Knowledge catalogue
arXiv:2610.20845v1 Announce Type: new Abstract: Skill-policy co-evolution, in which an agent's policy model and its skill bank improve each other during training, is a promising paradigm for self-impr
arXiv:2610.21350v1 Announce Type: new Abstract: Consistency within a document is a crucial feature indicative of its quality. Recently, within the vast amount of information produced across various me
Reflection AI's Beam is an open-weight model for agentic coding and long-horizon tasks. This post shows how to deploy Beam on AWS: start with an Amazon SageMaker JumpStart real-time endpoint, or use A
arXiv:2610.21522v1 Announce Type: new Abstract: Specialized vision-language-action (VLA) policies acquire strong domain-specific skills, yet consolidating these skills into one shared policy remains c
Muse Spark Open is now live on Wally, day 0 Best US open model thanks to @finkd 370 tok/s, ~2x faster than any provider on OpenRouter. $5 Free on signup. Media 1/ muse spark open is the most capable U
arXiv:2610.20935v1 Announce Type: new Abstract: Engineering agents must produce artifacts that satisfy exact, coupled constraints. Existing solutions often require agents to make semantic decisions an
arXiv:2610.21950v1 Announce Type: cross Abstract: Tabular foundation models based on prior-data fitted networks (PFNs) predict on a new data set in a single forward pass, but they cannot report which
arXiv:2610.21139v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used upstream of decision-making to clean data, detect label errors, and reconstruct missing values. Yet
Amazon.com Inc. today debuted two new wearable, artificial intelligence-enabled devices aimed at making everyday life simpler by listening to conversations and helping users remember what matters. Bee
arXiv:2610.19704v1 Announce Type: new Abstract: Large language models (LLMs) increasingly help users arrange appointments, plan journeys, and allocate limited resources. These tasks require models to
arXiv:2610.19367v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for multi-turn agentic tasks that require interactions with users and environments over extended sequ
arXiv:2610.14118v1 Announce Type: new Abstract: The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents op
arXiv:2610.16876v1 Announce Type: new Abstract: Target-aware multimodal instruction selection requires useful examples and an appropriate balance of supervision. Sample-level rankings can overrepresen
arXiv:2606.17029v2 Announce Type: replace Abstract: Deep research agents synthesize long-form reports by searching and reasoning over retrieved evidence. Reinforcement learning with rubric-based rewar
arXiv:2610.14346v2 Announce Type: replace Abstract: Enterprise customer-support agents increasingly rely on Large Language Models (LLMs) to execute bounded, tool-using workflows. We study this problem
Giving my Dot a dedicated email address turned out to be surprisingly painless & solved a few problems around how to relate to a personal agent. I don't want it using my email or drafting messages on
arXiv:2510.24469v2 Announce Type: replace-cross Abstract: Personalized text generation requires models not only to produce coherent text but also to align with a target user's style, tone, and topical
Microsoft AI: Microsoft unveils MAI-Base-2, a MoE model with 2.8T total and 80B active parameters, claiming 4x-12x more pretraining FLOPs-efficiency than DeepSeek-V4-Pro-Base — In June, we announced M
Muse Spark Open is live on @huggingface! 🤗 - Strong agentic model (especially for personal agents) - Multimodal from the ground up - 816B parameter model - 42B Active parameters Models link: https://h
arXiv:2610.19931v1 Announce Type: new Abstract: Segment Anything Model 3 (SAM 3) is a foundation model for image and video segmentation that sets the state of the art in visual object tracking. Its tr
arXiv:2603.09200v2 Announce Type: replace-cross Abstract: Situational awareness, the capacity of an AI system to recognize its own nature, understand its training and deployment context, and reason st
arXiv:2610.14115v1 Announce Type: new Abstract: Large language models have significantly lowered the barrier to writing code. Naturally, this has also led to the development of data science agents tha
arXiv:2610.14701v1 Announce Type: cross Abstract: Model merging has become widely adopted for enhancing the task-specific performance of Large Language Models (LLMs) without additional training. While
Overview llama.cpp v0.7.0 adds the LiliCorr speculative decoding technique and MTP for GLM5-Next, a new GPU cache for MoE experts kept in host memory (--moe-cache-mib, up to ~2.2x decode speedup when
arXiv:2610.19035v1 Announce Type: cross Abstract: Pluralistic alignment needs to accommodate diverse preferences under limited human feedback. Using AI simulators to label preference comparisons reduc
https://www.bloomberg.com/news/articles/2026-10-14/anthropic-executive-says-open-source-ai-models-are-higher-risk https://www.business-standard.com/technology/artificial-intelligence/open-source-ai-mo
arXiv:2610.17968v1 Announce Type: new Abstract: Diffusion MRI (dMRI) probes water diffusion within the brain, providing unique information about tissue microstructure and white matter connectivity. Hi
arXiv:2610.16596v1 Announce Type: new Abstract: Seizure prediction and detection, essential for clinical treatment of epilepsy, remain the crucial task of this neurological disease. EEG and iEEG are w
arXiv:2610.14260v1 Announce Type: new Abstract: Augmentation-based self-supervised learning can recover the content shared across views without separating its underlying factors into individual coordi
Suggestion for you: Pick an agent for work, and pick an agent for personal. You could explore to do this all with Grok Bot (with many different types of bots) Personally, I like @bot for work, and @Mu
arXiv:2603.05911v2 Announce Type: replace-cross Abstract: Medical image segmentation is undergoing a paradigm shift from conventional visual pattern matching to cognitive reasoning analysis. Although
My AI agent doing proactive customer service: Someone emailed me that, after subscribing to my Substack, they were automatically signed up for others (which shouldn't happen) Without my asking, my Dot
The ultimate LLM benchmark: Chilean Spanish. 80% of AI models fail to recognize Chilean Spanish and insist on speaking like an Argentine 80% de modelos de IA no logra reconocer el español chileno e in
What does the world look like inside an AI model? Here are 3 world model architectures based on how they represent the world (+ the subtypes) ↓ 1. A generated observation – a model predicts what comes
arXiv:2610.12118v1 Announce Type: new Abstract: Automated methods have been proposed to overcome the limitations of human verbal deception detection, but evidence remains fragmented across disciplines
arXiv:2610.11923v1 Announce Type: cross Abstract: The brain maintains stable cognition despite continuously changing neural activity. How to extract stable cognitive states from variable neural observ
Manus, the creator of the eponymous artificial intelligence agent, has raised more than 500 million in funding. The Chinese startup announced the round today. It stated that private equity firm Boyu C
arXiv:2610.10379v1 Announce Type: new Abstract: Continual learning requires models to adapt to new domains and new classes while retaining prior knowledge. Many existing methods rely on continued opti
arXiv:2610.09197v1 Announce Type: cross Abstract: Agent evolvers automate the design of the prompts, skills and workflows around language model agents, yet the optimization process they follow is stil
arXiv:2610.08995v1 Announce Type: new Abstract: Astra can act, yet reliable manipulation depends on the system through which it observes and controls the world. We introduce PhysEvo, a framework for p
arXiv:2610.10088v1 Announce Type: cross Abstract: Self-evolving agents distill task-solving experience into skills for future reuse, but these skills can encode incorrect procedures or non-transferabl
arXiv:2610.09360v1 Announce Type: cross Abstract: Real-world documents distribute evidence across text, tables, figures, and captions within complex page layouts. Answering complex questions over such
arXiv:2610.07447v1 Announce Type: new Abstract: Autoresearch agents tackle open-ended problems by repeatedly proposing candidate solutions, evaluating them, and using feedback to guide subsequent expe
On October 7, 2026, Clement Delangue noted that Microsoft’s Windows launch—highlighted by Satya Nadella and others—demonstrated the growing excitement around local AI solutions such as llamacpp. The e
arXiv:2610.08475v1 Announce Type: new Abstract: In many-query scenarios, data-driven surrogate models provide an efficient alternative to high-fidelity solvers for simulating physical systems governed
arXiv:2610.07627v1 Announce Type: new Abstract: Scientific discovery systems typically optimize experiments within a fixed hypothesis space. This creates a failure mode when all available candidates o
arXiv:2610.08570v1 Announce Type: cross Abstract: Handcrafted preprocessing is widely employed in automated dermoscopic analysis to suppress imaging artifacts and enhance lesion visibility. Neverthele
Maxwell Zeff / Wall Street Journal: Letter: three fired OpenAI researchers urge AI labs to halt work that could impair AI monitoring and say their firings are “chilling those who remain at OpenAI” — I
arXiv:2610.04381v1 Announce Type: new Abstract: Fine-grained image editing requires more than producing a visually plausible result: an editor must execute the requested attribute change precisely whi
arXiv:2610.04931v1 Announce Type: new Abstract: This paper introduces a real-time thumbnail optimization system deployed at a global O(B) scale on a major short-form video platform. Unlike traditional
arXiv:2610.05898v1 Announce Type: new Abstract: Real-world users often exhibit highly heterogeneous preferences over multiple objectives for LLM responses. A lightweight aligner can tailor these respo
arXiv:2610.06663v1 Announce Type: new Abstract: A significant problem in endoscopic image analysis is that the machine learning (ML) models used for this purpose usually underperform when applied on i
arXiv:2610.05532v1 Announce Type: cross Abstract: AI agents that send emails, edit files, and make purchases must decide when to act on their own and when to check with the user first. This decision i
arXiv:2610.03945v1 Announce Type: new Abstract: A constrained optimization problem may involve a parameter in its objective and active constraints, yet the final decision may remain insensitive to sma
arXiv:2610.04649v1 Announce Type: new Abstract: Continual learning is typically framed as acquiring new knowledge without catastrophically forgetting previous tasks. However, a flexible continual lear
arXiv:2610.04723v1 Announce Type: cross Abstract: This work proposes a latent Lagrangian-based framework for reduced-order modelling of forced nonlinear dynamical systems. In contrast with conventiona
arXiv:2610.06195v1 Announce Type: cross Abstract: Learned feature representations in neural networks often contain structure beyond that directly used by the final task output. We study this structure
arXiv:2610.06342v1 Announce Type: new Abstract: While reinforcement learning with verifiable rewards provides reliable outcome supervision for VideoLLMs, sequence-level rewards offer limited token-lev
Mistral AI SAS today opened access to Mistral Large 4, its most capable large language model to date. On launch, the LLM is available in public preview through the company’s cloud platform. Mistral pl
arXiv:2610.04269v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vuln