Knowledge catalogue
arXiv:2605.14612v1 Announce Type: cross Abstract: AI-enabled features built on LLMs and agentic workflows are difficult to test, debug, and reproduce, especially for product-focused software engineers
'In the past nine months, the United States has produced more AI legislation than in the prior decade,' write @JeffSonnenfeld, @GaryMarcus, and Stephen Henriques in a commentary piece for Fortune. 'No
Release: inaturalist-clumper 0.1 Part of the infrastructure I use for publishing my iNaturalist sightings on my blog. I've been running this in production for a few weeks now, inspiring some iteration
Pramugdha Mamgain / DealStreetAsia: Indian ride-hailing app Rapido raised 240M led by Prosus as part of a broader primary and secondary financing transaction, valuing Rapido at 3B post-money — Ride-ha
arXiv:2605.13871v1 Announce Type: cross Abstract: This paper presents a novel population-based metaheuristic, Indian Wedding System Optimization (IWSO), inspired by the socio-cultural dynamics of trad
Inference is becoming the largest compute market and energy consumer in AI. Pearl turns inference CapEx of hyperscalers into a profit center: every LLM token produced by GPUs can simultaneously genera
arXiv:2605.14967v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) provides the standard approach for teaching LLMs new behaviors from offline expert demonstrations. However, standard SFT un
arXiv:2605.14333v1 Announce Type: new Abstract: Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregr
arXiv:2605.14455v1 Announce Type: new Abstract: The Intelligence Impact Quotient (IIQ) is a composite metric intended to quantify the depth to which AI systems are integrated into organizational work
arXiv:2605.14712v1 Announce Type: cross Abstract: Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators
arXiv:2605.14831v1 Announce Type: new Abstract: One of the bottlenecks on the way towards recursively self-improving systems is the challenge of interestingness: the ability to prospectively identify
Introducing Gemma-4-31B-it-Pearl on Together AI, Pearl Research Labs’ instruction-tuned checkpoint of Gemma 4 31B powered by @prlnet Proof of Useful Work protocol. AI natives can now use this Pearl mo
arXiv:2605.13851v1 Announce Type: new Abstract: Multi-agent orchestration -- in which a hidden coordinator manages specialized worker agents -- is becoming the default architecture for enterprise AI d
arXiv:2511.15407v3 Announce Type: replace Abstract: Humans learn by observing, interacting with environments, and internalizing physics and causality. Here, we aim to ask whether an agent can similarl
arXiv:2605.15184v1 Announce Type: new Abstract: Recent advances in Large Language Model (LLM) agents have enabled complex agentic workflows where models autonomously retrieve information, call tools,
𝕏 is the mind of humanity If you want to reach senior decision makers, most influential people, company owners, most intellectual people of the world, then the 𝕏 platform is by far the best. They are
arXiv:2602.12105v2 Announce Type: replace-cross Abstract: We propose a system for differentiating through solutions to geometry processing problems. Our system differentiates a broad class of geometri
arXiv:2605.14736v1 Announce Type: cross Abstract: Target speech extraction remains difficult for compact devices because monaural neural models lack spatial evidence and classical beamformers lose res
it almost never makes sense to use real api's for your evals. with how good coding agents have become, i will pretty much always opt to create a fake mock server for my agent to hit. the workflow is u
It has been a pleasure collaborating with the @NVIDIAAI team to ensure that Hermes Agent runs perfectly on DGX Spark! Run @NousResearch's Hermes Agent fully locally on DGX Spark. 🚀 Our newest playbook
arXiv:2510.00977v3 Announce Type: replace-cross Abstract: GRPO has emerged as a prominent reinforcement learning algorithm for post-training LLMs. Unlike critic-based methods, GRPO computes advantages
it’s kind of awesome that continual learning has now come to the agent & harness level. i remember when online learning was the big craze in traditional ml a couple of years ago, that transitioned int
arXiv:2512.12772v2 Announce Type: replace-cross Abstract: Understanding videos inherently requires reasoning over both visual and auditory information. To properly evaluate Omni-Large Language Models
𝕏 (formerly Twitter) open-sourced its 'For You' recommendation algorithm, marking a significant transparency initiative by the social platform. This move allows developers and researchers to examine h
𝕏 just open sourced the latest recommendation algorithm on GitHub 𝕏 is the only major social platform in the world to publicly open source its core recommendation algorithm It is by far the most trans
arXiv:2605.14828v1 Announce Type: cross Abstract: Existing clustering methods for functional data often prioritize partitioning accuracy over interpretability, making it challenging to extract meaning
arXiv:2509.25826v3 Announce Type: replace Abstract: Inherent temporal heterogeneity, such as varying sampling densities and periodic structures, has posed substantial challenges in zero-shot generaliz
Key ideas I picked up at the @LangChain conference this week: 'AI engineering is data science. Look at your data.' — @sh_reya & @HamelHusain 'Data strategy *before* agents.' — @AndrewYNg 'Coding agent
arXiv:2605.14123v1 Announce Type: cross Abstract: Feature sharing via split inference offers a lightweight alternative to federated learning for resource-constrained hospitals, but transmitted feature
arXiv:2605.14907v1 Announce Type: new Abstract: Knowledge graph (KG) foundation models aim to generalize across graphs with unseen entities and relations by learning transferable relational structure.
Bloomberg: Kioxia reports record Q4 earnings of ~3.8B, forecasts Q1 operating profit of ~8.2B, and says it is planning a US listing; Kioxia shares are up 300% YTD — Kioxia Holdings Corp., the world's
arXiv:2605.14062v1 Announce Type: new Abstract: While synthetic data generation with large language models (LLMs) is widely used in post-training pipelines, existing approaches typically generate full
arXiv:2605.14404v1 Announce Type: new Abstract: While LLMs are increasingly used in commercial services, they pose privacy risks such as leakage of sensitive personally identifiable information (PII).
arXiv:2605.14786v1 Announce Type: cross Abstract: As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model po
arXiv:2511.07686v2 Announce Type: replace-cross Abstract: Chemical Reaction Neural Networks (CRNNs) have emerged as an interpretable machine learning framework for discovering reaction kinetics direct
arXiv:2602.11534v3 Announce Type: replace-cross Abstract: Self-attention in Transformers relies on globally normalized softmax weights, causing all tokens to compete for influence at every layer. When
arXiv:2605.14278v1 Announce Type: new Abstract: Aligning streaming autoregressive (AR) video generators with human preferences is challenging. Existing reinforcement learning methods predominantly rel
arXiv:2601.21349v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models scale neural networks by conditionally activating a small subset of experts, where the router plays a central
arXiv:2605.14527v1 Announce Type: new Abstract: Developing machine learning interatomic potentials (MLIPs) for complex materials systems remains challenging because it requires expertise in atomistic
@LangChain’s Interrupt 2026 conference was a blast!! such a pleasure to with @VictorMoreira16 about deep agents! ICYMI: we just dropped v0.6, which is focused on performance at the model, harness, and
arXiv:2605.14531v1 Announce Type: new Abstract: This work reformulates language generation as a stochastic optimal control problem, providing a unified theoretical perspective to analyze autoregressiv
arXiv:2605.14301v1 Announce Type: new Abstract: Domain adaptation faces a fundamental paradox in the cold-start regime. When target data is scarce, statistical methods fail to distinguish relevant sou
arXiv:2605.14524v1 Announce Type: cross Abstract: Recent studies have reported extit{saturation effects} and extit{multiple descent behavior} in large dimensional kernel ridge regression (KRR). Howeve
arXiv:2605.13873v1 Announce Type: cross Abstract: Web accessibility aims to ensure that web content and services are usable by people with diverse abilities. In recent years, Large Language Models (LL
arXiv:2605.14241v1 Announce Type: new Abstract: Tool-augmented LLM agents increasingly access the same tool type through multiple functionally equivalent providers, such as web-search APIs, retrievers
arXiv:2605.15054v1 Announce Type: new Abstract: Vision-language models (VLMs) have recently emerged as a promising paradigm for video anomaly detection (VAD) due to their strong visual reasoning abili
arXiv:2510.00757v3 Announce Type: replace Abstract: Graph neural networks (GNNs) largely rely on the message-passing paradigm, where nodes iteratively aggregate information from their neighbors. Yet,
arXiv:2605.14805v1 Announce Type: new Abstract: Accurate dynamics models are critical for aerial manipulators operating under complex tasks such as payload transport. However, modeling these systems r
arXiv:2605.14998v1 Announce Type: new Abstract: From subcellular structures to entire organisms, many natural systems generate complex organisation through self-organisation: local interactions that c
arXiv:2605.14832v1 Announce Type: cross Abstract: We present a flow-matching planner for autonomous driving that directly outputs actionable control trajectories defined by acceleration and curvature
arXiv:2602.21302v2 Announce Type: replace Abstract: We introduce a Task-Level Iterative Learning Control method for dynamic manipulation of ropes. We demonstrate this method on a non-planar rope manip
arXiv:2605.14539v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language mo
arXiv:2605.15113v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning
arXiv:2512.02920v3 Announce Type: replace-cross Abstract: We consider analyzing traffic accident patterns using both road network data and satellite images aligned to road graph nodes. Previous work f
arXiv:2605.14494v1 Announce Type: new Abstract: Two-Stage Robust Optimization (2RO) with discrete uncertainty is challenging, often rendering exact solutions prohibitive. Scenario reduction alleviates
arXiv:2601.21151v2 Announce Type: replace Abstract: Recent machine-learning approaches to weather forecasting often employ a monolithic architecture in which distinct physical mechanisms-advection (lo
arXiv:2605.14392v1 Announce Type: new Abstract: We pursue a vision for self-improving language models in which the model does not merely generate problems or traces to imitate, but constructs the envi
arXiv:2605.14346v1 Announce Type: new Abstract: Single-frame Infrared Small Target Detection (ISTD) aims to localize weak targets under heavy background clutter, yet dense pixel-wise annotations are e
arXiv:2605.14927v1 Announce Type: new Abstract: The success of deep learning in high-dimensional settings is often attributed to the presence of low-dimensional structure in real-world data. While sta
arXiv:2605.14483v1 Announce Type: new Abstract: Large language models (LLMs) have become a strong foundation for multi-agent systems, but their effectiveness depends heavily on orchestration design. A