Search for: All records

Retrieval-augmented generation (RAG) systems can effectively address user queries by leveraging indexed document corpora to retrieve the relevant contexts. Ranking techniques have been adopted in RAG systems to sort the retrieved contexts by their relevance to the query so that users can select the most useful contexts for their downstream tasks. While many existing ranking methods rely on the similarity between the embedding vectors of the context and query to measure relevance, it is important to note that similarity does not equate to relevance in all scenarios. Some ranking methods use large language models (LLMs) to rank the contexts by putting the query and the candidate contexts in the prompt and asking LLM about their relevance. The scalability of those methods is contingent on the number of candidate contexts and the context window of those LLMs. Also, those methods require fine-tuning the LLMs, which can be computationally expensive and require domain-related data. In this work, we propose a scalable ranking framework that does not involve LLM training. Our framework uses an off-the-shelf LLM to hypothesize the user's query based on the retrieved contexts and ranks the contexts based on the similarity between the hypothesized queries and the user query. Our framework is efficient at inference time and is compatible with many other context retrieval and ranking techniques. Experimental results show that our method improves the ranking performance of retrieval systems in multiple benchmarks. 

Polyethylene oxide (PEO)-based solid composite electrolytes (SCEs), with inorganic fillers, are studied extensively due to their effective balance between mechanical and electrochemical properties. The correlation between the composition of SCEs and their electrochemical behavior has been studied extensively, primarily focusing on the type of polymer matrix with a bias towards high lithium (Li) salt. In this study, we examine the changes in the properties of SCEs at two low EO : Li ratios, 43:1 and 18:1, in the PEO-LiTFSI matrix (with and without 10 wt% of 5 μm LLZTO) and evaluate their impact on Li stripping and plating reactions. Although higher salt concentration (18:1) results in substantially higher ionic conductivity (by approximately an order of magnitude), interestingly we observe that lower salt concentration (43:1) exhibits up to 3 times longer Li cycling life. Notably, electrolytes with low salt concentration (43:1) are much stiffer, with compressive modulus more than twice as high as the 18:1 counterpart. Although the ionic conductivity of the electrolyte is often the most immediate concern in the electrolyte design process, these findings accentuate the equal importance of mechanical properties in order to ensure successful electrolyte performance throughout prolonged Li cycling. 

Interleaved text-and-image generation has been an intriguing research direction, where the models are required to generate both images and text pieces in an arbitrary order. Despite the emerging advancements in interleaved generation, the progress in its evaluation still significantly lags behind. Existing evaluation benchmarks do not support arbitrarily interleaved images and text for both inputs and outputs, and they only cover a limited number of domains and use cases. Also, current works predominantly use similarity-based metrics which fall short in assessing the quality in open-ended scenarios. To this end, we introduce InterleavedBench, the first benchmark carefully curated for the evaluation of interleaved text-and-image generation. InterleavedBench features a rich array of tasks to cover diverse real-world use cases. In addition, we present InterleavedEval, a strong reference-free metric powered by GPT-4o to deliver accurate and explainable evaluation. We carefully define five essential evaluation aspects for InterleavedEval, including text quality, perceptual quality, image coherence, text-image coherence, and helpfulness, to ensure a comprehensive and fine-grained assessment. Through extensive experiments and rigorous human evaluation, we show that our benchmark and metric can effectively evaluate the existing models with a strong correlation with human judgments surpassing previous reference-based metrics. We also provide substantial findings and insights to foster future research in interleaved generation and its evaluation. 

Photoacoustic imaging has demonstrated recent promise for surgical guidance, enabling visualization of tool tips during surgical and non-surgical interventions. To receive photoacoustic signals, most conventional transducers are rigid, while a flexible array is able to deform and provide complete contact on surfaces with different geometries. In this work, we present photoacoustic images acquired with a flexible array transducer in multiple concave shapes in phantom andex vivobovine liver experiments targeted toward interventional photoacoustic applications. We validate our image reconstruction equations for known sensor geometries with simulated data, and we provide empirical elevation field-of-view, target position, and image quality measurements. The elevation field-of-view was 6.08 mm at a depth of 4 cm and greater than 13 mm at a depth of 5 cm. The target depth agreement with ground truth ranged 98.35-99.69%. The mean lateral and axial target sizes when imaging 600μm-core-diameter optical fibers inserted within the phantoms ranged 0.98-2.14 mm and 1.61-2.24 mm, respectively. The mean ± one standard deviation of lateral and axial target sizes when surrounded by liver tissue were 1.80±0.48 mm and 2.17±0.24 mm, respectively. Contrast, signal-to-noise, and generalized contrast-to-noise ratios ranged 6.92–24.42 dB, 46.50–67.51 dB, and 0.76–1, respectively, within the elevational field-of-view. Results establish the feasibility of implementing photoacoustic-guided surgery with a flexible array transducer.