Search Results for author:
Found 11 papers, 5 papers with code
Text Generation Beyond Discrete Token Sampling
In standard autoregressive generation, an LLM predicts the next-token distribution, samples a discrete token, and then discards the distribution, passing only the sampled token as new input.
Self-Taught Agentic Long Context Understanding
Answering complex, long-context questions remains a major challenge for large language models (LLMs) as it requires effective question clarifications and context retrieval.
Vector-ICL: In-context Learning with Continuous Vector Representations
Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities on textual data.
Data Contamination Can Cross Language Barriers
In addition, we discuss the potential utilization of cross-lingual contamination in interpreting LLMs' working mechanisms and in post-training LLMs for enhanced multilingual capabilities.
Learning a Decision Tree Algorithm with Transformers
Decision trees are renowned for their ability to achieve high predictive performance while remaining interpretable, especially on tabular data.
WavSpA: Wavelet Space Attention for Boosting Transformers' Long Sequence Learning Ability
Recent works show that learning attention in the Fourier space can improve the long sequence learning capability of Transformers.
Data-Driven AI Model Signal-Awareness Enhancement and Introspection
AI modeling for source code understanding tasks has been making significant progress, and is being adopted in production development pipelines.
Software Vulnerability Detection via Deep Learning over Disaggregated Code Graph Representation
Identifying vulnerable code is a precautionary measure to counter software security breaches.
Probing Model Signal-Awareness via Prediction-Preserving Input Minimization
We measure the signal awareness of models using a new metric we propose- Signal-aware Recall (SAR).
Exploring Software Naturalness through Neural Language Models
We explore this hypothesis through the use of a pre-trained transformer-based language model to perform code analysis tasks.
Learning to map source code to software vulnerability using code-as-a-graph
We explore the applicability of Graph Neural Networks in learning the nuances of source code from a security perspective.
