobile Agents
Heng Li, Fulin Zhao, Zhe Geng et al. (+3 more)
Mobile
agents may act on interface content that users cannot see or easily notice, making their actions harder to oversee. We characterize this gap as human-
agent UI desynchronization and investigate how attackers can exploit it through perturbations embedded in applications before deployment. Beyond accessibility metadata, we identify two mechanisms that expose misleading cues to screenshot-based
agents: content rendered in display-occluded regions under compatible device configurations, and low-contrast text that remains encoded in screenshots but is difficult for users to notice. We develop an automated framework that searches application-specific perturbation strategies, optimizes their content using representative tasks, and realizes the perturbations in deployable applications. The perturbation content remains fixed at runtime and requires neither access to future user instructions nor detection of
agent use. Using a
benchmark of 546 tasks across 13 applications, we evaluate five mobile-
agent frameworks and three backbone models. The attacks achieve average misleading rates of 77.4% in static observation-space evaluation and 67.2% in dynamic application-level evaluation, where success denotes selection of an attacker-designated decoy control. We invited 195 participants to assess the perceptibility of our visual perturbations and found that none spontaneously noticed the low-contrast text. These findings expose a security gap between human-visible interfaces and
agent-observable representations, showing that inconspicuous application content can redirect delegated actions even without runtime adaptation.
Read the full abstract ▾
All authors Heng Li, Fulin Zhao, Zhe Geng, Zhiyuan Yao, Wei Yuan, Xiapu Luo
Distributed Computing
The Price of Random Access: Measuring Block Granularity Across Four Compressed Formats
Yakiv Shavidze
Random access into compressed data is normally bought with density. We measure the exchange rate. Across four formats and nine axes on a common corpus, the cost of cutting a 254 MB archive into independently addressable 16 KiB units is 1.632% of the archive for an absolute-offset format against 6.57% for seekable zstd, and the gap widens as the unit shrinks: at 4 KiB, 5.33% against 10.06%. Because the cost is small, several properties follow that are usually unavailable: splitting an archive is free and occasionally profitable (-0.28% on tiled input), append needs no format change, seek latency does not depend on position, and one archive is read by both a CPU and a GPU decoder. We give three structural results with proofs and bit-perfect verification - that the repeat-distance chain of an LZ77 parse forms a substitution monoid and is therefore prefix-scannable without touching the bitstream, that self-overlapping matches are periodic rather than chained, and that dependency depth admits an encoder-enforced bound - and we report each measured limit together with the mechanism that sets it. Seventeen rejected directions are listed with their numbers, including one that improved density by 26% and was declined. Every claim carries a level: reproducible by command, measured with a stated reason, or estimated. The measurement tool is released separately (DOI 10.5281/zenodo.22713364) with 435 provenanced records.
Read the full abstract ▾
Artificial Intelligence
LSREP: A Longitudinal State-Replay Protocol for Evaluating Conversational Memory, with ICE v2 as an Audited Local-First Architecture
Deepesh Sonar
Conversational
memory changes during use, so endpoint question answering alone cannot establish how a persistent state accumulates, ages, or incorporates revisions. We introduce LSREP, a Longitudinal State-Replay Evaluation Protocol combining ordered replay, explicit lifecycle schedules, repeated probes, evolving reference answers, and mechanism-fidelity checks. Its architectural case study is ICE v2, a local-first
memory middleware with typed stores,
retrieval fusion, and dynamic context budgets. The private, single-user instantiation contains 1,985 turns, 219 distinct probes, and 1,211 probe-checkpoint observations across 52 checkpoints. On three ordinary-density
datasets, ICE v2 has a near-zero mean quality difference from vector-RAG while selecting 32% fewer fragments but using 6.6% more estimated
prompt tokens. A fourth, dense
dataset exposes catastrophic failures of the unbudgeted baseline. The fidelity audit limits attribution: procedural
retrieval is defective, several mechanisms are unexercised, and graph utility is not established. In a complementary matched public diagnostic, ICE v2 loses decisively to pure vector-RAG on LongMemEval: 50.8% versus 72.8% in the evidence-only oracle and 43.0% versus 69.5% in full-S. Paired differences are -22.0 points (95% CI [-26.6, -17.4]) and -26.5 ([-31.3, -21.8]). Conservative abstention accompanies severe multi-session and temporal failures. ICE uses less context in this diagnostic, establishing a quality-cost trade-off rather than superior efficiency. Together, replay, fidelity
auditing, and public endpoint testing expose distinct failure modes that neither architectural descriptions nor aggregate scores identify alone.
Read the full abstract ▾
Hardware Architecture
SpecLens: LLM-Based Verilog Generation with Specification-Derived Constraints via Behavioral Divergence
Wen Bing and Bing Li
Large
language models (LLMs) have recently shown promise in Verilog generation, but producing functionally correct RTL directly from natural-
language specifications remains a highly challenging task. Existing approaches improve LLM-based Verilog generation mainly with
retrieval-augmented generation (RAG), self-planning, or few-shot prompting. However, these methods focus primarily on external or generic forms of enhancement rather than strengthening the specification with task-specific constraints. In this work, we propose SpecLens, an automated framework for LLM-based Verilog generation that derives specification-driven constraints by analyzing behavioral divergence among multiple candidate implementations, using the original specification as the only external semantic source during generation. On the VerilogEval v2.0 spec-to-RTL
benchmark, SpecLens achieves a functional pass@1 ratio of 86.2% with o3-mini-medium and 89.4% with o3-mini-high. This corresponds to a 3.6 percentage-point gain over the SOTA prompting method with o3-mini-medium and a 3.8 percentage-point gain over the SOTA behavioral divergence method with o3-mini-high. In addition, on RTLLM v1.1 and v2.0, analysis shows that SpecLens is more specification-faithful and less prone to
benchmark-aligned priors. SpecLens achieves 100% syntactic correctness on VerilogEval v2.0, 86.2% on RTLLM v1.1, and 88% on RTLLM v2.0, even without using costly compile-repair loops to revise generated code iteratively. The code is open source and available at https://anonymous.4open.science/r/SpecLens-4632/readme.md.
Read the full abstract ▾
Computer Vision
PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimation
Yihan Chen, Huan Ren, Wenfei Yang et al. (+3 more)
Category-level object pose estimation seeks to recover a similarity transform $(R,t,s)$ for unseen instances without instance-specific CAD models. Most competitive methods are correspondence-based: prior-free variants regress canonical (NOCS) coordinates directly from local observations and implicitly memorize the canonical frame in the weights, which ties the parameters to category-typical orientations and hurts generalization under distribution shift; prior-based variants introduce a category prior but typically follow a serial deform-then-align pipeline, where underconstrained canonical completion can corrupt correspondences and induce error cascades in pose. We propose PriorPose, a reference-guided correspondence framework that keeps the category prior explicit and solves canonicalization and
alignment jointly in a shared feature space. A reference-guided seeded
transformer embeds the partial observation and the category prior as
token sets and fuses them via geometry-aware seeds, from which the network jointly predicts a per-point NOCS field for visible points and a canonical deformation of the prior that reconstructs a full canonical instance, while a deep pose head regresses $(R,t,s)$ from the induced correspondences. A two-part shape consistency objective, with canonical-space and camera-space consistency losses, couples correspondence, deformation, and pose, reducing reliance on memorized canonical orientations and avoiding deform-then-align error cascades. Experiments on standard and larger-category
benchmarks demonstrate that PriorPose sets new state-of-the-art results on most evaluated metrics, especially under strict pose thresholds, while remaining competitive on relaxed pose and IoU metrics and showing improved robustness under shape variation and domain shift.
Read the full abstract ▾
All authors Yihan Chen, Huan Ren, Wenfei Yang, Hang Du, Tianzhu Zhang, Feng Wu
Computational Complexity · Cross-listed from quant-ph
Improved Separations between Quantum and Classical Communication Complexity of Total Functions
François Le Gall
We refine Gavinsky's framework (arXiv:2608.18784) for exponential separations between
quantum and randomized communication complexity of total functions and obtain larger separations: polylogarithmic
quantum communication versus $\tilde\Omega(\sqrt n)$ randomized communication with two
quantum messages, and versus $\Omega(n^{1-\varepsilon})$ for every fixed $0<\varepsilon<1$ with more
quantum messages.
Read the full abstract ▾
Robotics
CorrRisk-WM: Corridor-Conditioned Risk World Modeling for Safety-Critical Trajectory Planning
Tingyu Guo and Reza Langari
Safe local planning requires
forecasting surrounding-
agent motion and evaluating candidate-specific risks, since identical
agent motion can pose different risks to different ego trajectories. We present CorrRisk-WM, a planning-oriented partial world model coupling environment
evolution with supervised intrusion and near-miss prediction over bounded candidate-trajectory corridors. A latent environment model recursively predicts
agent states and updates
agent-
agent and
agent-map interactions. Each candidate queries the evolving environment through footprint- aware geometry and learned
agent-corridor representations. A lightweight recurrent risk module uses temporal context to estimate per-slice hazards; survival aggregation yields first-entry and horizon-level event probabilities. On 29,176 scenarios from 100 Waymo validation shards, CorrRisk-WM achieves intrusion average precision (AP) of 0.8567 and 1-m near-miss first-entry AP of 0.8671. In baseline comparisons, it attains the highest near-miss AP at all three distance thresholds and the lowest observed open-loop collision rate (4.88%), with route progress of 15.35 m. Across three seeds, removing dynamic environment modeling or candidate-conditioned
geometric interaction reduces mean intrusion AP from 0.8590 to 0.7624 and 0.7252, respectively. These results support coupling environment
evolution with candidate-conditioned
geometric reasoning for risk prediction and safety-oriented candidate selection.
Read the full abstract ▾
Data Structures and Algorithms
A deterministic $(2 + \varepsilon)$-approximation for directed feedback vertex sets in tournaments
Ebrahim Ghorbani and Matthias Mnich
We nearly settle the
polynomial-time approximability of the Directed Feedback Vertex Set problem in tournaments. This problem is Vertex Cover-hard, and thus cannot have a $(2 - \varepsilon)$-approximation for any $\varepsilon > 0$ in
polynomial time assuming the Unique Games
Conjecture. In the past 28 years, several works have attempted to attain this approximability barrier of 2, and have designed
algorithms with smaller and smaller approximation factors. This includes a $5/2$-approximation by Cai, Deng and Zang (FOCS 1998, SICOMP 2001); a $7/3$-approximation by Mnich, Vassilevska Williams and Végh (ESA 2016), another $7/3$-approximation by Aprile, Drescher, Fiorini and Huynh (DAM 2023), and a $9/4$-approximation by Ghorbani and Mnich (ICALP 2026). Our main result improves upon all of those works: we give the first deterministic
polynomial-time $(2+\varepsilon)$-approximation for Directed Feedback Vertex Set in tournaments, for all $\varepsilon > 0$. We thereby almost answer an open question by Lokshtanov, Misra, Mukherjee, Panolan, Philip and Saurabh (SODA 2020) who asked for a deterministic 2-approximation in
polynomial time. Furthermore, we extend our result to the broader class of quasi-transitive digraphs
Read the full abstract ▾
Artificial Intelligence
VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMs
Haoyu Guo, Yuan Feng, Junlin Lv et al. (+3 more)
Scaling
Multimodal Large
Language Models (MLLMs) to long-form
video understanding is bottlenecked by the explosion of visual
tokens, which saturates context windows and incurs prohibitive costs. Current solutions predominantly rely on auxiliary models for
token reduction but face a fundamental dilemma: lightweight encoder-driven approaches often overlook critical semantic information, whereas heavyweight MLLM-driven reduction negates the efficiency gains. {In this work, we identify a more fundamental inefficiency underlying this dilemma: while fine-grained visual details are essential for detailed understanding, they are largely redundant for the preliminary task of selecting semantically relevant regions. } Motivated by this, we introduce VideoMM, which marks a paradigm shift from model-centric downsizing to adaptive perceptual granularity. Specifically, our framework {decouples selection from
reasoning} by executing semantic filtering on a cost-effective Macro Proxy (derived from downscaled frames), and projecting the selected regions onto high-fidelity Micro
Tokens for detailed understanding only when necessary. Extensive evaluations show that VideoMM significantly outperforms existing solutions. It achieves a 6.13$\times$ speedup and a 7.4% accuracy gain over full-context baselines on LongVideoBench, and further accelerates inference by 2.73$\times$ over current leading methods, establishing a highly scalable paradigm for long-
video understanding. Our code is available at: https://github.com/adfh917k/VideoMM.
Read the full abstract ▾
All authors Haoyu Guo, Yuan Feng, Junlin Lv, Mingjun Xiao, S Kevin Zhou, Xike Xie
Information Theory · Cross-listed from quant-ph
Phase Transition in Binary Compressed Sensing via Annealing with Adaptive Regularization
Xiaoxin Huang and Masayuki Ohzeki
Regularization choice changes the recovery phase diagrams of annealing-based binary compressed sensing. We develop a regularization-selection method that combines systematic parameter search with random forest regression. Under noiseless Gaussian measurements with known sparsity, reference parameters are selected from a candidate grid by minimizing mean squared reconstruction error over repeated simulated annealing (SA) trials. The fitted model predicts these reference values from signal dimension, sampling ratio, and sparsity. With predicted regularization, the SA recovery transition broadly follows the asymptotic reference boundary for box-constrained $\ell_1$ recovery at the larger signal dimensions examined. Without retraining, the same predictor supplies identical regularization values to SA and a
quantum–classical hybrid solver. On matched problem instances, the hybrid solver yields smaller mean squared reconstruction errors than SA in parts of the evaluated parameter space. The resulting rule reuses the searched information for subsequent reconstruction without repeating candidate searches at each setting. The results quantify empirical performance under the stated finite candidate grid and solver settings; they do not constitute a solver-independent recovery guarantee or a time-to-solution comparison.
Read the full abstract ▾
Computational Complexity
Euclidean SVP is NP-hard for Cyclic Lattices
Daqing Wan
We prove that exact Euclidean SVP is NP-hard under deterministic
polynomial-time many-one reductions for full-rank cyclic integer
lattices, equivalently full-rank ideals of $R_N:=\mathbb{Z}[X]/(X^N-1)$ in the coefficient norm. Hardness holds with $N=q-1$ for a varying odd
prime $q$. As an application, we prove the same hardness for the algebraic class of NTRU-form
lattices $\{(x,z)\in R_N^2:Hx\equiv z\pmod{QR_N}\}$, where $H,Q$ are unrestricted inputs. The decision problems are NP-complete, and the exact search problems are NP-hard under
polynomial-time Turing reductions. No hardness claim is made for cryptographic NTRU parameter subclasses or key-generation distributions.
Read the full abstract ▾
Machine Learning
Continuous-Time Machine Learning: A Unified Mathematical Perspective
Waleed Razzaq, Yun-Sheng Zhao and Yun-Bo Zhao
Continuous-time (CT) machine learning has emerged as a principled framework for modeling temporal dynamics as a continuous process, particularly when observations are sampled at arbitrary time points or span long-range horizons. However, major branches of CT machine learning have matured in separate research communities, leaving their mathematical relationships and design trade-offs insufficiently characterized. In this survey, we develop a unified, concept-driven view of major CT machine learning branches through a taxonomy that organizes families according to their underlying base mathematical formulations. We present a canonical mathematical formulation that relates these families through different architectural choices of vector-field parameterization, stochasticity,
memory mechanisms, and discretization. We compare training
algorithms, optimization strategies, and failure modes, highlighting the trade-offs across families. We further provide a comparative analysis of theoretical computational complexity alongside an illustrative architecture-controlled
benchmark analysis on representative architectures from each family. We also review software ecosystems supporting their implementation. Finally, we identify open challenges in approximation theory, training stability, hardware-efficient implementations, benchmarking, foundation models, and scientific machine learning, and discuss an agenda for future research.
Read the full abstract ▾
Logic in Computer Science
Vibe-Coded and Tuned: A State-of-the-Art SMT Solver for QF-LRA
Mikoláš Janota and Jan Jakubův
This paper presents the SMT solver primo, which is fully vibe-coded and then parameter-tuned, achieving state-of-the-art results on linear real arithmetic (QF-LRA). The performance of primo is achieved by a systematic literature survey, repeated profiling, and parameter tuning. The resulting solver outperforms the winner of the QF-LRA track of SMT-COMP~2026. This confirms that vibe-coding of automated
reasoning tools will enable us to make great strides in the future.
Read the full abstract ▾
Robotics
The Robot Data Factory
Sami Haddadin, Ivan Laptev, Ian Reid et al. (+18 more)
Physical AI requires more than increasingly large
robot datasets: intelligent
robots acquire knowledge through continuous interaction with the physical world. We argue that the defining scientific resource of Physical AI is therefore not raw
robot data alone, but
robot experience - physically grounded interaction whose observations, actions, embodiment, context, and outcomes preserve the perception-action-consequence loop. We introduce the
Robot Data Factory (RDF), a mission-driven infrastructure and methodology for continuously generating, validating, benchmarking, and reusing such experience. RDF organizes heterogeneous
robots and environment-specific training grounds through reproducible missions, skill curricula, synchronized
multimodal sensing, external ground truth, an agentic
robot network, data pipelines, and living
benchmarks. Rather than treating
datasets as static end products, RDF implements a closed Deploy-Measure-Learn-Repeat cycle in which validated physical experience supports world models,
vision-
language-action models,
embodied policies, digital twins, and subsequent
robot deployment. We further formalize
robot experience and its quality, introduce a mission-task-skill-episode-
dataset-
benchmark-capability hierarchy, and derive quantitative scaling laws and an algorithmic synthesis procedure connecting
robot fleet size, sensor rates, storage, learning representations, tokenization, training compute, inference, and latency to
Embodied-AI cluster requirements. The framework is instantiated in three complementary physical training grounds for domestic, environmental, and energy applications. RDF thus reframes
robot data generation as a continuous scientific production process and provides a pathway toward reproducible, scalable, and eventually
federated infrastructure for Physical AI.
Read the full abstract ▾
All authors Sami Haddadin, Ivan Laptev, Ian Reid, Dezhen Song, Cesare Stefanini, Abdalla Swikir, Xingxing Zuo, Lyes Saad Saoud, Mahmoud Hamandi, Mohamed Heshmat, Oualid Doukhi, Abdeldjallil Naceri, Attique Bashar, Abdelrahim Mohamed, Teodor Tomic, Yue Peng, Samuel Schneider, Cheng-Chung Lee, Janine Guo, Qinghao Zhang, Kim Jeffery
Robotics
World Models for Embodied Intelligence: From Plausible to Controllable to Actionable
Nanjie Yao, Hao Wang, Chong Cheng et al. (+10 more)
World models connect perception and decision-making in
embodied intelligence by maintaining hidden state, anticipating consequences, comparing interventions, and adapting when execution departs from expectations. Although progress is often measured by visual fidelity, their value lies in improving behavior. Before reaching for a cup, a person anticipates its weight and resistance to grasping, shaping the hand before contact. Such anticipation is coarse and rarely pictorial, yet it guides action. This raises a central question: which predictive capabilities improve behavior? Existing surveys, organized by architecture, output modality, or application domain, leave this question implicit. We introduce three progressively stronger capability levels: Plausible models preserve task-relevant temporal,
geometric, or physical structure; Controllable models additionally predict how interventions alter that structure; and Actionable models translate predictions into measurable gains in planning, action, learning, evaluation, verification, recovery, or data selection. We complement this hierarchy with a 3 x 4
matrix crossing geometry, physics, and action grounding with improvement loops centered on data, rewards, policies, and the model itself. Using this framework, we survey manipulation,
navigation, locomotion, autonomous driving, and general
embodied learning, tracing technical progressions, clarifying capability requirements, and examining
datasets,
benchmarks, and evaluation protocols. We identify challenges in long-horizon consistency, uncertainty calibration, causal intervention testing, latency, verification and recovery, and cross-embodiment transfer. This perspective shifts evaluation from visual plausibility toward whether predictions capture task-relevant state, reflect intervention effects, and improve the closed-loop behavior of
embodied agents.
Read the full abstract ▾
All authors Nanjie Yao, Hao Wang, Chong Cheng, Zhikang Chen, Wenzhe Li, Jiafei Lyu, Li Shen, Peilin Zhao, Zongqing Lu, Gao Huang, Steven Hoi, Dacheng Tao, Deheng Ye
Robotics
IL-ACT: Imitation Learning with Adaptive Cartesian Tracking Control for a 30-ton Excavator
Mehdi Heydari Shahna, Seihun Kim, Soyi Jung et al. (+3 more)
Autonomous excavator control is challenged by coupled kinematics, actuation lag, and uncertainty. We propose imitation learning and adaptive Cartesian tracking (IL-ACT), a novel motion control framework for a 30-ton-class excavator. An anchored, 14-input imitation policy pretrained on operator demonstrations generates nominal joint rates; adaptive Cartesian feedback and gated gain/bias estimation correct these commands before a stopping-distance governor constrains joint-reference generation. Simscape evaluation covers 100 sequential goals and spiral, figure-eight, and rounded-raster tracking, including 88 additional runs across three training seeds, two initializations, and speeds, under hydraulic response and sensing conditions. Compared with Teacher+ACT, IL-ACT completes all goals with shorter duration and lower terminal errors under both response conditions. Telemetry-initialized IL-ACT lowers RMSE in all 24 figure-eight and rounded-raster seed comparisons and lowers additional-load spiral mean RMSE by approximately 29%. Original spiral RMSE also improves over IL-only and PID. Under a shared sensor-noise realization, telemetry-initialized IL-ACT achieves 27.67% lower mean RMSE than Teacher+ACT; enabling estimation reduces mean RMSE by $22.44\%$ relative to the frozen
estimator. Pretrained-weight effects remain mixed, and the original teacher comparison exhibits a spiral RMSE–maximum-error tradeoff. Analysis establishes bounded adaptive states and Cartesian feedback, with reference admissibility conditional on governor feasibility.
Read the full abstract ▾
All authors Mehdi Heydari Shahna, Seihun Kim, Soyi Jung, Soohyun Park, Jouni Mattila, Joongheon Kim
Computer Vision
MAETrack: Unleashing the Potential of Pretrained Geometric Priors for 3D Single Object Tracking
Sifan Zhou, Qiwei Wang, Linyue Tan et al. (+3 more)
Large-scale pre-training has transformed representation learning in 2D
vision, yet its transferability to 3D single object tracking (SOT) remains insufficiently understood. Directly fine-tuning self-supervised 3D encoders, such as masked autoencoders (MAE), often leads to sub-optimal adaptation because the reconstruction objective is not fully aligned with the spatial-temporal matching requirements of tracking. In this paper, we observe that this difficulty can be interpreted as a layer-wise transfer mismatch: shallow layers tend to preserve transferable
geometric cues, while deeper layers become increasingly specialized to the reconstruction pretext task and are less suitable for downstream tracking. Based on this observation, we propose MAETrack, a lightweight adaptation framework for transferring pre-training MAE representations to 3D SOT. MAETrack includes Layer-Selective Initialization (LSI), which initializes only the shallow stages of the tracking backbone from pre-trained weights while re-initializing deeper stages, and
Geometric Residual Gating (GRG), which reinforces structurally salient regions in the search BEV features before template-search fusion through residual spatial modulation. Extensive experiments on standard 3D SOT
benchmarks show that MAETrack consistently improves upon vanilla fine-tuning baselines with limited computational overhead. More broadly, our results suggest that effective transfer from 3D reconstruction pre-training to 3D tracking is not merely a matter of partial fine-tuning, but depends on a tracking-oriented transfer principle that preserves shallow geometry while adapting deeper representations to the downstream objective.
Read the full abstract ▾
All authors Sifan Zhou, Qiwei Wang, Linyue Tan, Ziyu Liu, Ziyu Zhao, Xiaobo Lu
Cryptography and Security
Toward Secure AI-Powered Penetration Testing Agents: Security Threats, Guardrails, and Architectural Perspectives
Rahul Dev T Y and Hiran V Nath
LLM-powered autonomous
agents are transforming the penetration testing space with dynamic, multi-step offensive security workflows that require minimal supervision by humans. These
agents leverage sophisticated
reasoning abilities and external security tools to independently carry out reconnaissance, identify vulnerabilities, devise exploitation plans, and perform post-exploitation operations. But the ability to have persistent
memory, to take actions in the real world, and to do long-horizon
reasoning raises qualitatively different security concerns than traditional chat-based LLM systems. Existing guardrail mechanisms for conversational AI may not be sufficient to secure autonomous AI pentesting
agents accordingly. To address these issues, we carry out a comprehensive security analysis on autonomous AI-penetration testing
agents. We systematically analyse representative
agent architectures, characterise their trust boundaries and attack surfaces and propose a threat taxonomy that is aligned with the lifecycle and covers LLM lifecycle attacks,
agent-architecture attacks and cross-cutting behavioural attacks. We analyse the limitations of existing guardrail mechanisms, identify key research gaps, and discuss future research directions for developing specialised, context-aware, and architecture-aware guardrails to secure next-generation AI-driven offensive security systems.
Read the full abstract ▾
Computer Vision
Efficient 3D Whole-Body PET Image Denoising via Conditional Rectified Flow With Optimized Sampling Strategy
Jiale Shen, Guolin Wang, Chenhao Wang et al. (+3 more)
Reducing radiation exposure in Positron Emission
Tomography (PET) is important for patient safety; however, ultra-low-dose imaging suffers from severe noise, which may affect diagnostic interpretation without appropriate image enhancement. While current 3D deep generative models, particularly
diffusion models, have shown strong reconstruction fidelity, their practical use can be limited by long inference times. In contrast, faster 2D-based alternatives may have difficulty maintaining volumetric consistency, an important consideration for whole-body PET imaging analysis. To bridge this gap, we propose a one-pass conditional 3D rectified flow (3D Flow) framework for whole-body PET image denoising that incorporates a novel optimized non-uniform sampling strategy. The model is trained with a one-pass linear-interpolant velocity-matching objective. This approach reconstructs a full 3D volume in approximately 30 seconds in our implementation, compared with multi-hour inference for the evaluated 3D DDPM baseline. Evaluations including zero-shot transfer to an independent clinical
dataset show that our model achieves favorable global image quality and lesion conspicuity compared with the evaluated 3D DDPM and DDIM baselines, including on challenging short-acquisition data. Furthermore, the proposed method shows promising zero-shot transfer performance across the evaluated
datasets and unseen dose levels (down to 1/100 of the standard dose), with artifact-focused visual comparisons supporting the need for further lesion-level validation. By balancing reconstruction fidelity and computational efficiency, this work presents a candidate approach for ultra-low-dose whole-body PET image denoising.
Read the full abstract ▾
All authors Jiale Shen, Guolin Wang, Chenhao Wang, Xinhui Su, Wei Luo, Feng Yu
Computer Vision
Jinwoo Jeon, GyuYeop Do, Yubin Lim et al. (+4 more)
Large-scale
vision-
language models (VLM) such as CLIP enable strong open-vocabulary
reasoning, yet deploying these capabilities on resource-constrained edge devices remains challenging. EdgeVL addresses this problem by distilling CLIP representations into lightweight multi-modal encoders and applying quantization-aware training (QAT) for efficient Open-Vocabulary Classification (OVC) on edge hardware. However, its two-stage optimization applies different objectives for
distillation and QAT, and contrastive learning is performed within the quantized student space, which can result in inconsistent optimization and reduced training efficiency. Moreover, identical supervision across RGB and non-RGB modalities may lead to modality imbalance. We propose a unified framework for quantized semantic
distillation tailored to edge deployment. By jointly optimizing
distillation and quantization within a unified teacher-anchored framework, our method ensures consistent training under quantization, suppressing hard negatives and enlarging decision margins. Additionally, we design a lightweight cross-
attention adapter that enhances non-RGB representations through RGB-guided semantic transfer, narrowing the modality gap. Extensive experiments demonstrate consistent improvements on non-RGB modalities while maintaining deployment efficiency.
Read the full abstract ▾
All authors Jinwoo Jeon, GyuYeop Do, Yubin Lim, Nam-Joon Kim, Hyun Gon Ryu, Hyuk-Jae Lee, Byung-Jun Lee
Human-Computer Interaction
NephoCodex: Exploring Bounded Material Agency in Weather Data Physicalization
Yuxuan Weng and Yunge Wen
Weather is a complex, continuously changing system in which uncertainty is intrinsic. Physicalizing this uncertainty introduces further variation because computational outputs cannot fully determine material behavior. We distinguish computational uncertainty from material variability and introduce bounded material agency: computation constrains material realization without fixing its exact appearance. We present NephoCodex, a data physicalization system informed by a formative study that constructs five artistic weather states and predicts probability distributions over them. Probability-weighted mappings translate these distributions into material control proposals, while
entropy-based regulation, local sensing, and safety constraints bound their execution through mist, airflow, light, and transparent displays. A within-participant study found increased spatial presence and physical demand, while perceived data comprehensibility remained inconclusive after correction. These findings contribute to hybrid data physicalization by showing how variable material expression can be paired with stable digital annotations and how
embodied experience can be evaluated separately from data comprehension.
Read the full abstract ▾
Robotics
Differentiable Mesh State Estimation via Factor Graph Inference for Deformable Object Reconstruction
Lidia Al-Zogbi, Fangjie Li, Samuel Tobin et al. (+13 more)
Estimating deformable object states remains a fundamental challenge in robotics and simulation. We propose a novel factor graph-based framework for probabilistic mesh state estimation of deformable objects. The method directly updates a tetrahedral mesh, a rich and physically-grounded representation of an environment, by combining physics priors, noisy sensor measurements, and temporal smoothness constraints within a unified probabilistic formulation. The estimation problem is posed as a nonlinear least-squares optimization and solved using Levenberg-Marquardt. Ex vivo central-airway obstruction experiments and simulations on deforming cube models demonstrate reliable and accurate reconstruction under both rigid motion and deformation, highlighting the potential of this probabilistic approach for principled, measurement-driven mesh state estimation in deformable object reconstruction.
Read the full abstract ▾
All authors Lidia Al-Zogbi, Fangjie Li, Samuel Tobin, James Ferguson, Nithesh Kumar, Alejandro Chara, Kuan-I Chung, Mingxing Rao, Ayberk Acar, Susheela Sharma Stern, Robert Webster, Daniel Moyer, Alan Kuntz, Caleb Rucker, Tucker Hermans, Jie Ying Wu
Computer Vision
MEgoVista: Multi-view Ego-aware Motion Estimation for Metric 4D Hands and Head in the Wild
Jiangong Xiao, Chao Ma, Zhihao Zhang et al. (+19 more)
Learning manipulation from human
video requires high-fidelity hand-motion reconstruction in metric units. Today's metric hand labels come from studio rigs and instrumented headsets, and both are confined in the same two ways: neither leaves a prepared setting, and neither is checked against an independent reference. Unconstrained head-worn recording promises the opposite trade-off, scaling with the number of people wearing a device. We therefore introduce MEgoVista, an offline pipeline that turns a single unprepared MEgo View recording into metric two-hand and head motion in one
gravity-aligned world frame. Three properties set it apart from existing
egocentric reconstruction systems: first, it reconstructs in settings studio volumes and tabletop rigs cannot reach, settling hand ownership at detection so bystander hands stay out of the wearer's trajectory; second, it takes its metric gauge from calibrated stereo rather than a
monocular prior, installing scale at initialisation so policies receive physical units, not arbitrary coordinates; third, both outputs are scored inside a motion-capture volume against independent Chingmu optical capture, under a protocol that audits its own reference and charges what a method declines to predict. MEgoVista is offered as a measured route from
egocentric video to metric hand supervision, one that widens where such labels can be gathered. To bridge the gap between lab validation and industrial-scale data annotation, we further introduce MEgoDeploy, a production-grade GPU stack that fully preserves reconstruction fidelity while achieving a 14.05x end-to-end throughput speedup, scaling the generation of metric 4D pseudo-labels for
embodied foundation models.
Read the full abstract ▾
All authors Jiangong Xiao, Chao Ma, Zhihao Zhang, Yifei Dong, Zhouyi Jin, Zhiwen Hou, Haoyi Wang, Junle Yu, Amu Zheng, Chen Wang, Kaishu Lin, Hanwen Shi, Shiyun Zhang, Renquan Wan, Jingmei Jin, Xuan Hu, Weihuang Chen, Hongbin Sun, Jinli Suo, Maoqing Li, Li Liu, Maoqing Yao
Robotics
Weave: Learning Whole-Body Dexterous Loco-Manipulation from Human-Object Interactions
Liu Cao, Xingze Wu, Jingzhi Cui et al. (+4 more)
Learning
humanoid-object interaction requires coordinating whole-body balance, locomotion, and dexterous hand contact to control both
robot and object motion. Human demonstrations provide examples of coordinated interaction, but transferring these behaviors to
humanoid robots requires learning how to establish and maintain effective contacts under different embodiments and dynamics. We present Weave, a unified framework for learning whole-body dexterous
humanoid-object interaction from captured human demonstrations. Weave first converts captured human-object interactions into executable
robot-object references through contact-aware retargeting and approach-motion completion. At its core is a contact- and geometry-aware policy that jointly commands 29 body joints and 12 actuated finger joints across multiple objects and interaction sequences. Evaluation across nine objects yields a 92.5% success rate on trained interactions and, without any additional training, 65.0% on sequences never seen during training. We additionally release ~9,000 physically executed rollouts spanning ~23 hours, providing
robot-object trajectories with contact annotations for downstream interaction-policy learning and physically consistent HOI motion generation. Project website: https://xiaohu-art.github.io/Weave/
Read the full abstract ▾
All authors Liu Cao, Xingze Wu, Jingzhi Cui, Botian Xu, Mingzhi Pei, Ruoqu Chen, Mengdi Xu
Distributed Computing
DeepShare: Assurance-Driven Deep Learning Job Scheduling for Multi-Tenant Clusters
Jinghao Wang, Yihang Zhou, Xiao Zhou et al. (+5 more)
Multi-tenant GPU clusters frequently remain underutilized even when tenants experience long queueing delays, because quota control, queue ordering, preemption, and GPU sharing are driven by different local signals. We present DeepShare, a scheduler that uses a continuous tenant-assurance signal to coordinate these decisions at runtime. DeepShare combines elastic quota borrowing, tenant-specific runtime prediction, cost-aware best-effort preemption, and interference-aware MPS colocation, while using the same assurance signal to decide when borrowed capacity should be reclaimed and when sharing should become more conservative. In trace-driven experiments on 23,859 Venus jobs and 3,200 internal jobs, DeepShare achieves an average GPU utilization of 70.58%, a 29.5% improvement over the strongest non-intrusive sharing baseline, while reducing average queueing delay by 46%. On a 16-GPU Kubernetes testbed, it reduces the average job completion time by 34% and maintains 93% QoS compliance for guaranteed tenants. These results show that treating tenant assurance as a runtime control loop achieves a more advantageous utilization-QoS trade-off than optimizing quotas, scheduling, and resource sharing independently.
Read the full abstract ▾
All authors Jinghao Wang, Yihang Zhou, Xiao Zhou, Xinlei Zheng, Xiaoyang Sun, Tianyu Wo, Chunming Hu, Renyu Yang
Cryptography and Security
MarkSec: Capability-Aware Evaluation of Adversarial Attacks Against LLM Watermarks
Kairong Li, Zhikun Zhang, Xiao Ren et al. (+1 more)
LLM watermarking helps trace the origin of generated text, but faces stealing attacks that recover watermark information, scrubbing attacks that remove watermark signals, and spoofing attacks that forge text accepted as watermarked. These attacks are often studied in isolation, leaving their connections unclear. Evaluations also often lack shared detector calibration, metric definitions, and reporting protocols. Moreover, measuring attack success and text quality separately makes it difficult to identify attacks that are both effective and quality-preserving. We propose MarkSec, a general framework that unifies analyses of stealing, scrubbing, and spoofing. We evaluate attacks under a common reporting protocol and introduce a quality-constrained attack success metric to assess effectiveness and text quality jointly. Experiments across representative watermark families, attacks, LLMs, and
datasets reveal three findings. First, attacks that appear strongest by watermark removal alone can fall behind general rewriting when success also requires acceptable text quality. Second, general rewriting remains a strong baseline across watermark families, while its advantage over other scrubbers varies by family. Third, in a case study of one watermark family, stealing-based scrubbers often underperform the best general-scrubbing baselines when text quality is required. These results show that apparent attack winners depend on text-quality constraints, attack generality, and capability assumptions.
Read the full abstract ▾
All authors Kairong Li, Zhikun Zhang, Xiao Ren, Yunjun Gao
Artificial Intelligence
little m: An AI Agent for Industrial Process Optimization
Yongchao Ye, Xinyu He, Dutliff Boshoff et al. (+2 more)
Manufacturing consumes one third of global energy and still has significant room for improvement in terms of energy efficiency. Optimal process control is essential for this purpose. However, synthesizing mathematical optimization models from messy, real-world industrial specifications requires bridging unstructured natural
language and spatial diagrams with rigorous mathematical syntax. This poses a profound challenge for general-purpose Large
Language Models (LLMs), which may introduce invalid constraints when tasked with modeling continuous multi-physics dynamics. To address this, we introduce little m, an AI
agent designed to assist the formulation of industrial process control models. Combining a domain-specific knowledge repository with LLM-driven interaction, the proposed framework formulates real-world optimization problems as mathematical models. For systematic evaluation, we introduce the Industrial Process Control
Benchmark (IPC-Bench), a novel
multimodal dataset of 50 canonical scenarios requiring joint
reasoning over text and process diagrams. Through comprehensive automated structural assessments and double-blind human evaluation, little m substantially outperforms state-of-the-art LLMs, generating semantically correct models. These evaluations assess formulation quality rather than solver feasibility, formal physical validity, or closed-loop industrial performance. The implementation of little m and the IPC-Bench
dataset are available at https://github.com/yeyongchao/process-modeling-
benchmark.
Read the full abstract ▾
All authors Yongchao Ye, Xinyu He, Dutliff Boshoff, Way Kuo, Lishuai Li
Artificial Intelligence
AI for Games in the Foundation Model Era
Meng Luo, Yanlin Li, Hao Li et al. (+7 more)
Foundation models, alongside advances in learned game-world models, are reshaping AI across the game lifecycle. Beyond playing games, recent systems model players and game dynamics, support design and development, adapt player-facing experiences at runtime, and evaluate resulting artifacts. Yet these directions have evolved largely separately, obscuring which capabilities transfer across settings and which remain tied to particular games, engines, interfaces, or player populations. We organize the literature into six roles according to the immediate use of AI output: playing and acting; modeling players and games; designing games; building and maintaining games; generating and adapting at runtime; and testing and evaluating games. For each role, we examine what structure is supplied by the game or workflow, what AI learns or produces, which capabilities and artifacts transfer across settings and roles, and what evidence supports the claims. We identify cross-role connections: trajectories train world models, learned environments provide experience for
agents, design specifications drive executable implementations, and play or testing feedback guides revision. However, control schemes, rules, engine interfaces, state representations, and player contexts often remain setting-specific, so downstream claims require validation in the target setting. Evaluation is most standardized for bounded game playing and selected learned environments, while persistent state in learned worlds, repeated software revision, validated player modeling, sustained runtime adaptation, and representative automated testing remain less established. The central challenge is to reuse or transfer outputs and capabilities across roles while re-establishing evidence for effectiveness in the game-specific contexts where they are used.
Read the full abstract ▾
All authors Meng Luo, Yanlin Li, Hao Li, Hongzhan Lin, Pengfei Zhou, Tianjie Ju, Ran Zhang, Yeying Jin, Mong-Li Lee, Wynne Hsu
Cryptography and Security
From Hypervisor to Container: Cloud Security Vulnerabilities, Defense Mechanisms, and Open Challenges
Swapnil Vishwas Baviskar, Sanoj R and Hiran V Nath
In cloud computing, different users share the same physical hardware, which creates serious security risks. To protect data, cloud systems rely on virtual machines and containers to keep users isolated. This paper reviews over 120 security publications from 2008 to 2025, focusing on how these isolation boundaries can be breached. We examine threats like virtual machine escape, virtual machine hopping, CPU cache side-channels, container breakouts, vulnerable container images, and distributed denial of service (DDoS) attacks. We evaluate these security threats and their defenses using three key research questions. To compare different defense systems, we introduce a quantitative scoring framework called ADPO, which rates defenses from 0 to 3 based on their Accuracy, Deployment ease, Performance impact, and Operational overhead. We also map the impact of these attacks onto a 1-to-5 severity scale for Confidentiality, Integrity, and Availability. Finally, we highlight the trade-offs between security and system performance, and we outline open challenges like building low-overhead intrusion detection and creating realistic test
datasets.
Read the full abstract ▾