RAT: Retrieval Augmented Thoughts Elicit
Context-Aware Reasoning in Long-Horizon
Generation
https://arxiv.org/pdf/2403.05313
Context-Aware Reasoning in Long-Horizon
Generation
https://arxiv.org/pdf/2403.05313
#LCLM #vs #RAG
In Defense of RAG in the Era of Long-Context Language Models
https://arxiv.org/pdf/2409.01666
#observability #opentelemetry #llm #traceloop #team
https://www.youtube.com/watch?v=KVgbERRPU4M
In Defense of RAG in the Era of Long-Context Language Models
https://arxiv.org/pdf/2409.01666
#observability #opentelemetry #llm #traceloop #team
https://www.youtube.com/watch?v=KVgbERRPU4M
SCBENCH: A KV CACHE-CENTRIC ANALYSIS OF LONG-CONTEXT METHODS
https://arxiv.org/pdf/2412.10319
#MInference #LLMLingua #SnapKV #Jamba #KIVI #kvcache #benchmarks
#unsloth #team #distributed_sft #sft #fine_tuning
https://github.com/unslothai/unsloth/issues/1707#issuecomment-2658933732
https://arxiv.org/pdf/2412.10319
#MInference #LLMLingua #SnapKV #Jamba #KIVI #kvcache #benchmarks
#unsloth #team #distributed_sft #sft #fine_tuning
https://github.com/unslothai/unsloth/issues/1707#issuecomment-2658933732
https://blog.google/technology/google-deepmind/gemini-model-thinking-updates-march-2025/
#llm #new #sota #team #google #vs #openai
#MoLE #Phi #team #microsoft #multimodal
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
https://ritvik19.medium.com/papers-explained-322-phi-4-mini-phi-4-multimodal-2be1a69be78c
https://arxiv.org/abs/2503.01743
#llm #new #sota #team #google #vs #openai
#MoLE #Phi #team #microsoft #multimodal
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
https://ritvik19.medium.com/papers-explained-322-phi-4-mini-phi-4-multimodal-2be1a69be78c
https://arxiv.org/abs/2503.01743
Google
Gemini 2.5: Our most intelligent AI model
Gemini 2.5 is our most intelligent AI model, now with thinking.
#alibaba #team #qwen #llm
https://www.scmp.com/tech/big-tech/article/3304935/alibabas-qwen3-ai-model-coming-month-sources-say-bid-cement-industry-lead
https://www.scmp.com/tech/big-tech/article/3304935/alibabas-qwen3-ai-model-coming-month-sources-say-bid-cement-industry-lead
South China Morning Post
Alibaba’s Qwen3 AI model coming this month, sources say
The latest upgrade to the Qwen family of models will include a mixture-of-experts version and one with just 600 million parameters for mobile devices.
#agents #tree #search #CMU #team #backtrack #agentic_design_pattern #adp
Tree Search for Language Model Agents
https://arxiv.org/abs/2407.01476
Tree Search for Language Model Agents
https://arxiv.org/abs/2407.01476
arXiv.org
Tree Search for Language Model Agents
Autonomous agents powered by language models (LMs) have demonstrated promise in their ability to perform decision-making tasks such as web automation. However, a key limitation remains: LMs,...
#unsloth #vs #torchtune #vs #axolotl #team #hyperbolic #modal #wandb
https://x.com/hyperbolic_labs/status/1910497498826989831
https://modal.com/blog/fine-tuning-llms
https://wandb.ai/augmxnt/train-bench/reports/Trainer-performance-comparison-torchtune-vs-axolotl-vs-Unsloth---Vmlldzo4MzU3NTAx
https://x.com/hyperbolic_labs/status/1910497498826989831
https://modal.com/blog/fine-tuning-llms
https://wandb.ai/augmxnt/train-bench/reports/Trainer-performance-comparison-torchtune-vs-axolotl-vs-Unsloth---Vmlldzo4MzU3NTAx
X (formerly Twitter)
Hyperbolic (@hyperbolic_labs) on X
Comparing Fine Tuning Frameworks
#openai #team #gpt41
https://www.youtube.com/watch?v=kA-P9ood-cE
#cncf #team #survey #kubernetes #ml #ai
https://www.cncf.io/wp-content/uploads/2025/04/Blue-DN29-State-of-Cloud-Native-Development.pdf
https://www.youtube.com/watch?v=kA-P9ood-cE
#cncf #team #survey #kubernetes #ml #ai
https://www.cncf.io/wp-content/uploads/2025/04/Blue-DN29-State-of-Cloud-Native-Development.pdf
YouTube
GPT 4.1 in the API
Join Michelle Pokrass, Ishaan Singal, and Kevin Weil as they introduce and demo our new family of GPT-4.1 models in the API
For Developers
#stability_ai #team #deepseek #vs #openai #comments #forecast https://youtu.be/lY8Ja00PCQM?si=aChjauEHB0Qu_41z&t=1277
#cpu #inference #llm #gen_ai
https://techcrunch.com/2025/04/16/microsoft-researchers-say-theyve-developed-a-hyper-efficient-ai-model-that-can-run-on-cpus/
https://techcrunch.com/2025/04/16/microsoft-researchers-say-theyve-developed-a-hyper-efficient-ai-model-that-can-run-on-cpus/
TechCrunch
Microsoft researchers say they've developed a hyper-efficient AI model that can run on CPUs | TechCrunch
Microsoft researchers have developed — and released — a hyper-efficient AI model that can run on CPUs, including Apple's M2.
#rag #es #cqrs #even_sourcing #human_feedback #kafka #apache_kafka #team
https://www.linkedin.com/pulse/beyond-human-feedback-bringing-cqrs-event-sourcing-ai-goturkarnam-t5vde?utm_source=share&utm_medium=member_ios&utm_campaign=share_via
https://www.linkedin.com/pulse/beyond-human-feedback-bringing-cqrs-event-sourcing-ai-goturkarnam-t5vde?utm_source=share&utm_medium=member_ios&utm_campaign=share_via
Linkedin
Beyond Human Feedback: Bringing CQRS & Event Sourcing into Vector Database-Driven AI Systems
In traditional AI systems, especially those involving recommendation engines or Retrieval-Augmented Generation (RAG), fine-tuning models is typically driven by explicit human feedback — thumbs up/down, star ratings, or click-through behavior. While this approach…
#agentic #rag #langchain #langgraph #aws #amazon #team
https://aws.amazon.com/blogs/machine-learning/build-multi-agent-systems-with-langgraph-and-amazon-bedrock/
https://aws.amazon.com/blogs/machine-learning/build-multi-agent-systems-with-langgraph-and-amazon-bedrock/
Amazon
Build multi-agent systems with LangGraph and Amazon Bedrock | Amazon Web Services
This post demonstrates how to integrate open-source multi-agent framework, LangGraph, with Amazon Bedrock. It explains how to use LangGraph and Amazon Bedrock to build powerful, interactive multi-agent applications that use graph-based orchestration.
#observability #llm #openLLMetry #opentelemetry #aws
https://aws.amazon.com/blogs/apn/elevating-llm-observability-with-amazon-bedrock-and-dynatrace/
#grafana #team #assistant #ai
https://www.youtube.com/watch?v=ETZnD483mHI
https://aws.amazon.com/blogs/apn/elevating-llm-observability-with-amazon-bedrock-and-dynatrace/
#grafana #team #assistant #ai
https://www.youtube.com/watch?v=ETZnD483mHI
Amazon
Elevating LLM Observability with Amazon Bedrock and Dynatrace | Amazon Web Services
In this post, we explain how Dynatrace provides end-to-end monitoring and visibility into generative AI applications utilizing Amazon Bedrock models allowing for comprehensive LLM observability.