Extracting optical flow from videos remains a core computer vision problem. Motivated by the recent success of large general-purpose models, we ask whether frozen self-supervised video models trained only to predict future frames can be prompted, without fine-tuning, to output flow. Prior attempts to read out depth or illumination from video generators required fine-tuning; that strategy is ill-suited for flow, where labeled data is scarce and synthetic datasets suffer from a sim-to-real gap. Inspired by the Counterfactual World Model (CWM) paradigm, which can obtain point-wise correspondences by injecting a small tracer perturbation into a next-frame predictor and tracking its propagation, we extend this idea to generative video models for zero-shot flow extraction. We explore several popular architectures and find that successful zero-shot flow extraction in this manner is aided by three model properties: (1) distributional prediction of future frames (avoiding blurry or noisy outputs); (2) factorized latents that treat each spatio-temporal patch independently; and (3) random-access decoding that can condition on any subset of future pixels. These properties are uniquely present in the recently introduced Local Random Access Sequence (LRAS) architecture. Building on LRAS, we propose KL-tracing: a novel test-time inference procedure that injects a localized perturbation into the first frame, rolls out the model one step, and computes the Kullback–Leibler divergence between perturbed and unperturbed predictive distributions. Without any flow-specific fine-tuning, our method is competitive with state-of-the-art, task-specific models on the real-world TAP-Vid DAVIS benchmark and the synthetic TAP-Vid Kubric. Our results show that counterfactual prompting of controllable generative video models is an effective alternative to supervised or photometric-loss methods for high-quality flow.

Estimating motion primitives from video (e.g., optical flow and occlusion) is a critically important computer vision problem with many downstream applications, including controllable video generation and robotics. Current solutions are primarily supervised on synthetic data or require tuning of situation-specific heuristics, which inherently limits these models' capabilities in real-world contexts. A natural solution to transcend these limitations would be to deploy large-scale, self-supervised video models, which can be trained scalably on unrestricted real-world video datasets. However, despite recent progress, motion-primitive extraction from large pretrained video models remains relatively underexplored. In this work, we describe Opt-CWM, a self-supervised flow and occlusion estimation technique from a pretrained video prediction model. Opt-CWM uses ``counterfactual probes'' to extract motion information from a base video model in a zero-shot fashion. The key problem we solve is optimizing the quality of these probes, using a combination of an efficient parameterization of the space counterfactual probes, together with a novel generic sparse-prediction principle for learning the probe-generation parameters in a self-supervised fashion. Opt-CWM achieves state-of-the-art performance for motion estimation on real-world videos while requiring no labeled data.

AI agents have the potential to significantly alter the cybersecurity landscape. Here, we introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems. Instantiating this framework with BountyBench, we set up 25 systems with complex, real-world codebases. To capture the vulnerability lifecycle, we define three task types: Detect (detecting a new vulnerability), Exploit (exploiting a given vulnerability), and Patch (patching a given vulnerability). For Detect, we construct a new success indicator, which is general across vulnerability types and provides localized evaluation. We manually set up the environment for each system, including installing packages, setting up server(s), and hydrating database(s). We add 40 bug bounties, which are vulnerabilities with monetary awards from \\$10 to \\$30,485, covering 9 of the OWASP Top 10 Risks. To modulate task difficulty, we devise a new strategy based on information to guide detection, interpolating from identifying a zero day to exploiting a given vulnerability. We evaluate 10 agents: Claude Code, OpenAI Codex CLI with o3-high and o4-mini, and custom agents with o3-high, GPT-4.1, Gemini 2.5 Pro Preview, Claude 3.7 Sonnet Thinking, Qwen3 235B A22B, Llama 4 Maverick, and DeepSeek-R1. Given up to three attempts, the top-performing agents are OpenAI Codex CLI: o3-high (12.5% on Detect, mapping to \\$3,720; 90% on Patch, mapping to \\$14,152), Custom Agent with Claude 3.7 Sonnet Thinking (67.5% on Exploit), and OpenAI Codex CLI: o4-mini (90% on Patch, mapping to \\$14,422). OpenAI Codex CLI: o3-high, OpenAI Codex CLI: o4-mini, and Claude Code are more capable at defense, achieving higher Patch scores of 90%, 90%, and 87.5%, compared to Exploit scores of 47.5%, 32.5%, and 57.5% respectively; while the custom agents are relatively balanced between offense and defense, achieving Exploit scores of 17.5-67.5% and Patch scores of 25-60%.

Ensuring fairness in blockchain-based data trading presents significant challenges, as the transparency of blockchain can expose sensitive details and compromise fairness. Fairness ensures that the seller receives payment only if they provide the correct data, and the buyer gains access to the data only after making the payment. Existing approaches face limitations in efficiency, particularly when applied to large-scale data. Moreover, preserving privacy has also been a significant challenge in blockchain. In this paper, we introduce zkMarket, a privacy-preserving fair trade system on the blockchain. We ensure fairness by integrating encryption with zk-SNARKs, enabling verifiable proofs for fair trading. However, applying zk-SNARKs directly can be computationally expensive for the prover. To address this, we improve efficiency by leveraging our novel matrix-formed PRG (MatPRG) and commit-and-prove SNARK (CP-SNARK), making the data registration process more concise and significantly reducing the seller's proving time. To ensure transaction privacy, zkMarket is built upon an anonymous transfer protocol. Experimental results demonstrate that zkMarket significantly reduces the computational overhead associated with traditional blockchain solutions while maintaining robust security and privacy. Specifically, our evaluation quantifies this high efficiency: the seller can register 1 MB of data in 2.8 seconds, the buyer can generate the trade transaction in 0.2 seconds, and the seller can finalize the trade within 0.4 seconds.

Continuous-time score-based generative models consist of a pair of stochastic differential equations (SDEs)—a forward SDE that smoothly transitions data into a noise space and a reverse SDE that incrementally eliminates noise from a Gaussian prior distribution to generate data distribution samples—are intrinsically connected by the time-reversal theory on diffusion processes. In this paper, we investigate the use of stochastic evolution equations in Hilbert spaces, which expand the applicability of SDEs in two aspects: sample space and evolution operator, so they enable encompassing recent variations of diffusion models, such as generating functional data or replacing drift coefficients with image transformation. To this end, we derive a generalized time-reversal formula to build a bridge between probabilistic diffusion models and stochastic evolution equations and propose a score-based generative model called Hilbert Diffusion Model (HDM). Combining with Fourier neural operator, we verify the superiority of HDM for sampling functions from functional datasets with a power of kernel two-sample test of 4.2 on Quadratic, 0.2 on Melbourne, and 3.6 on Gridwatch, which outperforms existing diffusion models formulated in function spaces. Furthermore, the proposed method shows its strength in motion synthesis tasks by utilizing the Wiener process with values in Hilbert space. Finally, our empirical results on image datasets also validate a connection between HDM and diffusion models using heat dissipation, revealing the potential for exploring evolution operators and sample spaces.

In this video clip, the development of ubiquitous CPR(Cellular Phone Robot), which adds personal robotic features such as mobility and emotion to CP(Cellular Phone), is presented. We described a prototype implementation of CPR and demonstrated its successful navigational ability. CPR movement are controlled by the data acquired from velocity sensors and the coordinates from RFID tags on the floor. Emotion modules of the CPR Interaction system stimulate human touch-sense through vibrations, olfactory-sense through perfumes, and visual-sense through motion patterns. Biometric signals of human can be effectively measured with ECG and EDR. Experimental results show these easy-to-mount on CPR Equipments are sufficient for generating reliable signal measurements. People will rely more and more on robotic assistants in the near future. Personal robots will lead the way to the new era. CPR provides a stepping stone.

The robot technology (RT), along with rapid growth of information technology (IT), are being developed as the next generation of future technology. Current robots require advanced technology, such as soft computing, human-friendly interface, interaction technique, speech recognition, object recognition etc. unlike the industrial robots of the past. Most recently, cellular phone (CP) has been one of the most important technologies in the IT field, and it is situated in a position of great importance industrially and economically. To produce the best CP in the world, a new technological concept and its advanced implementation technique is required, due to the extreme level of competition in the world market. Therefore, this paper develops new technological concepts such as the robotic cellular phone (RCP) in which a synergy effect can be generated by merging RT and IT. RCP, CP having personal robot services, will be an intermediate hi-tech personal machine between one CP a person and one robot a person generations. RCP infra consists of RCP/sup Mobility/, RCP/sup Interaction/, RCP/sup Integration/ technologies. For RCP/sup Mobility/, human-friendly motion automation and personal service with walking and arming ability are developed. RCP/sup Interaction/ ability is achieved by modeling an emotion-generating engine and RCP/sup Integration/ that in miniature integrates the robotic modules into CP is developed with application service programs. By joining intelligent algorithms and CP communication network with the three base modules, a RCP system is constructed. This paper presents the definition, the basic theory and experiment results of the RCP sub-technologies. We confirm a good performance of the RCP through the results.

A new stability analysis and controller synthesis methodology for a continuous affine fuzzy system is proposed in this paper. The method suggested is based on the numerical convex optimization techniques. In analysis, the stability condition under which the affine fuzzy system is quadratically stable is derived and is recast in the formulation of linear matrix inequalities (LMIs). The emphasis of this paper, however, is on the synthesis of fuzzy controller based on the derived stability condition. In the synthesis, the stabilizability condition turns out to be in the formulation of bilinear matrix inequalities and is solved numerically in an iterative manner. Fuzzy local controllers also assume the affine form and their bias terms are solved in a numerical manner simultaneously together with the gains. Continuous iterative LMI (ILMI) approach is presented to obtain a feasible solution for the synthesis of the affine fuzzy system.

This paper proposes a new variable structure controller (VSC) for the accurate tracking control of a manipulator using the variable boundary layer. Up to now, VSC applying the variable boundary layer did not remove chattering from an arbitrary initial state of the system trajectory because VSC has used the fixed sliding surface. But, by using the linear time-varying sliding surfaces, the scheme has the robustness against chattering from all states. This scheme can be applied to the second-order nonlinear systems with parameter uncertainty and extraneous disturbances, and have better tracking performance than the conventional method. To demonstrate its performance, the proposed control algorithm is applied to a two-link manipulator.

This paper presents an explanation of a fuzzy model considering the correlation among components of input data. Generally, fuzzy models have a capability of dividing an input space into several subspaces compared to a linear model. But hitherto suggested fuzzy modeling algorithms have not taken into consideration the correlation among components of sample data and have addressed them independently, which results in an ineffective partition of the input space. In order to solve this problem, this paper proposes a new fuzzy modeling algorithm, which partitions the input space more effectively than conventional fuzzy modeling algorithms by taking into consideration the correlation among components of sample data. As a way to use the correlation and divide the input space, the method of principal component is used. Finally, the results of the computer simulation are given to demonstrate the validity of this algorithm.

This paper suggests a new fuzzy adaptive controller, which is able to solve the problems of classical adaptive controllers and conventional fuzzy adaptive controllers. It explains the architecture of a fuzzy adaptive controller using the robust property of a fuzzy controller. The basic idea of new adaptive control scheme is that an adaptive controller can be constructed with parallel combination of robust controllers. This new adaptive controller uses a multirule-base architecture which has several independent fuzzy controllers in parallel, each with different robust stability area. Out of several independent fuzzy controllers, the most suited one is selected by a system identifier which observes variations in the controlled system parameter. Here, we propose a design procedure which can be carried out mathematically and systematically from the model of a controlled system; related mathematical theorems and their proofs are also given. The performance of the proposed adaptive control algorithm is analyzed through a design example and a DC motor control simulation.

A fuzzy adaptive controller, which is able to solve the problems of classical adaptive controllers and conventional fuzzy adaptive controllers, is suggested in this paper. The suggested design method is applied to hybrid robot control. The architecture of a fuzzy adaptive controller using the robust property of a fuzzy controller is explained. A design procedure which can be carried out mathematically and systematically from the model of an objective system is suggested. This fuzzy adaptive controller is used in the control algorithm which is adaptive to the parametric uncertainty in hybrid force/position robot system, and its practicality is confirmed by an experiment on hybrid force/position robot system.

In recent years, lots of researches on autonomous mobile robot have been accomplished. However they focused on environment recognition and its processing to make a decision on the motion. And cooperative multy-robot, which must be able to avoid crash and to make mutual communication, has not been studied much. This paper deals whth cooperative motion of two robots, Meari I and Meari 2 made in our laboratory, based on communication between the two. Because there is an interference on communication occurring in cooperative motion of multi-robot, many restrictive conditions are required. Therefore, lie have designed these robot system so that communication between them is available and mutual interference is precluded, and lie used fuzzy interference to overcome unstability of sensor data.

Proposes a compliance robot control algorithm using fuzzy adaptive controller and fuzzy compliance vector generator. In the compliance robot control, one needs more adaptivity because the linear modeling in robot dynamics is getting more difficult by contact with external environment. Existing adaptive controllers have difficulty in realtime processing. So in order to overcome it, the authors adopt fuzzy adaptive controller and propose fuzzy compliance vector generator for flexible compliant motion. They analyze and confirm the proposed algorithm by surface processing experiment with a control system implemented by VME system.>