5/ Contextual Hallucinations Mitigation in LLMs – proposes a new method that detects and significantly reduces contextual hallucinations in LLMs (e.g., reduces by 10% in the XSum summarization task)…
RESEARCH
-
RouteLLM: Efficient Router Models for Cost-Performance Balance
By
–
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;
-
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.
-
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
… -
Yasaman Etesam presents emotion research at ISRE 2024
By
–
Excited to present work by PhD candidate Yasaman Etesam at The International Society for Research on Emotion 2024 Conference in Belfast this Wednesday. Anyone else attending @ISREorg ? I'll be in town from Tues!
-
Quantum Supremacy Record Broken by 56-Qubit H2-1 Computer
By
–
How long will it take before someone reproduces this result on a laptop using a tensor network? “The 56-qubit H2-1 computer has broken the previous record in the 'quantum supremacy' benchmark first set by Google in 2019.” Source: http://
livescience.com -
Generative AI’s Next Transformative Frontiers and Applications
By
–
Transformative technology: What next for generative AI? – Financial Times – Partner Content by PwC #GenAI #GAI #AI #IoT #Tech #ArtificialIntelligence https://
ft.com/partnercontent
/pwc/transformative-technology-what-next-for-generative-ai.html?twclid=2-34z7v62nk53u7qke1gn3zsb9a&utm_source=TW&utm_medium=technology&utm_content=paid
… -
Speaker on Fine-Tuning and Model Merging at GenAI DevCon
By
–
Fellow Londoners, I'll be speaking at the GenAI DevCon on July 18th about fine-tuning and model merging. Then I'm flying to Vienna for @icmlconf
, see you there!