Editing CXCSCMU GroupWiki (section)

=== Meeting 2 - November 3, 2023 ===
{| class="wikitable"
|+
!Paper
!#Votes
|-
|[https://arxiv.org/pdf/2310.11511.pdf SELF-RAG: Learning to Retrieve, Generate and Critique through Self-reflection]
|4
|-
|[https://arxiv.org/pdf/2310.11716.pdf Reflection-Tuning:Data Recycling Improves LLM Instruction-Tuning]
|2
|-
|[https://arxiv.org/abs/2310.14034 Tree Prompting: Efficient Task Adaptation without Fine-Tuning]
|2
|-
|[https://arxiv.org/abs/2306.04488 Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards]
|2
|-
|[https://arxiv.org/pdf/2309.12307.pdf LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models]
|2
|-
|[https://arxiv.org/pdf/2304.15004.pdf Are Emergent Abilities of Large Language Models a Mirage?]
|2
|-
|[https://arxiv.org/abs/2205.14135 FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness]
|2
|-
|[https://arxiv.org/pdf/2310.11451.pdf Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective]
|1
|-
|[https://arxiv.org/pdf/2301.13808.pdf Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning]
|1
|-
|[https://aclanthology.org/2021.acl-long.568/ Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning]
|1
|-
|[https://arxiv.org/pdf/2310.17680v1.pdf CodeFusion: A Pre-trained Diffusion Model for Code Generation]
|0
|-
|[https://arxiv.org/abs/2309.08532 Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers]
|0
|-
|[https://openreview.net/pdf?id=9k27IITeAZ ChunkAttention: Efficient Attention on KV Cache with Chunking Sharing and Batching]
|0
|-
|[https://arxiv.org/abs/2310.05029 Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading]
|0
|}