924 citations · 1.5k across the 16 of their papers we have counts for
8 papers · 1 filter
Personalised Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generation
Hailin Chen, Amrita Saha, Steven Hoi +1
With the rise of powerful closed-sourced LLMs (ChatGPT, GPT-4), there are increasing interests in distilling the capabilies of close-sourced LLMs to smaller open-sourced LLMs. Prev…
RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair
Weishi Wang, Yue Wang, Shafiq Joty +1
Automatic program repair (APR) is crucial to reduce manual debugging efforts for developers and improve software reliability. While conventional search-based techniques typically r…
BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing
Dongxu Li, Junnan Li, Steven C. H. Hoi
Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties p…
InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
Wenliang Dai, Junnan Li, Dongxu Li +6
Large-scale pre-training and instruction tuning have been successful at creating general-purpose language models with broad competence. However, building general-purpose vision-lan…
CodeTF: One-stop Transformer Library for State-of-the-art Code LLMs
Nghi D. Q. Bui, Hung Le, Yue Wang +3
Code intelligence plays a key role in transforming modern software engineering. Recently, deep learning-based models, especially Transformer-based large language models (LLMs), hav…
CodeT5+: Open Code Large Language Models for Code Understanding and Generation
Yue Wang, Hung Le, Akhilesh Deepak Gotmare +3
Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. However, existing code LLMs have two main limitations in terms of…
LogAI: A Library for Log Analytics and Intelligence
Qian Cheng, Amrita Saha, Wenzhuo Yang +3
Software and System logs record runtime information about processes executing within a system. These logs have become the most critical and ubiquitous forms of observability data t…
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
Junnan Li, Dongxu Li, Silvio Savarese +1
The cost of vision-and-language pre-training has become increasingly prohibitive due to end-to-end training of large-scale models. This paper proposes BLIP-2, a generic and efficie…