Search
Results
-
Exploiting Symmetric Temporally Sparse BPTT for Efficient RNN Training
(2024)Proceedings of the AAAI Conference on Artificial Intelligence ~ AAAI-24 Technical Tracks 10Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses. Implementing online training of RNNs on the edge calls for optimized algorithms for an efficient deployment on hardware. Inspired by the spiking neuron model, the Delta RNN exploits temporal sparsity during ...Conference Paper -
LERE: Learning-Based Low-Rank Matrix Recovery with Rank Estimation
(2024)Proceedings of the AAAI Conference on Artificial Intelligence ~ AAAI-24 Technical Tracks 14A fundamental task in the realms of computer vision, Low-Rank Matrix Recovery (LRMR) focuses on the inherent low-rank structure precise recovery from incomplete data and/or corrupted measurements given that the rank is a known prior or accurately estimated. However, it remains challenging for existing rank estimation methods to accurately estimate the rank of an ill-conditioned matrix. Also, existing LRMR optimization methods are heavily ...Conference Paper -
ESG Accountability Made Easy: DocQA at Your Service
(2024)Proceedings of the AAAI Conference on Artificial Intelligence ~ IAAI-24, EAAI-24, AAAI-24 Student Abstracts, Undergraduate Consortium and DemonstrationsWe present Deep Search DocQA. This application enables information extraction from documents via a question-answering conversational assistant. The system integrates several technologies from different AI disciplines consisting of document conversion to machine-readable format (via computer vision), finding relevant data (via natural language processing), and formulating an eloquent response (via large language models). Users can explore ...Conference Paper -
Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text
(2024)Proceedings of the AAAI Conference on Artificial Intelligence ~ AAAI-24 Technical Tracks 2Recently, Transformer-based text detection techniques have sought to predict polygons by encoding the coordinates of individual boundary vertices using distinct query features. However, this approach incurs a significant memory overhead and struggles to effectively capture the intricate relationships between vertices belonging to the same instance. Consequently, irregular text layouts often lead to the prediction of outlined vertices, ...Conference Paper -
Graph of Thoughts: Solving Elaborate Problems with Large Language Models
(2024)Proceedings of the AAAI Conference on Artificial Intelligence ~ AAAI-24 Technical Tracks 16We introduce Graph of Thoughts (GoT): a framework that advances prompting capabilities in large language models (LLMs) beyond those offered by paradigms such as Chain-of-Thought or Tree of Thoughts (ToT). The key idea and primary advantage of GoT is the ability to model the information generated by an LLM as an arbitrary graph, where units of information (“LLM thoughts”) are vertices, and edges correspond to dependencies between these ...Conference Paper -
Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers
(2024)Proceedings of the AAAI Conference on Artificial Intelligence ~ IAAI-24, EAAI-24, AAAI-24 Student Abstracts, Undergraduate Consortium and DemonstrationsThis work presents an analysis of the effectiveness of using standard shallow feed-forward networks to mimic the behavior of the attention mechanism in the original Transformer model, a state-of-the-art architecture for sequence-to-sequence tasks. We substitute key elements of the attention mechanism in the Transformer with simple feed-forward networks, trained using the original components via knowledge distillation. Our experiments, ...Conference Paper -
Unravelling Expressive Delegations: Complexity and Normative Analysis
(2024)Proceedings of the AAAI Conference on Artificial Intelligence ~ AAAI-24 Technical Tracks 9We consider binary group decision-making under a rich model of liquid democracy recently proposed by Colley, Grandi, and Novaro (2022): agents submit ranked delegation options, where each option may be a function of multiple agents' votes; e.g., "I vote yes if a majority of my friends vote yes." Such ballots are unravelled into a profile of direct votes by selecting one entry from each ballot so as not to introduce cyclic dependencies. ...Conference Paper -
Dissecting the EIP-2930 Optional Access Lists
(2024)Ethereum introduced Transaction Access Lists (TALs) in 2020 to optimize gas costs during transaction execution. In this work, we present a comprehensive analysis of TALs in Ethereum, focusing on adoption, quality, and gas savings. Analyzing a full month of mainnet data with 31,954,474 transactions, we found that only 1.46% of transactions included a TAL, even though 42.6% of transactions would have benefited from it. On average, access ...Conference Paper -
Recursion in Secondary Computer Science Education: A Comparative Study of Visual Programming Approaches
(2024)SIGCSE 2024: Proceedings of the 55th ACM Technical Symposium on Computer Science EducationWhile recursion is a fundamental technique in computer programming, it is challenging for novices, for example since it requires tracing non-linear and hierarchical sequences of execution. Though algorithm visualizations and visual programming may be helpful, such tools need to offer sufficiently expressive environments that support active, constructivist learning via exploration and experimentation. In this study, we investigated whether ...Conference Paper -
Comparing Cognitive Load Among Undergraduate Students Programming in Python and the Visual Language Algot
(2024)SIGCSE 2024: Proceedings of the 55th ACM Technical Symposium on Computer Science EducationThis paper examines whether undergraduate students perform better and experience lower cognitive load when programming in Algot, a visual programming language that supports programming by demonstration, than in the textual programming language Python. We recruited 38 first-semester computer science university students who had received prior instruction in the programming language Python but were unfamiliar with Algot. Participants reviewed ...Conference Paper