AtMem 2.3.15 is out.🚀 Please upgrade and give us ⭐️ • RAG with citations and source revisions • Encrypted local document storage • Scoped MCP access • Action outcomes and readback evidence • Budgeted memory policy evaluationTested on Windows, macOS and Linux.
Dashboard, CLI and MCP share AtMem’s permission state. Owner grants scope retrieval; evidence exports require consent tied to a recipient and purpose.Includes an owner-only evaluation SDK and a matching OpenClaw bridge.
Can a general-purpose LLM erase a concept from a diffusion model by editing its weights directly, with no gradients?
We tested it under a preregistered protocol. GPT-6 Astra got tool access to the weights of segmind/tiny-sd and had to remove Van Gogh's painting style. Every edit was a closed-form tensor operation in a sandbox that blocks all autograd paths.
Held-out test, confirmatory runs (paired, template-clustered 95% CIs): • vs random search with the same edit space and the same feedback: −52.1 pts Van Gogh rate [−61.7, −42.3] • vs UCE (closed-form erasure): −11.5 pts [−22.9, −0.9], with identical damage to neighbouring painters • vs ESD (gradient fine-tuning): equal removal, +11.8 pts better neighbour preservation
Limits, stated up front: one model × one concept so far; no method (the agent included) removes the style when it is described without the artist's name; no recovery attacks yet.
Every run is public: hash-chained logs, budgets, the agent's full transcripts, per-prompt scores, checkpoints, the frozen protocol and costs.
VIGOR (Vision Intelligence and Guardrail Oriented Reasoning) is now available on the Hugging Face Model Hub. It is a multimodal vision classification model based on Qwen3.5, designed for visual content-safety analysis and conservative classification, with a particular focus on identifying potentially sensitive content.
Flux-3-Image-Klein-LoRAs-Fast is now live on Hugging Face Spaces.🤗🔥
Plug and play with any custom LoRAs based on flux-3-image-klein. 16-step distilled fast inference, with support for prompt upsampling. More LoRAs will be added in the coming days!
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%).
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.
It is not always positive results that worth noting. I ran a long run of training to improve AtMem (agent memory) on storage path using Laya as a decision model. However, I found it did not give me any better result than original AtMem. Indeed we can use laya on the retrieval path, we have used than by pluging Jev. So we kinda proved something that is still a gap in memory systems (improving storage) is not as easy as it sounds. Check details https://huggingface.co/blog/javadtaghia/we-fine-tuned-a-memory-classifier-for-our-agent-he
This demo showcases the OneDecision-VisionGuard family of multimodal image classification models for detecting NSFW and other sensitive visual content, with structured JSON reasoning, improved accuracy, and better handling of edge cases such as sensitive imagery, uncensored analysis, scene descriptions, and classification reasoning.
I’m preparing to submit my article to arXiv and need an endorsement for the cs.AI category.
If you’re eligible to endorse submissions in this area and would be willing to help, I’d really appreciate it. Please DM me and I can send you the arXiv endorsement link.
Thank you!
from arXiv cs.AI community, can anyone support me?
Just launched Qwen Image 2.1 Uncensored All-In-One LoRA Studio on @huggingface #ZeroGPU! Includes 15+ on-demand LoRAs (Turbo 4-step, Anime, Photoreal, FaceSwap) with 0 data retention: arudradey/qwen-image-2.1-uncensored-aio-loras
VisionGuardrail EVO-2, a multimodal image-classification content-safety model based on Qwen/Qwen3.8-27B, is now available on the Hub!
Stricter image classification than before, with a dense 27-billion-parameter multimodal model, more precise reasoning, and improved captions for classifying visual media.
Scribble-Board-Fast is a sketch-to-image workspace powered by Klein-9B, transforming doodles, brush strokes, stickers, and uploaded images into high-fidelity visuals with 4-step distilled sampling.
VisionGuardrail, a multimodal content-safety classifier based on Qwen3.5, is now available on Hugging Face in 4B and 9B variants. It is a direct upgrade to ImageShield-MMCF, providing improved parental controls through conservative visual content-safety filtering.