Robotics
Safety-Filtered Distributed Koopman-MPC
Shengjun Zhang, Wenhao Li, Zhenxin Lin et al. (+1 more)
Distributed model predictive control (DMPC) often constructs both predictions and collision constraints from neighbor trajectories, so packet loss can remove both. We separate these roles: received trajectories drive Koopman-MPC, while local sensing and shelf geometry define a hard-constrained quadratic program (QP) that projects the applied input. Its radial demand is the least constant acceleration that keeps a supporting-plane clearance nonnegative throughout one zero-order-hold interval. Complementary pair rows recover the coupled demand without exchanging safety decisions. We give an intersample separation
theorem under bounded snapshot and directional plant errors, an exact max-min test for simultaneous local feasibility, and a sensing-radius condition for switching interaction graphs. Anticipatory high-order rows may be relaxed for performance, but the finite-hold rows contain no safety slack. Matched eight-
robot warehouse simulations use a frozen Koopman model, nonlinear drift, bounded inputs and speed, shelf constraints, a 120 ms control period, and packet dropout. The full controller is collision-free in 20/20 matched trials and reaches 160/160
robot goals; predictive Koopman-MPC without the final projection is collision-free in 1/20 trials. All 38,400 full-method hard-row sets pass the online feasibility test, and every local QP solves. Five-stream fleet sweeps are collision-free and hard-row feasible through 16
robots; the 20-
robot boundary fails only after the online margin turns negative, while the reconstructed per-
agent critical path remains below the sampling period. Bounded-sensing and differential-drive tests provide additional deployment stress.
Read the full abstract ▾
All authors Shengjun Zhang, Wenhao Li, Zhenxin Lin, Zhenglong Sun
Computer Vision
Hybrid Gaussians for Robust Open-Vocabulary 3D Segmentation with Multi-View Object Association and Boundary Refinement
Xueqi Qiu, Yueming Sun, Tianyu Zhang et al. (+2 more)
Open-vocabulary 3D
segmentation localizes objects from free-form text queries, but remains challenging in real image sequences: incomplete or noisy 2D supervision destabilizes multi-view identity assignment, while full-scene semantic learning weakens object-level discriminability. We introduce Hybrid Gaussians, a unified 3D representation jointly modeling object association and
language-aligned semantics. Its Multi-View Object Association mechanism combines Observation Fusion and Semantic Contrastive Learning to improve identity consistency and semantic discrimination. Boundary Reconstruction Optimization further refines local boundary structure to improve contour quality. Experiments on LERF and 3D-OVS demonstrate strong quantitative and qualitative performance. Our method achieves 59.1% mIoU on LERF, yielding a 13.4% relative gain over the baseline. Project page: https://nora202.github.io/hybridgaussians.
Read the full abstract ▾
All authors Xueqi Qiu, Yueming Sun, Tianyu Zhang, Yuxuan Xia, Yang Long
Computer Vision
Invisible in Space, Visible in Time: Motion Vision CAPTCHA against GUI Agents
Zeyu Zhang, Dingyi Rong, Zijian Chen et al. (+3 more)
Most existing visual CAPTCHAs remain spatially solvable: the required information is exposed by static appearance, local structure, and interface state. This assumption is weakened by advances in
multimodal large
language models (MLLMs) and Graphical User Interface (GUI)
agents, which exhibit strong visual perception,
reasoning, and browser interaction capabilities. We propose Motion
Vision CAPTCHA (MVCAP), a hierarchical motion-based CAPTCHA framework in which target semantics are instantiated as motion-defined foreground structures and become recoverable only through temporal segregation from a dynamically evolving background. Built on this shared principle, MVCAP is instantiated in three perceptually progressive levels: coherent motion, structural motion, and biological motion. To evaluate this framework, we introduce MVCAP-Bench, a browser-based
benchmark with 600 live CAPTCHA instances, together with a matched foreground-only control
benchmark, MVCAP-Bench-FG. We evaluate humans, Browser Use
agents, native computer use
agents, and a supplementary offline VQA setting derived from the same instances. Results reveal a substantial human–
agent gap: on the full MVCAP-Bench, human accuracy reaches 99.6%, whereas the best GUI
agent achieves only 16.8%, close to the six-way chance level. The foreground-only control further shows that the key difficulty comes from dynamic background camouflage rather than answer format or browser interaction alone. These findings identify a measurable human–
agent perception gap and position MVCAP-Bench as a
benchmark for studying motion-defined perception in current
agents.
Read the full abstract ▾
All authors Zeyu Zhang, Dingyi Rong, Zijian Chen, Zicheng Zhang, Xiongkuo Min, Guangtao Zhai
Neural and Evolutionary Computing
Spiking Neural Network Predicting Sequence of the External Worlds States in Model-Based Reinforcement Learning
Mikhail Kiselev
This paper presents a spiking neural network (SNN) designed to predict the sequence of the external world states starting from the current world state. This SNN does not create the world dynamics model - instead it incorporates the SNN trained to predict the next world state and provides all mechanisms necessary to make the chain of predicted world states. These mechanisms are entirely spiking - they are implemented as spiking
neuron ensembles. The present article describes this neuronal structure and tests its operation on a classic RL
benchmark - ATARI ping-pong.
Read the full abstract ▾
Computer Vision
Beyond Balanced Accuracy: A Resolution and Parity-Controlled Benchmark for Vision-Language and Vision-Only Defect Assessment in UAV Power-Line Inspection
Linghao Zhang, Siyu Xiang, Junwei Kuang et al. (+1 more)
Vision-
language models (VLMs) are often reported to outperform task-specific
vision backbones for unmanned aerial vehicle (
UAV) power-line defect assessment. We test that claim on ElecVQA-Bench, a 56,972-item
benchmark derived from the public InsPLAD
dataset, across six evaluation choices: partition, evaluated item set, label space, replication, input resolution, and side information. On a matched partition, a Swin
Transformer and the strongest adapted VLM differ by only 0.03 points at binary screening. At seven-way defect typing, increasing the
vision backbones from 224 px to the measured pixel budget of the VLM preprocessor narrows the gap against InternVL3.5-8B from +20.53 to -0.57 points for ResNet-50 and from +23.67 to +4.70 points for Swin-T. A pixel-budget audit shifts Qwen3-VL-8B macro recall by 10.78 points, yet a source-pixel-matched InternVL control still leaves Qwen ahead by 7.43 to 13.61 points while using 56% fewer visual
tokens, so neither source pixels nor
token budget explains the difference between the two VLMs. A two-seed global replication changes Qwen binary accuracy and seven-way macro recall by 0.86 and 1.02 points. After split-specific retraining, Qwen does not lead at crop or image level, and a 14-tower, three-seed replication reverses the sign across seeds, giving mean common-six macro recall of 0.9085 for Qwen against 0.9509 for ResNet-50. No split regime yields a family-level advantage that survives multiple-comparison correction. The study supports a
benchmark-audit contribution rather than a general claim of VLM superiority.
Read the full abstract ▾
All authors Linghao Zhang, Siyu Xiang, Junwei Kuang, Peiyu Yi
Hardware Architecture · Cross-listed from quant-ph
Precision and resource scaling of real-time flux distortion compensation for superconducting quantum control
Qi Zhou, Zi-Hao Mei, Peng Duan et al. (+7 more)
Real-time waveform generation supports dynamic
quantum circuits without pre-storing complete waveforms for every execution path. However, long-lived distortions in flux-control lines degrade gate fidelity, requiring compensation to account for the actual pulse history. A frequency-domain inversion and time-domain fitting method is proposed for resource-efficient real-time flux distortion compensation. The method fits the reconstructed compensation impulse response with a compact hybrid infinite impulse response (IIR) and finite impulse response (FIR) filter. Look-ahead parallelization enables this filter to process synthesized waveforms at 1.2GSa/s on a field-programmable gate array (FPGA). Two-
qubit cross-
entropy benchmarking shows that real-time IIR filtering achieves a median controlled-Z Pauli fidelity close to the software-reference value of 99.57%. Numerical analysis and FPGA synthesis indicate approximately logarithmic growth in hardware resource use with compensation timescale. Extending compensation from microsecond to hundred-microsecond timescales increases look-up table (LUT) and digital signal processing (DSP) resource use by only about 14% and 4%, respectively, while maintaining a relative arithmetic error below $10^{-4}$. This work provides a scalable hardware foundation for high-fidelity flux control in dynamic superconducting
quantum circuits.
Read the full abstract ▾
All authors Qi Zhou, Zi-Hao Mei, Peng Duan, Peng Wang, Liang-Liang Guo, Hao-Ran Tao, Wei-Cheng Kong, Hui Yang, Guo-Ping Guo, Zhao-Yun Chen
Computer Vision
LeWAM: Latent evolving World Action Model
Xueji Fang, Boqiang Duan, Hua Wu et al. (+2 more)
World Action Models (WAMs) jointly model action generation and environment dynamics and are mostly built on pretrained
Video Diffusion Models (VDMs). In VDM-based WAMs, observations are first encoded by a VAE, and the resulting compressed latents are then processed by large
video diffusion backbones to extract effective features for action generation. However, this paradigm ties WAM performance and training cost to large-scale
video generation pretraining, limiting WAM efficiency and scalability. In this paper, we theoretically and empirically investigate how visual representations affect action generation in WAMs. Our results show that predictive
embeddings from Joint-
Embedding Predictive Architecture (JEPA) encoders better support action generation than compressed VAE latents, with I-JEPA performing best in our encoder comparison. Based on these findings, we propose LeWAM, which conditions action generation on JEPA
embeddings and models environment
evolution by predicting future
embeddings in the same space, without relying on a
video diffusion backbone. We further find that imitation learning matches demonstrated actions but does not distinguish better actions from worse ones, even though small action deviations can greatly affect task success. To address this limitation without additional environment interaction or the human oversight required for resets and safety, we introduce Demonstration-Guided DPO (DemoDPO), an offline preference refinement stage that derives preference supervision directly from demonstrations. With only 0.4B trainable parameters, LeWAM achieves an average success rate of 92.28% on RoboTwin 2.0, comparable to that of state-of-the-art VLAs and WAMs, and maintains practical effectiveness on real-world manipulation tasks.
Read the full abstract ▾
All authors Xueji Fang, Boqiang Duan, Hua Wu, Jingdong Wang, Guo-Jun Qi
Hardware Architecture
Implementation and Evaluation of BitNet Inference on a CGLA by Signed-Int4 Instructions
Takuto Ando and Yasuhiko Nakashima
Large
language model (LLM) inference transfers model weights and activations for every generated
token, making
memory traffic and its energy cost part of the decode path. BitNet b1.58 represents its low-bit weights by ternary values and uses integer activations. However, this arithmetic does not match conventional int8 or floating-point general
matrix multiplication, and existing BitNet accelerators implement it in specialized datapaths. We instead map this operation to a CPU-Grounded Linear Array (CGLA), a programmable ASIC with explicit direct
memory access, local
memories, and reusable compiler-visible integer lanes. The mapping adds OP_SMA4 as a reusable signed-int4 multiply-accumulate instruction rather than a BitNet-only datapath. Each ternary weight occupies one signed 4-bit lane. Each int8 activation is split into two signed-int4 fragments and reconstructed by shift-and-add. Frequency scaling of the 145 MHz FPGA measurement to an 840 MHz 28 nm CGLA achieved 0.390 ns per signed-int4 product. We showed that CGLA-offloaded BitNet C++ execution measures 2.52
tokens/s.
Read the full abstract ▾
Cryptography and Security
Issuer-Sovereign Agentic Payments
Dishant Sharma, Rajneesh Kaushal and Ashu Kanaujia
AI
agents are beginning to make real payments. Current approaches let an
agent pay by relying on a credential provider that, in the approaches deployed today, typically sits outside the cardholder's bank. The spending rules are then enforced by the card network or that provider, and not by the bank itself. This leaves the issuing bank, which carries the financial risk, with little direct control at the moment a payment happens. This paper describes Issuer-Sovereign Agentic Payments, a method that keeps that control with the issuer. The cardholder approves a spending rule once, and the bank's own authentication component records it. Later, when the
agent pays a specific merchant, the bank checks the merchant against the approved rule and generates the card authentication value only if the merchant is allowed. The payment then travels the normal card rails and is validated by the issuer, with no extra dependency introduced at execution.
Read the full abstract ▾
Robotics
BEE: Intervention-Adaptive Real-World Reinforcement Learning with Vision-Language-Action Models
Weihui Zhao, Xiaohan Yan, Zunian Wan et al. (+14 more)
Vision-
language-action (VLA) models handle long-horizon manipulation, yet success hinges on a few precision-critical phases where millimeter-scale errors undo all prior progress. Online reinforcement learning (RL) can optimize exactly these actions, but free exploration is far too costly on real
robots, which makes human corrections indispensable. However, existing online RL methods for VLAs either cannot incorporate such corrections or fold them into undifferentiated supervision. Yet human corrections are not uniformly noisy but reliable along some action dimensions and variable along others. Building on this, we introduce BEE, an intervention-adaptive framework for real-world RL on a frozen VLA that lets the policy go BEyond Expert imitation. We formulate human corrections not as actions to reproduce but as evidence about a constraint: a Correction Model predicts how a human would correct a given VLA proposal and how consistent the correction is along each action dimension. This predicted consistency sets the per-dimension tightness of a constraint on policy optimization. Where corrections are consistent the policy stays close to the human, and where they vary, the constraint relaxes. We evaluate BEE on three real-world manipulation tasks and one LIBERO-Pro simulation task at a matched online-data budget. BEE attains the highest success rate on every task, 91.2% on average against 57.5% for RLT and 42.1% for DSRL, and the lowest human intervention rate on all real-world tasks.
Read the full abstract ▾
All authors Weihui Zhao, Xiaohan Yan, Zunian Wan, Xuan Du, Zhaozhan Chi, Jianbo Mao, Ruipu Wu, Rushuai Yang, Houlin Li, Shukai Yang, Jing Wu, Yuxiang Yan, Yongcheng Liu, Chuankang Li, Guanghui Ren, Wei Shan, Maoqing Yao
Robotics
X2Real: an eXtensive simulation benchmark for real-world generalist policies
Lian Ruan, Jade Yang, Sherphylan Gao et al. (+23 more)
Generalist
robot manipulation policies have developed rapidly, yet their reliable evaluation remains challenging due to fundamental flaws in existing simulation
benchmarks: prominent sim-to-real gaps, narrow task coverage, and unfair evaluation caused by ambiguous training-test pipelines. Prior works only partially resolve these issues and lack simultaneous faithfulness, diversity, and
fairness, while static
benchmark designs fail to sustain long-term policy development. We present X2Real, an evolvable simulation
benchmark for faithfully evaluating the real-world performance of robotic manipulation policies based on Nvidia Isaac Lab-Arena. Following three core principles (faithfulness, diversity, and
fairness), X2Real calibrates simulation visual and physical properties to align with real hardware, achieving a 0.84 linear correlation between simulated and real-
robot evaluation results. It features a comprehensive taxonomy with 10 capability dimensions and 44 hierarchical long-horizon tasks, covering basic manipulation skills and advanced capacities such as visual grounding,
language understanding, and bimanual control. We further adopt multi-axis domain randomization and strictly disjoint training-evaluation pipelines to mitigate
benchmark exploitation and ensure credible evaluation. Powered by a custom physical domain-specific
language, the Mana simulation ecosystem supports modular task design and iterative performance analysis, alongside a nearly 300-hour annotated simulation trajectory
dataset. X2Real offers a faithful, diverse, and fair evolving evaluation infrastructure, effectively bridging the sim-to-real evaluation gap and supporting the advancement of generalist robotic manipulation policies.
Read the full abstract ▾
All authors Lian Ruan, Jade Yang, Sherphylan Gao, Felix Gao, Kyson Liang, Galen Liu, Ligo Wu, Lane Jin, Guu Gu, Bevan Xie, Cloud Yan, Zongzi Yuan, Kino Luo, Emma Chen, Shuwen Chen, Yang Ping, Miles Guo, Rain Sun, Kayden Zhang, Alex Du, Ruihai Wu, Liang Hao, Zhaoshuo Li, Roy Gan, Hao Wang, Qian Wang
Machine Learning
Quantum Reinforcement Learning for Cost and Delay Tradeoffs in Quantum Cloud Orchestration
An N. H. Phan, Dang Van Huynh, Muhammad Usman et al. (+1 more)
Quantum cloud computing, delivered through the
quantum-as-a-service (QaaS) model, provides access to
quantum computing resources. However, applying uniform time-based pricing across fundamentally heterogeneous
quantum resources significantly complicates task orchestration, particularly when addressing the tradeoff between execution costs and system performance. While heuristic methods rely on predefined scheduling rules, classical deep reinforcement learning (DRL) models may require more trainable parameters in this setting. Motivated by the potential of parameterised
quantum circuits (PQCs) as compact function approximators, we propose QRLQ, a cost-delay-aware
quantum cloud scheduling framework integrating PQCs with a dueling double deep Q-network (D3QN) to dynamically account for both cost and delay. Our simulation results show that QRLQ achieves lower mean cost and delay than the heuristic baselines, achieving a 5-11% lower mean cost relative to availability-based and rotation-based heuristics and reducing mean delay by 17% and 82% relative to the strongest and weakest heuristic baselines, respectively, while retaining execution fidelity within 2% of a fidelity-greedy policy. Compared with the classical DRL baseline, QRLQ achieves comparable scheduling performance while using 72% fewer trainable parameters. This work explores the feasibility of using QRL for task orchestration in
quantum cloud environments and demonstrates its potential for cost-delay-aware
quantum resource management.
Read the full abstract ▾
All authors An N. H. Phan, Dang Van Huynh, Muhammad Usman, Hoa T. Nguyen
Computer Vision
SatUnreal: A High-Precision Synthetic Dataset for Satellite Stereo Matching via Unreal Engine
Han-Gyeol Kim, JaeWan Park, Junmin Park et al. (+1 more)
3D reconstruction from satellite imagery is essential for large-scale topographic analysis, yet the lack of high-fidelity training
datasets with accurate occlusion labels remains a primary bottleneck. Existing
benchmarks, such as US3D and WHU-Stereo, face inherent challenges in spatio-temporal mismatch – environmental changes and shadow displacements between multi-view acquisitions – and provide ambiguous ground truth in occluded regions due to
LiDAR sparsity. In this paper, we propose SatUnreal, a high-precision synthetic
dataset designed to fundamentally overcome these limitations through an Unreal Engine-based simulation pipeline. SatUnreal provides 10,000 stereo pairs with high resolution (0.3m GSD) and is characterized by: (1) Physical Geometry Simulation, replicating realistic satellite orbits by systematically varying baselines and azimuths; (2) Spatio-temporal Consistency, eliminating temporal noise through fixed virtual environments; (3) Topographic Diversity, spanning dense urban canyons to low-texture natural terrains; and (4) Mathematical Label Integrity, utilizing a novel two-step linetrace
algorithm to generate flawless occlusion masks. Experimental results using SOTA iterative models demonstrate that models trained exclusively on SatUnreal achieve superior zero-shot transfer performance on real-world
benchmarks (US3D, WHU-Stereo) compared to those trained on real
datasets. Our findings prove that physically accurate synthetic data provides a more effective supervisory signal for learning
geometric features than complex real-world observations, establishing a new paradigm for Sim-to-Real transfer in Earth Observation. Code and
dataset are available at https://github.com/jmp-Telepix/SatUnreal_A_High-Precision_Synthetic_
Dataset_for_Satellite_Stereo_Matching_via_UnrealEngine
Read the full abstract ▾
All authors Han-Gyeol Kim, JaeWan Park, Junmin Park, Darongsae Kwon
Machine Learning
Stable Neural Decoding Across Sessions via Task-Conditioned Latent Alignment for Brain-Machine Interfaces
Canyang Zhao, Bolin Peng, J. Patrick Mayo et al. (+2 more)
Achieving stable long-term neural decoding in invasive
brain-machine interfaces (BMIs) remains challenging due to variations in recorded neural populations across sessions. Current latent
alignment approaches may overlook task-dependent structure during cross-session adaptation. We propose Task-Conditioned Latent
Alignment (TCLA), a framework that stabilizes neural decoding by learning a shared latent space. TCLA learns a low-dimensional source representation using neural reconstruction and continuous behavioral supervision. During target-session adaptation, the shared representation is fixed, while target neural activity is mapped into the source latent space by aligning source and target distributions separately for each task condition. We evaluated TCLA on seven nonhuman primate
datasets spanning multiple tasks. In long-term cross-session evaluation, TCLA achieved a mean $R^2$ of $0.476\pm0.014$ with a negative $R^2$ failure rate of only 6.8%. Across 1,356 within-subject session pairs, TCLA achieved a mean $R^2$ of $0.371\pm0.009$ with a failure rate of 6.8%. Across 2,134 cross-subject session pairs, TCLA achieved a mean $R^2$ of $0.218\pm0.004$ with a failure rate of 12.9%, substantially better than those of the comparison methods. These results demonstrate that by preserving behaviorally relevant and task-dependent latent structure, TCLA improves the robustness of neural decoding across recording sessions and subjects. The source code is publicly available at \href{https://github.com/FAMD-CASIA/TCLA}{https://github.com/FAMD-CASIA/TCLA}.
Read the full abstract ▾
All authors Canyang Zhao, Bolin Peng, J. Patrick Mayo, Ce Ju, Bing Liu
Data Structures and Algorithms
Sampling Line-Graph Colorings with Constant Extra Colors
Alireza Haqi
Let $G$ be the line graph of a finite simple graph, with $n\geq1$ vertices and maximum degree $\Delta$. We prove that single-site Glauber dynamics for uniform proper $q$-colorings mixes in $O_\Delta(n\log(n/\varepsilon))$ steps for every integer $q\geq\Delta+5$. Our proof uses the Bochner framework of Chen and Liu (2026).
Read the full abstract ▾
Robotics
Compressed delayed-information projection for underwater navigation under acoustic measurement latency
Shuyue Li, Miguel López-Benítez, Eng Gee Lim et al. (+5 more)
Delayed acoustic position measurements describe past states but may reach an
underwater vehicle after its
navigation estimate has advanced. This paper presents compressed delayed-information projection (CDIP), a causal delayed-update method implemented in a 15-dimensional error-state Kalman filter (ESKF). CDIP retains source-associated inertial measurement unit (IMU) snapshots and maintains current-to-snapshot cross-covariances, projecting delayed corrections without repeated full-from-start filtering. In 154 paired simulation recordings with synthetic horizontal-position fixes delayed by 1.5~s, CDIP reduced mean trajectory-position root-mean-square error (RMSE) from 1.062~m for a reception-time Baseline to 0.456~m (57.1%). Its mean RMSE approached that of full-from-start Replay (0.451~m), with 99.2% lower mean core-loop time per processed IMU step for the tested implementations. A six-delay sweep, scheduled permanent-loss outages of 50–300~s, and packet-erasure tests further characterized sensitivity to measurement timing and availability. A separate 256-trial nonlinear synthetic assessment identified departures from the prespecified calibration criterion for CDIP and two fully augmented ESKF references. Together, these results demonstrate an accuracy–computation trade-off for causal
underwater navigation under the evaluated delayed-measurement simulation conditions.
Read the full abstract ▾
All authors Shuyue Li, Miguel López-Benítez, Eng Gee Lim, Fei Ma, Qian Dong, Mengze Cao, Limin Yu, Xiaohui Qin
Hardware Architecture
Energy-Oriented CGLA Mapping of a Memory-Polynomial Digital Predistortion Kernel
Takuto Ando and Yasuhiko Nakashima
Memory-
polynomial digital predistortion (DPD) evaluates a small fixed coefficient set over a sliding input history, so its reduction step is a complex-MAC workload with local reuse. We map this DPD reduction kernel onto In-
Memory Accelerator eXtension (IMAX), a programmable CPU-Grounded Linear Array (CGLA) composed of a one-dimensional processing-element/local-
memory pipeline. For a (P,M)=(5,5) odd-order
memory-
polynomial instance, the mapping keeps the 120 B coefficient set in local
memory, advances the five-tap history over 1024-sample tiles, and realizes the 15 order-delay terms as a 33-stage streaming complex-MAC reduction. The evaluation measures kernel latency and modeled energy. All measured paths use the same single-precision complex workload of 32 sequences, each with 2048 complex samples, across an IMAX FPGA prototype, a CUDA implementation on an RTX 4090 system, and an ARM-NEON implementation on Jetson AGX Orin. With this 1024-sample tile configuration, the IMAX FPGA prototype reports 20.201 ms end-to-end latency and 1.948 ms kernel-only latency. Using the previously reported 28 nm IMAX frequency and power model, the projected IMAX configuration gives 3.14 ms end-to-end latency and 0.34 ms kernel-only latency. The RTX 4090 baseline has the lowest end-to-end latency at 0.484 ms. Under model-based platform power accounting and the stated power assumptions, the projected IMAX configuration gives 169.1 times smaller modeled end-to-end energy per batch than the RTX 4090 baseline. This value uses platform power assumptions rather than workload-dependent runtime power or a direct silicon power measurement. A controlled synthetic PA-model validation checks that the same 15-term form improves test-set NMSE by 26.1 dB and ACLR by 26.0 dB. These results characterize the mapped
memory-
polynomial DPD reduction on IMAX for the evaluated tile configuration and power model.
Read the full abstract ▾
Hardware Architecture
Mamba-Family State-Space Model Kernels on a Programmable CGLA
Takuto Ando and Yasuhiko Nakashima
Edge and embedded inference is constrained by power and data movement. Mamba-family state-space models replace
attention with sequence-linear recurrence, but their inference path combines dense projections, short-reduction SSD kernels, and recurrent-state updates. This paper maps these kernel groups onto IMAX, a programmable CPU-Grounded Linear Array (CGLA), and measures them from kernel execution to
token-level integration. Projection kernels match the long-reduction IMAX pipeline, whereas SSD Step-1 is limited by short reductions and kernel-boundary overheads. Mamba-130M
token-level integration identifies projection GEMV as the decode bottleneck. These results show that programmable CGLAs fit long-reduction projection kernels, while SSD and decode-time projection support require boundary reduction and persistent-weight execution.
Read the full abstract ▾
Information Theory
The Sharp Rényi and Tsallis Threshold in the Shepp–Olkin Concavity Problem
Haoran Wang
Let $B_1,\ldots,B_n$ be independent Bernoulli random variables with parameters $p_1,\ldots,p_n$, and let $S=\sum_i B_i$. Hillion and Johnson proved that the Shannon
entropy of $S$ is jointly concave in the parameter vector and proposed corresponding critical-order
conjectures for R'enyi and Tsallis
entropies, with predicted thresholds $2$ and approximately $3.65986$, respectively. We determine both thresholds exactly. For every $0<q<1$, the power sum $\sum_k \mathbb P(S=k)^q$ is jointly concave in $(p_1,\ldots,p_n)$, and strictly concave on the open parameter cube. Consequently, the R'enyi and Tsallis
entropies of order $q$ are jointly concave. At $q=1$ this agrees with the Shannon
theorem. For every $q>1$, joint concavity fails already for the sum of two Bernoulli variables: a transverse interpolation in which the two parameters move in opposite directions gives strict local convexity for both
entropies. Hence the universal joint-concavity range for both families is exactly $0<q\leq 1$. Below order one, the proof combines the Hillion–Johnson transport inequality with an explicit nonlinear telescoping correction. The corrected local
curvature reduces to a two-dimensional quadratic form. An exact Riccati identity, together with a one-sided zero-crossing argument, proves positivity of its determinant throughout the full range $0<q<1$.
Read the full abstract ▾
Neural and Evolutionary Computing
An Unbounded Archive-based Transfer Strategy for Dynamic Multi-Objective Optimization with a Changing Number of Objectives
Zhiyun Xiao, Ke Shang, Yajun Liu et al. (+3 more)
Dynamic multi-objective optimization with a variable number of objectives is difficult because objective-dimensional variations may significantly change the Pareto front and degrade
algorithm adaptability. This paper proposes an unbounded archive-based transfer strategy (UATS), which maintains an unbounded archive of offspring solutions within each environment stage and extracts feasible nondominated solutions as transferable elites when objective changes occur. UATS is embedded into SPEA2SDE to construct UATS-SPEA2SDE, enabling the
algorithm to reuse historical evolutionary information while retaining the convergence and diversity advantages of shift-based density estimation. Experiments are conducted on four
benchmark problems under three objective-changing settings, where UATS-SPEA2SDE is compared with a restart-based SPEA2SDE baseline and four representative dynamic multi-objective optimization
algorithms. The results indicate that the archive-guided transfer improves recovery after environmental changes and enhances adaptability to objective-number variations.
Read the full abstract ▾
All authors Zhiyun Xiao, Ke Shang, Yajun Liu, Jianguo Li, Shaojiang Wang, Wei Sun
Cryptography and Security
A Bulletproof Business? Towards Detecting Infrastructure-as-a-Service Offerings on Telegram
Roy Ricaldi, Kristiyan Kyurkchiev and Irdin Pekaric
Cybercriminal operations increasingly depend on reusable digital infrastructure—including hosting, proxies, and virtual private networks (VPNs)—rented through Cybercrime-as-a-Service
markets and advertised on platforms such as Telegram. We present a taxonomy for identifying Telegram messages advertising cybercriminal Infrastructure-as-a-Service (IaaS). The taxonomy comprises six service categories across compute, network, and communication infrastructure, together with three trust attributes: Bulletproof, Payment Security, and Transparency. Using 261 human-annotated messages, we evaluate keyword-based and TF–IDF classifiers and examine
prompt-based large
language models as exploratory baselines. We select a TF–IDF pipeline and apply it to 1,116,071 messages from 167 cybercrime-related Telegram communities. The pipeline assigns at least one infrastructure category to 207,244 messages (18.57%) spanning 113 communities. Classified advertising is highly concentrated: a single community accounts for 50.3% of infrastructure-positive messages, while the trust-attribute classifiers identify Bulletproof claims in 37.66% of those messages. These findings characterize the scale, composition, and concentration of infrastructure advertising on Telegram and can inform the prioritization of communities and actors for monitoring and investigation.
Read the full abstract ▾
Cryptography and Security
Extracting CNNs in the Unknown-Architecture and Feedback-Agnostic Setting
Jiashuo Liu, Ruijie Ma, Manman Li et al. (+2 more)
This paper studies the cryptanalytic extraction of convolutional neural networks (CNNs). Existing cryptanalytic extraction attacks on CNNs assume that the network architecture is known, and try to recover model parameters.In this paper, we prove for the first time that the architecture assumption can be removed for CNNs with both max and average pooling. Our core finding is that the spatial geometry of the weight vectors recovered by existing parameter-recovery attacks naturally leaks the architecture. We formalize this geometry and establish its correspondence with the architectural knowledge of a convolutional layer: (1) The sparsity consistency with the convolution receptive field reveals the layer type, the kernel size, and the stride; (2) The numerical consistency with the kernel parameters reveals the padding mode and the output-channel number; (3) The structural consistency with the pooling operation reveals the pooling type, the window size, and the stride. Although the recovered vectors are obtained using different methods in the raw-output and hard label settings, their spatial geometry remains the same. Therefore, our architecture recovery is feedback-agnostic: combined with a parameter-recovery attack, it yields a complete cryptanalytic extraction framework that recovers both the architecture and the parameters in the black-box setting. Extensive experiments, including both layer-wise and end-to-end ones, on a wide range of CNNs demonstrate that simultaneously recovering the network architecture and the model parameters is practical.
Read the full abstract ▾
All authors Jiashuo Liu, Ruijie Ma, Manman Li, Yi Chen, Shaozhen Chen
Cryptography and Security
EVAGE: Autonomous MEV Generation and Adaptation via Multi-Agent Harness
Yan Wen, Zichun Cai, Iliya Mirzaei et al. (+4 more)
Maximal Extractable Value (MEV) has evolved into a major economic force in blockchain ecosystems, yet its capture is dominated by experienced teams, and both strategy design and implementation rely on manual expert work that scales poorly across heterogeneous protocols and chains. We present EVAGE, the first fully autonomous multi-
agent framework for end-to-end MEV strategy generation and adaptation. Equipped with three specialized operation modes, it automatically discovers novel MEV variants, adapts execution logic across disparate protocols, and ports strategies between chains, including Layer-1 and Layer-2 networks. To avoid inference latency on the critical MEV execution path, EVAGE generates and refines MEV bot code offline rather than making real-time decisions directly. Under the coordination of an orchestrator
agent, three specialized subagents collectively implement and repair the full MEV bot workflow via closed-loop diagnostics, eliminating human intervention while producing validated and deterministic Proof-of-Concept implementations. We evaluate EVAGE on over 1.5M blocks from each of Ethereum, Base, and BNB Smart Chain (BSC). On Ethereum, EVAGE uncovers five novel MEV strategy variants, yielding a profit increase of 1.02$\times$ to 15.97$\times$. It also successfully adapts 11 MEV strategies from CPMM to both CLMM and Balancer V2 and ports strategies from Ethereum to Base and BSC, all with less than 60 dollars in LLM
token costs.
Read the full abstract ▾
All authors Yan Wen, Zichun Cai, Iliya Mirzaei, Xiaohua Cai, Mohammad Javad Amiri, Haoxian Chen, Chenyuan Wu
Computer Vision
Overlapping Visual Grouping Without Semantic Priors
Teemu Saukkio, Hashem Haghbayan and Juha Plosila
Most computer-
vision systems organize visual input toward a predefined interpretation, such as semantic categories, prompted regions, learned object-like representations, or a single spatial partition. This work considers an earlier stage of visual organization: the formation of candidate perceptual units directly from sensor measurements before their identity, meaning, or task relevance is known. We introduce Domain Parent Grouping (DPG), a sensor-grounded grouping method in which complementary measurement relationships are represented in separate processing domains. Spatially connected groups formed within these domains are related through cross-domain overlap, yielding a non-exclusive grouping representation rather than a single mutually exclusive
segmentation. This representation retains broader and more localized groups, as well as alternative grouping boundaries over the same image locations, simultaneously available. DPG also includes a native mechanism for reprocessing selected group content, in which input-relative measurement ranges allow the observational resolution to change while preserving previously formed groups. DPG is implemented using three domains representing locally contextualized luminance, direct chromatic relationships, and contextual chromatic relationships. Experiments on the BSDS500
dataset demonstrate the benefit of combining the three domains. The results further show that DPG forms measurement-supported groups corresponding to low-level image structure, and that these groups exhibit measurable correspondence with human-annotated regions and boundaries. This demonstrates that structured visual organization can emerge directly from relationships among sensor measurements.
Read the full abstract ▾
Cryptography and Security
RAMP: Reversing Adversarial Perturbations to Strengthen Clean-Label Backdoor Attacks against Malware Detectors
Jinwen Xin, Dongni Zhang, Chenyang Wang et al. (+3 more)
Deep learning-based malware detectors are commonly updated by fine-tuning on newly collected samples, but this practical update pipeline also creates an attack surface for training-time
backdoor attacks. In realistic crowdsourced data collection, however, strict label vetting typically restricts attackers to the clean-label setting, in which poisoned samples must retain benign labels and functionality, making effective
backdoor injection substantially harder. We present a new attack perspective based on feature-space manipulation: instead of relying solely on stronger trigger designs or selecting benign samples that are naturally similar to malware, we deliberately construct benign programs whose representations shift toward the malware region before trigger injection, thereby creating stronger feature-label conflicts during training. Based on this insight, we propose RAMP, an attack enhancement method that uses a genetic
algorithm to optimize reversed
adversarial perturbations under black-box access and then injects them through functionality-preserving binary manipulations. Extensive experiments show that RAMP substantially improves attack effectiveness over trigger-only baselines, with especially pronounced gains at low poisoning ratios, while maintaining accuracy on clean data. Moreover, RAMP can be combined with advanced trigger designs.
Read the full abstract ▾
All authors Jinwen Xin, Dongni Zhang, Chenyang Wang, Jianming Fu, Ming Tang, Guojun Peng
Machine Learning
Counterfactual Constraint-Conditioned On-Policy Distillation for Multi-Constraint Instruction Following
Yanzhao Zheng, Yuanqiang Yu, Tianze Xu et al. (+6 more)
Multi-constraint instruction following requires a model to respond to a query under many simultaneously active constraints. Even strong instruction-tuned models still routinely violate some of them. Existing approaches either augment supervision with sequence- or
token-level RL rewards from external verifiers or learned graders, or use on-policy
distillation (OPD) against a single full-context teacher whose probability mass becomes diluted as more constraints become simultaneously active. We propose CC-OPD (Counterfactual Constraint-Conditioned On-Policy
Distillation), which inverts the standard supervision-generation direction in
distillation. Rather than enriching the teacher with information beyond what the student sees, CC-OPD ablates each constraint from the teacher's conditioning in turn, and constructs the per-constraint signal from the resulting per-
token probability differentials. The resulting per-
token leave-one-out log-likelihood shifts are summed, clipped, and added to the vanilla OPD reward as a
token-level shaping term. All shaping terms are obtained from the frozen teacher, without an external verifier during
distillation, and the reward equals vanilla OPD wherever the aggregate shift is zero. Across two Qwen model pairs and seven
benchmarks, CC-OPD achieves the highest average among all evaluated student-training methods. A 1.5B student trained with CC-OPD surpasses its own 7B RL-trained teacher on the MulDimIF
benchmark.
Read the full abstract ▾
All authors Yanzhao Zheng, Yuanqiang Yu, Tianze Xu, Chao Ma, Zhentao Zhang, Jihuai Zhu, Baohua Dong, Hangcheng Zhu, Ruohui Huang
Numerical Analysis
A Deformation Approach to Axially Symmetric Kernels on the Sphere: Harmonic Coupling and Regularity
Janin Jäger and Fabian Stallbauer
In this paper, we construct axially symmetric kernels on the sphere. We start by taking an isotropic kernel and transform it into an axially symmetric kernel via a specific deformation. For a general deformation, an explicit spherical-harmonic representation is not necessarily available. For our deformation, we can obtain such a representation of the deformed kernel in terms of the expansion coefficients of the original isotropic kernel. We derive this representation by explicitly describing the effect of the deformation on the spherical harmonic basis. From this, an explicit finite sum formula for the coupling coefficients is deduced and we show that, for each fixed input mode, the coefficients decay geometrically at a rate controlled by our deformation parameter. We further note that if the native space of the isotropic kernel is norm equivalent to a Sobolev-space, then the deformed kernel has the same native space with an equivalent norm. In our numerical experiments, we show that our deformation can improve prediction when the underlying random field has an axially symmetric covariance.
Read the full abstract ▾
Computation and Language
EviStreams: Human-in-the-Loop AI Data Extraction for Systematic Reviews in Medicine
Sai Karthik Kosuri, Ankita Shashikant Bhosale, Michael Glick et al. (+2 more)
Systematic reviews underpin clinical guidelines, yet their data-extraction step is a major expert-labor bottleneck bound by a protocolized workflow: two reviewers extract each study independently, an adjudicator resolves disagreements, and the team keeps an auditable record of how every value was produced. Large
language models can assist with extraction, but that assistance must fit established review protocols and preserve reproducibility. We present EviStreams, a live, open-source, no-code web platform that puts review teams in control of AI-assisted extraction at three key stages: program design (a structured decomposition approved before any code runs), field specification (typed field definitions calibrated from a pilot), and extracted predictions (reviewer-blinded dual review with adjudication). Working through a form builder, a domain expert defines typed fields rather than
prompts, runs extraction over uploaded PDFs, inspects every value alongside the supporting passage it came from, and resolves a reviewer-blinded dual review into an auditable consensus export. An evaluation across four clinical corpora and three frontier model families, released with the system, shows that extraction quality is shaped far more by the field specification than by the choice of model. EviStreams is live at https://evistreams.com/demo and released under Apache-2.0.
Read the full abstract ▾
All authors Sai Karthik Kosuri, Ankita Shashikant Bhosale, Michael Glick, Alonso Carrasco-Labra, Chris Callison-Burch
Artificial Intelligence
Emergi-PersonaOS: A Persona Agent Operating System for Situational Adaptation and Controllable Evolution
Haoluan Fu, Keni Chen, Xinyu Jia et al. (+3 more)
Symbiosis between humans and digital beings offers a
vision for the future of human–machine interaction. In enduring human–machine relationships, personality provides a foundation for continuity of identity, individuality in interaction, and development through experience. We investigate this capacity through persona
agents as computational implementations and introduce Emergi-PersonaOS, a psychology-grounded operating system for managing persona objects throughout their lifecycle. The system organizes dispositional traits, characteristic adaptations, and narrative identity into a three-layer persona representation, distinguishing relatively enduring persona beliefs from their activation in the current persona state. During situational adaptation, it integrates the current interlocutor, relationship, event, and retrieved
memories to infer a persona state and generate actions and replies; during long-term development, it records experiences and outcomes, and develops and evaluates revision candidates through change attribution, meaning-making, and behavioral testing. Belief updates are managed through explicit review, traceable evidence and version records, and the ability to reject candidates, making persona
evolution controllable. Using television-character dialogue as longitudinal material, we demonstrate long-horizon system operation and examine its principal mechanisms in a concrete implementation. This work provides a computational framework for persona
agents to maintain individual continuity, produce situation-specific expression, and develop through experience over sustained interaction.
Read the full abstract ▾
All authors Haoluan Fu, Keni Chen, Xinyu Jia, Jinpeng Wang, Yuyu Yin, Yubiao Hu
Human-Computer Interaction
Forced Yet Free: What Magicians' Forcing Reveals Beyond Intentional Binding
Koichi Toida
In magicians' forcing, spectators may experience a choice as self-determined even when that choice has been externally directed. Research on the sense of agency has developed largely around action-outcome relations, most notably intentional binding; however, the problem of choice authorship (why a particular choice is experienced as originating from oneself) must be treated as distinct. This paper integrates research on agency and forcing by distinguishing the locus of intervention within the choice-action-outcome chain, self-attribution at the Decision, Action, and Outcome levels, and the processes by which feeling of agency and judgment of agency are constructed. On this basis, a distinction is drawn between intentional binding, which concerns the temporal/causal relation between action and outcome, and the different binding problem exposed by forcing: the relation between a choice and its author. This theoretical relation is termed authorship binding. Authorship binding does not denote a new implicit measure; rather, it refers to the constructive relation through which a choice whose formation has been directed by external factors can nevertheless be experienced as originating from the self. Forcing can sustain this relation not by eliminating agency, but by selectively preserving, substituting, and redistributing agency cues. XR, in which body-centred spatial relations can be manipulated, is further conceptualised as a medium for extending the forced-yet-free structure into space.
Read the full abstract ▾