搜索结果：orcas

Spoken dialogue is a primary source of information in videos; therefore, accurately identifying who spoke what and when is essential for deep video understanding. We introduce D-ORCA, a \textbf{d}ialogue-centric \textbf{o}mni-modal large language model optimized for \textbf{r}obust audio-visual \textbf{ca}ptioning. We further curate DVD, a large-scale, high-quality bilingual dataset comprising nearly 40,000 multi-party dialogue videos for training and 2000 videos for evaluation in English and Mandarin, addressing a critical gap in the open-source ecosystem. To ensure fine-grained captioning accuracy, we adopt group relative policy optimization with three novel reward functions that assess speaker attribution accuracy, global speech content accuracy, and sentence-level temporal boundary alignment. These rewards are derived from evaluation metrics widely used in speech processing and, to our knowledge, are applied for the first time as reinforcement learning objectives for audio-visual captioning. Extensive experiments demonstrate that D-ORCA substantially outperforms existing open-source models in speaker identification, speech recognition, and temporal grounding. Notably, despite h

Causal analysis is a crucial task in many domains, including manufacturing, social science, and medicine. However, despite recent progress, the conceptual and methodological complexity of causal methods makes them largely inaccessible to domain experts. This gap prevents experts from leveraging these advances and hinders researchers who lack access to real-world data for validation. To bridge this divide, we introduce ORCA, a copilot for end-to-end causal analysis. ORCA orchestrates agents to understand the user's goals and guide them through the most appropriate causal analysis workflow, from fully automatic to highly user-guided execution. It features causal discovery, causal effect estimation, explainability and Root-Cause-Analysis (RCA). ORCA evaluates and compares performance, generates key metrics and diagrams, and generates insights through structured reports. We highlight its effectiveness across several real-world use-cases.

Document Visual Question Answering (DocVQA) remains challenging for existing Vision-Language Models (VLMs), especially under complex reasoning and multi-step workflows. Current approaches struggle to decompose intricate questions into manageable sub-tasks and often fail to leverage specialized processing paths for different document elements. We present ORCA: Orchestrated Reasoning with Collaborative Agents for Document Visual Question Answering, a novel multi-agent framework that addresses these limitations through strategic agent coordination and iterative refinement. ORCA begins with a reasoning agent that decomposes queries into logical steps, followed by a routing mechanism that activates task-specific agents from a specialized agent dock. Our framework leverages a set of specialized AI agents, each dedicated to a distinct modality, enabling fine-grained understanding and collaborative reasoning across diverse document components. To ensure answer reliability, ORCA employs a debate mechanism with stress-testing, and when necessary, a thesis-antithesis adjudication process. This is followed by a sanity checker to ensure format consistency. Extensive experiments on three benchma

Heterogeneous reconfigurable platforms with tensor cores, such as AMD ACAP, are increasingly adopted for deep neural network (DNN) inference due to their high throughput and flexibility. However, their suitability for microsecond-scale inference on small problem sizes remains underexplored. In jet-tagging applications in high-energy physics, inefficient on-chip communication and large inter-layer latency prevent existing frameworks from meeting the 1-μs latency budget. Moreover, hardware overheads such as synchronization and VLIW processor prologue are often overlooked, making it infeasible to optimize accelerators correctly. To address these problems, we propose μ-ORCA, a customized heterogeneous accelerator framework for ultra-low-latency model inference. μ-ORCA enables direct inter-layer communication between DNN layers on the AIE array, instead of using shared memory tiles or FPGA fabric. Moreover, a 512-bit/cycle cascade connection is applied instead of a 32-bit/cycle DMA connection. μ-ORCA also provides an overhead-aware performance model that adapts to different NN layer sizes, and conducts design space exploration to optimize end-to-end latency. μ-ORCA supports MLP and Deep

Standard risk models reduce the rich dependence structure of financial markets to scalar volatility estimates, discarding the topological information encoded in cross-asset correlation networks. We present ORCA (Online Regime Correlation Analyzer), an end-to-end framework that fuses spectral graph theory, random matrix theory, and supervised machine learning to deliver calibrated probability estimates for both rally and crash events over a ten-day forward horizon. ORCA constructs rolling correlation matrices from 24 diversified exchange-traded instruments using three parallel estimators at different time scales, and extracts 127 spectral features (absorption ratios, eigenvalue entropy, effective rank, spectral gap, eigenvector concentration, and graph-topological descriptors at multiple correlation thresholds), concatenated with 79 traditional price-derived indicators to form a 206-dimensional feature vector. A depth-limited Random Forest with balanced sub-sample weighting is evaluated under a strict eight-fold walk-forward protocol with ten-day anti-leakage gaps spanning fifteen years of daily US market data. ORCA achieves a Balanced Crisis Detection AUC (BCD-AUC, the geometric me

We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multimodal readout interfaces. Rather than optimizing isolated next-token, next-frame, or next-action prediction, we are centered on Next-State-Prediction modeling, offering a unified state-transition modeling route toward understanding, predicting, and acting upon the world. Orca learns through two complementary paradigms: unconscious learning captures dense natural state transitions from continuous videos, and conscious learning models sparse meaningful state transitions by language-described events and VQA supervision. For pre-training, we construct a large-scale world-learning inventory data, including 125K hours of video data and 160M event annotations. After pre-training, Orca learns a unified world latent space. To examine whether the learned latent supports downstream, we evaluate it by three representative downstream readouts: text generation, image prediction, and embodied action generation. Orca's backbone is frozen, and only the lightweight modality-specific decoders are trainable. Experiments show

Multi-Agent Path Finding (MAPF) is a problem that requires computing collision-free paths for a set of agents from their start locations to designated goal locations. The problem has broad applications in domains where teams of robots must operate in a coordinated manner. ORCA* is a real time MAPF solver that assigns for each timestep a velocity for each agent. Due to its real time nature, it is myopic to future deadlocks that result from current decisions. ORCA*-MAPF attempts to remedy this limitation by introducing fallback mechanisms when deadlocks are detected. However, post hoc interventions often introduce significant flowtime overhead. In this paper, we introduce C-ORCA* and C-ORCA*-MAPF, continuous space MAPF algorithms that incorporate agents' entire spatial trajectory and their spatial dependencies to proactively prevent deadlocks from occurring, thus avoiding the high flowtime overhead associated with post hoc corrections in ORCA*-MAPF. The C-ORCA* family of algorithms significantly outperform previous state-of-the-art in terms of solve rate, runtime, and flowtime.

Robotics manipulation research increasingly focuses on two-finger parallel grippers for their effectiveness, affordability, and ease of teleoperation. Grippers are nonetheless limited by their form factor, often requiring bimanual setups even for simple reorientation tasks. Anthropomorphic hands are a more natural platform for dexterous robot learning -- closer to the human hand, and capable of learning from human video -- yet they remain hard to use in learning research: even where open and accessible hand hardware exists, the software for control, simulation, teleoperation, and retargeting is scattered in one-off code bases, and largely disconnected from the robot-learning ecosystem. In this work, we introduce the \orca~learning stack, an open-source research stack for dexterity as a first-class robot learning domain. Our \orca~stack unifies low-level control, simulation, teleoperation from a range of consumer platforms, and hand retargeting, behind a single interface, and integrates natively with popular robot-learning frameworks such as \lerobot, so dexterous hand researchers can leverage the same data, training, and evaluation pipelines used for non-dexterous robot learning. W

Counting the orbits of graphlets in a network is a vital tool for understanding the structural roles of vertices in various graph analytics tasks. While existing algorithms efficiently compute orbits of induced graphlets, many real-world applications require non-induced orbit counts. However, no current method offers exact, scalable, and parallel support for non-induced orbit counting. This paper presents NI-ORCA, a parallel algorithm to efficiently compute the orbits of non-induced graphlets up to size four (4-clique). NI-ORCA extends the ORCA framework for non-induced orbit counting by reformulating a system of linear equations. The algorithm consists of three stages: triangle counting, 4-clique enumeration, and orbit solving. We design and implement stage-specific parallelisation strategies using thread and vertex-local memory models and data structures, minimising contention and balancing workload. We further analyse the impact of scheduling policies, chunk sizes, and affinity strategies on performance. Experimental analysis on eight real-world datasets and a series of synthetic Erddos-Renyi graphs demonstrates that a mixed mode combining stage-specific data structure, with dyn

Obstacle avoidance enables autonomous agents and robots to operate safely and efficiently in dynamic and complex environments, reducing the risk of collisions and damage. For a robot or autonomous system to successfully navigate through obstacles, it must be able to detect such obstacles. While numerous collision avoidance algorithms like the dynamic window approach (DWA), timed elastic bands (TEB), and reciprocal velocity obstacles (RVO) have been proposed, they may lead to suboptimal paths due to fixed weights, be computationally expensive, or have limited adaptability to dynamic obstacles in multi-agent environments. Optimal reciprocal collision avoidance (ORCA), which improves on RVO, provides smoother trajectories and stronger collision avoidance guarantees. We propose ORCA-FL to improve on ORCA by using fuzzy logic controllers (FLCs) to better handle uncertainty and imprecision for obstacle avoidance in path planning. Numerous multi-agent experiments are conducted and it is shown that ORCA-FL can outperform ORCA in reducing the number of collision if the agent has a velocity that exceeds a certain threshold. In addition, a proposed algorithm for improving ORCA-FL using fuzzy

Boson Sampling, a non-universal computing paradigm, has resulted in impressive claims of quantum supremacy. ORCA Computing have developed a time-bin interferometer (TBI) that claims to use the principles of boson sampling to solve a number of computational problems including optimisation and generative adversarial networks. We solve a dominating set problem with a surveillance use case on the ORCA TBI simulator to benchmark the use of these devices against classical algorithms. Simulation has been used to consider the optimal performance of the computing paradigm without having to factor in noise, errors and scaling limitations. We show that the ORCA TBI is capable of solving moderately sized (n<250) dominating set problems with comparable success to linear programming and greedy methods. Wall clock timing shows that the simulator has worse scaling than the classical methods, but this is unlikely to carry over to the physical device where the outputs are measured rather than calculated.

Reliable assessment of the abilities of large audio language models (LALMs) is essential to advancing the state of the art. As benchmarks rapidly evolve to incorporate complex reasoning and subjective tasks, they increasingly necessitate open-ended responses from LALMs. We present Open-ended Response Correctness Assessment (ORCA) -- a reliable and lightweight model-based approach for answer correctness and disagreement modeling. We employ a three-stage annotation pipeline combining human judgment, structured feedback, and human-AI correction, yielding 9,663 annotations across 3,699 question-answer pairs from 15 LALMs on three audio understanding and reasoning benchmarks (achieving a Krippendorff's alpha of 0.82). Our experiments employing curriculum learning show that ORCA models achieve a Spearman correlation of 0.91 with average human correctness ratings on seen benchmarks and generalize to unseen benchmarks with a score of 0.85, outperforming several LLM judge baselines including Gemini 2.5 Flash. Furthermore, we demonstrate that ORCA's predicted variance correlates strongly with human disagreement, allowing it to effectively identify problematic benchmark items.

Modern software development increasingly depends on open-source libraries and third-party components, which are often encapsulated into containerized environments. While improving the development and deployment of applications, this approach introduces security risks, particularly when outdated or vulnerable components are inadvertently included in production environments. Software Composition Analysis (SCA) is a critical process that helps identify and manage packages and dependencies inside a container. However, unintentional modifications to the container filesystem can lead to incomplete container images, which compromise the reliability of SCA tools. In this paper, we examine the limitations of both cloud-based and open-source SCA tools when faced with such obscure images. An analysis of 600 popular containers revealed that obscure containers exist in well-known registries and trusted images and that many tools fail to analyze such containers. To mitigate these issues, we propose an obscuration-resilient methodology for container analysis and introduce ORCA (Obscuration-Resilient Container Analyzer), its open-source implementation. We reported our findings to all vendors using

Large Vision-Language Models (LVLMs) exhibit strong multimodal capabilities but remain vulnerable to hallucinations from intrinsic errors and adversarial attacks from external exploitations, limiting their reliability in real-world applications. We present ORCA, an agentic reasoning framework that improves the factual accuracy and adversarial robustness of pretrained LVLMs through inference-time structured inference reasoning with a suite of small vision models (less than 3B parameters). ORCA operates via an Observe-Reason-Critique-Act loop, querying multiple visual tools with evidential questions, validating cross-model inconsistencies, and refining predictions iteratively without access to model internals or retraining. ORCA also stores intermediate reasoning traces, which supports auditable decision-making. Though designed primarily to mitigate object-level hallucinations, ORCA also exhibits emergent adversarial robustness without requiring adversarial training or defense mechanisms. We evaluate ORCA across three settings: (1) clean images on hallucination benchmarks, (2) adversarially perturbed images without defense, and (3) adversarially perturbed images with defense applied.