Hugging Face's logo
Javad Taghia | PhD's picture
🏗️ Building on HF

Javad Taghia | PhD PRO

javadtaghia
7 8 49
sskela's profile picture asigalov61's profile picture legolasyiu's profile picture
·
https://AtMem.ai

AI & ML interests

Work with agentic systems, agent memory, model fine tuning and unlearning, generative AI, and the development and deployment of open source AI

Recent Activity

repliedto their post about 1 hour ago
Hugging face article: https://huggingface.co/blog/javadtaghia/atmem-2310-bounded-evidence-discovery-for-persiste AtMem 2.3.10 is out; and our full DolphinBench result has more than doubled. AtMem 2.3.9 passed 192 of 600 tasks (32%). AtMem 2.3.10 passed 390 of 600 (65%). We doubled it. What changed? We focused on how an agent discovers and uses evidence. AtMem combined lexical and semantic retrieval while keeping related passages together with their original source and provenance and more. Where do we stand? This is substantial progress, with a clear tradeoff: median recorded task latency increased from 31.87 to 85.78 seconds. More successful investigation currently takes more time. The published Hermes/Luna/Mem0 reference scores 424/600 (70.7%). What comes next? We want to understand the remaining failures: was evidence missing, poorly ranked, packed incompletely, interpreted with the wrong temporal state, or used incorrectly during an action? Evidence discovery remains opt-in. Release: https://github.com/aetna000/atmem/releases/tag/v2.3.10 DolphinBench submission PR: https://github.com/mem0ai/dolphinbench/pull/10 Results and execution evidence: https://huggingface.co/datasets/atmem/atmem-2.3.10b1-dolphinbench PS: DolphinBench tests whether an agent can use a simulated user’s history to complete actions in applications. Finding a relevant passage isn’t enough—a task passes only when all its required checks pass.
repliedto their post about 1 hour ago
Hugging face article: https://huggingface.co/blog/javadtaghia/atmem-2310-bounded-evidence-discovery-for-persiste AtMem 2.3.10 is out; and our full DolphinBench result has more than doubled. AtMem 2.3.9 passed 192 of 600 tasks (32%). AtMem 2.3.10 passed 390 of 600 (65%). We doubled it. What changed? We focused on how an agent discovers and uses evidence. AtMem combined lexical and semantic retrieval while keeping related passages together with their original source and provenance and more. Where do we stand? This is substantial progress, with a clear tradeoff: median recorded task latency increased from 31.87 to 85.78 seconds. More successful investigation currently takes more time. The published Hermes/Luna/Mem0 reference scores 424/600 (70.7%). What comes next? We want to understand the remaining failures: was evidence missing, poorly ranked, packed incompletely, interpreted with the wrong temporal state, or used incorrectly during an action? Evidence discovery remains opt-in. Release: https://github.com/aetna000/atmem/releases/tag/v2.3.10 DolphinBench submission PR: https://github.com/mem0ai/dolphinbench/pull/10 Results and execution evidence: https://huggingface.co/datasets/atmem/atmem-2.3.10b1-dolphinbench PS: DolphinBench tests whether an agent can use a simulated user’s history to complete actions in applications. Finding a relevant passage isn’t enough—a task passes only when all its required checks pass.
reacted to fffiloni's post with 🚀 1 day ago
Carbon-X brings DNA and language together: it reads sequences and answers questions about them 🧬 To accompany the release article, I put together Carbon-X Playground: five experiments exploring sequence completion, single-letter changes, regulatory roles, DNA origins and motif finding. Try curated samples or your own sequences, ask questions and compare answers with references when available. Built with Gradio, running on ZeroGPU. 📖 https://huggingface.co/spaces/HuggingFaceBio/Carbon-X-Release 🧬 https://huggingface.co/spaces/fffiloni/Carbon-X-Playground
View all activity

Organizations

Blog-explorers's profile picture PowergenAI's profile picture OpenFree_AI's profile picture AtMem.Ai's profile picture