Search

Vision-language models (VLMs) demonstrate impressive capabilities in coarse-grained tasks like image classification and retrieval. However, they struggle with fine-grained tasks that require localized understanding. To investigate this weakness, we comprehensively analyze CLIP features and identify an important issue: semantic features are highly correlated. Specifically, the features of a class encode information about other classes, which we call mutual feature information (MFI). This mutual information becomes evident when we query a specific class and unrelated objects are activated along with the target class. To address this issue, we propose Unmix-CLIP, a novel framework designed to reduce MFI and improve feature disentanglement. We introduce MFI loss, which explicitly separates text features by projecting them into a space where inter-class similarity is minimized. To ensure a corresponding separation in image features, we use multi-label recognition (MLR) to align the image features with the separated text features. This ensures that both image and text features are disentangled and aligned across modalities, improving feature separation for downstream tasks. For the COCO- 14 dataset, Unmix-CLIP reduces feature similarity by 24.9%. We demonstrate its effectiveness through extensive evaluations of MLR and zeroshot semantic segmentation (ZS3). In MLR, our method performs competitively on the VOC2007 and surpasses SOTA approaches on the COCO-14 dataset, using fewer training parameters. Additionally, Unmix-CLIP consistently outperforms existing ZS3 methods on COCO and VOC

The last few years have witnessed a spate of data protection regulations in conjunction with an ever-growing appetite for data usage in large businesses, thus presenting significant challenges for businesses to maintain compliance. To address this conflict, we present Data Guard - a fine-grained, purpose-based access control system for large data warehouses. Data Guard enables authoring policies based on semantic descriptions of data and purpose of data access. Data Guard then translates these policies into SQL views that mask data from the underlying warehouse tables. At access time, Data Guard ensures compliance by transparently routing each table access to the appropriate data-masking view based on the purpose of the access, thus minimizing the effort of adopting Data Guard in existing applications. Our enforcement solution allows masking data at much finer granularities than what traditional solutions allow. In addition to row and column level data masking, Data Guard can mask data at the sub-cell level for columns with non-atomic data types such as structs, arrays, and maps. This fine-grained masking allows Data Guard to preserve data utility for consumers while ensuring compliance. We implemented a number of performance optimizations to minimize the overhead of data masking operations. We perform numerous experiments to identify the key factors that influence the data masking overhead and demonstrate the efficiency of our implementation.

Going beyond short-range interactions, we explore the role of long-range interactions in the extended XY model for transferring quantum states through evolution. In particular, employing a spin-1/2 chain with interactions decaying as a power law, we demonstrate that long-range interactions significantly enhance the efficiency of a quantum state transfer (QST) protocol, reducing the minimum time required to achieve fidelity beyond the classical limit. Our study identifies the long-range regime as providing an optimal balance between interaction range and transfer efficiency, outperforming the protocol with the short-range interacting model. Our detailed analysis reveals the impact of system parameters, such as anisotropy, magnetic field strength, and coordination number, on QST dynamics. Specifically, we find that intermediate coordination numbers lead to a faster and more reliable state transfer, while extreme values diminish performance. Further, we exhibit that the presence of long-range interactions also improves the achievable fidelity, mitigating its decline associated with increasing system-size., Comment: 9 pages, 7 figures

White matter bundle segmentation is crucial for studying brain structural connectivity, neurosurgical planning, and neurological disorders. White Matter Segmentation remains challenging due to structural similarity in streamlines, subject variability, symmetry in 2 hemispheres, etc. To address these challenges, we propose TractoGPT, a GPT-based architecture trained on streamline, cluster, and fusion data representations separately. TractoGPT is a fully-automatic method that generalizes across datasets and retains shape information of the white matter bundles. Experiments also show that TractoGPT outperforms state-of-the-art methods on average DICE, Overlap and Overreach scores. We use TractoInferno and 105HCP datasets and validate generalization across dataset., Comment: Accepted as a conference paper at 23rd IEEE International Symposium on Biomedical Imaging 2025. IEEE holds the copyright for this publication

Implicit neural representations (INRs) have become an important method for encoding various data types, such as 3D objects or scenes, images, and videos. They have proven to be particularly effective at representing 3D content, e.g., 3D scene reconstruction from 2D images, novel 3D content creation, as well as the representation, interpolation, and completion of 3D shapes. With the widespread generation of 3D data in an INR format, there is a need to support effective organization and retrieval of INRs saved in a data store. A key aspect of retrieval and clustering of INRs in a data store is the formulation of similarity between INRs that would, for example, enable retrieval of similar INRs using a query INR. In this work, we propose INRet, a method for determining similarity between INRs that represent shapes, thus enabling accurate retrieval of similar shape INRs from an INR data store. INRet flexibly supports different INR architectures such as INRs with octree grids, triplanes, and hash grids, as well as different implicit functions including signed/unsigned distance function and occupancy field. We demonstrate that our method is more general and accurate than the existing INR retrieval method, which only supports simple MLP INRs and requires the same architecture between the query and stored INRs. Furthermore, compared to converting INRs to other representations (e.g., point clouds or multi-view images) for 3D shape retrieval, INRet achieves higher accuracy while avoiding the conversion overhead., Comment: 3DV 2025

Clustering algorithms are fundamental tools in data analysis, with hierarchical methods being particularly valuable for their flexibility. Chameleon is a widely used hierarchical clustering algorithm that excels at identifying high-quality clusters of arbitrary shapes, sizes, and densities. Chameleon2 is the most recent variant that has demonstrated significant improvements, but suffers from critical failings and there are certain improvements that can be made. The first failure we address is that the complexity of Chameleon2 is claimed to be $O(n^2)$, while we demonstrate that it is actually $O(n^2\log{n})$, with $n$ being the number of data points. Furthermore, we suggest improvements to Chameleon2 that ensure that the complexity remains $O(n^2)$ with minimal to no loss of performance. The second failing of Chameleon2 is that it lacks transparency and it does not provide the fine-tuned algorithm parameters used to obtain the claimed results. We meticulously provide all such parameter values to enhance replicability. The improvement which we make in Chameleon2 is that we replace the exact $k$-NN search with an approximate $k$-NN search. This further reduces the algorithmic complexity down to $O(n\log{n})$ without any performance loss. Here, we primarily configure three approximate nearest neighbor search algorithms (Annoy, FLANN and NMSLIB) to align with the overarching Chameleon2 clustering framework. Experimental evaluations on standard benchmark datasets demonstrate that the proposed Chameleon2++ algorithm is more efficient, robust, and computationally optimal., Comment: 29 Pages, 15 Figures, 12 Tables

Limited accessibility to high field MRI scanners (such as 7T, 11T) has motivated the development of post-processing methods to improve low field images. Several existing post-processing methods have shown the feasibility to improve 3T images to produce 7T-like images [3,18]. It has been observed that improving lower field (LF, <=1.5T) images comes with additional challenges due to poor image quality such as the function mapping 1.5T and higher field (HF, 3T) images is more complex than the function relating 3T and 7T images [10]. Except for [10], no method has been addressed to improve <=1.5T MRI images. Further, most of the existing methods [3,18] including [10] require example images, and also often rely on pixel to pixel correspondences between LF and HF images which are usually inaccurate for <=1.5T images. The focus of this paper is to address the unsupervised framework for quality improvement of 1.5T images and avoid the expensive requirements of example images and associated image registration. The LF and HF images are assumed to be related by a linear transformation (LT). The unknown HF image and unknown LT are estimated in alternate minimization framework. Further, a physics based constraint is proposed that provides an additional non-linear function relating LF and HF images in order to achieve the desired high contrast in estimated HF image. The experimental results demonstrate that the proposed approach provides processed 1.5T images, i.e., estimated 3T-like images with improved image quality, and is comparably better than the existing methods addressing similar problems. The improvement in image quality is also shown to provide better tissue segmentation and volume quantification as compared to scanner acquired 1.5T images., Comment: conference paper

AI deployed in the real-world should be capable of autonomously adapting to novelties encountered after deployment. Yet, in the field of continual learning, the reliance on novelty and labeling oracles is commonplace albeit unrealistic. This paper addresses a challenging and under-explored problem: a deployed AI agent that continuously encounters unlabeled data - which may include both unseen samples of known classes and samples from novel (unknown) classes - and must adapt to it continuously. To tackle this challenge, we propose our method COUQ "Continual Open-world Uncertainty Quantification", an iterative uncertainty estimation algorithm tailored for learning in generalized continual open-world multi-class settings. We rigorously apply and evaluate COUQ on key sub-tasks in the Continual Open-World: continual novelty detection, uncertainty guided active learning, and uncertainty guided pseudo-labeling for semi-supervised CL. We demonstrate the effectiveness of our method across multiple datasets, ablations, backbones and performance superior to state-of-the-art., Comment: Manuscript Under Review (full-length); Related 4-page manuscripts accepted at Neurips 2024 Non-Archival Workshops https://sites.google.com/view/continual-fomo-workshop and https://imol-workshop.github.io/

In the field of continual learning, relying on so-called oracles for novelty detection is commonplace albeit unrealistic. This paper introduces CONCLAD ("COntinuous Novel CLAss Detector"), a comprehensive solution to the under-explored problem of continual novel class detection in post-deployment data. At each new task, our approach employs an iterative uncertainty estimation algorithm to differentiate between known and novel class(es) samples, and to further discriminate between the different novel classes themselves. Samples predicted to be from a novel class with high-confidence are automatically pseudo-labeled and used to update our model. Simultaneously, a tiny supervision budget is used to iteratively query ambiguous novel class predictions, which are also used during update. Evaluation across multiple datasets, ablations and experimental settings demonstrate our method's effectiveness at separating novel and old class samples continuously. We will release our code upon acceptance.

AI deployed in many real-world use cases should be capable of adapting to novelties encountered after deployment. Here, we consider a challenging, under-explored and realistic continual adaptation problem: a deployed AI agent is continuously provided with unlabeled data that may contain not only unseen samples of known classes but also samples from novel (unknown) classes. In such a challenging setting, it has only a tiny labeling budget to query the most informative samples to help it continuously learn. We present a comprehensive solution to this complex problem with our model "CUAL" (Continual Uncertainty-aware Active Learner). CUAL leverages an uncertainty estimation algorithm to prioritize active labeling of ambiguous (uncertain) predicted novel class samples while also simultaneously pseudo-labeling the most certain predictions of each class. Evaluations across multiple datasets, ablations, settings and backbones (e.g. ViT foundation model) demonstrate our method's effectiveness. We will release our code upon acceptance.

Using tools by Large Language Models (LLMs) is a promising avenue to extend their reach beyond language or conversational settings. The number of tools can scale to thousands as they enable accessing sensory information, fetching updated factual knowledge, or taking actions in the real world. In such settings, in-context learning by providing a short list of relevant tools in the prompt is a viable approach. To retrieve relevant tools, various approaches have been suggested, ranging from simple frequency-based matching to dense embedding-based semantic retrieval. However, such approaches lack the contextual and common-sense understanding required to retrieve the right tools for complex user requests. Rather than increasing the complexity of the retrieval component itself, we propose leveraging LLM understanding to generate a retrieval query. Then, the generated query is embedded and used to find the most relevant tools via a nearest-neighbor search. We investigate three approaches for query generation: zero-shot prompting, supervised fine-tuning on tool descriptions, and alignment learning by iteratively optimizing a reward metric measuring retrieval performance. By conducting extensive experiments on a dataset covering complex and multi-tool scenarios, we show that leveraging LLMs for query generation improves the retrieval for in-domain (seen tools) and out-of-domain (unseen tools) settings.

White matter tract segmentation is crucial for studying brain structural connectivity and neurosurgical planning. However, segmentation remains challenging due to issues like class imbalance between major and minor tracts, structural similarity, subject variability, symmetric streamlines between hemispheres etc. To address these challenges, we propose TractoEmbed, a modular multi-level embedding framework, that encodes localized representations through learning tasks in respective encoders. In this paper, TractoEmbed introduces a novel hierarchical streamline data representation that captures maximum spatial information at each level i.e. individual streamlines, clusters, and patches. Experiments show that TractoEmbed outperforms state-of-the-art methods in white matter tract segmentation across different datasets, and spanning various age groups. The modular framework directly allows the integration of additional embeddings in future works., Comment: Accepted at 27th International Conference on Pattern Recognition (ICPR), 2024 15 pages, 2 figures

Fiber tractography is a cornerstone of neuroimaging, enabling the detailed mapping of the brain's white matter pathways through diffusion MRI. This is crucial for understanding brain connectivity and function, making it a valuable tool in neurological applications. Despite its importance, tractography faces challenges due to its complexity and susceptibility to false positives, misrepresenting vital pathways. To address these issues, recent strategies have shifted towards deep learning, utilizing supervised learning, which depends on precise ground truth, or reinforcement learning, which operates without it. In this work, we propose Tract-RLFormer, a network utilizing both supervised and reinforcement learning, in a two-stage policy refinement process that markedly improves the accuracy and generalizability across various data-sets. By employing a tract-specific approach, our network directly delineates the tracts of interest, bypassing the traditional segmentation process. Through rigorous validation on datasets such as TractoInferno, HCP, and ISMRM-2015, our methodology demonstrates a leap forward in tractography, showcasing its ability to accurately map the brain's white matter tracts., Comment: Accepted at 27th International Conference on Pattern Recognition (ICPR), 2024

Topology Bench is a comprehensive topology dataset designed to accelerate benchmarking studies in optical networks. The dataset, focusing on core optical networks, comprises publicly accessible and ready-to-use topologies, including (a) 105 georeferenced real-world optical networks and (b) 270,900 validated synthetic topologies. Prior research on real-world core optical networks has been characterised by fragmented open data sources and disparate individual studies. Moreover, previous efforts have notably failed to provide synthetic data at a scale comparable to our present study. Topology Bench addresses this limitation, offering a unified resource and represents a 61.5% increase in spatially-referenced real world optical networks. To benchmark and identify the fundamental nature of optical network topologies through the lens of graph-theoretical analysis, we analyse both real and synthetic networks using structural, spatial and spectral metrics. Our comparative analysis identifies constraints in real optical network diversity and illustrates how synthetic networks can complement and expand the range of topologies available for use. Currently, topologies are selected based on subjective criteria, such as preference, data availability, or perceived suitability, leading to potential biases and limited representativeness. Our framework enhances the generalisability of optical network research by providing a more objective and systematic approach to topology selection. A statistical and correlation analysis reveals the quantitative range of all of these graph metrics and the relationships between them. Finally, we apply unsupervised machine learning to cluster real-world topologies into distinctive groups using nine optimal graph metrics using K-means. We conclude the analysis by providing guidance on how to use such clusters to select a diverse set of topologies for future studies.

The COVID-19 pandemic has underscored the need for low-cost, scalable approaches to measuring contactless vital signs, either during initial triage at a healthcare facility or virtual telemedicine visits. Remote photoplethysmography (rPPG) can accurately estimate heart rate (HR) when applied to close-up videos of healthy volunteers in well-lit laboratory settings. However, results from such highly optimized laboratory studies may not be readily translated to healthcare settings. One significant barrier to the practical application of rPPG in health care is the accurate localization of the region of interest (ROI). Clinical or telemedicine visits may involve sub-optimal lighting, movement artifacts, variable camera angle, and subject distance. This paper presents an rPPG ROI selection method based on 3D facial landmarks and patient head yaw angle. We then demonstrate the robustness of this ROI selection method when coupled to the Plane-Orthogonal-to-Skin (POS) rPPG method when applied to videos of patients presenting to an Emergency Department for respiratory complaints. Our results demonstrate the effectiveness of our proposed approach in improving the accuracy and robustness of rPPG in a challenging clinical environment., Comment: preprint

Benchmark contamination refers to the presence of test datasets in Large Language Model (LLM) pre-training or post-training data. Contamination can lead to inflated scores on benchmarks, compromising evaluation results and making it difficult to determine the capabilities of models. In this work, we study the contamination of popular multilingual benchmarks in LLMs that support multiple languages. We use the Black Box test to determine whether $7$ frequently used multilingual benchmarks are contaminated in $7$ popular open and closed LLMs and find that almost all models show signs of being contaminated with almost all the benchmarks we test. Our findings can help the community determine the best set of benchmarks to use for multilingual evaluation., Comment: 11 pages, 2 tables

We propose a novel scaling law for general-purpose decoder-only language models (LMs) trained on multilingual data, tackling the problem of balancing languages during multilingual pretraining. A primary challenge in studying multilingual scaling is the difficulty of analyzing individual language performance due to cross-lingual transfer. To address this, we shift the focus from individual languages to language families. We introduce and validate a hypothesis that the test cross-entropy loss for each language family is determined solely by its own sampling ratio, independent of other languages in the mixture. This insight simplifies the complexity of multilingual scaling and make the analysis scalable to an arbitrary number of languages. Building on this hypothesis, we derive a power-law relationship that links performance with dataset size, model size and sampling ratios. This relationship enables us to predict performance across various combinations of the above three quantities, and derive the optimal sampling ratios at different model scales. To demonstrate the effectiveness and accuracy of our proposed scaling law, we perform a large-scale empirical study, training more than 100 models on 23 languages spanning 5 language families. Our experiments show that the optimal sampling ratios derived from small models (85M parameters) generalize effectively to models that are several orders of magnitude larger (1.2B parameters), offering a resource-efficient approach for multilingual LM training at scale.

Combining LiDAR and Camera-view data has become a common approach for 3D Object Detection. However, previous approaches combine the two input streams at a point-level, throwing away semantic information derived from camera features. In this paper we propose Cross-View Center Point-Fusion, a state-of-the-art model to perform 3D object detection by combining camera and LiDAR-derived features in the BEV space to preserve semantic density from the camera stream while incorporating spacial data from the LiDAR stream. Our architecture utilizes aspects from previously established algorithms, Cross-View Transformers and CenterPoint, and runs their backbones in parallel, allowing efficient computation for real-time processing and application. In this paper we find that while an implicitly calculated depth-estimate may be sufficiently accurate in a 2D map-view representation, explicitly calculated geometric and spacial information is needed for precise bounding box prediction in the 3D world-view space., Comment: 7 pages, 5 figures. arXiv admin note: text overlap with arXiv:2205.02833 by other authors

In this work, we tackle a challenging and extreme form of subpopulation shift, which is termed compositional shift. Under compositional shifts, some combinations of attributes are totally absent from the training distribution but present in the test distribution. We model the data with flexible additive energy distributions, where each energy term represents an attribute, and derive a simple alternative to empirical risk minimization termed compositional risk minimization (CRM). We first train an additive energy classifier to predict the multiple attributes and then adjust this classifier to tackle compositional shifts. We provide an extensive theoretical analysis of CRM, where we show that our proposal extrapolates to special affine hulls of seen attribute combinations. Empirical evaluations on benchmark datasets confirms the improved robustness of CRM compared to other methods from the literature designed to tackle various forms of subpopulation shifts., Comment: Preprint. Under Review

Large language models (LLMs) have been used to generate formal proofs of mathematical theorems in proofs assistants such as Lean. However, we often want to optimize a formal proof with respect to various criteria, depending on its downstream use. For example, we may want a proof to adhere to a certain style, or to be readable, concise, or modularly structured. Having suitably optimized proofs is also important for learning tasks, especially since human-written proofs may not optimal for that purpose. To this end, we study a new problem of automated proof optimization: rewriting a proof so that it is correct and optimizes for an arbitrary criterion, such as length or readability. As a first method for automated proof optimization, we present ImProver, a large-language-model agent that rewrites proofs to optimize arbitrary user-defined metrics in Lean. We find that naively applying LLMs to proof optimization falls short, and we incorporate various improvements into ImProver, such as the use of symbolic Lean context in a novel Chain-of-States technique, as well as error-correction and retrieval. We test ImProver on rewriting real-world undergraduate, competition, and research-level mathematics theorems, finding that ImProver is capable of rewriting proofs so that they are substantially shorter, more modular, and more readable., Comment: 19 pages, 21 figures

We present the results obtained from X-ray and optical analysis of the Be/X-ray binary IGR~J06074+2205, focusing on before, during, and after the X-ray outbursts in October and December 2023. The properties of the neutron star in the binary are investigated using NICER and NuSTAR observations during the X-ray outbursts. The pulse profiles across a broad energy range, are found to be strongly dependent on luminosity and energy, revealing the complex nature of the emitting region. An absorbed power-law can describe each NICER spectrum in the 1-7 keV band. The 3-79 keV NuSTAR spectrum can be well-described by a negative and positive power-law with an exponential cut-off model. Utilizing the MAXI/GSC long-term light curve, we estimate the probable orbital period to be 80 or 80/n (n=2,3,4) days. We investigate the evolution of the circumstellar disc around the Be star by using optical spectroscopic observations of the system between 2022 and 2024. We observe variable H$\alpha$ and FeII emission lines with an increase in equivalent width, indicating the presence of a dynamic circumstellar disc. A distinct variation in the V/R value for H$\alpha$ and FeII lines is also observed. The appearance of additional emission lines, such as HeI (5875.72 \AA), HeI (6678 \AA), and HeI (7065 \AA), during the post-outburst observation in February 2024 suggests the growing of a larger or denser circumstellar disc. The disc continues to grow without any noticeable mass loss, even during the 2023 X-ray outbursts, which may lead to a future giant X-ray outburst., Comment: Accepted for publication in MNRAS

Vision-language models (VLMs) like CLIP have been adapted for Multi-Label Recognition (MLR) with partial annotations by leveraging prompt-learning, where positive and negative prompts are learned for each class to associate their embeddings with class presence or absence in the shared vision-text feature space. While this approach improves MLR performance by relying on VLM priors, we hypothesize that learning negative prompts may be suboptimal, as the datasets used to train VLMs lack image-caption pairs explicitly focusing on class absence. To analyze the impact of positive and negative prompt learning on MLR, we introduce PositiveCoOp and NegativeCoOp, where only one prompt is learned with VLM guidance while the other is replaced by an embedding vector learned directly in the shared feature space without relying on the text encoder. Through empirical analysis, we observe that negative prompts degrade MLR performance, and learning only positive prompts, combined with learned negative embeddings (PositiveCoOp), outperforms dual prompt learning approaches. Moreover, we quantify the performance benefits that prompt-learning offers over a simple vision-features-only baseline, observing that the baseline displays strong performance comparable to dual prompt learning approach (DualCoOp), when the proportion of missing labels is low, while requiring half the training compute and 16 times fewer parameters

The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability of maximum likelihood estimation (MLE) for next token prediction led to its role as predominant paradigm. However, the broader field of imitation learning can more effectively utilize the sequential structure underlying autoregressive generation. We focus on investigating the inverse reinforcement learning (IRL) perspective to imitation, extracting rewards and directly optimizing sequences instead of individual token likelihoods and evaluate its benefits for fine-tuning large language models. We provide a new angle, reformulating inverse soft-Q-learning as a temporal difference regularized extension of MLE. This creates a principled connection between MLE and IRL and allows trading off added complexity with increased performance and diversity of generations in the supervised fine-tuning (SFT) setting. We find clear advantages for IRL-based imitation, in particular for retaining diversity while maximizing task performance, rendering IRL a strong alternative on fixed SFT datasets even without online data generation. Our analysis of IRL-extracted reward functions further indicates benefits for more robust reward functions via tighter integration of supervised and preference-based LLM post-training., Comment: Published at NeurIPS 2024

The healthcare system collects extensive data, encompassing patient administrative information, clinical measurements, and home-monitored health metrics. To support informed decision-making in patient care and treatment management, it is essential to review and analyze these diverse data sources. Data visualization is a promising solution to navigate healthcare datasets, uncover hidden patterns, and derive actionable insights. However, the process of creating interactive data visualization can be rather challenging due to the size and complexity of these datasets. Progressive data science offers a potential solution, enabling interaction with intermediate results during data exploration. In this paper, we reflect on our experiences with three health data visualization projects employing a progressive data science approach. We explore the practical implications and challenges faced at various stages, including data selection, pre-processing, data mining, transformation, and interpretation and evaluation. We highlighted unique challenges and opportunities for three projects, including visualizing surgical outcomes, tracking patient bed transfers, and integrating patient-generated data visualizations into the healthcare setting. We identified the following challenges: inconsistent data collection practices, the complexity of adapting to varying data completeness levels, and the need to modify designs for real-world deployment. Our findings underscore the need for careful consideration of using a progressive data science approach when designing visualizations for healthcare settings., Comment: 4 pages

XR devices running chat-bots powered by Large Language Models (LLMs) have tremendous potential as always-on agents that can enable much better productivity scenarios. However, screen based chat-bots do not take advantage of the the full-suite of natural inputs available in XR, including inward facing sensor data, instead they over-rely on explicit voice or text prompts, sometimes paired with multi-modal data dropped as part of the query. We propose a solution that leverages an attention framework that derives context implicitly from user actions, eye-gaze, and contextual memory within the XR environment. This minimizes the need for engineered explicit prompts, fostering grounded and intuitive interactions that glean user insights for the chat-bot. Our user studies demonstrate the imminent feasibility and transformative potential of our approach to streamline user interaction in XR with chat-bots, while offering insights for the design of future XR-embodied LLM agents.