Related papers: Planning with Large Language Models for Code Gener…
Programmers often reuse code from source code repositories to reduce the development effort. Code clones are candidates for reuse in exploratory or rapid development, as they represent often repeated functionality in software systems. To…
This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…
Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent…
Despite their impressive performance, large language models (LMs) still struggle with reliably generating complex output structures when not finetuned to follow the required output format exactly. To address this issue, grammar-constrained…
Code completion aims at speeding up code writing by predicting the next code token(s) the developer is likely to write. Works in this field focused on improving the accuracy of the generated predictions, with substantial leaps forward made…
We propose an iterative programmatic planning (IPP) framework for solving grid-based tasks by synthesizing interpretable agent policies expressed in code using large language models (LLMs). Instead of relying on traditional search or…
Code completion is one of the most useful features in the Integrated Development Environments (IDEs), which can accelerate software development by suggesting the next probable token based on the contextual code in real-time. Recent studies…
Fine-tuning is a promising technique for leveraging Transformer-based language models in downstream tasks. As model sizes continue to grow, updating all model parameters becomes increasingly costly. Parameter-efficient fine-tuning methods…
Recent work in offline reinforcement learning (RL) has demonstrated the effectiveness of formulating decision-making as return-conditioned supervised learning. Notably, the decision transformer (DT) architecture has shown promise across…
Code generation is one of the tasks for which the use of Large Language Models is widely adopted and highly successful. Given this popularity, there are many benchmarks dedicated to code generation that can help select the best model.…
Existing large language models (LLMs) for register transfer level code generation face challenges like compilation failures and suboptimal power, performance, and area (PPA) efficiency. This is due to the lack of PPA awareness in…
Aligning language models (LMs) to human preferences has emerged as a critical pursuit, enabling these models to better serve diverse user needs. Existing methods primarily focus on optimizing LMs for a single reward function, limiting their…
Vision-language navigation is the task of directing an embodied agent to navigate in 3D scenes with natural language instructions. For the agent, inferring the long-term navigation target from visual-linguistic clues is crucial for reliable…
Deep learning has contributed remarkably to the advancement of time series analysis. Still, deep models can encounter performance bottlenecks in real-world data-scarce scenarios, which can be concealed due to the performance saturation with…
Successful application of large language models (LLMs) to robotic planning and execution may pave the way to automate numerous real-world tasks. Promising recent research has been conducted showing that the knowledge contained in LLMs can…
Code generation has been greatly enhanced by the profound advancements in Large Language Models (LLMs) recently. Nevertheless, such LLM-based code generation approaches still struggle to generate error-free code in a few tries when faced…
Temporal graph neural networks (TGNNs) outperform regular GNNs by incorporating time information into graph-based operations. However, TGNNs adopt specialized models (e.g., TGN, TGAT, and APAN ) and require tailored training frameworks…
In this paper, we introduce TreeCoders, a novel family of transformer trees. We moved away from traditional linear transformers to complete k-ary trees. Transformer blocks serve as nodes, and generic classifiers learn to select the best…
Top-$k$ decoding is a widely used method for sampling from LLMs: at each token, only the largest $k$ next-token-probabilities are kept, and the next token is sampled after re-normalizing them to sum to unity. Top-$k$ and other sampling…
Recent advancements in large pre-trained transformer models (GPT2/3, T5) have found use in program synthesis to generate programs that satisfy a set of input/output examples. However, these models perform poorly on long-horizon and low-data…