Data-to-text (D2T) generation is a crucial task in many natural language understanding (NLU) applications and forms the foundation of task-oriented dialog systems. In the context of conversational AI solutions that can work directly with local data on the user's device, architectures utilizing large pre-trained language models (PLMs) are impractical for on-device deployment due to a high memory footprint. To this end, we propose TrICy, a novel lightweight framework for an enhanced D2T task that generates text sequences based on the intent in context and may further be guided by user-provided triggers. We leverage an attention-copy mechanism to predict out-of-vocabulary (OOV) words accurately. Performance analyses on E2E NLG dataset [1] (BLEU: 66.43%, ROUGE-L: 70.14%), WebNLG dataset [2] (BLEU:Seen64.08%,Unseen52.35%), and our Custom dataset related to text messaging applications, showcase our architecture's effectiveness. Moreover, we show that by leveraging an optional trigger input, data-to-text generation quality increases significantly and achieves the new SOTA score of 69.29% BLEU for E2E NLG. Furthermore, our analyses show that TrICy achieves at least 24% and 3% improvement in BLEU and METEOR respectively over LLMs like GPT-3, ChatGPT, and Llama 2. We also demonstrate that in some scenarios, performance improvement due to triggers is observed even when they are absent in training.

Network-Based Biocomputation (NBC) circuits are computational devices that utilize biological agents to efficiently explore designed nanofabricated networks and thus solve combinatorial problems. The main advantages of NBCs are the potential to combine massively parallel computation, inherent energy efficiency of the biological agents and maturity of nanofabrication technology. We present an integrated computational-aided toolset for simulation and verification of these circuits that enables analysis of both circuit correctness and the effects of agent stochastic dynamics on circuit behavior. Our approach enables early identification of design flaws and can lead to significant savings in resources, thus playing an important role in advancing this emerging paradigm.

We present a graph variational autoencoder with a structured prior for generating the layout of indoor 3D scenes. Given the room type (e.g., living room or library) and the room layout (e.g., room elements such as floor and walls), our architecture generates a collection of objects (e.g., furniture items such as sofa, table and chairs) that is consistent with the room type and layout. This is a challenging problem because the generated scene needs to satisfy multiple constrains, e.g., each object should lie inside the room and two objects should not occupy the same volume. To address these challenges, we propose a deep generative model that encodes these relationships as soft constraints on an attributed graph (e.g., the nodes capture attributes of room and furniture elements, such as shape, class, pose and size, and the edges capture geometric relationships such as relative orientation). The architecture consists of a graph encoder that maps the input graph to a structured latent space, and a graph decoder that generates a furniture graph, given a latent code and the room graph. The latent space is modeled with autoregressive priors, which facilitates the generation of highly structured scenes. We also propose an efficient training procedure that combines matching and constrained learning. Experiments on the 3D-FRONT dataset show that our method produces scenes that are diverse and are adapted to the room layout.

We introduce Amazon Berkeley Objects (ABO), a new large-scale dataset designed to help bridge the gap between real and virtual 3D worlds. ABO contains product catalog images, metadata, and artist-created 3D models with com-plex geometries and physically-based materials that cor-respond to real, household objects. We derive challenging benchmarks that exploit the unique properties of ABO and measure the current limits of the state-of-the-art on three open problems for real-world 3D object understanding: single-view 3D reconstruction, material estimation, and cross-domain multi-view object retrieval.

Intent detection is a crucial task in any Natural Language Understanding (NLU) system and forms the foundation of a task-oriented dialogue system. To build high-quality real-world conversational solutions for edge devices, there is a need for deploying intent detection model on device. This necessitates a light-weight, fast, and accurate model that can perform efficiently in a resource-constrained environment. To this end, we propose LIDSNet, a novel lightweight on-device intent detection model, which accurately predicts the message intent by utilizing a Deep Siamese Network for learning better sentence representations. We use character-level features to enrich the sentence-level representations and empirically demonstrate the advantage of transfer learning by utilizing pre-trained embeddings. Furthermore, to investigate the efficacy of the modules in our architecture, we conduct an ablation study and arrive at our optimal model. Experimental results prove that LIDSNet achieves state-of-the-art competitive accuracy of 98.00% and 95.97% on SNIPS [1] and ATIS [2] public datasets respectively, with under 0.59M parameters. We further benchmark LIDSNet against fine-tuned BERTs and show that our model is at least 41x lighter and 30x faster during inference than MobileBERT [3] on Samsung Galaxy S20 device, justifying its efficiency on resource-constrained edge devices.

Verifying whether a procedure is observationally pure (that is, it always returns the same result for the same input argument) is challenging when the procedure uses mutable (private) global variables, e.g., for memoization, and when the procedure is recursive. We present a deductive verification approach for this problem. Our approach encodes the procedure’s code as a logical formula, with recursive calls being modeled using a mathematical function symbol assuming that the procedure is observationally pure . Then, a theorem prover is invoked to check whether this logical formula agrees with the function symbol referred to above in terms of input-output behavior for all arguments. We prove the soundness of this approach. We then present a conservative approximation of the first approach that reduces the verification problem to one of checking whether a quantifier-free formula is satisfiable and prove the soundness of the second approach. We evaluate our approach on a set of realistic examples, using the Boogie intermediate language and theorem prover. Our evaluation shows that the invariants are easy to construct manually, and that our approach is effective at verifying observationally pure procedures.

Region based features are getting popular due to their higher descriptive power relative to other features. However, real world images exhibit changes in image segments capturing the same scene part taken at different time, under different lighting conditions, from different viewpoints, etc. Segmentation algorithms reflect these changes, and thus segmentations exhibit poor repeatability. In this paper we address the problem of matching regions of similar objects under unstable segmentations. Merging and splitting of regions makes it difficult to find such correspondences using one-to-one matching algorithms. We present partial region matching as a solution to this problem. We assume that the high contrast, dominant contours of an object are fairly repeatable, and use them to compute partial matching cost (PMC) between regions. Region correspondences are obtained under region adjacency constraints encoded by region adjacency graph (RAG). We integrate PMC in a many-to-one label assignment framework for matching RAGs, and solve it using belief propagation. We show that our algorithm can match images of similar objects across unstable image segmentations. We also compare the performance of our algorithm with that of the standard one-to-one matching algorithm on three motion sequences. We conclude that our partial region matching approach is robust under segmentation irrepeatabilities.

Super-resolution reconstruction algorithms assume the availability of exact registration and blur parameters. Inaccurate estimation of these parameters adversely affects the quality of the reconstructed image. However, traditional approaches for image registration are either sensitive to image degradations such as variations in blur, illumination and noise, or are limited in the class of image transformations that can be estimated. We propose an accurate registration algorithm that uses the local phase information, which is robust to the above degradations. We derive the theoretical error rate of the estimates in presence of non-ideal band-pass behavior of the filter and show that the error converges to zero over iterations. We also show the invariance of local phase to a class of blur kernels. Experimental results on images taken under varying conditions clearly demonstrates the robustness of our approach.

We propose a method for simultaneous detection, localization and segmentation of objects of a known category. We show that this is possible by using segments as features. To this end, we propose an object model in which the image is represented as a tree, that captures containment relationships among the segments. Using segments as features has the advantage that object detection and segmentation is done simultaneously, forgoing the need for a separate sophisticated model for object segmentation. A generative model of an object category is estimated in a supervised mode, in terms of the characteristics of its constituent regions, their relative locations, and their mutual containment. The novel aspect of this work lies in simplifying the description of the hierarchy in terms of constraints that apply to only pairs of nodes, instead of all nodes in the tree. We show that this indeed improves the speed of learning algorithm. Inference is done using graph cuts. We report the performance of the model on standard datasets.

We describe an unsupervised method to segment objects detected in images using a novel variant of an interest point template, which is very efficient to train and evaluate. Once an object has been detected, our method segments an image using a conditional random field (CRF) model. This model integrates image gradients, the location and scale of the object, the presence of object parts, and the tendency of these parts to have characteristic patterns of edges nearby. We enhance our method using multiple unsegmented images of objects to learn the parameters of the CRF, in an iterative conditional maximization framework. We show quantitative results on images of real scenes that demonstrate the accuracy of segmentation.

The design of a fractional-N PLL in the 900 MHz ISM band is presented to enable 5-Mbps data transmission for neuro application using GMSK modulation. The frac-N PLL consists of a phase frequency detector (PFD), charge pump (CP), loop filter, LC-VCO, and a prescaler. To minimize the CP current, the VCO control node capacitance is used to realize the on-chip loop filter's 3rd pole. Measured results of the MASH-12 frac-N synthesizer at 925 MHz show a phase noise of -104dBc/Hz at 22.5 KHz offset, in-band rms phase error of 0.7deg over 2.25 MHz bandwidth and out-of-band rms phase error of 2.3 deg. The measured phase noise spectrum correlates well with behavioral noise model predictions, including noise due to CP and PFD non-linearities. The chip was designed in 1.8V TSMC0.18μm Mixed Signal and RF process.

We describe a novel method for learning templates for recognition and localization of objects drawn from categories. A generative model repre- sents the configuration of multiple object parts with respect to an object coordinate system; these parts in turn generate image features. The com- plexity of the model in the number of features is low, meaning our model is much more efficient to train than comparative methods. Moreover, a variational approximation is introduced that allows learning to be or- ders of magnitude faster than previous approaches while incorporating many more features. This results in both accuracy and localization im- provements. Our model has been carefully tested on standard datasets; we compare with a number of recent template models. In particular, we demonstrate state-of-the-art results for detection and localization.