Hugging Face's logo
William Suffill's picture
1 7 52

William Suffill

wsuff
shtefcs's profile picture
Ā·

AI & ML interests

None yet

Recent Activity

reacted to Kseniase's post with šŸ‘ 6 days ago
11 new types of RAG RAG is evolving fast, keeping pace with cutting-edge AI trends. Today it becomes more agentic and smarter at navigating complex structures like hypergraphs. Here are 11 latest RAG types: 1. InstructRAG -> https://huggingface.co/papers/2504.13032 Combines RAG with a multi-agent framework, using a graph-based structure, an RL agent to expand task coverage, and a meta-learning agent for better generalization 2. CoRAG (Collaborative RAG) -> https://huggingface.co/papers/2504.01883 A collaborative framework that extends RAG to settings where clients train a shared model using a joint passage store 3. ReaRAG -> https://huggingface.co/papers/2503.21729 It uses a Thought-Action-Observation loop to decide at each step whether to retrieve information or finalize an answer, reducing unnecessary reasoning and errors 4. MCTS-RAG -> https://huggingface.co/papers/2503.20757 Combines RAG with Monte Carlo Tree Search (MCTS) to help small LMs handle complex, knowledge-heavy tasks 5. Typed-RAG - > https://huggingface.co/papers/2503.15879 Improves answers on open-ended questions by identifying question types (a debate, personal experience, or comparison) and breaking it down into simpler parts 6. MADAM-RAG -> https://huggingface.co/papers/2504.13079 A multi-agent system where models debate answers over multiple rounds and an aggregator filters noise and misinformation 7. HM-RAG -> https://huggingface.co/papers/2504.12330 A hierarchical multi-agent RAG framework that uses 3 agents: one to split queries, one to retrieve across multiple data types (text, graphs and web), and one to merge and refine answers 8. CDF-RAG -> https://huggingface.co/papers/2504.12560 Works with causal graphs and enables multi-hop causal reasoning, refining queries. It validates responses against causal pathways To explore what is Causal AI, read our article: https://www.turingpost.com/p/causalai Subscribe to the Turing Post: https://www.turingpost.com/subscribe Read further šŸ‘‡
reacted to eugenesiow's post with šŸ‘€ 8 days ago
GPT-4.1 dropped this week - and it puts OpenAI back in the race for coding & agentic leadership. āš™ļø API only - no ChatGPT toggle for this. šŸ’» Coding performance is back on par with Claude 3.7 Sonnet & Gemini 2.5 Pro (though Gemini still leads). šŸ’ø Pricing: ā€¢ Full: $3.50 / 1M tokens ā€¢ Mini: $0.70 / 1M ā€¢ Nano: $0.17 / 1M šŸ‘‰ Gemini 2.5 Pro = best price/perf ($3.44 / 1M) šŸ˜µ Claude 3.5 Sonnet = $6 / 1M (!) šŸ§  Not a "thinking" model. šŸ“Š Mini shines on general reasoning tasks (e.g. GPQA), but only the full model holds up in SWE-bench-verified (GitHub issue solving).
reacted to m-ric's post with šŸš€ 9 days ago
New king of open VLMs: InternVL3 takes Qwen 2.5's crown! šŸ‘‘ InternVL have been a wildly successful series of model : and the latest iteration has just taken back their crown thanks to their superior, natively multimodal vision training pipeline. āž”ļø Most of the vision language models (VLMs) these days are built like Frankenstein : take a good text-only Large Language Model (LLM) backbone, stitch a specific vision transformer (ViT) on top of it. Then the training is sequential šŸ”¢ : 1. Freeze the LLM weights while you train the ViT only to work with the LLM part, then 2. Unfreeze all weights to train all weights in order to work together. šŸ’« The Shanghai Lab decided to challenge this paradigm and chose this approach that they call "native". For each of their model sizes, they still start from a good LLM (mostly Qwen-2.5 series, did I tell you I'm a huge fan of Qwen? ā¤ļø), and stitch the ViT, but they don't freeze anything : they train all weights together with interleaved text and image understanding data in a single pre-training phase šŸŽØ. They claim it results in more seamless interactions between modalities. And the results prove them right: they took the crown of top VLMs, at nearly all sizes, from their Qwen-2.5 parents. šŸ‘‘
View all activity

Organizations

None yet

wsuff's activity

liked a model 13 days ago
liked a model about 1 month ago
liked a model about 2 months ago
liked a model 2 months ago
liked 2 models 3 months ago
liked 4 models 4 months ago
liked a model 5 months ago
liked a model 6 months ago
liked a model 7 months ago
liked a Space 7 months ago
liked a model 7 months ago
liked 4 models 8 months ago
liked a Space 8 months ago