6/ RouteLLM – proposes efficient router models to dynamically select between stronger and weak LLMs during inference to achieve a balance between cost and performance; the training framework leverages human preference data and data augmentation techniques to boost performance;
LLMS
-
Mixture of Million Experts: Sparse Parameter-Efficient Expert Retrieval
By
–
3/ Mixture of A Million Experts – introduces a parameter-efficient expert retrieval mechanism that leverages the product key technique for sparse retrieval from a million tiny experts.
-
LLM Reasoning: Geometric Perspective and Expressive Capacity
By
–
4/ Reasoning in LLMs: A Geometric Perspective – explores the reasoning of LLMs from a geometrical perspective; reports that a higher intrinsic dimension implies greater expressive capacity of the LLM.
-
RankRAG: Instruction Fine-Tuning Framework for LLM RAG Enhancement
By
–
2/ RankRAG – introduces a new instruction fine-tuning framework to perform effective context ranking and answering generation to enhance an LLM’s RAG capabilities.
-
FlashAttention-3 Optimizes GPU Attention Operations for Modern Hardware
By
–
1/ FlashAttention-3 – proposes to adapt FlashAttention to take advantage of modern hardware; the techniques used to speed up attention on modern GPUs include producer-consumer asynchrony, interleaving block-wise matmul and softmax operations, and block quantization and incoherent
-
Top ML Papers of the Week: RankRAG, RouteLLM, FlashAttention-3
By
–
The Top ML Papers of the Week (July 8 – July 14): – RankRAG
– RouteLLM
– FlashAttention-3
– Internet of Agents
– Learning at Test Time
– Mixture of A Million Experts
… -
Agentic RAG Tutorial Coming Soon with Llama Index
By
–
I am working on an agentic RAG using @llama_index tutorial, will be out in a few days! Stay tuned!!
-
Transform Agents into Microservices with Llama-Agents
By
–
Turn your agents into microservices In llama-agents, you can set up both an agent service and a tool service, turning your agents into powerful microservices. The agent service takes user input and reasons about the next task to solve, while the tool service can execute
-
Larger AI Models Better Understanding Intent Performance
By
–
Agreed but it feels like the bigger models should understand the intent and performer better than the smaller ones still