Hugging Face's logo
Ksenia Se's picture
1 100 3

Ksenia Se

Kseniase
mehmet582025's profile picture Ningyu's profile picture pyterpam's profile picture
Ā·
https://www.turingpost.com/

AI & ML interests

None yet

Recent Activity

replied to their post 2 days ago
What we learned about memory in 2025: 8 comprehensive resources If models forget everything, how can they be reliable? AI systems need to remember past interactions, update knowledge, stay consistent over time, and work beyond a single prompt. That's why many start to talk more about memory in AI. Hereā€™s a useful set of studies and videos on where AI memory stands today: 1. https://huggingface.co/papers/2512.13564 A great survey that organizes agent memory research. It gives concrete taxonomies across memory form, function, and dynamics, summarizes benchmarks, frameworks, and emerging directions for building systematic agent memory systems 2.WhenĀ WillĀ WeĀ GiveĀ AIĀ TrueĀ Memory? A conversation with Edo Liberty, CEO and founder @ Pinecone -> https://youtu.be/ITbwVFZYepc?si=_lAbRHciC740dNz0 Edo Liberty discusses what real memory in LLMs requires beyond RAG - from scalable vector storage to reliable knowledge systems - and why storage, not compute, is becoming the key bottleneck for building dependable AI agents. 3. Why AI Intelligence is Nothing Without Visual Memory | Shawn Shen on the Future of Embodied AI -> https://youtu.be/3ccDi4ZczFg?si=SbJg487kwrkVXgUu Shawn Shen argues AI needs a separate, hippocampus-like memory to move beyond chatbots, enabling long-term visual memory, object permanence, and on-device intelligence for robots, wearables, and the physical world 4. https://huggingface.co/papers/2504.15965 Links human memory types to LLM memory, introduces a taxonomy across object, form, and time, and identifies concrete limitations and future research directions 5. Rethinking Memory in AI: Taxonomy, Operations, Topics, and Future Directions -> https://arxiv.org/abs/2505.00675v2 Proposes a concrete taxonomy, core operations, and research directions to systematically organize and advance agent memory systems. Read further below ā¬‡ļø If you like it, also subscribe to the Turing Post: https://www.turingpost.com/subscribe
posted an update 2 days ago
What we learned about memory in 2025: 8 comprehensive resources If models forget everything, how can they be reliable? AI systems need to remember past interactions, update knowledge, stay consistent over time, and work beyond a single prompt. That's why many start to talk more about memory in AI. Hereā€™s a useful set of studies and videos on where AI memory stands today: 1. https://huggingface.co/papers/2512.13564 A great survey that organizes agent memory research. It gives concrete taxonomies across memory form, function, and dynamics, summarizes benchmarks, frameworks, and emerging directions for building systematic agent memory systems 2.WhenĀ WillĀ WeĀ GiveĀ AIĀ TrueĀ Memory? A conversation with Edo Liberty, CEO and founder @ Pinecone -> https://youtu.be/ITbwVFZYepc?si=_lAbRHciC740dNz0 Edo Liberty discusses what real memory in LLMs requires beyond RAG - from scalable vector storage to reliable knowledge systems - and why storage, not compute, is becoming the key bottleneck for building dependable AI agents. 3. Why AI Intelligence is Nothing Without Visual Memory | Shawn Shen on the Future of Embodied AI -> https://youtu.be/3ccDi4ZczFg?si=SbJg487kwrkVXgUu Shawn Shen argues AI needs a separate, hippocampus-like memory to move beyond chatbots, enabling long-term visual memory, object permanence, and on-device intelligence for robots, wearables, and the physical world 4. https://huggingface.co/papers/2504.15965 Links human memory types to LLM memory, introduces a taxonomy across object, form, and time, and identifies concrete limitations and future research directions 5. Rethinking Memory in AI: Taxonomy, Operations, Topics, and Future Directions -> https://arxiv.org/abs/2505.00675v2 Proposes a concrete taxonomy, core operations, and research directions to systematically organize and advance agent memory systems. Read further below ā¬‡ļø If you like it, also subscribe to the Turing Post: https://www.turingpost.com/subscribe
replied to their post 9 days ago
From Prompt Engineering to Context Engineering: Main Design Patterns Earlier on, we relied on clever prompt wording, but now structured, complete context matters more than just magic phrasing. The next year is going to be a year of context engineering which expands beyond prompt engineering. The two complement each other: prompt engineering shapes how we ask, while context engineering shapes what the model knows, sees, and can do. To keep things clear, here are the main techniques and design patterns in both areas, with some useful resources for further exploration: ā–Ŗļø 9 Prompt Engineering Techniques (configuring input text) 1. Zero-shot prompting ā€“ giving a single instruction without examples. Relies entirely on pretrained knowledge. 2. Few-shot prompting ā€“ adding inputā€“output examples to encourage model to show the desired behavior. āŸ¶ https://arxiv.org/abs/2005.14165 3. Role prompting ā€“ assigning a persona or role (e.g. "You are a senior researcher," "Say it as a specialist in healthcare") to shape style and reasoning. āŸ¶ https://arxiv.org/abs/2403.02756 4. Instruction-based prompting ā€“ explicit constraints or guidance, like "think step by step," "use bullet points," "answer in 10 words" 5. Chain-of-Thought (CoT) ā€“ encouraging intermediate reasoning traces to improve multi-step reasoning. It can be explicit ("letā€™s think step by step"), or implicit (demonstrated via examples). āŸ¶ https://arxiv.org/abs/2201.11903 6. Tree-of-Thought (ToT) ā€“ the model explores multiple reasoning paths in parallel, like branches of a tree, instead of following a single chain of thought. āŸ¶ https://arxiv.org/pdf/2203.11171 7. Reasoningā€“action prompting (ReAct-style) ā€“ prompting the model to interleave reasoning steps with explicit actions and observations. It defines action slots and lets the model generate a sequence of "Thought ā†’ Action ā†’ Observation" steps. āŸ¶ https://arxiv.org/abs/2210.03629 Read further ā¬‡ļø Also subscribe to Turing Post: https://www.turingpost.com/subscribe
View all activity

Organizations

Turing Post's profile picture Journalists on Hugging Face's profile picture Social Post Explorers's profile picture Hugging Face Discord Community's profile picture Sandbox's profile picture