Abstract

Named Entity Recognition (NER) is a use- ful component in Natural Language Process- ing (NLP) applications. It is used in various tasks such as Machine Translation, Summa- rization, Information Retrieval, and Question- Answering systems. The research on NER is centered around English and some other ma- jor languages, whereas limited attention has been given to Indian languages. We analyze the challenges and propose techniques that can be tailored for Multilingual Named Entity Recog- nition for Indian Languages. We present a hu- man annotated named entity corpora of ∼40K sentences for 4 Indian languages from two of the major Indian language families. Addition- ally,we present a multilingual model fine-tuned on our dataset, which achieves an F1 score of ∼0.80 on our dataset on average. We achieve comparable performance on completely unseen benchmark datasets for Indian languages which affirms the usability of our model.

Abstract

Language models often exhibit undesirable behavior, e.g., generating toxic or gender-biased text. In the case of neural language models, an encoding of the undesirable behavior is often present in the model's representations. Thus, one natural (and common) approach to prevent the model from exhibiting undesirable behavior is to steer the model's representations in a manner that reduces the probability of it generating undesirable text. This paper investigates the formal and empirical properties of steering functions, i.e., transformation of the neural language model's representations that alter its behavior. First, we derive two optimal, in the least-squares sense, affine steering functions under different constraints. Our theory provides justification for existing approaches and offers a novel, improved steering approach. Second, we offer a series of experiments that demonstrate the empirical effectiveness of the methods in mitigating bias and reducing toxic generation.

Abstract

In today’s dynamic technological landscape, sustainability has emerged as a pivotal concern, especially with respect to architecting Machine Learning enabled Systems (MLS). Many ML models fail in transitioning to production, primarily hindered by uncertainties due to data variations, evolving requirements, and model instabilities. Machine Learning operations (MLOps) offers a promising solution by enhancing adaptability and technical sustainability in MLS. However, MLOps itself faces challenges related to environmental impact, technical maintenance, and economic concerns. Over the years, self-adaptation has emerged as a potential solution to handle uncertainties. This paper introduces a novel approach employing self-adaptive principles integrated into the MLOps architecture through a MAPE-K loop to bolster MLOps sustainability. By autonomously responding to uncertainties, including data, model dynamics, and environmental variations, our approach aims to address the sustainability concerns of a given MLOps pipeline identified by an architect at design time. Further, we implement the method for a Smart City use case to display the capabilities of our approach.

Abstract

In recent studies, the extensive utilization of large language models has underscored the im- portance of robust evaluation methodologies for assessing text generation quality and rel- evance to specific tasks. This has revealed a prevalent issue known as hallucination, an emergent condition in the model where gener- ated text lacks faithfulness to the source and deviates from the evaluation criteria. In this study, we formally define hallucination and pro- pose a framework for its quantitative detection in a zero-shot setting, leveraging our definition and the assumption that model outputs entail task and sample specific inputs. In detecting hallucinations, our solution achieves an accu- racy of 0.78 in a model-aware setting and 0.61 in a model-agnostic setting. Notably, our so- lution maintains computational efficiency, re- quiring far less computational resources than other SOTA approaches, aligning with the trend towards lightweight and compressed models.

Abstract

Understanding the structural organisation of 3D indoor scenes in terms of rooms is often accomplished via floorplan extraction. Robotic tasks such as planning and navigation require a semantic understanding of the scene as well. This is typically achieved via object-level semantic segmentation. However, such methods struggle to segment out topological regions like “kitchen” in the scene. In this work, we introduce a two-step pipeline. First, we extract a topological map, i.e., floorplan of the indoor scene using a novel multi-channel occupancy representation. Then, we generate CLIP-aligned features and semantic labels for every room instance based on the objects it contains using a self-attention transformer. Our language-topology alignment supports natural language querying, e.g. a “place to cook” locates the “kitchen”. We outperform the current state-of-the-art on room segmentation by ∼20% and room classification by ∼12%. Our detailed qualitative analysis and ablation studies provide insights into the problem of joint structural and semantic 3D scene understanding.

Abstract

The paper presents a 0.5 V, ultra-low power current, and voltage reference circuit in a single block, giving reference values of 90.7 pA and 288 mV. The proposed block uses proper addition of CTAT and PTAT curves, resulting in an excellent temperature coefficient of 15.2 ppm/°C and 36.8 ppm/°C for compensated current and voltage values, respectively, at a nominal supply of 0.5 V for a wide temperature range of −55 °C to 100 °C. Usage of gate leakage transistors in place of resistors helps in reducing the power and area of the circuit to 0.087 mm2. The circuit is implemented in 90 nm technology and operates effectively across a wide voltage range of 0.5 V–2.6 V with a supply sensitivity of 0.028 %/V and 0.154 %/V for current and voltage reference, respectively. The entire circuit takes a power of 275.26 pW at nominal conditions.

Abstract

In this study, we address the challenge of obstacle avoidance for Unmanned Aerial Vehicles (UAVs) through an innovative composite imitation learning ap- proach that combines Proximal Policy Optimization (PPO) with Behavior Cloning (BC) and Generative Adversarial Imitation Learning (GAIL), enriched by the integration of ray-tracing techniques. Our research underscores the sig- nificant role of ray-tracing in enhancing obstacle detection and avoidance capabilities. Moreover, we demonstrate the effectiveness of incorporating GAIL in coordinating the flight paths of two UAVs, showcasing improved collision avoidance capabilities. Extending our methodology, we apply our combined PPO, BC, GAIL, and ray-tracing framework to scenarios involving four UAVs, illustrating its scalability and adaptability to more complex scenarios. The findings indicate that our approach not only improves the reliability of basic PPO based obstacle avoidance but also paves the way for advanced autonomous UAV operations in crowded or dynamic environments.

Abstract

RNA molecules play a significant role in many biological pathways and have diverse functional roles, which is a result of their structural flexibility to fold into diverse conformations. This structural flexibility makes it challenging to obtain the structures of RNAs experimentally. Deep learning can be used to predict the secondary structures of RNA and other properties such as the backbone torsion angles, to be used as restraints for the computational optimization of the tertiary structures of RNA. TorRNA is a transformer encoder-decoder model, that takes an input RNA sequence and predicts the (pseudo)torsion angles of each nucleotide with a pre-trained RNA-FM model as the encoder. TorRNA is able to achieve a performance boost of 2% − 16% over the previous (pseudo)torsion angle prediction method for RNAs. We also demonstrate that TorRNA can used as a tool for model quality assessment of candidate RNA structures

Abstract

This paper examines the enhancement of quadrotor efficiency through adaptive control to address the critical need for Fault-Tolerant Control (FTC) in quadrotors amidst operational uncertainties and component inefficiency. State-of-the-art adaptive FTC strategies often assume the uncertainties to be bounded by a constant a priori; however, imprecise knowledge of inertial system parameters lead to state-dependent uncertainties which do not follow such assumption. Remain unattended, statedependent uncertainties can lead to instability, especially under actuator faults. The proposed adaptive FTC offers actuator fault mitigation while tackling unknown (statedependent) uncertainties via suitably designed adaptive laws. Additionally, real-time fault detection and control allocation are used simultaneously to avoid conservative control application. The closed-loop system stability is studied analytically and the effectiveness of the proposed solution is verified on a realistic simulator in comparison to the state of the art.

Abstract

Examining limitations is a crucial step in the scholarly research reviewing process, revealing aspects where a study might lack decisiveness or require enhancement. This aids readers in considering broader implications for further research. In this article, we present a novel and challenging task of Suggestive Limitation Generation (SLG) for research papers. We compile a dataset called LimGen, encompassing 4068 research papers and their associated limitations from the ACL anthology. We investigate several approaches to harness large language models (LLMs) for producing suggestive limitations, by thoroughly examining the related challenges, practical insights, and potential opportunities. Our LimGen dataset and code can be accessed at https://github. com/arbmf/LimGen.