Search

Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs). Existing methods mainly rely on training an external reward model (i.e., another language model) or fine-tuning the LLM using self-generated data to influence the outcome. In this paper, we show that LLMs have the capability of self-detoxification without the use of an additional reward model or re-training. We propose \textit{Self-disciplined Autoregressive Sampling (SASA)}, a lightweight controlled decoding algorithm for toxicity reduction of LLMs. SASA leverages the contextual representations from an LLM to learn linear subspaces characterizing toxic v.s. non-toxic output in analytical forms. When auto-completing a response token-by-token, SASA dynamically tracks the margin of the current output to steer the generation away from the toxic subspace, by adjusting the autoregressive sampling strategy. Evaluated on LLMs of different scale and nature, namely Llama-3.1-Instruct (8B), Llama-2 (7B), and GPT2-L models with the RealToxicityPrompts, BOLD, and AttaQ benchmarks, SASA markedly enhances the quality of the generated sentences relative to the original models and attains comparable performance to state-of-the-art detoxification techniques, significantly reducing the toxicity level by only using the LLM's internal representations., Comment: 20 pages

Survival prediction is a crucial task associated with cancer diagnosis and treatment planning. This paper presents a novel approach to survival prediction by harnessing comprehensive information from CT and PET scans, along with associated Genomic data. Current methods rely on either a single modality or the integration of multiple modalities for prediction without adequately addressing associations across patients or modalities. We aim to develop a robust predictive model for survival outcomes by integrating multi-modal imaging data with genetic information while accounting for associations across patients and modalities. We learn representations for each modality via a self-supervised module and harness the semantic similarities across the patients to ensure the embeddings are aligned closely. However, optimizing solely for global relevance is inadequate, as many pairs sharing similar high-level semantics, such as tumor type, are inadvertently pushed apart in the embedding space. To address this issue, we use a cross-patient module (CPM) designed to harness inter-subject correspondences. The CPM module aims to bring together embeddings from patients with similar disease characteristics. Our experimental evaluation of the dataset of Non-Small Cell Lung Cancer (NSCLC) patients demonstrates the effectiveness of our approach in predicting survival outcomes, outperforming state-of-the-art methods., Comment: Accepted in WACV 2025

Synthesizing accurate geometry and photo-realistic appearance of small scenes is an active area of research with compelling use cases in gaming, virtual reality, robotic-manipulation, autonomous driving, convenient product capture, and consumer-level photography. When applying scene geometry and appearance estimation techniques to robotics, we found that the narrow cone of possible viewpoints due to the limited range of robot motion and scene clutter caused current estimation techniques to produce poor quality estimates or even fail. On the other hand, in robotic applications, dense metric depth can often be measured directly using stereo and illumination can be controlled. Depth can provide a good initial estimate of the object geometry to improve reconstruction, while multi-illumination images can facilitate relighting. In this work we demonstrate a method to incorporate dense metric depth into the training of neural 3D representations and address an artifact observed while jointly refining geometry and appearance by disambiguating between texture and geometry edges. We also discuss a multi-flash stereo camera system developed to capture the necessary data for our pipeline and show results on relighting and view synthesis with a few training views., Comment: Project webpage: https://stereomfc.github.io

In this study, we present a novel approach for predicting genomic information from medical imaging modalities using a transformer-based model. We aim to bridge the gap between imaging and genomics data by leveraging transformer networks, allowing for accurate genomic profile predictions from CT/MRI images. Presently most studies rely on the use of whole slide images (WSI) for the association, which are obtained via invasive methodologies. We propose using only available CT/MRI images to predict genomic sequences. Our transformer based approach is able to efficiently generate associations between multiple sequences based on CT/MRI images alone. This work paves the way for the use of non-invasive imaging modalities for precise and personalized healthcare, allowing for a better understanding of diseases and treatment.

Addressing the issue of hallucinations in large language models (LLMs) is a critical challenge. As the cognitive mechanisms of hallucination have been related to memory, here we explore hallucination for LLM that is enabled with explicit memory mechanisms. We empirically demonstrate that by simply scaling the readout vector that constrains generation in a memory-augmented LLM decoder, hallucination mitigation can be achieved in a training-free manner. Our method is geometry-inspired and outperforms a state-of-the-art LLM editing method on the task of generation of Wikipedia-like biography entries both in terms of generation quality and runtime complexity., Comment: 7 pages; accepted at ICML 2024 Workshop on Large Language Models and Cognition

An energy/area-efficient low-cost broadband linearity enhancement technique for electro-optic micro-ring modulators (MRM) is proposed to achieve 6.1-dB dynamic linearity improvement in spurious-free-dynamic-range with intermodulation distortions (IMD) and 17.9-dB static linearity improvement in integral nonlinearity over a conventional notch-filter MRM within a 4.8-dB extinction-ratio (ER) full-scale range based on rapid silicon-photonics fabrication results for the emerging applications of various analog and digital optical communication systems., Comment: 4 pages, 5 figures

Current large language models (LLMs) often perform poorly on simple fact retrieval tasks. Here we investigate if coupling a dynamically adaptable external memory to a LLM can alleviate this problem. For this purpose, we test Larimar, a recently proposed language model architecture which uses an external associative memory, on long-context recall tasks including passkey and needle-in-the-haystack tests. We demonstrate that the external memory of Larimar, which allows fast write and read of an episode of text samples, can be used at test time to handle contexts much longer than those seen during training. We further show that the latent readouts from the memory (to which long contexts are written) control the decoder towards generating correct outputs, with the memory stored off of the GPU. Compared to existing transformer-based LLM architectures for long-context recall tasks that use larger parameter counts or modified attention mechanisms, a relatively smaller size Larimar is able to maintain strong performance without any task-specific training or training on longer contexts., Comment: 5 pages; slightly revised abstract

Enterprises have a growing need to identify relevant tables in data lakes; e.g. tables that are unionable, joinable, or subsets of each other. Tabular neural models can be helpful for such data discovery tasks. In this paper, we present TabSketchFM, a neural tabular model for data discovery over data lakes. First, we propose novel pre-training: a sketch-based approach to enhance the effectiveness of data discovery in neural tabular models. Second, we finetune the pretrained model for identifying unionable, joinable, and subset table pairs and show significant improvement over previous tabular neural models. Third, we present a detailed ablation study to highlight which sketches are crucial for which tasks. Fourth, we use these finetuned models to perform table search; i.e., given a query table, find other tables in a corpus that are unionable, joinable, or that are subsets of the query. Our results demonstrate significant improvements in F1 scores for search compared to state-of-the-art techniques. Finally, we show significant transfer across datasets and tasks establishing that our model can generalize across different tasks and over different data lakes.

EEG slowing is reported in various neurological disorders including Alzheimer's, Parkinson's and Epilepsy. Here, we investigate alpha rhythm slowing in individuals with refractory temporal lobe epilepsy (TLE), compared to healthy controls, using scalp electroencephalography (EEG) and magnetoencephalography (MEG). We retrospectively analysed data from 17,(46) healthy controls and 22,(24) individuals with TLE who underwent scalp EEG and (MEG) recordings as part of presurgical evaluation. Resting-state, eyes-closed recordings were source reconstructed using the standardized low-resolution brain electrographic tomography (sLORETA) method. We extracted low (slow) 6-9 Hz and high (fast) 10-11 Hz alpha relative band power and calculated the alpha power ratio by dividing low (slow) alpha by high (fast) alpha. This ratio was computed for all brain regions in all individuals. Alpha oscillations were slower in individuals with TLE than controls (p<0.05). This effect was present in both the ipsilateral and contralateral hemispheres, and across widespread brain regions. Alpha slowing in TLE was found in both EEG and MEG recordings. We interpret greater low (slow)-alpha as greater deviation from health.

Text-based reinforcement learning involves an agent interacting with a fictional environment using observed text and admissible actions in natural language to complete a task. Previous works have shown that agents can succeed in text-based interactive environments even in the complete absence of semantic understanding or other linguistic capabilities. The success of these agents in playing such games suggests that semantic understanding may not be important for the task. This raises an important question about the benefits of LMs in guiding the agents through the game states. In this work, we show that rich semantic understanding leads to efficient training of text-based RL agents. Moreover, we describe the occurrence of semantic degeneration as a consequence of inappropriate fine-tuning of language models in text-based reinforcement learning (TBRL). Specifically, we describe the shift in the semantic representation of words in the LM, as well as how it affects the performance of the agent in tasks that are semantically similar to the training games. We believe these results may help develop better strategies to fine-tune agents in text-based RL scenarios.

Contemporary conversational systems often present a significant limitation: their responses lack the emotional depth and disfluent characteristic of human interactions. This absence becomes particularly noticeable when users seek more personalized and empathetic interactions. Consequently, this makes them seem mechanical and less relatable to human users. Recognizing this gap, we embarked on a journey to humanize machine communication, to ensure AI systems not only comprehend but also resonate. To address this shortcoming, we have designed an innovative speech synthesis pipeline. Within this framework, a cutting-edge language model introduces both human-like emotion and disfluencies in a zero-shot setting. These intricacies are seamlessly integrated into the generated text by the language model during text generation, allowing the system to mirror human speech patterns better, promoting more intuitive and natural user interactions. These generated elements are then adeptly transformed into corresponding speech patterns and emotive sounds using a rule-based approach during the text-to-speech phase. Based on our experiments, our novel system produces synthesized speech that's almost indistinguishable from genuine human communication, making each interaction feel more personal and authentic., Comment: 10 pages, 1 figure, for associated code and media files, see https://github.com/Rohan-Chaudhury/Humane-Speech-Synthesis-through-Zero-Shot-Emotion-and-Disfluency-Generation

Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is one of the most pressing research challenges today. This paper presents Larimar - a novel, brain-inspired architecture for enhancing LLMs with a distributed episodic memory. Larimar's memory allows for dynamic, one-shot updates of knowledge without the need for computationally expensive re-training or fine-tuning. Experimental results on multiple fact editing benchmarks demonstrate that Larimar attains accuracy comparable to most competitive baselines, even in the challenging sequential editing setup, but also excels in speed - yielding speed-ups of 8-10x depending on the base LLM - as well as flexibility due to the proposed architecture being simple, LLM-agnostic, and hence general. We further provide mechanisms for selective fact forgetting, information leakage prevention, and input context length generalization with Larimar and show their effectiveness. Our code is available at https://github.com/IBM/larimar, Comment: ICML 2024

Text-based games (TBGs) have emerged as an important collection of NLP tasks, requiring reinforcement learning (RL) agents to combine natural language understanding with reasoning. A key challenge for agents attempting to solve such tasks is to generalize across multiple games and demonstrate good performance on both seen and unseen objects. Purely deep-RL-based approaches may perform well on seen objects; however, they fail to showcase the same performance on unseen objects. Commonsense-infused deep-RL agents may work better on unseen data; unfortunately, their policies are often not interpretable or easily transferable. To tackle these issues, in this paper, we present EXPLORER which is an exploration-guided reasoning agent for textual reinforcement learning. EXPLORER is neurosymbolic in nature, as it relies on a neural module for exploration and a symbolic module for exploitation. It can also learn generalized symbolic policies and perform well over unseen data. Our experiments show that EXPLORER outperforms the baseline agents on Text-World cooking (TW-Cooking) and Text-World Commonsense (TWC) games.

Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be feasible to impose direct safety constraints on a deployed model. Therefore, an efficient and reliable alternative is required. To this end, we present our ongoing efforts to create and deploy a library of detectors: compact and easy-to-build classification models that provide labels for various harms. In addition to the detectors themselves, we discuss a wide range of uses for these detector models - from acting as guardrails to enabling effective AI governance. We also deep dive into inherent challenges in their development and discuss future work aimed at making the detectors more reliable and broadening their scope.

There is a growing need for Large Language Models (LLMs) to effectively use tools and external Application Programming Interfaces (APIs) to plan and complete tasks. As such, there is tremendous interest in methods that can acquire sufficient quantities of train and test data that involve calls to tools / APIs. Two lines of research have emerged as the predominant strategies for addressing this challenge. The first has focused on synthetic data generation techniques, while the second has involved curating task-adjacent datasets which can be transformed into API / Tool-based tasks. In this paper, we focus on the task of identifying, curating, and transforming existing datasets and, in turn, introduce API-BLEND, a large corpora for training and systematic testing of tool-augmented LLMs. The datasets mimic real-world scenarios involving API-tasks such as API / tool detection, slot filling, and sequencing of the detected APIs. We demonstrate the utility of the API-BLEND dataset for both training and benchmarking purposes., Comment: Accepted at ACL'24-main conference

In this paper, we investigate the influence of claims in analyst reports and earnings calls on financial market returns, considering them as significant quarterly events for publicly traded companies. To facilitate a comprehensive analysis, we construct a new financial dataset for the claim detection task in the financial domain. We benchmark various language models on this dataset and propose a novel weak-supervision model that incorporates the knowledge of subject matter experts (SMEs) in the aggregation function, outperforming existing approaches. We also demonstrate the practical utility of our proposed model by constructing a novel measure of optimism. Here, we observe the dependence of earnings surprise and return on our optimism measure. Our dataset, models, and code are publicly (under CC BY 4.0 license) available on GitHub., Comment: Accepted at The Seventh FEVER Workshop EMNLP 2024

We study the computation of competitive equilibrium for Fisher markets with $n$ agents and $m$ divisible chores. Prior work showed that competitive equilibria correspond to the nonzero KKT points of a non-convex analogue of the Eisenberg-Gale convex program. We introduce an analogue of the Eisenberg-Gale dual for chores: we show that all KKT points of this dual correspond to competitive equilibria, and while it is not a dual of the non-convex primal program in a formal sense, the objectives touch at all KKT points. Similar to the primal, the dual has problems from an optimization perspective: there are many feasible directions where the objective tends to positive infinity. We then derive a new constraint for the dual, which restricts optimization to a hyperplane that avoids all these directions. We show that restriction to this hyperplane retains all KKT points, and surprisingly, does not introduce any new ones. This allows, for the first time ever, application of iterative optimization methods over a convex region for computing competitive equilibria for chores. We next introduce a greedy Frank-Wolfe algorithm for optimization over our program and show a state-of-the-art convergence rate to competitive equilibrium. In the case of equal incomes, we show a $\mathcal{\tilde O}(n/\epsilon^2)$ rate of convergence, which improves over the two prior state-of-the-art rates of $\mathcal{\tilde O}(n^3/\epsilon^2)$ for an exterior-point method and $\mathcal{\tilde O}(nm/\epsilon^2)$ for a combinatorial method. Moreover, our method is significantly simpler: each iteration of our method only requires solving a simple linear program. We show through numerical experiments on simulated data and a paper review bidding dataset that our method is extremely practical. This is the first highly practical method for solving competitive equilibrium for Fisher markets with chores., Comment: 25 pages, 17 figures

Implicit 3D surface reconstruction of an object from its partial and noisy 3D point cloud scan is the classical geometry processing and 3D computer vision problem. In the literature, various 3D shape representations have been developed, differing in memory efficiency and shape retrieval effectiveness, such as volumetric, parametric, and implicit surfaces. Radial basis functions provide memory-efficient parameterization of the implicit surface. However, we show that training a neural network using the mean squared error between the ground-truth implicit surface and the linear basis-based implicit surfaces does not converge to the global solution. In this work, we propose locally supported compact radial basis functions for a linear representation of the implicit surface. This representation enables us to generate 3D shapes with arbitrary topologies at any resolution due to their continuous nature. We then propose a neural network architecture for learning the linear implicit shape representation of the 3D surface of an object. We learn linear implicit shapes within a supervised learning framework using ground truth Signed-Distance Field (SDF) data for guidance. The classical strategies face difficulties in finding linear implicit shapes from a given 3D point cloud due to numerical issues (requires solving inverse of a large matrix) in basis and query point selection. The proposed approach achieves better Chamfer distance and comparable F-score than the state-of-the-art approach on the benchmark dataset. We also show the effectiveness of the proposed approach by using it for the 3D shape completion task.

Ring artifacts in X-ray micro-CT images are one of the primary causes of concern in their accurate visual interpretation and quantitative analysis. The geometry of X-ray micro-CT scanners is similar to the medical CT machines, except the sample is rotated with a stationary source and detector. The ring artifacts are caused by a defect or non-linear responses in detector pixels during the MicroCT data acquisition. Artifacts in MicroCT images can often be so severe that the images are no longer useful for further analysis. Therefore, it is essential to comprehend the causes of artifacts and potential solutions to maximize image quality. This article presents a convolution neural network (CNN)-based Deep Learning (DL) model inspired by UNet with a series of encoder and decoder units with skip connections for removal of ring artifacts. The proposed architecture has been evaluated using the Structural Similarity Index Measure (SSIM) and Mean Squared Error (MSE). Additionally, the results are compared with conventional filter-based non-ML techniques and are found to be better than the latter.

This paper provides a theoretical understanding of Deep Q-Network (DQN) with the $\varepsilon$-greedy exploration in deep reinforcement learning. Despite the tremendous empirical achievement of the DQN, its theoretical characterization remains underexplored. First, the exploration strategy is either impractical or ignored in the existing analysis. Second, in contrast to conventional Q-learning algorithms, the DQN employs the target network and experience replay to acquire an unbiased estimation of the mean-square Bellman error (MSBE) utilized in training the Q-network. However, the existing theoretical analysis of DQNs lacks convergence analysis or bypasses the technical challenges by deploying a significantly overparameterized neural network, which is not computationally efficient. This paper provides the first theoretical convergence and sample complexity analysis of the practical setting of DQNs with $\epsilon$-greedy policy. We prove an iterative procedure with decaying $\epsilon$ converges to the optimal Q-value function geometrically. Moreover, a higher level of $\epsilon$ values enlarges the region of convergence but slows down the convergence, while the opposite holds for a lower level of $\epsilon$ values. Experiments justify our established theoretical insights on DQNs.

In plug-and-play (PnP) regularization, the proximal operator in algorithms such as ISTA and ADMM is replaced by a powerful denoiser. This formal substitution works surprisingly well in practice. In fact, PnP has been shown to give state-of-the-art results for various imaging applications. The empirical success of PnP has motivated researchers to understand its theoretical underpinnings and, in particular, its convergence. It was shown in prior work that for kernel denoisers such as the nonlocal means, PnP-ISTA provably converges under some strong assumptions on the forward model. The present work is motivated by the following questions: Can we relax the assumptions on the forward model? Can the convergence analysis be extended to PnP-ADMM? Can we estimate the convergence rate? In this letter, we resolve these questions using the contraction mapping theorem: (i) for symmetric denoisers, we show that (under mild conditions) PnP-ISTA and PnP-ADMM exhibit linear convergence; and (ii) for kernel denoisers, we show that PnP-ISTA and PnP-ADMM converge linearly for image inpainting. We validate our theoretical findings using reconstruction experiments., Comment: Errors in the proof of Lemma 1 and the statement of Theorem 2 were identified after the publication; these have been rectified in the revised version (v2)

We present a stochastic framework to decipher fluctuations propagation in classes of coherent feed-forward loops. The systematic contribution of the direct (one-step) and indirect (two-step) pathways is considered to quantify fluctuations of the output node. We also consider both additive and multiplicative integration mechanisms of the two parallel pathways (one-step and two-step). Analytical expression of the output node's coefficient of variation shows contributions of intrinsic, one-step, two-step, and cross-interaction in closed form. We observe a diverse range of degeneracy and non-degeneracy in each of the decomposed fluctuations term and their contribution to the overall output fluctuations of each coherent feed-forward loop motif. Analysis of output fluctuations reveals a maximal level of fluctuations of the coherent feed-forward loop motif of type 1., Comment: 20 pages, 4 figures

Within enterprises, there is a growing need to intelligently navigate data lakes, specifically focusing on data discovery. Of particular importance to enterprises is the ability to find related tables in data repositories. These tables can be unionable, joinable, or subsets of each other. There is a dearth of benchmarks for these tasks in the public domain, with related work targeting private datasets. In LakeBench, we develop multiple benchmarks for these tasks by using the tables that are drawn from a diverse set of data sources such as government data from CKAN, Socrata, and the European Central Bank. We compare the performance of 4 publicly available tabular foundational models on these tasks. None of the existing models had been trained on the data discovery tasks that we developed for this benchmark; not surprisingly, their performance shows significant room for improvement. The results suggest that the establishment of such benchmarks may be useful to the community to build tabular models usable for data discovery in data lakes.

Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do not generalize well to unseen games. On the other hand, neuro-symbolic methods, specifically those that leverage an intermediate formal representation, are gaining significant attention in language understanding tasks. This is because of their advantages ranging from inherent interpretability, the lesser requirement of training data, and being generalizable in scenarios with unseen data. Therefore, in this paper, we propose a modular, NEuro-Symbolic Textual Agent (NESTA) that combines a generic semantic parser with a rule induction system to learn abstract interpretable rules as policies. Our experiments on established text-based game benchmarks show that the proposed NESTA method outperforms deep reinforcement learning-based techniques by achieving better generalization to unseen test games and learning from fewer training interactions., Comment: ACL 2023

With the growing interest in large language models, the need for evaluating the quality of machine text compared to reference (typically human-generated) text has become focal attention. Most recent works focus either on task-specific evaluation metrics or study the properties of machine-generated text captured by the existing metrics. In this work, we propose a new evaluation scheme to model human judgments in 7 NLP tasks, based on the fine-grained mismatches between a pair of texts. Inspired by the recent efforts in several NLP tasks for fine-grained evaluation, we introduce a set of 13 mismatch error types such as spatial/geographic errors, entity errors, etc, to guide the model for better prediction of human judgments. We propose a neural framework for evaluating machine texts that uses these mismatch error types as auxiliary tasks and re-purposes the existing single-number evaluation metrics as additional scalar features, in addition to textual features extracted from the machine and reference texts. Our experiments reveal key insights about the existing metrics via the mismatch errors. We show that the mismatch errors between the sentence pairs on the held-out datasets from 7 NLP tasks align well with the human evaluation., Comment: Accepted at ACL 2023 (ACL Findings Long)

We introduce Logical Offline Cycle Consistency Optimization (LOCCO), a scalable, semi-supervised method for training a neural semantic parser. Conceptually, LOCCO can be viewed as a form of self-learning where the semantic parser being trained is used to generate annotations for unlabeled text that are then used as new supervision. To increase the quality of annotations, our method utilizes a count-based prior over valid formal meaning representations and a cycle-consistency score produced by a neural text generation model as additional signals. Both the prior and semantic parser are updated in an alternate fashion from full passes over the training data, which can be seen as approximating the marginalization of latent structures through stochastic variational inference. The use of a count-based prior, frozen text generation model, and offline annotation process yields an approach with negligible complexity and latency increases as compared to conventional self-learning. As an added bonus, the annotations produced by LOCCO can be trivially repurposed to train a neural text generation model. We demonstrate the utility of LOCCO on the well-known WebNLG benchmark where we obtain an improvement of 2 points against a self-learning parser under equivalent conditions, an improvement of 1.3 points against the previous state-of-the-art parser, and competitive text generation performance in terms of BLEU score.

We study fair division of indivisible chores among $n$ agents with additive disutility functions. Two well-studied fairness notions for indivisible items are envy-freeness up to one/any item (EF1/EFX) and the standard notion of economic efficiency is Pareto optimality (PO). There is a noticeable gap between the results known for both EF1 and EFX in the goods and chores settings. The case of chores turns out to be much more challenging. We reduce this gap by providing slightly relaxed versions of the known results on goods for the chores setting. Interestingly, our algorithms run in polynomial time, unlike their analogous versions in the goods setting. We introduce the concept of $k$ surplus which means that up to $k$ more chores are allocated to the agents and each of them is a copy of an original chore. We present a polynomial-time algorithm which gives EF1 and PO allocations with $(n-1)$ surplus. We relax the notion of EFX slightly and define tEFX which requires that the envy from agent $i$ to agent $j$ is removed upon the transfer of any chore from the $i$'s bundle to $j$'s bundle. We give a polynomial-time algorithm that in the chores case for $3$ agents returns an allocation which is either proportional or tEFX. Note that proportionality is a very strong criterion in the case of indivisible items, and hence both notions we guarantee are desirable.

Nearly all general-purpose neural semantic parsers generate logical forms in a strictly top-down autoregressive fashion. Though such systems have achieved impressive results across a variety of datasets and domains, recent works have called into question whether they are ultimately limited in their ability to compositionally generalize. In this work, we approach semantic parsing from, quite literally, the opposite direction; that is, we introduce a neural semantic parsing generation method that constructs logical forms from the bottom up, beginning from the logical form's leaves. The system we introduce is lazy in that it incrementally builds up a set of potential semantic parses, but only expands and processes the most promising candidate parses at each generation step. Such a parsimonious expansion scheme allows the system to maintain an arbitrarily large set of parse hypotheses that are never realized and thus incur minimal computational overhead. We evaluate our approach on compositional generalization; specifically, on the challenging CFQ dataset and three Text-to-SQL datasets where we show that our novel, bottom-up semantic parsing technique outperforms general-purpose semantic parsers while also being competitive with comparable neural parsers that have been designed for each task., Comment: Accepted to ACL main conference

The electron density is a key parameter to characterize any plasma. Most of the plasma applications and research in the area of low-temperature plasmas (LTPs) are based on the accurate estimations of plasma density and plasma temperature. The conventional methods for electron density measurements offer axial and radial profiles for any given linear LTP device. These methods have major disadvantages of operational range (not very wide), cumbersome instrumentation, and complicated data analysis procedures. The article proposes a Deep Learning (DL) assisted microwave-plasma interaction-based non-invasive strategy, which can be used as a new alternative approach to address some of the challenges associated with existing plasma density measurement techniques. The electric field pattern due to microwave scattering from plasma is utilized to estimate the density profile. The proof of concept is tested for a simulated training data set comprising a low-temperature, unmagnetized, collisional plasma. Different types of symmetric (Gaussian-shaped) and asymmetrical density profiles, in the range $10^{16}-10^{19}$ m$^{-3}$, addressing a range of experimental configurations have been considered in our study. Real-life experimental issues such as the presence of noise and the amount of measured data (dense vs sparse) have been taken into consideration while preparing the synthetic training data-sets. The DL-based technique has the capability to determine the electron density profile within the plasma. The performance of the proposed deep learning-based approach has been evaluated using three metrics- SSIM, RMSLE, and MAPE. The obtained results show promising performance in estimating the 2D radial profile of the density for the given linear plasma device and affirms the potential of the proposed ML-based approach in plasma diagnostics.

Controlling illumination can generate high quality information about object surface normals and depth discontinuities at a low computational cost. In this work we demonstrate a robot workspace-scaled controlled illumination approach that generates high quality information for table top scale objects for robotic manipulation. With our low angle of incidence directional illumination approach, we can precisely capture surface normals and depth discontinuities of monochromatic Lambertian objects. We show that this approach to shape estimation is 1) valuable for general purpose grasping with a single point vacuum gripper, 2) can measure the deformation of known objects, and 3) can estimate pose of known objects and track unknown objects in the robot's workspace., Comment: Project webpage: https://arkadeepnc.github.io/projects/active_workspace/index.html

Micro and/or Nano sized emulsions are formed when an organic liquid gently comes in contact with water in the presence of a surfactant, where no external agitation is required. Many years of research made it clear that the driving force for spontaneous emulsification arises from the differences of the chemical potentials of various components in the organic and aqueous phases, which triggers diffusion coupled hydrodynamic fluctuation. While extraordinary theoretical developments have taken place that attempted to describe these processes within the scopes of equilibrium and non-equilibrium thermodynamics, the local processes underlying the spontaneous emulsification, however, still remain elusive. In this research, we investigate the local processes that involve the transfer of surfactant as well as water from one phase to another (i.e. water to oil), which results in the formation of water-in-oil emulsion in the organic phase and, subsequently. Thes emulsions invert into oil-in-water emulsion, rather abruptly, as they cross the phase boundary. Studies based on UV spectroscopy and molecular dynamics indicate that these processes may involve explosive events and subsequent assembly of the fragments to other organized structures which are reminiscent of cusp catastrophe proposed earlier by Dickinson. These processes lead to either to a strong or a weak fluctuation of the component concentrations below the interface that also becomes evident in the fast (athermal) diffusion of the emulsion droplets from the interfacial region farther into the bulk water. These events can be arrested suitably with polymeric additives.

Recent studies demonstrated that an elastomer containing hygroscopic inclusions absorbs moisture and swell. Here we show that a thin film of such an elastomer bonded to a rigid substrate undergoes morphological instability upon absorption of water, the wavelength of which increases linearly with its thickness. As the driving force for such a morphological instability arises from the difference of the chemical potential of water between its source and that in the film, its development is slowed down as the salinity of the water increases. Nonetheless, the wavelength of the fully developed morphology, but not its amplitude, is independent of the salinity. We also demonstrate that if a domed disk shaped adherent is attached to the hygro-elastomeric film before moisture absorption, the elastic force generated during the morphological transition is able to dislodge it completely without the need of any external force. These patterns, once developed in pure water, is subdued when the salinity of water increases or if it is exposed to dry air. They re-emerge when the film is immersed in water again. Such an active response could be important in fouling release when a ship coated with such a hygro-elastomer changes its location during its long travel through sea, where salinity varies from place to place.