samynhn retweeted
⌘C ⌘V: Introducing Copy-Paste Language Models!
CPLMs learn to copy tokens better, improving downstream accuracy, CoT, long-context performance, and memory-efficiency for RAG at <3% overhead
PS: they (partially) mitigate the LM head bottleneck
Paper: arxiv.org/abs/2610.19247
samynhn retweeted
Whale 🐋 is back
🚀 DeepSeek-V4.1-Flash-1017 is here!
Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API.
🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model.
1/4
samynhn retweeted
New #NVIDIA paper: what if robots never had to wait for their own thoughts?
TacitVLA learns to reason in chain-of-thought or subtasks, but its actions never read them.
→ Keeps the gains of reasoning at up to 3.4× lower latency on 4 benchmarks, and tops RoboMME and RMBench 🧵👇
samynhn retweeted
Another highlight from today’s Research@ event: After successful deployments across 16K+ submissions at STOC, ICML, NeurIPS, & ICLR, learn how Deep Review is expanding from scientific peer review to provide rigorous, grounded verification for knowledge documents, including Google Docs & presos. Try it today: goo.gle/4zx1OEP
samynhn retweeted
SAM 3.1 + DINOv3 from @AIatMeta is a crazy combo 🔥
it can even hold onto surgical tools while a forearm sweeps over them. one leaves for 15 seconds, its near-identical twin stays, and it knows exactly which one came back!
one NVIDIA A100 on @huggingface Jobs 🤗
samynhn retweeted
Introducing Code Video Model 🎬
Amazing work led by @raywzy1 and the team!
Agentic coding as the engine for controllable video generation.
Scene layout, motion, timing, camera trajectories, and physical dynamics, all in editable code.
A coding agent turns prompts into executable programs that render proxy videos. Our training-free early-step conditioning lets a pretrained video model follow the proxy’s structure while adopting a reference image’s appearance.
From physics-grounded motion and bullet time to 3D/4D reconstruction and robotics simulation, it all starts with code.
Watch the demo and explore more visual results 👇
Project page: code-video-model.github.io/
Paper: code-video-model.github.io/t…
Code: github.com/code-video-model/…
Data: huggingface.co/datasets/code…
Youtube: youtube.com/watch?v=dTtiVkSR…
samynhn retweeted
How to write a rebuttal letter
Nature Methods, Editorial
nature.com/articles/s41592-0…
samynhn retweeted
很多研究灵感，可能并不藏在自己的领域里。
Meta、CMU 等团队这篇 IdeaScientist，想让 Agent 学会提出更有依据的科研 idea。
它的流程很清晰：
先读相关论文，找到当前方法真正卡住的问题；
再跳出本领域，去其他方向寻找解决过类似结构问题的方法；
最后把这些线索整理成完整的研究方案。
为了支持这种跨领域检索，团队还构建了一个包含 277 万条研究 idea 的数据库。
评测也挺有意思，系统只能看到 2026 年 1 月 1 日之前的论文，再看它能不能提前提出后来真实研究中出现的方向。
结果显示，IdeaScientist 在综合评分上超过多种 autoresearch baseline。
更值得注意的是，把搜索范围从同领域扩展到跨领域后，novelty 从 36.3% 提升到 67.0%。
这其实很像真实科研里常见的一种突破路径：
先把问题抽象清楚，再去别的领域看看，有没有人已经解决过「同一种难题」。
未来 Research Agent 想真正产生好 idea，可能得学会主动离开自己的领域边界。
📎 arxiv: arxiv.org/abs/2610.04074
samynhn retweeted
Craziest portfolio i have seen in a while
Https://hancore.dev
samynhn retweeted
1/8 BudgetPix: one model, any compute budget.
Our pixel-space image generator adapts computation to image content at inference time. Same prompt, same noise, from 100% down to just 10% of the tokens.
→ Project Webpage: karaozgur.com/BudgetPix
samynhn retweeted
ChatGPT just got a lot more visual—introducing Intelligent UI.
Intelligent UI allows ChatGPT to answer quickly with fully interactive user interfaces that make everyday answers more visual.
It makes learning complex topics easier, and it quickly creates tools to solve a task right in the moment.
Oh, and also...GPT-6 is coming to ChatGPT. For everyone.
samynhn retweeted
Was meant to be a Valentine's gift, but I'm releasing it early ❤️
Wrote a long piece on KV caching in flow models for image generation.
Includes intuition, commentary, implementation details, benchmarks, & some quirky experiments.
sayak.dev/posts/kv-flow.html
