Search

We present Chunked Augmented Generation (CAG), an architecture specifically designed to overcome the context window limitations of Google Chrome's built-in Gemini Nano model. While Chrome's integration of Gemini Nano represents a significant advancement in bringing AI capabilities directly to the browser, its restricted context window poses challenges for processing large inputs. CAG addresses this limitation through intelligent input chunking and processing strategies, enabling efficient handling of extensive content while maintaining the model's performance within browser constraints. Our implementation demonstrates particular efficacy in processing large documents and datasets directly within Chrome, making sophisticated AI capabilities accessible through the browser without external API dependencies. Get started now at https://github.com/vivekVells/cag-js., Comment: 36 pages, 19 figures

In this paper, we present strategies for designing curvature-bounded trajectories of any desired length between any two given oriented points. The proposed trajectory is constructed by the concatenation of three circular arcs of varying radii. Such a trajectory guarantees a complete coverage of the maximum set of reachable lengths while minimising the number of changeover points in the trajectory to a maximum of two under all scenarios. Additionally, by using the notion of internally tangent circles, we expand the set of Circle-Circle-Circle trajectories to eight kinds, consisting of {LLL, LLR, LRR, LRL, RRL, RLL, RLR, RRR} paths. The paper presents a mathematical formulation of the proposed trajectory and the conditions for the existence and classification of each kind of trajectory. We also analyse the variation of the length of the trajectory using suitable elongation strategies and derive the set of reachable lengths for all pairs of oriented points. Finally, the results of this paper are illustrated using numerical simulations., Comment: Preprint submitted to Automatica

Cyanobacteriochromes are bi-stable photoreceptor proteins with desirable photochemical properties for biotechnological applications such as optogenetics or fluorescence microscopy. Here, we investigated Slr1393-g3, a cyanobacteriochrome that reversibly photo-switches between a red-absorbing (Pr) and green-absorbing (Pg) form. We applied advanced IR spectroscopic methods to track the sequence of intermediates during the photocycle over many orders in magnitude in time. In the conversion from Pg to Pr, we have revealed a new intermediate which precedes the Pr formation by using transient IR spectroscopy. In addition, stationary and transient 2D~IR experiments measured the vibrational couplings between different groups of the chromophore and the protein during these intermediate states. Anharmonic QM/MM calculations predict spectra in close-to-quantitative agreement with experimental 2D~IR spectra of the initial and the final state of the photocycle. They facilitate the assignment of the IR spectra and provide an atomistic insight into the coupling mechanism. This serves as a basis for the interpretation of the spectroscopic results and suggests structural changes of the intermediates along the photocycle.

Purpose: Thalamic nuclei are largely invisible in conventional MRI due to poor contrast. Thalamus Optimized Multi-Atlas Segmentation (THOMAS) provides automatic segmentation of 12 thalamic nuclei using white-matter-nulled (WMn) MPRAGE sequence at 7T. Application of THOMAS to Magnetization Prepared 2 Rapid Gradient Echo (MP2RAGE) sequence acquired at 7T has been investigated in this study. Methods: 8 healthy volunteers and 5 pediatric-onset multiple sclerosis patients were recruited at the Children's Hospital of Philadelphia and scanned at Siemens 7T with WMn-MPRAGE and multi-echo MP2RAGE (ME-MP2RAGE) sequences. White-matter-nulled contrast was synthesized (MP2-SYN) from T1 maps from ME-MP2RAGE sequence. Thalamic nuclei were segmented using THOMAS joint label fusion algorithm from WMn-MPRAGE and MP2-SYN datasets. THOMAS pipeline was modified to use majority voting to segment the bias corrected MP2-UNI images. Thalamic nuclei from MP2-SYN and MP2-UNI images were evaluated against corresponding nuclei obtained from WMn-MPRAGE images using dice coefficients, volume similarity indices (VSI) and distance between centroids. Results: For MP2-SYN, dice > 0.85 and VSI > 0.95 was achieved for the 5 larger nuclei and dice > 0.6 and VSI > 0.7 was achieved for the 7 smaller nuclei. The dice and VSI were slightly higher whilst the distance between centroids were smaller for MP2-SYN compared to MP2-UNI, indicating improved performance using the synthesized WMn image. Discussion: THOMAS algorithm can successfully segment thalamic nuclei in routinely acquired bias-free MP2RAGE images with essentially equivalent quality when evaluated against WMn-MPRAGE, hence has wider applicability in studies focused on thalamic involvement in aging and disease., Comment: 13 pages, 4 figures

We propose a mechanism to use the features of flavour to enhance the quality of food recommendations. An empirical method to determine the flavour of food is incorporated into a recommendation engine based on major gustatory nerves. Such a system has advantages of suggesting food items that the user is more likely to enjoy based upon matching with their flavour profile through use of the taste biological domain knowledge. This preliminary intends to spark more robust mechanisms by which flavour of food is taken into consideration as a major feature set into food recommendation systems. Our long term vision is to integrate this with health factors to recommend healthy and tasty food to users to enhance quality of life., Comment: In Proceedings of 5th International Workshop on Multimedia Assisted Dietary Management, Nice, France, October 21, 2019, MADiMa 2019, 6 pages