Knowledge catalogue
arXiv:2606.07229v1 Announce Type: cross Abstract: We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose ins
arXiv:2606.06746v1 Announce Type: new Abstract: Deep reinforcement learning (RL) algorithms often suffer from low run-to-run robustness, manifesting as significant performance variation across indepen
Phoenix crossed 10,000 GitHub stars. Here is how the open-source AI observability project grew from a Jupyter notebook extension into a community-shaped platform for traces, evals, OpenInference, and
arXiv:2606.07437v1 Announce Type: cross Abstract: The ISO 26262 standard defines functional safety for road vehicles through risk assessments based on Severity, Exposure, and Controllability, grounded
arXiv:2606.07401v1 Announce Type: new Abstract: Document parsing systems are increasingly deployed in high-stakes, regulated workflows such as mortgage underwriting, financial reporting, supply-chain
arXiv:2602.16073v2 Announce Type: replace-cross Abstract: Developing autonomous driving systems for complex traffic environments requires balancing multiple objectives, such as avoiding collisions, ob
For some industries and dev orgs, this will happen already in 2026. For others, it may take until 2030. A short list of key differences for whether orgs will reach that level soon or later: • How much
Super-powerful AI models will launch in the coming weeks. We are looking at a potential step change in model capabilities. The biggest mistake right now is to lock into one vendor. I say this not only
arXiv:2606.05692v1 Announce Type: cross Abstract: Deep learning has enabled significant advances in time-series causal inference, yet progress remains constrained by the lack of realistic benchmarks w
arXiv:2606.05463v1 Announce Type: new Abstract: Patient safety event triage, determining whether a clinical event is reportable under jurisdiction-specific policy, is a high-stakes task typically perf
arXiv:2602.19373v3 Announce Type: replace-cross Abstract: Deep reinforcement learning systems often suffer from unstable training dynamics due to non-stationarity, where learning objectives and data d
Your margin is my opportunity: AI version… The biggest surprise of 2026 is that the capability gap between the best open-weight/source models and the best closed models has narrowed much faster than t
arXiv:2606.05168v1 Announce Type: new Abstract: Training on synthetic data causes model collapse, but existing analyses treat this as single-chain degradation. In reality, the AI ecosystem involves cr
arXiv:2512.21430v2 Announce Type: replace Abstract: Visuomotor policies based on generative such as diffusion and flow-matching have shown strong performance for robotics applications but degrade unde
arXiv:2606.05873v1 Announce Type: cross Abstract: Humanoid robots hold great promise for operating in human-centered environments, yet ladder climbing remains one of the most challenging tasks due to
arXiv:2606.05744v1 Announce Type: new Abstract: Spatial planning maps are central to territorial governance, translating planning objectives, regulations, and spatial strategies into visual forms for
# Reality: The Final Eval This post argues that real-world task completion rate is the ultimate metric for evaluating AI systems, prioritizing actual production performance over benchmark scores like
arXiv:2606.05901v1 Announce Type: new Abstract: Large language models (LLMs) have fundamentally transformed the landscape of Natural Language Processing. Despite these advances, LLMs and LLM-based sys
arXiv:2606.05506v1 Announce Type: new Abstract: We propose a sensor-guided adaptive contrastive learning framework for visual representation learning in PointGoal navigation. During training, privileg
arXiv:2606.05660v1 Announce Type: new Abstract: Embodied AI systems are increasingly expected to reason and act over extended horizons in physical environments. This growing capability brings safety t
arXiv:2606.05563v1 Announce Type: cross Abstract: Evaluating LLM mediators remains challenging, as mediation unfolds as a real-time trajectory shaped by disputants' shifting emotions, intentions, and
arXiv:2606.05436v1 Announce Type: cross Abstract: Summarizing the latest medical literature to guide clinical decision-making is essential for evidence-based medicine and high-quality patient care. Ye
The NVIDIA Nemotron Coalition continues to grow. We're excited to welcome new members: @hcompany_ai, @NousResearch, and @PrimeIntellect. And a big thank you to our existing members: @bfl_ai, @cursor_a
arXiv:2606.04172v1 Announce Type: new Abstract: Task-conditioned manipulation requires grounding instructions to task-relevant functional parts rather than object categories. This setting is scene-dep
AI enthusiasts are in a race against time, AI skeptics are in a race against entropy Charity Majors neatly captures the dynamic between AI enthusiasts and AI skeptics, both of whom are trying to build
Enterprise AI is entering a new phase where competitive advantage depends less on foundation models and more on the ability to connect data and business knowledge through an enterprise context layer.
arXiv:2603.03482v2 Announce Type: replace-cross Abstract: Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities. However, e
arXiv:2603.23420v2 Announce Type: replace Abstract: If autoresearch is itself a form of research, then autoresearch can be applied to research itself. We present Bilevel Autoresearch, a bilevel framew
arXiv:2509.10247v1 Announce Type: cross Abstract: This letter introduces DiffAero, a lightweight, GPU-accelerated, and fully differentiable simulation framework designed for efficient quadrotor contro
arXiv:2606.04206v1 Announce Type: new Abstract: We address the challenge of enabling robots to manipulate deformable linear objects (DLOs), such as ropes, cables, and rubber bands. Prior work has prim
Enterprise AI usage leaderboards are BAD and lead to the wrong behaviors. Employees feel pressure to hit higher token usage numbers without any of the positive work transformation. I’ve heard directly
arXiv:2606.04282v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are predominantly evaluated on free-form vision-language tasks such as visual question answering, captioning, a
Highlighting recent advances in multi-GPU and tensor parallel support in llama.cpp Over the last few months llama.cpp maintainers and engineers from NVIDIA collaborated to improve the multi-GPU perfor
arXiv:2606.04534v1 Announce Type: new Abstract: Agile quadrotor flight in cluttered scenes requires more than a reactive mapping from a depth image to a control command: the vehicle must remember whic
arXiv:2606.04569v1 Announce Type: new Abstract: Underground mines present extreme conditions for autonomous robot navigation: GPS is denied, lighting is degraded, and tunnel topology is loop-rich and
The search results primarily discuss the Nemotron 3 Nano Omni model rather than Nemotron 3 Ultra. However, I found a recent NVIDIA blog post reference that indicates Nemotron 3 Ultra is available thro
On TV Tokyo’s WBS (@wbs_tvtokyo) tonight I’ll be discussing Sakana AI’s upcoming 1T parameter model project, supported by METI’s GENIAC initiative. We are scaling up to build Japan’s first 1T paramete
arXiv:2604.01161v2 Announce Type: replace Abstract: Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remar
arXiv:2606.04923v1 Announce Type: cross Abstract: Rubric-based reinforcement learning (RL) uses an LLM-as-a-Judge (LaaJ) to score model outputs according to rubrics as rewards. However, policy models
arXiv:2606.04507v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become increasingly adopted in daily applications, with deep research standing out as a particularly important capab
arXiv:2606.04735v1 Announce Type: cross Abstract: Temporal credit assignment is central to both biological and artificial intelligence, yet its interaction with non-linear function approximation is po
Healthcare AI is moving out of the pilot phase and into production environments, where the gap between a compelling demo and a clinically trustworthy output has never been more consequential. As AI ag
We're presenting ParseBench at CVPR 2026! ParseBench is the most comprehensive document understanding benchmark for VLMs. ✅ It contains 2k pages of real-world enterprise documents ✅ It has comprehensi
what makes building on replit different? it all happens in one place. → describe your idea in plain english, get working software → generate UI, add auth + databases, deploy → collaborate with your te
arXiv:2606.02755v1 Announce Type: cross Abstract: Large language model (LLM) applications are increasingly expected to satisfy deterministic institutional requirements while relying on probabilistic g
arXiv:2606.02775v1 Announce Type: new Abstract: The KV-cache is the right memory for datacenters but the wrong memory for robots. Datacenter inference batches many short requests and resets them, amor
arXiv:2606.02800v1 Announce Type: cross Abstract: We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences
Google DeepMind released Gemma 4 12B, an open AI model that brings multimodal capabilities to everyday laptops by processing text, images, and audio natively without separate encoders. Small enough to
Harvey just published a study showing a hybrid setup, open source GLM 5.1 as primary worker, routing to Opus 4.7 only when needed beats pure Opus 4.7 on quality and costs less. This is the multi-model
arXiv:2511.21731v2 Announce Type: replace-cross Abstract: We present the results of cognitive tests on conceptual combinations, performed using specific Large Language Models (LLMs) as test subjects.
arXiv:2603.19551v2 Announce Type: replace-cross Abstract: We develop horizon-aware anytime-valid tests and confidence sequences for bounded means under a strict deadline N. Using the betting/e-process
At Microsoft's annual Build conference on Tuesday, the company announced a slew of new or expanded AI initiatives, including a super app, in-house reasoning models, a cybersecurity tool, and OpenClaw-
arXiv:2606.02964v1 Announce Type: cross Abstract: Large Language Model (LLM) inference relies on key-value (KV) caches to avoid redundant attention computation. While approximate KV cache retention te
Nice primer on post-training reasoning data. (bookmark it) This is one of the first primers to pull the scattered post-training reasoning-data literature into one place, synthesizing over 150 public s
arXiv:2606.03159v1 Announce Type: cross Abstract: As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-lo
arXiv:2606.03743v1 Announce Type: new Abstract: While Large Language Models (LLMs) have shown strong performance in generating formal proofs, their outputs often remain less readable, modular, maintai
Routing and post-training open-source models won't only give you more accurate systems but also meaningfully faster and cheaper systems as most companies are currently learning (in addition to giving
arXiv:2606.03301v1 Announce Type: new Abstract: We introduce SagaQA, a long-form video benchmark for multi-hop reasoning over full-length TV series. Existing video reasoning benchmarks often emphasize
arXiv:2606.03026v1 Announce Type: cross Abstract: Spiking language models expose activation sparsity that dense Transformer runtimes do not directly exploit. This paper studies that property from a sy
Two bits here I think we're going to see a lot more: 1. custom harnesses / finetunes on smaller open source models to beat frontier models at specific skill or task 2. using frontier models as critics