Date | Title (arxiv) | Keyword | Affiliation | Note | Conference |
---|---|---|---|---|---|
2024.02 | Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models | Griffin, Hawk | Google DeepMind | Blog | |
2024.02 | OLMo: Accelerating the Science of Language Models | Open Source, OLMo | AI2 | Makrdown | |
2024.01 | Orion-14B: Open-source Multilingual Large Language Models | Open Source, MLLM | OrionStar Inc. | Markdown | |
2023.05 | PaLM2 Technical Report | PaLM2 | Blog | ||
2023.04 | Scaling Transformer to 1M tokens and beyond with RMT | Attention, RMT | Neural Networks and Deep Learning Lab, MIPT, Dolgoprudny, Russia | Blog | |
2023.03 | GPT-4 Technical Report | GPT-4 | OpenAI | Blog | |
2019.05 | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | BERT | Google AI Language | Blog | NAACL-HLT 2019 |
Date | Title (arxiv) | Keyword | Affiliation | Note | Conference |
---|---|---|---|---|---|
2024.02 | Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledge | HSP, Summarization (not mentioned though) | National University of Singapore | Markdown | |
2024.02 | A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts | Gist Memory, ReadAgent | Google DeepMind | Markdown | |
2024.01 | Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding | Meta-Prompting | Stanford University, OpenAI | Markdown |
Date | Title(arxiv) | Keyword | Affiliation | Note | Conference |
---|---|---|---|---|---|
2024.02 | ResLoRA: Identity Residual Mapping in Low-Rank Adaption | ResLoRA, Merge | Microsoft | Blog | |
2024.02 | LoRA+: Efficient Low Rank Adaptation of Large Models | LoRA+ | UC Berkeley | Markdown | |
2023.04 | LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model | LLaMA, Visual Instruction | Shanghai Artificial Intelligence Laboratory | Blog |
Date | Title(arxiv) | Keyword | Affiliation | Note | Conference |
---|---|---|---|---|---|
2024.01 | SliceGPT: Compress Large Language Models by Deleting Rows and Columns | Model Compression | Microsoft Research | Markdown | |
2023.04 | Learning to Compress Prompts with Gist Tokens | Gist Token, Compression | Stanford University | Blog | NeurIPS 2023 |
2022.05 | Matryoshka Representation Learning | Matryoshka, Adaptive | Google Research | Markdown | NeurIPS 2022 |
Date | Title(arxiv) | Keyword | Affiliation | Note | Conference |
---|---|---|---|---|---|
2023.04 | Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models | Tools, Chameleon | University of California, Los Angeles, Microsoft Research | Blog | NeurIPS 2023 |
Date | Title (arxiv) | Keyword | Affiliation | Note | Conference |
---|---|---|---|---|---|
2024.03 | RewardBench: Evaluating Reward Models for Language Modeling | Reward Model, DPO | AI2 | Markdown | |
2024.02 | Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation | Bonito, Instruction Tuning Dataset | Brown University | Markdown | ACL 2024 submission |
2024.02 | LLM-based NLG Evaluation: Current Status and Challenges | NLG, Evaluation | Peking University | Markdown | |
2024.02 | Can Large Language Models Understand Context? | Benchmark, In-Context Learning | Apple | Markdown | Findings of EACL 2024 |
2024.01 | Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research | Dolma, Dataset, Pretraining | AI2 | Markdown | |
2023.05 | Do Large Language Models Know What They Don't Know? | Self-Knowledge, SelfAware (Dataset) | School of Computer Science, Fudan University | Markdown | |
2023.04 | Are Emergent Abilities of Large Language Models a Mirage? | Emergent Ability | Stanford University | Blog | NeurIPS 2023 oral |
2023.04 | Evaluating Verifiability in Generative Search Engines | Generative Search Engine | Stanford University | Blog | Findings of EMNLP 2023 |
2016.10 | SQuAD: 100,000+ Questions for Machine Comprehension of Text | SQUAD, QA, Benchmark | Stanford University | Blog |
Date | Title (arxiv) | Keyword | Affiliation | Note | Conference |
---|---|---|---|---|---|
2024.02 | The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits | 1-bit, BitNet b1.58 | Microsoft Research | Blog | |
2024.02 | LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens | LongRoPE, 2048k tokens | Microsoft Research | Makrdown | |
2023.04 | ResiDual: Transformer with Dual Residual Connections | Layer Normalization | Microsoft Research | Blog | ICLR 2024 rejected |
Date | Title (arxiv) | Keyword | Affiliation | Note | Conference |
---|---|---|---|---|---|
2023.03 | Visual Instruction Tuning | LLaVA, Visual Instruction Tuning | Microsoft Research | Blog | NeurIPS 2023 oral |