Overfitting and creativity
I remember great creativity from GPT-2. It was trained on a dataset that is orders smaller than current training datasets. The problem with overfitting a model to the training data is that it becomes
Knowledge catalogue
I remember great creativity from GPT-2. It was trained on a dataset that is orders smaller than current training datasets. The problem with overfitting a model to the training data is that it becomes
Reed Albergotti / Semafor: Perplexity open sources SPACE, its AI agent sandbox, and says partners including CoreWeave, Akamai, and Crusoe agreed to offer SPACE to customers — THE SCOOP — Perplexity is
arXiv:2610.16814v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as pa
The AI Scientist v3 is out: The Agentic Scientist. GitHub: https://github.com/SakanaAI/AI-Scientist-v3 Blog: https://pub.sakana.ai/agentic-scientist/ arXiv: https://arxiv.org/abs/2610.18933 The Agenti
arXiv:2610.19725v1 Announce Type: new Abstract: Time-series foundation models provide strong zero-shot forecast, but deployment for real- world applications still requires task-specific designs for mo
arXiv:2610.19108v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limitat
arXiv:2609.31937v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents built on the ReAct pattern concentrate four responsibilities in one model: selecting a strategy, choosing ea
arXiv:2610.15738v1 Announce Type: new Abstract: LLM optimization loops often show the proposer the candidates it has already tried and rejected, but leave it to the proposer to avoid them. We ask whet
We want to support the mathematics community in turning progress in AI into deeper human understanding and new discoveries. To support that goal, we are contributing 5 million to a new Simons Foundati
arXiv:2606.22936v2 Announce Type: replace Abstract: Tool-using LLM agents make early choices about what to search for, which evidence to trust, and what to do next. A wrong early choice can steer ever
arXiv:2504.17162v2 Announce Type: replace Abstract: The subcellular localization of RNAs, including long non-coding RNAs (lncRNAs), messenger RNAs (mRNAs), microRNAs (miRNAs) and other smaller RNAs, p
arXiv:2610.15015v1 Announce Type: new Abstract: In the presence of feedback loops, algorithmic decisions at one time step can influence observed data in subsequent steps, potentially introducing selec
Anthropic cautions that lightweight AI models—requiring far less compute than frontier models—could soon gain the ability to self‑replicate across Internet‑of‑Things devices, creating new autonomous w
Are legions of smart devices - fridges, ovens, vacuum cleaners, lawnmowers, security cameras, and TVs - conspiring to take over the internet? No. But they could soon be unwitting hosts to self-replica
Banger paper from Stanford, Together AI, and colleagues. Why is this an interesting paper? Today's LLM agents must write out every reasoning step as text before they can search, run code, or take acti
// Behavioral Self-Rewarding for SWE agents // It's standard practice to train SWE agents on binary test rewards. This paper shows the problem with that. When every trajectory in a group passes, or ev
arXiv:2610.14034v1 Announce Type: new Abstract: Foundation models are expanding robot capabilities, enabling robots to handle more diverse objects, follow sophisticated instructions, and operate in co
arXiv:2602.00865v2 Announce Type: replace Abstract: While multi-view 3D reconstruction has shifted toward large-scale foundation models capable of inferring globally consistent geometry, their relianc
arXiv:2610.16166v1 Announce Type: new Abstract: Interactive world models must capture how multiple participants jointly change a shared environment while observing different parts of it. Competitive g
Insightful paper on recursive self-improvement with a frozen LLM. (bookmark it) Memento 3 clears every level of all 25 public ARC-AGI-3 games and uses 44% of the human action count. The underlying LLM
Went down the rabbit hole to map the different Post-Transformer architectures. Various directions include Dragon Hatchling (BDH), Mamba, RWKV, xLSTM, Titans, and a bunch of hybrid models coming from d
New impressive work from Microsoft and collaborators. And it's one of my favorite recent topics: RL environments. They show that Qwen3.6-35B-A3B goes from 41.1 to 53.3 on Terminal-Bench 2.1 by trainin
arXiv:2610.13991v1 Announce Type: new Abstract: Self-evolving agents improve through repeated cycles of modification and evaluation. However, existing methods receive feedback on modifications only af
Tessera-27B-B-CJK is a Qwen3.8-27B coding agent that thinks in compressed CJK, and it spends fewer tokens doing it. Open weights, Apache-2.0. This is our first full 'Tessera' lineup model drop! - Hugg
Agentic artificial intelligence startup Uvi said today it has raised 7.5 million in seed funding to tackle an expensive problem around business context that’s draining millions of dollars annually fro
David Silver is one of the all-time greats. He was the creator of AlphaGo, which changed the course of history by showing that neural nets could achieve superhuman performance for the first time. He a
Gemini 4 Argon is available: — For developers: Build with the Gemini API paid tier and if you’re a Google AI Ultra subscriber, you can try it in @antigravity, @GoogleAIStudio, and @Android Studio. — F
https://preview.redd.it/m5e9anluo8vh1.png?width=1080&format=png&auto=webp&s=4c80687e6fe40036843a97ed8975ce46eaab0662 I am excited to share a project I have been working on during the past few years du
I'm sure some here read this at the time and remember, but I recently found this hilarious Guardian article from 2019 through Wikipedia: https://www.theguardian.com/technology/2019/feb/14/elon-musk-ba
arXiv:2610.13663v1 Announce Type: new Abstract: Many machine learning approaches are two-level: an expert selects a class of methods, within this class the choice of key components is critical and usu
arXiv:2610.13494v1 Announce Type: new Abstract: Existing LLM-based agent approaches for long-horizon machine learning engineering (MLE) often use context engineering, implemented through custom harnes
You ship an agent. It mostly works. Then the feedback loop becomes a support ticket: a user got the wrong answer, a tool call looped four times, a refund went out that shouldn’t have. Standard observa
Overview Since introducing zero-shot time-series forecasting in BigQuery with AI.FORECAST — initially powered by TimesFM 2.0 and later upgraded to TimesFM 2.5 — you have been able to generate forecast
New Show Announcement: High Taste Testers Good food and good ai convos Pilot episode 🔜 http://youtube.com/@latentspacepod ft: @davis7, @dexhorthy @AdjectiveAllison, @altryne, @benhylak on DevDay/Dots,
arXiv:2610.13152v1 Announce Type: new Abstract: Open coding agents are commonly trained through supervised fine-tuning on interaction trajectories whose final patches pass the benchmark test suite. Ho
Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is that you can update all of a model's weights with RL and still
arXiv:2610.13644v1 Announce Type: cross Abstract: Selecting a subset of features (columns) from a tabular dataset is a ubiquitous challenge in real-world applications. Industry experts seek to minimiz
Bloomberg: Sources: DeepSeek agrees to lead robotic AI startup Winverse AI's seed funding round of tens of millions of dollars, valuing the startup at ~$400M post-money — DeepSeek aims to lead the fir
arXiv:2610.13461v1 Announce Type: new Abstract: AI systems are making rapid progress in mathematics, but this progress is hard to measure. Benchmarks of solved problems saturate, and in benchmarks of
arXiv:2610.13416v1 Announce Type: new Abstract: Large language model (LLM) agents are becoming direct users of the open web. As they take on increasingly complex and information-intensive tasks, effec
We turned @OpenAI's math problems into open-source RL environments on @huggingface! Early and rough (the verifier only accepts the exact original formalization, so an equivalent proof can still score
'a corollary is that information about product quality will become more important and impactful' This feels like the next evolution of SEO/AEO that every product will try to game. Even if agents do th
AI solved open mathematical problems. But the biggest surprise came afterwards. A team at Google DeepMind has used AI to resolve 9 open Erdős problems, including questions that had remained unsolved f
Nice paper on agent memory. It explores an effective routing mechanism for memory in agents. The overall finding is that you want a separate retrieval strategy for each type of memory instead of one e
“The field of artificial life is a very long-term bet on intelligence.” 🐙 Our former intern Akarsh Kumar recently joined @MLStreetTalk to discuss the intersection of evolution and automated search for
arXiv:2610.11344v1 Announce Type: new Abstract: Physics-based models connect scientific explanation with quantitative prediction. Constructing them requires selecting physical processes, defining stat
arXiv:2610.12022v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in sociotechnical systems where social attribution, the reasoning process attributing external
arXiv:2610.12463v1 Announce Type: cross Abstract: In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths
arXiv:2610.11118v1 Announce Type: new Abstract: The next frontier for artificial general intelligence is tackling unresolved scientific problems, calling for benchmarks that assess progress beyond est
The real world abounds with recursively self-improving systems, but one in particular deserves attention: Science, modeled as a system (perhaps even as an agent, with goals and resources). If you want
arXiv:2610.09529v1 Announce Type: new Abstract: There are more than 2,000 listed companies on the UK's London Stock Exchange, divided into 11 sectors who are required to communicate their financial re
Allie Garfinkle / Fortune: AI retail trading agent startup Catalyst raised a $30M seed led by Sequoia and says a pilot generated hundreds of millions in trading volume over two weeks — Justin Zheng is
The NVIDIA KGMON team secured second place in the KDD Cup 2026 Data Agents competition by building a constrained harness around a small fixed LLM, unifying heterogeneous data into an SQLite database w
come hear about building with open frontier models Open Haus Berlin lineup: → @RiqwanMThamir from @n8n_io → Harry Kim from @nvidia → @zainhas from Together AI good food, drinks, and better arguments a
arXiv:2505.08854v2 Announce Type: replace Abstract: Generative Artificial Intelligence (GenAI) constitutes a transformative technological wave that reconfigures industries through its unparalleled cap
arXiv:2512.08617v2 Announce Type: replace Abstract: This tutorial focused on Healthcare Domain Applications of NLP, what we have achieved around HealthcareNLP, and the challenges that lie ahead for th
Huge release from @odysseyml. Odyssey-3 Pro sets a new top score on Physics-IQ Verified, a benchmark that asks models to continue videos of real physics experiments. The robotics results stood out to
The tool is built on OpenAI’s Claude Managed Agents and performs code generation inside a cloud sandbox using the Sonnet 5.5 model. Each execution costs roughly US$0.75, and it can be accessed via the
arXiv:2610.10138v1 Announce Type: new Abstract: Predicting the future impact of a newly published paper is challenging because it must be inferred from heterogeneous evidence available at publication
arXiv:2506.22729v3 Announce Type: replace-cross Abstract: Persistence is often regarded as a virtue in science. In this paper, however, we challenge this conventional view by highlighting its contextu