Knowledge catalogue
arXiv:2601.21649v2 Announce Type: replace-cross Abstract: The deployment of coding agents in privacy-sensitive and resource-constrained environments drives the demand for capable open-weight Small Lan
arXiv:2610.18933v1 Announce Type: cross Abstract: Modern coding agents are fundamentally reshaping the role of human input for computational research: they write code, launch in silico experiments, an
arXiv:2610.16725v1 Announce Type: new Abstract: Improving an LLM agent requires knowing what to change when it fails. Similar failures can require different fixes, and resolving one problem can expose
arXiv:2610.16555v1 Announce Type: cross Abstract: We introduce qtBench, a benchmark of 29 open problems in algebraic combinatorics. These problems ask for a simple combinatorial algorithm that explain
But meanwhile the numbers of suicides and self-harming are rising. Interesting that is implanted into algorithms everywhere. Why? Why if a person is researching the topic on YT, on NDE's for example w
arXiv:2610.16523v1 Announce Type: cross Abstract: Training LLM agents to interact with users over multiple turns is challenging because the learning signal depends not only on the agent, but also on t
arXiv:2610.16277v1 Announce Type: new Abstract: Prior avatar embodiment research has studied tracking completeness (how faithfully the body, hands, and face are sensed and reproduced) and personalized
arXiv:2610.18188v1 Announce Type: new Abstract: Learning robot policies from demonstrations is often limited by the cost of collecting diverse, high-quality expert data. While an appealing alternative
arXiv:2610.17016v1 Announce Type: new Abstract: Evaluating model uncertainty on real-world data is challenging because each instance provides only a single observed label, leaving true conditional cla
arXiv:2606.15734v2 Announce Type: replace-cross Abstract: Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate
arXiv:2511.00655v3 Announce Type: replace Abstract: Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, yet its scalability is limited by
Last week, Anthropic and OpenAI looked like they had the AI race to themselves, pulling ahead with increasingly powerful models that left their rivals in the dust. Google seemed hopelessly far behind,
The cancelation of the Grace Hopper Conference may actually point to a reduction in overall junior-level recruitment and job growth. I spoke about AI at GHC 2018, and it was 20,000+ attendees, majorit
arXiv:2610.18789v1 Announce Type: new Abstract: Agentic remote sensing is evaluated on how many questions it can answer, whereas crisis response depends on whether its answers can be relied on and how
arXiv:2610.18842v1 Announce Type: cross Abstract: Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive S
A coding agent finishes a change and wants to open a GitHub issue with a link to its results. The agent can describe the issue, but creating it belongs to a different system. It needs a tool that can
Release: llm-gemini 0.35 I added support to llm-gemini for the new Gemini 4 Argon model, made available today via the Gemini API and for customers of their 100/month subscription plan. Here are the lo
This post is to let people know about a workshop/tutorial on Machine Learning that will run on the (blue) math discord server: discord.gg/maths. The place is nice, people are cool and helpful, and as
arXiv:2610.13303v1 Announce Type: cross Abstract: LLM judges are increasingly deployed as panels, and disagreement among panel members is often read as a symptom of an unclear rubric. We test a label-
arXiv:2610.12936v1 Announce Type: new Abstract: Vision-language-action (VLA) models provide a unified framework for visual understanding, language grounding, and robot control, yet anticipating how th
arXiv:2506.09956v2 Announce Type: replace-cross Abstract: Indirect prompt injection attacks exploit a fundamental weakness of LLMs: executing unauthorized tasks from untrusted sources. Despite the pra
arXiv:2610.13818v1 Announce Type: new Abstract: Representations of supervised datasets support higher-level machine-learning tasks such as dataset retrieval and distribution-shift monitoring. However,
arXiv:2610.13690v1 Announce Type: new Abstract: Diffusion models typically learn the generative dynamics of a single target distribution or a family of distributions indexed by conditioning variables
arXiv:2610.11963v1 Announce Type: cross Abstract: A no-code fix resolves an invalid bug report by directing the user to change a setting, update to a version where the problem is already fixed, or adj
arXiv:2610.11085v1 Announce Type: new Abstract: Offline multi-task reinforcement learning (Offline MTRL) heavily depends on the quality and distribution of pre-collected data. However, existing method
arXiv:2610.11152v1 Announce Type: cross Abstract: LLM agents increasingly improve at inference time by accumulating experience in context rather than by updating parameters. This process is often desc
arXiv:2610.11790v1 Announce Type: new Abstract: Byte-level language models such as the Byte Latent Transformer (BLT) group bytes into patches and run their large global model once per patch. BLT start
arXiv:2610.12185v1 Announce Type: new Abstract: Reliable robotic manipulation requires timely intervention to correct emerging deviations and restore progress after execution errors. However, recovery
The Agent Economy Gala just maxed out at 400 guests Here’s a breakdown: - 203 founders ($1B+ raised combined) - 67 founding operators - 58 investors - 23 creators - 295 guests building agent applicati
arXiv:2610.11638v1 Announce Type: new Abstract: Evaluating user experience (UX) with automated computational methods has gained increasing attention, supported by empirical evidence from UXBench. Howe
arXiv:2610.11123v1 Announce Type: new Abstract: Most human-agent interaction today remains text-based. Natural language can impose cognitive overload, ambiguity, information chaos, and slow input for
arXiv:2610.08792v1 Announce Type: new Abstract: We present a foundational formulation of the Bayesian Mirror Architecture (BMA), a self-referential generative framework in which sensory abstractions,
arXiv:2610.09692v1 Announce Type: new Abstract: Pain perception varies substantially across individuals, making it difficult for population-based classifiers to generalise across all subjects in a dat
Classification is one of the oldest problems in machine learning. Unlike modern decoding transformers, most classification models were non-autoregressive by nature. Before Jev, the common approaches w
arXiv:2610.10394v1 Announce Type: new Abstract: Kernels encode the inductive bias of a wide range of machine learning models, yet automated kernel design faces a fundamental dilemma. A fixed grammar o
arXiv:2610.09795v1 Announce Type: new Abstract: The demand for personalized LLMs is shifting from style imitation toward content quality. We investigate whether self-distillation can bridge this gap i
arXiv:2610.09471v1 Announce Type: new Abstract: Learning systems adapt quickly inside a familiar family of models. The harder step comes earlier: deciding, from observations that could be noise, an ex
arXiv:2610.08651v1 Announce Type: cross Abstract: Software-engineering agents can enable people without formal software training to build systems they could not otherwise implement and simultaneously
A universal predictive model of the cell would dramatically accelerate science, allowing biologists to perform experiments digitally. Today we’re announcing a major partnership with the DOE and NIH. T
arXiv:2610.08544v1 Announce Type: cross Abstract: Probes are the workhorse of interpretability. If a model's hidden states predict a variable, the model is said to represent it. But a probe score has
arXiv:2610.07306v1 Announce Type: new Abstract: Scientific search systems can find papers that are relevant to a question, but they generally do not assess the quality of the evidence that those paper
arXiv:2610.08214v1 Announce Type: new Abstract: We report on an approach to teaching logic to mixed groups of computer science, mathematics, and philosophy students, based on the logico-pluralistic Lo
arXiv:2610.07253v1 Announce Type: new Abstract: Neural fields are usually evaluated by how well they reconstruct an observation. We show that this misses two useful properties of a fitted network: how
arXiv:2610.07800v1 Announce Type: cross Abstract: Artificial Intelligence (AI) tools are widely used to support decision making in tasks and domains where no immediate performance feedback is availabl
arXiv:2610.07434v1 Announce Type: new Abstract: When does a second artificial intelligence (AI) component improve a primary network-fraud decision rather than add operational burden? We study this que
arXiv:2610.04364v1 Announce Type: new Abstract: Designing effective reward functions in RL typically requires substantial expertise and trial and error. Recent work automates this process with LLM-bas
arXiv:2610.04671v1 Announce Type: cross Abstract: A federated objective is a weighted sum of client risks, and the weights are almost always fixed in advance. We treat them instead as the only instrum
ABC: At an Australian hearing, OpenAI Chief Strategy Officer Jason Kwon pledged faster safety incident disclosures; Anthropic representatives made similar pledges — By national AI reporter Cam Wilson
arXiv:2610.06651v1 Announce Type: new Abstract: Methods for generalization in model-based reinforcement learning typically assume that an agent cannot recover the latent context governing the environm
arXiv:2610.06801v1 Announce Type: new Abstract: Sparse attention is a primary approach to reducing the latency of diffusion transformers in long-sequence generation tasks, such as video and high-resol
arXiv:2610.04802v1 Announce Type: new Abstract: This project explores how multiple cognitive radars can learn to share limited wireless spectrum with other radio users without interfering with one ano
arXiv:2610.05852v1 Announce Type: new Abstract: Frozen representations are widely reused for downstream classification, yet each new task typically requires fitting a new predictor. We ask whether the
arXiv:2503.21975v2 Announce Type: replace Abstract: Long-horizon manipulation under sparse rewards remains challenging for reinforcement learning due to delayed feedback and inefficient exploration. E
SemiAnalysis: Analysis: Anthropic's subscriptions offer ~5x more API-equivalent value per month than OpenAI's for agentic workloads with Claude Opus 5.5 vs. GPT-6.1 Sol — Limit testing every AI subscr
arXiv:2610.03591v1 Announce Type: new Abstract: Understanding and assessing natural hazards is essential for disaster preparedness and risk reduction. Recent advances in large language models have spu
Huge release from EverMind AI. Raven is an open-source multi-agent system that builds a separate harness for each model and domain, evolves those harnesses from their failures, and coordinates them th
arXiv:2610.02396v1 Announce Type: cross Abstract: Multi-agent systems (MAS) built from large language models coordinate specialized agents to tackle complex tasks, but effective workflows are difficul
arXiv:2610.02398v1 Announce Type: new Abstract: A robot demonstration records two things in the same frames: what happened to the objects, and how one particular arm made it happen. We condition on th
arXiv:2610.02255v1 Announce Type: new Abstract: Time series forecasting remains a critical challenge across numerous domains. Despite significant advancements, existing approaches struggle with comple
arXiv:2610.03160v1 Announce Type: cross Abstract: Discovering broadly neutralizing antibodies (bnAbs) from human natural immune repertoires remains a fundamental challenge in immunology, hindered by: