Human-Computer Interaction
Frontier vision-language models have overtaken young adults at detecting AI-generated portraits – but not their calibration
Sunwhi Kim, Sunyul Kim, Meounggun Jo et al. (+1 more)
AI image generators now create face portraits that are hard to tell from real photographs.
Vision-
language models (VLMs) are increasingly proposed to flag such images. We benchmarked 19 VLMs on the same 198 face portraits – real photographs and identity-matched ChatGPT-4o and Imagen 3 versions – under the same task as our earlier study of 1,667 adults (85% correct overall; accuracy fell steeply with age). The June-2026 cohort of 14 models only matched adults in their 20s-30s. Four weeks later the ceiling broke. Among five July-2026 releases under the identical protocol, gpt-5.6-sol reached 92.8% balanced accuracy (five-draw mean 92.1%), clearly above adults in their 20s (88.5%), and claude-fable-5 detected every AI image while averaging 91.9%. Model sensitivity now exceeds young adults decisively (d' up to 3.4 versus ~ 2.4). What has not been overtaken is human calibration. Model criteria spread from c = -1.10 to +1.45 while humans sit near zero at every age; both new leaders are biased (+0.44, -0.97), and only a few mid-ranked models approach the human balance. Changing the labelled examples still flipped about one answer in four. The best machines now out-see young adults here, without matching the human balance between suspicion and trust.
Read the full abstract ▾
All authors Sunwhi Kim, Sunyul Kim, Meounggun Jo, Jini Tae
Computer Vision
DICS: Exploring Data Intrinsic Consistency for Visual Instruction Selection
Yuyang Hong, Jinhui Guo, Jiaqi Gu et al. (+6 more)
Visual instruction tuning is crucial for advancing the
vision-
language alignment and instruction-following capabilities of
Vision-
Language Models (VLMs). However, identifying optimal subsets under a fixed ratio constraint from rapidly expanding
datasets remains a significant bottleneck. While existing methods largely depend on distribution diversity or heuristic filtering, they often overlook the internal coherence within individual samples. To bridge this gap, we propose Data Intrinsic Consistency (DIC), a self-scoring metric designed to quantify the sample-level inter-component consistency. DIC consists of two modules: Visual Information Consistency (VIC), evaluating the
alignment between visual content and instructions, and Response Information Consistency (RIC), assessing response coherence relative to the instruction. Building upon DIC, we introduce Data Intrinsic Consistency Selection (DICS), an adaptive data selection method that optimizes the trade-off between high intra-sample consistency and global distributional diversity under varying data budgets. Extensive experiments demonstrate that DICS consistently outperforms state-of-the-art methods across diverse
dataset scales and model architectures, surpassing full-
dataset fine-tuning while using only 25% of the LLaVA-1.5-665K data. We further curate DICS-6M, a 6M-sample multi-modal instruction corpus that enables the largest-scale visual instruction selection study to date; remarkably, DICS reaches 94.52% of the official InternVL3-8B-Instruct performance using less than 25% of its reported training data. Code can be seen at https://github.com/cqu-student/DICS
Read the full abstract ▾
All authors Yuyang Hong, Jinhui Guo, Jiaqi Gu, Lubin Fan, Ruixiang Wang, Kun Ding, Yue Wu, Shiming Xiang, Jieping Ye
Cryptography and Security
SIR: Self-improving Red-teaming for Compute Use Agents
Chen Xiong, Zhiyuan He, Pin-Yu Chen et al. (+2 more)
Computer-use
agents (CUAs) are
agents powered by
vision-
language models (VLMs) that perceive a screen and operate an operating system through mouse, keyboard, and terminal interactions to automate everyday digital tasks. Their exposure to untrusted content creates a risk of indirect
prompt injection (IPI), where an adversary embeds instructions in content the
agent reads to redirect it toward actions that violate the user's intent. Evaluations based on fixed, hand-written injections may underestimate the risk posed by adaptive adversaries. We present SIR, a black-box self-improving IPI framework that (i) composes task-specific injections from a small library of reusable red-teaming principles stated in plain
language and (ii) uses an iterative feedback loop to analyze unsuccessful attack trajectories and distill new, named principles that are retained in a shared library and reused across tasks. We target operating-system-level compromise and evaluate outcomes through deterministic checks on filesystem, service, and permission state rather than an LLM judge. An attack counts as successful only when both the
adversarial objective and the benign user task are completed in the same execution. We evaluate three frontier CUAs, allowing SIR up to 10 attack attempts per case. It achieves joint attack success rates of 24% on Claude Opus 4.8 and 28% on Gemini 3.5 Flash, compared with 4% and 0%, respectively, for the
benchmark's fixed, hand-written injection. The red-teaming principles discovered against one victim also improve attacks against other victims, including a different model family, without additional feedback.
Read the full abstract ▾
All authors Chen Xiong, Zhiyuan He, Pin-Yu Chen, Stjepan Picek, Tsung-Yi Ho
Machine Learning
Diffusion-Based Refinement for Kilometer-Scale Probabilistic Precipitation Nowcasting
Dohyun Park, Changhoon Song, Tengyuan Chang et al. (+2 more)
Localized extreme precipitation is a major trigger of urban flash floods and landslides, yet producing nowcasts that combine fine spatial detail with probabilistic uncertainty remains challenging. Here we introduce exPreCast-ENS, a conditional residual
diffusion framework that transforms the deterministic 4 km radar nowcaster exPreCast into a 1 km probabilistic ensemble while correcting systematic forecast errors. Conditioning on both the forecast and preceding radar observations lets the ensemble-mean correct the baseline rather than perturb it, while members represent unresolved fine-scale variability. Over the Korean Peninsula, skill improves with ensemble size. In two high-impact events in 2023, a 30-member ensemble recovers 38-47% of heavy-rain pixels missed by exPreCast while retaining approximately 95% of its correct detections and alarming on under 1% of the pixels it correctly left clear. The method generates a 1-h forecast in 3.4 s on a single GPU and yields consistent improvements on the French regional MeteoNet radar
dataset.
Read the full abstract ▾
All authors Dohyun Park, Changhoon Song, Tengyuan Chang, Yoo-Geun Ham, Youngjoon Hong
Computation and Language
When Models Hear What They Expect: Diagnosing Prosodic Heuristics in Multimodal Sarcasm Detection
Yongjian Chen, Pengfei Wei, Yiqun Sun et al. (+2 more)
Multimodal Large
Language Models (MLLMs) process
speech and text jointly, yet whether they exploit prosodic cues for pragmatic inference or rely on surface acoustic patterns has received little systematic investigation. We address this through sarcasm detection, evaluating Qwen2.5-Omni and Qwen3-Omni on Mandarin Chinese and English under five modality conditions that decompose the contributions of lexical content, vocal semantics, and prosodic structure. Adding audio systematically inflates false positives without improving true positive detection. Acoustic error diagnosis reveals that model errors cluster on a shared stereotype of expressive prosody, namely elevated pitch and irregular pausing, that diverges from the actual cues marking sarcasm in both
languages. Targeted manipulation of only these two dimensions causally confirms the heuristic, inducing false positive rates of up to 60%. Applying the same manipulation template to Gemini~3 Flash Preview without modification replicates the effect, suggesting that the stereotype extends beyond the Qwen Omni family rather than arising from a single model architecture.
Read the full abstract ▾
All authors Yongjian Chen, Pengfei Wei, Yiqun Sun, Zhu Li, Lawrence B. Hsieh
Game Theory
Rival-Injective Allocations: Support-List Structure and Maximum-Anchor EFX$_0$ Certificates
Junshuo Wang
We study complete allocations under nonnegative additive valuations through the positive supports of goods, focusing on the all-good form of envy-freeness up to any good (EFX$_0$). We define rival-injective (RI) endpoint ownership: every good with nonempty positive support is assigned to an
agent who values it positively, and every ordered observer–owner pair is used by at most one good. RI ownership is exactly proper list coloring of the graph joining goods whose positive supports overlap in at least two
agents. For pair-supported goods with arbitrary exceptional goods, fixing the exceptional owners yields a necessary-and-sufficient pair-capacity criterion and an exact finite-domain owner constraint satisfaction problem (CSP). Every RI allocation in which each
agent's own bundle is worth at least her maximum-valued singleton is all-good EFX$_0$. A specified injective choice of maximum-singleton anchors, together with residual support-list degeneracy, constructs such an allocation by reverse greedy coloring in $O(nm^2)$ time. We give two explicit witness families: a nonempty relatively open, 22-dimensional cone on a fixed $4\times10$ support face, and a family for every $n\ge4$ with two universal-support goods and $m=(n-1)(n-2)+2$ goods. Both fail unanchored list degeneracy and are not implied by the explicit pure-multigraph or published high-girth/controlled-multiplicity hypotheses compared here. We also study recognition of the maximum-anchor certificate class, leaving its general complexity unresolved. The exact list-coloring and pair-capacity results concern RI ownership, not general EFX$_0$ existence; unrestricted four-
agent, ten-good all-good EFX$_0$ remains unresolved.
Read the full abstract ▾
Multimedia · Cross-listed from eess.IV
ReLViC: Loss-Resilient Learned Video Coding with Dispersed Packetization and Controllable Packet Dependencies
Xuyang Chen, Daquan Feng, Xianfu Chen et al. (+1 more)
Packet loss can severely impair learned
video coding because missing latent
tokens compromise both spatial reconstruction and temporal prediction. We present ReLViC, a loss-resilient learned
video coding framework that jointly addresses latent coding and packet-loss recovery. ReLViC disperses spatially adjacent latent
tokens across packets and employs a dual-purpose
Transformer to estimate
entropy-model parameters during coding and reconstruct missing latent
tokens at the receiver. It controls packet dependencies through a periodic-reset packet-context
topology parameterized by the segment length, thereby tuning the trade-off between compression efficiency and error-propagation range without retraining. A three-stage progressive training procedure establishes single-frame coding, learns temporal context for
entropy modeling, and then optimizes the recovery of masked latent
tokens under simulated packet loss. Experiments using burst-loss traces evaluate ReLViC against H.265 protected by Reed–Solomon forward error correction (FEC) and GRACE, a loss-resilient learned
video codec. ReLViC delivers more stable reconstruction and outperforms both baselines under severe packet loss.
Read the full abstract ▾
All authors Xuyang Chen, Daquan Feng, Xianfu Chen, Xiang-Gen Xia
Machine Learning
Certified Safety Radii in Forecast-Error Space for Wasserstein Distributionally Robust Small Signal Stability-Constrained AC Optimal Power Flow via Lifted Spectrahedral Containment
Ziqi Zhang and Xi Chen
Directly robustifying small-signal stability in AC optimal power flow is challenging since the stability boundary in the original uncertainty space is implicit, highly nonconvex, and changes with the operating decision. This paper exploits an alternative geometry. For a fixed model-specific stability certificate admitting suitable physical lifts, the small-signal stability requirement becomes an affine positive semidefinite constraint in the lifted variables, thereby defining a convex certified safe region. Instead of approximating the nonlinear instability boundary itself, we optimize a sample-wise safe radius in the original uncertainty space and certify, in the lifted space, that the entire power-flow image of the corresponding uncertainty ball is contained in the convex stability region. To this end, a componentwise Perron certificate guarantees existence, uniqueness, and Jacobian regularity of the target AC power-flow branch throughout each ball. An adjoint elimination then provides an exact affine-quadratic representation of the stability-relevant quantities, while rigorous
matrix remainder bounds convert their nonlinear variation into finite robust PSD constraints. The resulting radii are certified lower bounds on the distances from empirical samples to failure and can therefore be coupled directly to the distance-based reformulation of a Wasserstein distributionally robust chance constraint, without directly approximating the instability boundary. Numerical studies demonstrate the effectiveness of the proposed framework.
Read the full abstract ▾
Systems and Control
A High-Resolution Synthetic EV Charging Dataset for Cold-Climate Distribution Grid Impact Analysis: Trondheim, Norway (2020-2030)
Hanieh Taraghi Nazloo and Petr Musilek
This data article presents a high-resolution, long-term synthetic electric-vehicle (EV) charging
dataset for Trondheim, Norway, spanning February 2020 to December 2030. Empirically grounded in 14 months of historical charging logs from December 2018 to January 2020, the
dataset captures session-level behavioral patterns, including delivered energy, plug-in duration, connection schedules, user categorization (private vs. shared), seasonal variations, public-holiday effects, and daily ambient temperature dependencies. To model future electrification dynamics, the synthetic generation pipeline integrates historical session records, calendar and weather features from MET Norway, annual EV-adoption growth multipliers derived from Statistics Norway (SSB) registration trajectories, a daily session-count model, a Conditional Tabular Generative
Adversarial Network (CTGAN), seasonal Kernel Density Estimation (KDE), and post-generation physical charger-power feasibility correction. Under a standardized 7.2 kW AC charging constraint, the resulting medium EV-adoption scenario
dataset contains 76,993 hourly charging-activity records. The hourly profile is activity-based rather than a complete continuous hourly time series; hours with no allocated EV charging energy are not included. The records provide total hourly charging energy, equivalent average charging power, active session counts, private/shared user load breakdowns, ambient temperature features, and calendar indicators. The
dataset provides a validated cold-
climate benchmark for distribution-grid impact assessment,
transformer-loading analysis, EV charging-demand
forecasting, charger-capacity planning, energy-management optimization, and the development of data-driven smart-charging control strategies.
Read the full abstract ▾
Computation and Language
When Errors Become Memories: Causal Pathway Tracing in Multi-Turn Memory-Augmented LLMs
Shuyao Xiao, Shengling Wang, Xuan Chen et al. (+8 more)
Long-term
memory enables large
language models (LLMs) to preserve and reuse information across interactions, but it can also turn localized errors into persistent risks. Existing work mainly evaluates whether
memory systems store and retrieve information correctly, leaving limited understanding of how errors propagate across responses,
memory states, and future interactions. We propose a structural causal model (SCM)-based framework for cross-turn error propagation in
memory-augmented LLMs. We model user questions, model responses, and
memory states as a dynamic causal process, and identify two entry pathways: internal
memory updating and external question feedback. By intervening on these pathways, we construct four counterfactual trajectories and quantify their downstream effects and interaction. Error influence is evaluated at four levels:
memory retention, natural responses, targeted diagnostic probing, and probability-level error preference. Experiments show that error influence generally decays with interaction distance, while the
memory-update pathway contributes more persistent effects than question feedback; latent errors may remain even after disappearing from natural responses. Propagation patterns also vary across
memory categories and
memory mechanisms. Pathway-guided restoration further validates this decomposition: Question Repair reduces residual error by 27.5%,
Memory Repair by 70.2%, and Joint Repair by 98.3%, nearly eliminating residual propagation.
Read the full abstract ▾
All authors Shuyao Xiao, Shengling Wang, Xuan Chen, Ke Chao, Ming Cui, Feifei Qian, Fanlin Meng, Chaoyang Mei, Chaoyong Jiang, Qi Ouyang, Junxi Yi
Computation and Language
ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives
Hoejoon Kwon, Byeonggeuk Lim, Kahyeon Kim et al. (+1 more)
Safety
alignment is essential for deploying large
language models, requiring systems to prevent harmful compliance while preserving helpfulness on benign requests. Activation steering offers a training-free inference-time approach to safety control, but effective safety steering requires addressing two coupled questions: when to intervene and how generation should be shaped after intervention. However, existing safety steering methods remain limited along both dimensions, as their triggering mechanisms can be unstable across domains and refusal-oriented steering often yields rigid refusals rather than constructive safe guidance. To address these limitations, we propose ALTSTEER, an inference-time framework that couples selective intervention with refusal-anchored constructive redirection within a single inference pass. ALTSTEER uses an internal refusal-relevant signal to decide when to steer, and applies staged steering to shift generation from refusal-oriented control toward constructive alternatives. Evaluations on Llama-3.1 and Qwen2.5 show that ALTSTEER preserves benign utility while improving constructive safe-completion behavior, especially on models that otherwise tend to produce short refusals for harmful requests.
Read the full abstract ▾
All authors Hoejoon Kwon, Byeonggeuk Lim, Kahyeon Kim, YoungBin Kim
Numerical Analysis
Checkerboard Shells: A Position-Only Thin-Shell Discretization with Scale-Compatible Completion
Junjie Song, Xuanyu Wu, Zhifeng Zhang et al. (+5 more)
Checkerboard edge-midpoint geometry provides an exact planar Varignon parallelogram for every spatial quadrilateral, allowing a local tangent frame and normal to be recovered directly from nodal positions even when the raw quadrilateral is warped. Building on this property, we develop a position-only thin-shell discretization with no independent director, rotation, or strain variables. The connected edge-midpoint surface is taken as the physical midsurface: the first fundamental form is evaluated on planar B faces, while a W-centered second fundamental form is constructed from variations of neighboring B-face normals, so membrane and bending share the same
geometric carrier. A variational-kernel analysis shows that smooth second-order consistency does not eliminate
lattice-scale blind modes. After quotienting out the raw checkerboard gauge, the B metric has one physical membrane blind direction and the symmetric W
curvature has two
curvature blind directions. We introduce a quotient-minimal membrane compatibility coordinate $X_M$ and an objective reference-relative
curvature coordinate $X_W^{rel}$, placed consistently in the $O(t)$ membrane and $O(t^3)$ bending sectors. The formulation admits an explicit midpoint quotient, complete flat blind-mode classification, rigid-motion objectivity, reference-state consistency, and an $O(h^2)$ near-isometry approximation result for aligned generalized cylinders. Numerical tests show second-order
curvature convergence, targeted removal of the membrane defect, and a sub-percent, refinement-decaying influence of $X_W^{rel}$. Linear and nonlinear shell
benchmarks further demonstrate flat bending, curved-shell membrane-bending coupling, thickness sensitivity, large rotation, nonlinear pinching, and localized ovalization within a single position-only framework.
Read the full abstract ▾
All authors Junjie Song, Xuanyu Wu, Zhifeng Zhang, Bingtao Hu, Zhaoxi Hong, Xiuju Song, Yixiong Feng, Jianrong Tan
Computer Vision
NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation
Yujiang Pu and Yu Kong
Diffusion models have recently advanced text-to-
video (T2V) generation, yet they still struggle with fine-grained compositional
alignment, such as attribute binding, spatial relations, and object interactions. While reward-based fine-tuning improves
alignment, it is susceptible to reward hacking and adapts poorly to new
prompt distributions. In this work, we propose NoisEasier, a test-time scaling framework that improves T2V generation through differentiable reward-guided noise optimization without modifying the underlying model. By combining efficient short-step generators with a multi-objective reward formulation, NoisEasier enables stable and practical test-time optimization under realistic inference budgets. Our key insight is that jointly optimizing the entire
stochastic trajectory accelerates reward convergence and improves compositional
alignment over optimizing only the initial latent, with negligible additional computational and time cost. Experiments on VBench and T2V-CompBench demonstrate consistent improvements across multiple backbones, achieving over 10% average gains on challenging dimensions such as attribute binding, object interaction, and numeracy. Overall, NoisEasier serves as both a flexible alternative and a complementary enhancement to reward-based fine-tuning, establishing test-time scaling as an effective paradigm for controllable text-to-
video generation.
Read the full abstract ▾
Systems and Control
Robust Semi-passive Velocity Field Control with Boundedness Guarantees for Safe Interaction between Mechanical Systems and Physical Environment
Van Trong Dang, Sumitaka Honji and Takahiro Wada
Controllers that guarantee energetic passivity with respect to the pair of external force and velocity realize safe interaction between the mechanical system and its physical environment. However, solely adhering to energetic passivity constraints may impose fundamental limitations on control performance and, in some cases, prevent the successful execution of controlled tasks. In addition, external disturbances from the physical environment can drive the system energy level and states beyond operational regions, thereby undermining task performance and safety. In this paper, we study a robust time-varying semi-passive velocity field control to aim to relax the inherently conservative nature of fully passive control methods in a controlled manner. Specifically, the proposed control method guarantees passivity of the closed-loop system with respect to the force-velocity input-output pair when the energy level exceeds a predefined level, while permitting non-passive behaviors to preserve task performance otherwise. Furthermore, the energy level and the states of the closed-loop system are proved to converge to bounded domains even in the presence of unpredicted disturbances. Additionally, the proposed method also enables constraining power flow between the closed-loop system and its physical environment to enhance safety in the interaction process. Numerical simulation examples demonstrate the effectiveness of the proposed method.
Read the full abstract ▾
Artificial Intelligence
FaVOR: LLM-Based Agentic Framework for Factor Mining via Empirical Validation
Hyeonjin Kim, Minseok Kim, Seunghyeon Jung et al. (+3 more)
Traditional finance relies on experts to hand-craft factors through a principled process grounded in economic rationale. Recent LLM-based multi-
agent systems have automated this process, scaling factor mining far beyond manual effort. However, these automated approaches optimize directly for returns and rarely check whether a generated factor still expresses the economic hypothesis that motivated it. We identify this inconsistency between mathematical form and economic meaning as a structural failure mode of return-oriented automation. The resulting factors blur the line between real signals and spurious correlations and break down across regime shifts. We propose FaVOR (Factor Validation through Observable
Reasoning), an agentic framework that restructures factor mining around hypothesis-level evidence rather than return outcomes. In place of the standard hypothesis-to-formula leap, FaVOR enforces a three-stage consistency loop tying mathematical form to economic rationale throughout. (1) Decomposition splits a broad economic hypothesis into independent observable conditions. (2) Validation checks whether each factor reflects its intended condition. (3) Integration merges them into a composite whose structure remains interpretable. On the CSI 500 and S&P 500 in 2025, FaVOR outperforms existing baselines while remaining effective across regimes. FaVOR shows that hypothesis-grounded factor discovery produces signals that are interpretable by construction, regime-robust, and economically faithful. The code is available at https://github.com/damilab/FaVOR.
Read the full abstract ▾
All authors Hyeonjin Kim, Minseok Kim, Seunghyeon Jung, Sujin Pyo, Huisu Jang, Woojin Lee
Numerical Analysis · Cross-listed from math.SP
Spectra of Non-Self-Adjoint Almost Mathieu Matrices and the Scottish Flag Operator
Simon Becker and Izak Oltman
For $N\geq 3$ and a potential phase $\vartheta\in\mathbb{R}$, we study the non-self-adjoint almost Mathieu
matrix obtained by multiplying the discrete
Laplacian by a complex phase with angle $\varphi\in\mathbb{R}$, $A_N(\varphi,\vartheta)=e^{i\varphi}(S+S^{-1})/2+\operatorname{diag}(\cos(2\pi j/N+\vartheta))_{j\in\mathbb{Z}/N\mathbb{Z}}$, where $S e_j=e_{j+1}$ is the periodic shift on $\mathbb{C}^N$. We derive a Chambers formula and isolate the part $Q_{N,\varphi}$ of the characteristic
polynomial that depends only on $N$ and $\varphi$, but not on $\vartheta$ or on a change of boundary conditions for the shift operator. We then show, for every $N$, that the zeros of $Q_{N,\varphi}$ lie on the two perpendicular lines $e^{i\varphi/2}\mathbb{R}\cup e^{i(\varphi/2+\pi/2)}\mathbb{R}$. For even $N$, the same property holds for the
matrices $A_N(\varphi,\vartheta)$ with $\vartheta\in 2\pi\mathbb{Z}/N$, and we compute their limiting
eigenvalue measure explicitly. For $\varphi\in[-\pi,\pi]$, the
eigenvalue distribution approximates
elliptic-integral densities with masses $1-|\varphi|/\pi$ and $|\varphi|/\pi$, and maximal radii $2|\cos(\varphi/2)|$ and $2|\sin(\varphi/2)|$, respectively. At $\varphi=\pi/2$, the central
polynomial $Q_{N,\varphi}$ factors into positive quartic factors. This proves that the Scottish flag
matrix, after Trefethen and Chapman, has its spectrum on the two diagonal lines of the saltire.
Read the full abstract ▾
Computation and Language
GPAgentBench-2K: Benchmarking Large Language Model Agents in Complex Clinical Action Space
Boqi Chen, Xudong Liu, Yunke Ao et al. (+2 more)
Large
Language Models (LLMs) show great potential as clinical
agents, yet existing
benchmarks reduce clinical workflows to static predictions or unconstrained Markov Decision Processes (MDPs) with coarse action sets. To address this, we introduce GPAgentBench-2K, the first Constrained MDP (CMDP) LLM-
agent benchmark for primary-care clinical decision-making, constructed from expert-validated records of real-world GP encounters. Our environment models a full spectrum of six foundational clinical actions, imposes a topological workflow prior over the action space, and operationalizes safety-informed abstention as a first-class outcome. Evaluating 16 state-of-the-art LLMs reveals a significant performance degradation as the action space scales. Crucially, we uncover a clinical quality-safety gap: even frontier models with the highest diagnosis accuracy violate safety constraints in over half of high-risk cases. Finally, we establish a reference point using Constrained Group Relative Policy Optimization (C-GRPO), and show that while explicitly modeling constraints improves performance over unconstrained RL methods, it remains far from clinically acceptable safety.
Read the full abstract ▾
All authors Boqi Chen, Xudong Liu, Yunke Ao, Heejin Do, Jianing Qiu
Computational Engineering
The PUR-1 Cyber-Physical Digital Twin
Vasileios Theos, Jonah Lau, Konstantinos Gkouliaras et al. (+7 more)
Digital twin technologies have the potential to improve operational flexibility and responsiveness capabilities of
nuclear systems. To provide decision support, cyber event characterization, state estimation, predictive control, and real-time dynamic processing of operational data, however, an efficient digital twin needs to integrate multiple models (data-driven as well as physics-based) with explainability while at the same time maintain two-way synchronization with the physical facility at a time constant less than its operational cycle. In this work, we present the Purdue University Reactor One Digital Twin (PUR-1 DT), a cyber-physical digital twin with a complete high-fidelity physics-based and AI-driven virtual model stack (neutronics, thermal-hydraulics, point kinetics) which provides closed-loop explainable diagnostics,
forecasting, predictive control, and action recommendation back to the reactor via two-way communications and a cyber-physical testbed. We demonstrate real-time synchronized state estimation and short-term
forecasting over a full reactor operational cycle and conduct a series of benchmarking experiments to validate accuracy and latency. Our results show good agreement with experimental results and lay the groundwork for further development and experimental demonstration of DT-enabled functionalities in real-world facilities.
Read the full abstract ▾
All authors Vasileios Theos, Jonah Lau, Konstantinos Gkouliaras, Zachery Dahm, Konstantinos Vasili, Noah Fillgrove, William Richards, True Miller, Brian Jowers, Stylianos Chatzidakis
Computer Vision
ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation
Jiahao Wu, Jie Liang, Die Hu et al. (+6 more)
Volumetric
video enables immersive free viewpoint rendering of dynamic real world scenes, yet existing methods struggle with long sequences and complex motions, often leading to temporal instability and visual artifacts. To address these challenges, we propose \ourname, a Gaussian splatting based framework for volumetric
video reconstruction. Our key insight is that explicitly tracking long term complex motion with individual Gaussian primitives is inherently unstable. Instead, we organize Gaussians around time conditioned anchors that localize their spatial and temporal support, thereby reducing long range motion complexity. We further introduce a temporal windowing strategy to activate only anchors relevant to the queried time, which improves scalability and temporal coherence. In addition, to ensure spatial and temporal stability, we design a compact set of multi level anchor features that encode global features, local spatial features, and local temporal features, jointly constraining Gaussian generation. Extensive experiments demonstrate that \ourname \ consistently outperforms prior methods on long sequence volumetric
videos with complex motions. Project page: https://github.com/WuJH2001/ATGS.
Read the full abstract ▾
All authors Jiahao Wu, Jie Liang, Die Hu, Jiayu Yang, Kaiqiang Xiong, Xiang Li, Xiaoyun Zheng, Chao Wang, Ronggang Wang
Computer Vision · Cross-listed from hep-ex
ConCA: Concentration-Aware Channel Attention for Fine-Grained Visual Recognition
Yu-Sheng Liu and Yu-Chen Tung
Lightweight channel
attention mechanisms are widely used in image classification, yet their effectiveness in fine-grained visual recognition (FGVR) remains limited. Most modules summarize each channel by global average pooling (GAP), which captures activation magnitude but ignores spatial concentration, so channels with different spatial distributions but identical means receive the same descriptor. We propose Concentration-Aware Channel
Attention (ConCA), which pairs the mean with a shift-invariant negative-input
entropy (NegEnt), computed via a softmax over the negated activations, forming a dual descriptor that jointly encodes magnitude and concentration. A depthwise 1-D convolutional multi-layer perceptron (MLP), whose parameter count is linear in the number of channels, maps the pair to a per-channel weight. On six fine-grained
benchmarks, ConCA improves over
attention-free, SE-Net, and ECA-Net baselines as well as four richer descriptor-based modules under a controlled from-scratch protocol, and it generalizes across eight backbones on iNat2021-mini. These results indicate that the channel descriptor, together with the per-channel gating that maps it to
attention weights, is an important but underexplored aspect of lightweight channel
attention in FGVR.
Read the full abstract ▾
Artificial Intelligence
A.X K2 Technical Report
Cheolseung Baek, Dhammiko Arya, Eunki Kim et al. (+40 more)
We introduce A.X K2, a 688B-parameter Mixture-of-Experts (MoE)
language model trained from scratch as a high-performance foundation for agentic applications. Trained on approximately 8.5T
tokens—fewer than its predecessor, A.X K1—on a smaller but higher-quality mixture with substantially expanded agentic and software-engineering data, it nonetheless improves over A.X K1 across the board, by over 30 percentage points on some
benchmarks, reflecting large gains in
token efficiency. To support long contexts efficiently, we introduce Sparse Gated
Attention (SGA), which combines sparse
attention with gated
attention, and adopt Gated Norm (GN) to stabilize large-scale training. SGA is trained natively at 128K through a sparse indexer warmup that optimizes the indexer against its own sparse top-$k$ selection rather than the dense
attention distribution, making adaptation markedly cheaper: each query reads only 2,048 positions, yet long-context quality is unchanged and A.X K2 scores 94.6 on RULER out to 256K. The outlier suppression of GN in turn keeps 4-bit NVFP4 serving within one point of FP8 accuracy. A simple yet effective Think-Fusion recipe further lets users switch between thinking and non-thinking modes within a single unified model. Extensive evaluations show that A.X K2 performs competitively against strong open-weight baselines, matching or exceeding them on math and Korean-
language benchmarks.
Read the full abstract ▾
All authors Cheolseung Baek, Dhammiko Arya, Eunki Kim, Gun Song, Gyoungeun Han, Hyunho Yang, Hyunjun Eun, Jin Kim, Junyoung Park, Juyun Wee, Minki Hong, Minkyung Park, Minsang Kim, Minsoo Kang, SaeRom Kim, Sangjin Kim, Sangyeol Lee, Seojin Lee, Seokhwan Jo, Seokyoung Hong, Seongho Choi, Seonghye Cho, Seongmin Ok, Sereimony Sek, Seungmo Cho, Seungsik Kim, Singon Kim, Sohee Park, Sooyeon Park, Subin Yi, Sungbin Yoon, Sungeun Lee, Sung Jun Cheon, Sungwan Kim, Sunwoo Lee, Tae Yoon Kim, Wonbeom Jang, Yohan Ra, Yong-jin Han, Youngjin Kim, Youngrang Kim, Yujin Kang, Yujin Lee
Software Engineering
Open-Source Autonomous Driving System Analysis and Multi-Disciplinary Hardware-in-the-Loop Research Paradigm with Reinforcement-Learning Testing and Large Language Models
Dianjing Cheng, Yike Li, Lan Yang et al. (+23 more)
Open-source autonomous driving systems provide an inspectable software foundation for intelligent vehicle research. Under real-vehicle deployment conditions, the recording and review of experimental conditions are important for interpreting system behavior and reusing experimental results. However, in a shared real-vehicle environment involving multiple vehicles, task processes, code modifications, and hardware testing feedback are often distributed across different teams and experimental stages, making it challenging to maintain continuous and reviewable experimental records. To address this limitation, this paper examines an Apollo-on-Hongqi EV environment and proposes a real-vehicle experimental framework. The framework connects multi-vehicle experiments, repository-based code reuse and software-hardware testing feedback within a unified review process. Large
language models and RL-based testing serve as auxiliary components for record organization, anomaly summarization, and simulation-based candidate scenario generation. Based on this setting, this paper analyzes preliminary evidence from multi-vehicle collaborative experimentation, code and experimental-skill sharing, and software-hardware collaborative testing. The analysis shows that experimental records can be examined together with their operating conditions, providing a reviewable basis for Apollo-on-Hongqi EV research.
Read the full abstract ▾
All authors Dianjing Cheng, Yike Li, Lan Yang, Shan Fang, Wenjia Niu, Xiangyu Shi, Xinyi Zhao, Yunzhe Tian, XingYu Wu, Xiaoshu Cui, Yuanwan Chen, Jialu Sun, Zhongli Wang, Biao Liu, Jiaqi Yang, Jinghui Feng, Feifei Su, Juan Du, Shuangde Fang, Yi Qian, Huiyun Li, Yuansheng Liu, Peng Sun, Mingming Wan, Nan Chen, Ruipeng Gao
Cryptography and Security
Understanding Stage-Wise Utility-Risk Trade-offs in LLM Agent Memory
Chuanchao Zang, Zijian Cao, Xiangtao Meng et al. (+6 more)
Long-term
memory is becoming a core capability of LLM
agents, enabling personalization and long-horizon interaction. However,
memory mechanisms that retain, transform, or expose more information can affect both benign utility and susceptibility to
memory poisoning. Existing evaluations typically measure
memory utility or attack risk in isolation under fixed configurations, providing limited insight into how stage-specific design choices reshape their trade-off. We present MemGauge, a controllable framework that separately varies writing admission, management policy, and
retrieval exposure under matched clean and poisoned conditions. Across 11 LLMs and two long-term
memory benchmarks, controlled evaluations reveal three distinct profiles: a threshold-like risk transition during writing, policy-dependent local decoupling during management, and coupled growth of utility and risk during
retrieval. We further apply analogous stage-level measurements to four existing
memory systems and observe diagnostic associations qualitatively consistent with these profiles. These results show that targeted poisoning risk varies across
memory operations and motivate stage-aware evaluation and control of LLM-
agent memory.
Read the full abstract ▾
All authors Chuanchao Zang, Zijian Cao, Xiangtao Meng, Jianing Wang, Wenyu Chen, Xinyu Gao, Li Wang, Zheng Li, Shanqing Guo
Machine Learning
Benchmarking Peptide-Protein Affinity Prediction Across Peptide and Target Shifts
Jiaxin Tian, Darren An and Jun Li
Peptide-
protein affinity models are often evaluated with a single data split, obscuring whether they interpolate among measurements for observed targets or generalize across peptide or target shifts. We integrated three sources of quantitative peptide-
protein binding data to obtain 11,349 deduplicated pairs and benchmarked ten peptide representations, ESM-2
protein embeddings, and six regressors under peptide-similarity, within-target, and leave-target-out partitions. Across 60 matched representation-regressor configurations, mean test Spearman correlations were 0.462, 0.669, and 0.530, respectively. The top configuration shifted from ECFP-16 count fingerprints with random forest in the first two settings to HELM-BERT with Extra Trees when exact target sequences were excluded. Representation-rank correlations ranged from -0.042 to 0.624 across partitions, whereas regressor-rank correlations ranged from 0.771 to 0.943. Learning curves showed that representation differences were largest with limited supervision and narrowed as training data increased. PeptideCLM-2 adaptation and simple element-wise interaction features provided no consistent gain over a frozen encoder and direct concatenation under the tested protocols. These conclusions are specific to a
dataset that pools transformed Kd, Ki, and IC50 measurements and to target exclusion at the exact-sequence level. Peptide-
protein affinity
benchmarks should therefore align data partitions with the intended use and jointly assess the effects of data scale, molecular representation, and downstream learner.
Read the full abstract ▾
Cryptography and Security
Reducio: Optimized Confidential Serverless Cloud Deployments for Enterprise Customers
Vikram Ramaswamy, Chuqi Zhang and Adil Ahmad
Serverless platforms based on Confidential Virtual Machines (CVMs) have been recently proposed to address the
privacy problems with serverless functions, while achieving low latency. Unfortunately, our study indicates that to achieve these properties, existing proposals impose non-trivial requirements in terms of infrastructure changes and platform
memory. Reducio is an alternate serverless platform design that does not require infrastructure changes and significantly reduces platform
memory requirements. The platform is designed using two key components: (1) a function isolation framework inside a CVM based on kernel deprivileging features that minimize infrastructure requirements, and (2) a layer-wise caching methodology and
algorithm that effectively uses a small in-
memory function cache. Our evaluation indicates that Reducio can significantly reduce both platform requirements for deployment and function
memory consumption.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from q-bio.QM
Science sandboxes measure the scientific capability of AI agents
Arya S. Rao, Rodrigo I. Castro, Sager J. Gosai et al. (+8 more)
Scientific progress depends not only on finding solutions, but on learning the rules that explain why they work and using that understanding to design better experiments. We introduce science sandboxes, a framework for studying this capability in AI
agents through repeated cycles of experimentation, feedback, and hypothesis revision. Science sandboxes invite an
agent to query the natural world in different ways, ranging from "wet" physical experiments, to "damp" predictive models trained on empirical data, to "dry" invented rules. By establishing a common experimental loop and a protocol for evaluating
agents within it, science sandboxes allow assessment of both quantitative performance on specific metrics and qualitative scientific
reasoning, across a spectrum of empirical verifiability. Here, we instantiate this framework in two biological settings, models of regulatory genomics and
protein fitness prediction, and examine the capabilities of frontier
agents. Across these settings, we could see when
agents successfully optimized a quantitative metric without understanding the rules underlying the system. In particular, their scientific
reasoning deteriorated when they encountered systems whose rules fell outside familiar biological priors. By highlighting such failure modes, science sandboxes make the frontier of scientific capability measurable and provide a controlled setting in which to study and ultimately expand it.
Read the full abstract ▾
All authors Arya S. Rao, Rodrigo I. Castro, Sager J. Gosai, Kenneth B. Hsu, Yasha Ektefaie, Shantanu Singh, Sangeeta N. Bhatia, Steven K. Reilly, Ryan Tewhey, Eric S. Lander, Pardis C. Sabeti
Information Retrieval
Doc-REFRAG: Rethinking Multimodal Document Retrieval-Augmented Generation
Ruofan Hu, Shengyang Xu, Minjie Hong et al. (+5 more)
Real-world knowledge resides in
multimodal documents, necessitating
retrieval-augmented generation (RAG) for accurate question answering. However, existing
multimodal RAG models are primarily designed for single-image or closed-document settings and exhibit limited accuracy in realistic multi-image scenarios. Moreover, processing numerous retrieved images incurs substantial computational overhead from irrelevant visual
tokens. To address these challenges, we introduce DocLongRAG, a large-scale
dataset of 343K question–answer pairs, each associated with an average of 37.4 retrieved images to reflect authentic RAG workflows. Building on this
dataset, we propose Doc-REFRAG, a question-guided framework that compresses visual
tokens into coarse chunks and selectively expands question-relevant ones via a lightweight RL-based selector. Experiments on six
benchmarks show that Doc-REFRAG outperforms eleven strong baselines, achieving state-of-the-art accuracy with significantly lower inference latency. Our resources are available at https://github.com/Collab-Gen/Doc-REFRAG.
Read the full abstract ▾
All authors Ruofan Hu, Shengyang Xu, Minjie Hong, Xiaoda Yang, Sashuai Zhou, Ke Lei, Tao Jin, Zhou Zhao
Machine Learning
Reinforcement Learning for Symbolic Equation Solving
Kevin P O Keeffe
We present a reinforcement-learning
agent that solves symbolic equations step by step, covering both nonlinear closed equations (radicals, exponentials, trigonometric) and a controlled class of restricted-open families requiring a change of variables (CoV) such as completing the square. We cast
algebra as an MDP with a dynamic action space and a tree-structured policy (TreeMLP). The main policy learns from reward alone with no supervised solution traces; the CoV substitution comes from a supervised generator interchangeable with a CAS call. On closed equations the
agent matches the prior best on CommonCore (0.93 greedy vs. ConPoLe's 0.925) under a single policy. On four hand-designed restricted-open families (quadratic, cubic, quartic, exponential) it reaches 0.79 beam / 0.67 greedy, exceeding the strongest non-learned search (A-
star, 0.64). Learned CoV timing has content only on the exponential family, the one requiring a nested CoV, where a natural rule solves none of the held-out equations while the policy solves 75% from reward alone. At 10x scale a sharp seed-level bimodality emerges; a UCB learning-progress curriculum shows a non-significant positive trend toward mitigating it. We do not claim general open-equation solving: every open-equation result is confined to these four controlled families.
Read the full abstract ▾
Computer Vision
AI-enabled Low-Cost 3D Maize Ear Morphometry Platform at Breeding Scale
Therin Young, Elijah Rodriguez, Lisa Coffey et al. (+4 more)
Maize ear geometry (length, width,
curvature, and volume) is closely tied to yield and grain-filling outcomes, but existing high-throughput phenotyping pipelines remain constrained by the cost, labor, and specialized hardware they require. We developed and validated a low-cost pipeline that reconstructs a watertight 3-D mesh of a maize ear from a single 20-second
video captured with a consumer-grade DSLR on a motorized turntable under uniform LED illumination. Camera poses from a multi-seed COLMAP procedure initialize a Neural Radiance Field (NeRF), and a cylindrical holder of known diameter, visible in every frame, provides automatic metric scaling with downstream
geometric quality control. Applied to 300 ears spanning a diverse maize inbred panel, 250 (83.3%) passed automated processing and quality control. Skeleton length agreed with manual caliper measurements across all 250 ears (R^2 = 0.964, RMSE = 4.68 mm), and convex-hull volume agreed with water-displacement volume on a 15-ear subset spanning the full size range (R^2 = 0.982, RMSE = 5.26 mL). Residual length error grew with ear
curvature, whereas bounding-box height, which records the same straight-line chord as calipers, showed no such trend; the discrepancy therefore originates in the measurement definition, since calipers record the chord while skeleton length traces the geodesic arc. The capture hardware costs approximately 607 USD, and operator involvement fell from roughly five minutes to one minute per ear, with all downstream processing running unattended. The platform provides a foundation for breeding-scale 3-D ear phenotyping.
Read the full abstract ▾
All authors Therin Young, Elijah Rodriguez, Lisa Coffey, Talukder Zaki Jubery, Adarsh Krishnamurthy, Patrick Schnable, Baskar Ganapathysubramanian
Distributed Computing
Projection-Free Bandit Online Optimization for Multi-Agent Systems with Dynamic Regret
Xia Jiang, Lu Liu and Gang Feng
This paper investigates distributed online optimization for multi-
agent dynamical systems with constrained inputs and time-varying cost functions. While online convex optimization offers a principal framework for sequential decision-making, existing online learning and optimization
algorithms typically require accurate system models, limiting their applicability in practical settings. To overcome this challenge, we propose a distributed bandit online feedback optimization
algorithm that relies solely on real-time input-output data. The
algorithm employs a smoothing zeroth-order one-point
estimator to construct local gradient approximations directly from cost evaluations. Additionally, to enforce input constraints effectively, we integrate a projection-free conditional gradient update, making the
algorithm well-suited for online and large-scale settings. Furthermore, we establish a sublinear dynamic regret bound that depends on a temporal variation measure of system non-stationarity. Finally, numerical simulations demonstrate the effectiveness of the proposed
algorithm.
Read the full abstract ▾