Abstract

The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and chemical weapons. To measure these risks of malicious use, government institutions and major AI labs are developing evaluations for hazardous capabilities in LLMs. However, current evaluations are private, preventing further research into mitigating risk. Furthermore, they focus on only a few, highly specific pathways for malicious use. To fill these gaps, we publicly release the Weapons of Mass Destruction Proxy (WMDP) benchmark, a dataset of 3,668 multiple-choice questions that serve as a proxy measurement of hazardous knowledge in biosecurity, cybersecurity, and chemical security. WMDP was developed by a consortium of academics and technical consultants, and was stringently filtered to eliminate sensitive information prior to public release. WMDP serves two roles: first, as an evaluation for hazardous knowledge in LLMs, and second, as a benchmark for unlearning methods to remove such hazardous knowledge. To guide progress on unlearning, we develop RMU, a state-of-the-art unlearning method based on controlling model representations. RMU reduces model performance on WMDP while maintaining general capabilities in areas such as biology and computer science, suggesting that unlearning may be a concrete path towards reducing malicious use from LLMs. We release our benchmark and code publicly at https://wmdp.ai

Abstract

Fake news being spread on social media platforms has a disruptive and damaging impact on our lives. Multimedia content improves the visibility of posts more than text data but is also being used for creating fake news. Previous multimodal works have tried to address the problem of modeling heterogeneous modalities in identifying fake news. However, these works have the following limitations: (1) inefficient encoding of inter-modal relations by utilizing a simple concatenation operator on the modalities at a later stage in a model, which might result in information loss; (2) training very deep neural networks with a disproportionate number of parameters on small multimodal datasets result in higher chances of overfitting. To address these limitations, we propose GAME-ON, a Graph Neural Network based end-to-end trainable framework that allows granular interactions within and across different modalities to learn more robust data representations for multimodal fake news detection. We use two publicly available fake news datasets, Twitter and Weibo, for evaluations. GAME-ON outperforms on Twitter by an average of 11% and achieves state-of-the-art performance on Weibo while using 91% fewer parameters than the best comparable state-of-the-art baseline. For deployment in real-world applications, GAME-ON can be used as a lightweight model (less memory and latency requirements), which makes it more feasible than previous state-of-the-art models.

Abstract

Chemical reaction prediction, encompassing forward synthesis and retrosynthesis, stands as a fundamental challenge in organic synthesis. A widely adopted computational approach frames synthesis prediction as a sequence-to-sequence translation task, using the common SMILES representation for molecules. Current evaluation of machine learning methods for retrosynthesis assume perfect training data, overlooking imperfections in reaction equations in popular datasets, such as missing reactants, products, other physical and practical constraints such as temperature and cost, primarily driven by a focus on the target molecule. This limitation leads to an incomplete representation of viable synthetic routes, especially when multiple sets of reactants can yield a given desired product. In response to these shortcomings, this study examines the prevailing evaluation methods and introduces comprehensive metrics designed to address imperfections in the dataset. Our novel metrics not only assess absolute accuracy by comparing predicted outputs with ground truth but also introduce a nuanced evaluation approach. We provide scores for partial correctness and compute adjusted accuracy through graph matching, acknowledging the inherent complexities of retrosynthetic pathways. Additionally, we explore the impact of small molecular augmentations while preserving chemical properties and employ similarity matching to enhance the assessment of prediction quality. We introduce SynFormer, a sequence-to-sequence model tailored for SMILES representation. It incorporates architectural enhancements to the original transformer, effectively tackling the challenges of chemical reaction prediction. SynFormer achieves a top-1 accuracy of 53.2% on the USPTO-50k dataset, demonstrating an improvement over previous state-of-the-art language models while being more efficient and eliminating the need for pre-training.

Abstract

Reinforcement learning (RL) has been applied to various domains in computational chemistry and has found wide-spread success. In this review, we first motivate the application of RL to chemistry and list some broad application domains, for example, molecule generation, geometry optimization, and retrosynthetic pathway search. We set up some of the formalism associated with reinforcement learning that should help the reader translate their chemistry problems into a form where RL can be used to solve them. We then discuss the solution formulations and algorithms proposed in recent literature for these problems, the advantages of one over the other, together with the necessary details of the RL algorithms they employ. This article should help the reader understand the state of RL applications in chemistry, learn about some relevant actively-researched open problems, gain insight into how RL can be used to approach them and hopefully inspire innovative RL applications in Chemistry.

Abstract

Hysteresis is a widely known and applied phenomenon whereas proteresis, it’s complimentary effect, has yet to be explored. A proteretic device is a bistable switch whose states depend on system’s future unlike hysteresis where the states depend on history. As a result, realization of this switch would be of great interest and may find vast applications. Therefore, the first contribution of this work is to model the proteretic phenomenon and implement in circuit theory. This model has been achieved by providing a constraint feedforward path to a hysteric feedback system and the circuit implementation was done using op-amps. As mentioned, the hysteresis and proteresis are two complementary phenomenon, hence, the second contribution of this work is to introduce “Prohys” a switch, the two corresponding states of which are hysteresis and proteresis. The switching between hysteresis and proteresis was achieved by varying the constraint feedforward path in proteretic device. It can also be achieved by adding a variable memory feedback system to the aforementioned device. We present the theoretical model, design, simulation and circuit implementation of the proposed switch using op-amps. The experimental results obtained from the circuit design match well with the theoretical models proposed.

Abstract

We introduce GPNN-CAM, a novel method for CNN explanation, that bridges two distinct areas of computer vision: Image Attribution, which aims to explain a predictor by highlighting image regions it finds important, and Single Image Generation (SIG), that focuses on learning how to generate variations of a single sample.GPNN-CAM leverages samples generated by Generative Patch Nearest Neighbors (GPNN) into a Class Activation Map (CAM) flavored attribution scheme. Our findings reveal that the incorporation of these samples yields remarkably effective results, enabling GPNN-CAM to demonstrate superior performance across multiple classifier architectures, and datasets.

Abstract

India’s linguistic diversity is a testament to the cultural richness of the subcontinent, with 22 officially recognized languages, each possessing its unique script and identity. In this context, the need for efficient Optical Character Recognition (OCR) tools tailored to the complexities of these languages is paramount. IndicOCR is introduced as an innovative OCR pipeline designed to address this challenge. This paper aims to shed light on the capabilities of IndicOCR, underlining its role in bridging the gap between India’s linguistic heritage and the ever-expanding digital world. Finally, IndicOCR1 is a powerful tool for inclusivity, preservation, and progress in a linguistically diverse society.

Abstract

With the recent advancements, organizations have brought data to the forefront of their digital transformation journeys. Financial services industry is also moving towards adopting data-driven strategies for improved and faster decision making and providing enhanced customer experience. While advances generally in Artificial Intelligence (AI) and specifically in Machine Learning (ML) have fueled a lot of analytics, it is largely restricted to structured data as it is well organized and is easy to work with. This tutorial presents the opportunities to unlock the potential in unstructured documents in financial domain. These forms of data are more challenging to interpret, but can deliver a more comprehensive and holistic understanding of the bigger picture. While there are challenges around processing such document, ability to quickly make decisions by leveraging such data can provide differentiated value propositions and competitive benefits. This tutorial start with select problems & challenges in Document AI space and use cases involving such documents, show the business opportunities present and describe the technical challenges involved. Subsequently, we discuss techniques and algorithms for several document processing requirements and real world applications. References

Abstract

Large-scale capturing of real-world scenes as 3D point clouds (e.g., using LIDAR scanning) generates billions of points that are challenging to visualize. High storage requirements prevent the quick and easy inspection of captured datasets on user-grade hardware. The fastest real-time rendering methods are limited by the available GPU memory and render only around 1 billion points interactively. We show that we can achieve state-of-the-art in both while simultaneously supporting datasets that surpass the capabilities of other methods. We present an on-the-fly point cloud decompression scheme that tightly integrates with software rasterization to reduce on-chip memory requirements by more than 4×. Our method compresses geometry losslessly and provides high visual quality at real-time framerates. We use a GPU-friendly, clipped Huffman encoding for compression. Point clouds are divided into equal-sized batches, which are Huffman-encoded independently. Batches are further subdivided to form easy-to-consume streams of data for massively parallel execution. The compressed point clouds are stored in an access-aware manner to achieve coherent GPU memory access

Abstract

Phase-unwrapping (PU) is a critical signal processing step used in fields such as radar, sonar, and laser technology. This paper presents a faster and more efficient VLSI architecture for implementing the phase-unwrapping algorithm on FPGA platforms. To evaluate the effectiveness of the proposed FPGAbased VLSI architecture for the phase-unwrapping algorithm in chest wall vibration sensing, we compared its performance with both a PYNQ board implementation and an equivalent software solution. The results are compared in terms of speed, resource utilization, and power consumption. Additionally, prototypes were developed on both the ZedBoard and PYNQ board, and the outcomes were physically verified. The proposed VLSI architecture achieves nearly 70× and 111× speed-up compared to software-based solutions and PYNQ board implementations, respectively.