Dataset Distillation as Data Compression: A Rate-Utility Perspective
arxiv.org/abs/2507.17221
Read this paper tonight, get me some sense: Dataset Distillation ≈ Visual Tokenization?
Dataset Distillation: Replace full dataset with few synthetic samples
Visual Tokenizer: Replace…
ChatGPT can now do work for you using its own computer.
Introducing ChatGPT agent—a unified agentic system combining Operator’s action-taking remote browser, deep research’s web synthesis, and ChatGPT’s conversational strengths.
🎉 Big thanks to @_akhaliq for featuring our work! We’re excited to release the 💻 code & 🤗 Hugging Face checkpoints for PartCrafter:
👉 github.com/wgsxm/PartCraf…
---
⭐️ PartCrafter generates multiple parts from a single RGB image in one unified pass.
Stay tuned for updates! 🚀
🎉 Big thanks to @_akhaliq for featuring our work! We’re excited to release the 💻 code & 🤗 Hugging Face checkpoints for PartCrafter:
👉 github.com/wgsxm/PartCraf…
---
⭐️ PartCrafter generates multiple parts from a single RGB image in one unified pass.
Stay tuned for updates! 🚀
🤨Ever dream of a tool that can magically restore and upscale any (low-res) photo to crystal-clear 4K?
🔥Introducing "4KAgent: Agentic Any Image to 4K Super-Resolution", the most capable upscaling generalist designed to handle broad image types.
🔗4kagent.github.io
1/🧵
Thanks @_akhaliq for sharing AnyCoder with us!
It's an AI-powered code generator specifically focused on creating applications. If you're into faster, smarter UI development, definitely keep an eye on AnyCoder!
huggingface.co/spaces/akhaliq…
🚀 Introducing Kontext-Style-LoRAs!
Turn any image into Ghibli, Jojo, Chibi, Chinese Ink & more — with ONE Kontext model.
🔥 Built on FLUX.1 Kontext
✨ Powered by GPT-4o paired data
🎨 10+ stylish LoRA adapters
💻 100% open-source [Apache-2.0]
No more boring generations — remix…
We present VLM-3R: a Vision-Language Model capable of 3D spatial reasoning from monocular video, grounding visual cues, geometry, and camera motion.
✅ No depth sensor
✅ No pre-built 3D maps
✅ End-to-end spatial + temporal reasoning
🔗 Code & benchmark: vlm-3r.github.io…
4K Followers 150 Following🥷/acc + sxe 🥑🖤 to code neural nets🧑💻 / storytelling 🎬 & AI 🤖
AI Films Online Studio and soon Streaming platform 🎬
OPEN CALL to AI storytellers (+4200)
4K Followers 662 FollowingDecoding AI for PropTech | Active Real Estate Investor & Analyst | Eng Leader @Google (Views mine) | Building a Micro-SaaS in public
📩 My deep dives:
325K Followers 3K FollowingNVIDIA Director of Robotics & Distinguished Scientist. Co-Lead of GEAR lab. Solving Physical AGI, one motor at a time. Stanford Ph.D. OpenAI's 1st intern.
7K Followers 1K FollowingAssistant Professor @UW, Principal Research Scientist @Nvidia. Prior Cofounder @NexusflowX, @Berkeley_EECS @Google @Microsoft. I work on LLMs.
949K Followers 764 FollowingProfessor at NYU. Chief AI Scientist at Meta.
Researcher in AI, Machine Learning, Robotics, etc.
ACM Turing Award Laureate.
630 Followers 740 FollowingWriter concerned about where things are headed. Normal, white woman XX , Co-researcher of child development and social relations
4.3M Followers 3 FollowingOpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring: https://t.co/dJGr6Lg202
3K Followers 1K FollowingResearch Scientist @AIatMeta. Building digital humans. Lead on Sapiens. Past: EgoExo4D, EgoHumans, PhD @CarnegieMellon, CS @iitbombay