Knowledge catalogue
arXiv:2607.06614v1 Announce Type: cross Abstract: Accurate station-level demand forecasting is essential for the efficient operation of bike-sharing systems, yet it remains challenging due to complex
arXiv:2511.16107v3 Announce Type: replace-cross Abstract: Visual in-context learning (VICL) solves visual tasks by conditioning on a few input-output demonstrations without any model training. Recent
arXiv:2607.06841v1 Announce Type: cross Abstract: Diffusion models offer a powerful framework for sampling from complex probability densities by learning to reverse a noising process. A common approac
arXiv:2606.12629v3 Announce Type: replace-cross Abstract: The standard basis of transformer hidden states is a training-free, architecture-general feature basis for detecting concepts and, in language
The Solutions team @MistralAI is hiring globally! If you’re entrepreneurial, hands-on, and want to shape how enterprises adopt AI, let’s talk. Apply: https://mistral.ai/careers/?utm_source=linkedin&ut
This is confusing... Claude Cowork was a purposefully more secure (& slightly weaker) alternative to Code designed so non-coders couldn't cause too much trouble. I got that. But I don't understand wha
arXiv:2603.27742v2 Announce Type: replace Abstract: Vision-language agents that orchestrate specialized tools for image restoration (IR) have emerged as a promising method, yet most existing framework
arXiv:2507.10881v2 Announce Type: replace Abstract: Tubular tree structures, such as blood vessels and airways, are essential in human anatomy and accurately tracking them while preserving their topol
arXiv:2607.06601v1 Announce Type: cross Abstract: Conditional computation can decouple language model quality from per-token inference cost, yet leading techniques act on a single axis in isolation: M
Cognition AI announced new features or capabilities for Devin (their AI software engineer tool) that are now available across Devin Cloud, Devin Desktop, and Devin CLI, with additional details availab
arXiv:2607.07438v1 Announce Type: new Abstract: Action Quality Assessment (AQA) aims to evaluate how well a person performs a movement, which is essential in applications such as sports scoring, skill
u guys were clowning on @greptile but turns out they were just the inspo for @openai to go so, so much harder https://x.com/JangLawrenceK/status/2075204015890325703 guys I just cancelled my Claude pla
On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions this signal is beneficial and under which it is detrimental
arXiv:2607.06987v1 Announce Type: new Abstract: Reinforcement learning (RL) has become the standard paradigm for enhancing the complex reasoning capabilities of large language models (LLMs). To achiev
arXiv:2607.07416v1 Announce Type: new Abstract: Semi-supervised 3D medical image segmentation reduces the need for dense voxel-level annotations by exploiting unlabeled volumes. Although existing meth
We built a plugin that traces every Claude Code session straight into LangSmith. Three commands, one JSON block, and every message, tool call, and subagent run shows up as an inspectable trace. Setup
Perplexity conducted a cost efficiency comparison of language models, using GLM 5.2 as the baseline metric for cost per task. Results showed GLM 5.2 with an advisor achieved 2.1x cost efficiency on th
arXiv:2607.07395v1 Announce Type: cross Abstract: Reliable confidence estimation remains a key limitation of test-time adaptation in vision-language models (VLMs), where prompt tuning improves zero-sh
This post documents a Wordle game result (puzzle #1,845) played by Anthropic, showing the progression of guesses through color-coded tile feedback until reaching the correct five-letter word solution
1/3 Best-of-N leaves $$ on the table by not accounting for variance in task difficulty. We built budget-aware execution: turn the dial on compute or speed, while keeping quality constant, to save cost
2/3 By building a reliable early stopping mechanism, we could apply cascading (save up to 44% compute by not running unnecessary rollouts ) or parallel execution (up to 25% faster by sparing wait time
arXiv:2606.13566v2 Announce Type: replace Abstract: Current discussions of AI in scientific discovery are often dominated by two visible capabilities: search over existing knowledge and execution thro
Federal contracting software startup Arkenstone Defense Inc. formally launched today with 35 million in new funding to take on the compliance, security and workforce setup that keeps many commercial t
Artificial Analysis assessment SpaceXAI just released Grok 4.5, and it ranks #4 on GDPval-AA v2 with an Elo of 1543 - behind only the latest Claude releases from Anthropic on real-world agentic knowle
b9908 is a build-tagged release from llama.cpp , the open-source C/C++ inference engine for large language models. llama.cpp is an open-source software library that performs inference on various large
B9932 is a continuous build-tagged release from the llama.cpp project , an open-source C/C++ inference engine for running large language models locally. llama.cpp performs inference on various large l
arXiv:2607.05773v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making. We introduce A
Box Agent uses @LangChain’s Deep Agents harness to bring specialized agents into the enterprise content platform.w @NVIDIA + LangChain’s work with Nemotron 3 Ultra reinforces where AI is headed: open,
arXiv:2607.05469v1 Announce Type: cross Abstract: Unsupervised graph clustering is a fundamental technique for uncovering underlying semantic patterns in large-scale networks. Although Graph Contrasti
arXiv:2607.06335v1 Announce Type: new Abstract: Diffusion models generate high-quality images, but their inference cost comes from two sources: large denoising networks and repeated denoising steps. E
In this post, you build and connect that server end to end. You will implement MCP tools, set up two-layer JSON Web Token (JWT) authentication, deploy with AWS Cloud Development Kit (AWS CDK), and con
arXiv:2412.10860v2 Announce Type: replace-cross Abstract: Quantum Support Vector Machine is a kernel-based approach to classification problems. We study the applicability of quantum kernels to financi
dcode <> nemotron 3 ultra <> OpenShell 🔥 Never been easier to own your agent IP! Introducing the NemoClaw Deep Agents Blueprint, a reference architecture for building open agent systems developed with
arXiv:2607.05830v1 Announce Type: cross Abstract: The increasing uncertainty from flexible demand and renewable generation has made distributionally robust optimization (DRO) an important tool for rob
arXiv:2607.05546v1 Announce Type: cross Abstract: We develop a unified function space theory of deep fully connected neural networks. Functions in our spaces are defined recursively as ell^1-bounded l
arXiv:2607.06523v1 Announce Type: new Abstract: Long-context language model inference is increasingly limited by the memory bandwidth and capacity required to store key-value caches, yet existing comp
Didn't even have time to write up thoughts on my early access to the new GPT voice, but it is really good & much closer to the science fiction experience of talking to AI (in part because it is much s
arXiv:2607.05995v1 Announce Type: cross Abstract: We propose a novel approach to mine patterns in spatio-temporal event data based on discovering frequent closed embedded sub-Directed Acyclic Graphs (
arXiv:2607.05645v1 Announce Type: new Abstract: Deep-learning-based climate downscaling aims to learn relationships from historical low-resolution (LR) and high-resolution (HR) climate data to generat
arXiv:2607.05908v1 Announce Type: new Abstract: Real-world data distributions evolve over time, inducing temporal distribution shift that can substantially degrade the reliability of deployed machine
arXiv:2607.06258v1 Announce Type: new Abstract: Is word acquisition in children uneven with respect to semantic and lexical categories? To answer this question, we model early language learning as a s
arXiv:2607.05933v1 Announce Type: cross Abstract: Dynamic Voltage Frequency Scaling (DVFS) on resource-constrained embedded GPU platforms is essential for energy-efficient small language model (SLM) f
arXiv:2607.06150v1 Announce Type: new Abstract: Reliable seam segmentation is essential for autonomous robotic welding in construction, where harsh illumination, specular reflections, and thin weld ge
Enterprises don’t just need agents that perform. They need agents they can shape, govern and improve as their business evolves. That’s the idea behind our work with LangChain. Read more: https://nvda.
arXiv:2607.06327v1 Announce Type: cross Abstract: Uncertainty estimation (UE) enables LLM-powered systems to recognize when to abstain, yet existing research has predominantly focused on English. We p
Excited to team up with partners across the AI infrastructure + enterprise ecosystem. @EY_US @baseten @FireworksAI_HQ @nebiusai @CrusoeAI @DeepInfra @togethercompute Introducing the NemoClaw Deep Agen
Fable feels very different than Opus. GPT-5.6 feels like a part of the GPT-5 family. I developed a very complex set of heuristics about when to use which. Fable was often “smarter” but was also too se
arXiv:2607.05553v1 Announce Type: new Abstract: Transient stability control in smart grids requires rapid post-fault damping of generator frequency and rotor angle deviations to prevent cascading fail
arXiv:2607.05891v1 Announce Type: cross Abstract: Coreset selection aims to identify a small and highly representative subset of a massive dataset for efficient model training. The problem remains cha
arXiv:2607.06514v1 Announce Type: new Abstract: We present FootsiesGym, an open-source environment for learning in a non-trivial two-player, zero-sum, imperfect-information game. Built on HiFight's mi
arXiv:2607.05780v1 Announce Type: cross Abstract: While humans readily repurpose a book, a stone, or a shoe to drive a nail, robots trained on specific tools fail to transfer the same function to nove
Radhika Rajkumar / ZDNET: Former GitHub CEO Thomas Dohmke's Entire launches a decentralized Git network to handle high coding agent traffic, with servers in the US, the EU, and Australia — ZDNET's key
arXiv:2607.06269v1 Announce Type: new Abstract: Current large language models (LLMs) are fundamentally stateless: their behavior is fully determined by input at inference time, and any higher-order co
arXiv:2607.05543v1 Announce Type: cross Abstract: Semantic occupancy provides a structured spatial memory for embodied indoor agents by jointly representing occupied regions, observed free space, unkn
GLM-5.2 on Ollama's cloud just got more capacity in US & Europe! Ollama's cloud for GLM 5.2 consistently delivers between 80 to 120 output tokens per second, even during peak hours, compared to 30 to
gpt-5.6 sol isnt the only thinking launching thursday we're also releasing a big update to OpenWiki (auto create wikis of code bases... and more?) we're also going live with a webinar to talk all thin
OpenAI launched GPT-Live, a next-generation voice feature for ChatGPT that enables more natural, real-time voice interactions with the AI. The feature represents an advancement in conversational AI ca
arXiv:2607.06546v1 Announce Type: cross Abstract: Denoising graphs is a fundamental problem in graph learning and the core operation of graph diffusion models. Attention-based architectures like graph
arXiv:2601.20753v4 Announce Type: replace Abstract: Preference-Conditioned Policy Learning (PCPL) in Multi-Objective Reinforcement Learning (MORL) approximates diverse Pareto-optimal solutions by cond
Great writeup from the University of Oxford. It's a taxonomy of LLM-based agent limitations. Good read for anyone shipping with agents. Benchmark scores keep climbing, yet the same agent failures resu