Knowledge catalogue
arXiv:2605.07395v1 Announce Type: cross Abstract: Efficient routing across multiple LLMs enables cost-quality tradeoffs by directing queries to the cheapest capable model. Prior work attributes routin
arXiv:2603.09742v2 Announce Type: replace Abstract: Neural oscillators that originate from second-order ordinary differential equations (ODEs) have shown competitive performance in learning mappings b
arXiv:2509.11777v2 Announce Type: replace Abstract: Customer feedback in industrial forums offers rich but underexplored insights into real-world product experience. Yet systematic analysis remains ch
TIL: Using LLM in the shebang line of a script Kim_Bruning on Hacker News: But seriously, you can put a shebang on an english text file now (if you're sufficiently brave) [...] This inspired me to loo
arXiv:2602.16571v2 Announce Type: replace Abstract: Large-scale sharing of dialogue data is key to advancing the science of teaching and learning, yet rigorous de-identification remains a major barrie
This release fixes a macOS 26 target leakage issue in the v3 metallib component for the MLX framework. The fix addresses a problem where Metal library compilation was incorrectly targeting macOS 26, w
This release candidate addresses a macOS 26 target leakage issue in the v3 metallib component of Ollama, a machine learning framework. The fix prevents incorrect macOS version targeting that was affec
The search did not return specific information about v0.30.0-rc13. Based on the version designation and source, this is a release candidate for Ollama v0.30.0. As a pre-release version, it likely cont
This is a release candidate version of Ollama that merges updates from the main development branch into the llama-runner-phase-0 branch, likely incorporating bug fixes and features in preparation for
arXiv:2605.07481v1 Announce Type: cross Abstract: In this paper, we investigate the recent state-of-the-art schemes for watermarking large language models (LLMs) outputs. These techniques are claimed
arXiv:2605.07292v1 Announce Type: new Abstract: We prove that aerodynamic co-contraction in a redundant dual-rotor actuator can tune a passive, trim-defined aero-mechanical damping while keeping the c
arXiv:2603.05539v2 Announce Type: replace-cross Abstract: We introduce VDCook: a self-evolving video data operating system, a configurable video data construction platform for researchers and vertical
arXiv:2508.02129v2 Announce Type: replace Abstract: Dynamic urban scene modeling is a rapidly evolving area with broad applications. While current approaches leveraging neural radiance fields or Gauss
arXiv:2605.08070v1 Announce Type: new Abstract: A standard technique for scaling inference-time reasoning is Self-Consistency, whereby multiple candidate answers are sampled from an LLM and the most c
arXiv:2605.07385v1 Announce Type: cross Abstract: Editing a 3D asset locally, modifying a target region while preserving the rest, is a fundamental requirement of native 3D editing. Existing methods e
Jay Peters / The Verge: Venmo implements a major privacy measure, setting new users' posts to “friends only” by default during onboarding; in 2021, a reporter found Joe Biden's Venmo — As part of a b
Vercel has enhanced its Sandbox firewall feature to include request proxying and filtering capabilities, allowing developers to have greater control over network traffic within their sandboxed environ
arXiv:2508.02001v2 Announce Type: replace-cross Abstract: Pervasive encryption makes large-scale labeling infeasible for traffic analysis, while security operations demand edge analysis to avert servi
arXiv:2602.10693v3 Announce Type: replace-cross Abstract: Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous t
arXiv:2508.06819v3 Announce Type: replace Abstract: The task of parsing subcutaneous vessels in clinical images is often hindered by the high cost and limited availability of ground truth data, as wel
arXiv:2605.07751v1 Announce Type: cross Abstract: Early 2025 we ran a series of vibe coding challenges across four different student cohorts. The cohorts included 54 ICT students, 24 digital marketing
arXiv:2506.21582v5 Announce Type: replace-cross Abstract: Text analytics has traditionally required specialized knowledge in Natural Language Processing (NLP) or text analysis, which presents a barrie
arXiv:2605.07872v1 Announce Type: cross Abstract: Multimodal reward models have advanced substantially in text and image domains, yet progress in video understanding reward modeling remains severely l
arXiv:2605.05848v2 Announce Type: replace-cross Abstract: Video large multimodal models increasingly face a scalability bottleneck: long videos produce excessively long visual-token sequences, which s
arXiv:2605.07552v1 Announce Type: new Abstract: The rapid advances in deep learning have significantly enhanced the accuracy of multimodal 3D human pose estimation (HPE). However, the state-of-the-art
arXiv:2605.06094v2 Announce Type: replace-cross Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignme
arXiv:2605.06708v1 Announce Type: cross Abstract: Visual text compression (VTC) promises efficient long-context processing by rendering text into an image and re-encoding it with a vision-language mod
arXiv:2605.06765v1 Announce Type: cross Abstract: Human speech conveys expressiveness beyond linguistic content, including personality, mood, or performance elements, such as a comforting tone or humm
arXiv:2605.06175v2 Announce Type: replace Abstract: Vision-language-action (VLA) models inherit rich visual-semantic priors from pre-trained vision-language backbones, but adapting them to robotic con
arXiv:2605.07451v1 Announce Type: new Abstract: Neural network verification is an active and rapidly maturing research area, with a growing ecosystem of solvers and tools. The VNN-LIB standard was int
We don't have to accept the way AI is going. The biggest companies building AI aren't building it for us. They're building it to replace us. We’ve made a roadmap for how we can build pro-human AI: htt
“we gonna yolo our way into running the biggest conf in town.” and somehow… we actually did it with @aiDotEngineer singapore a year ago, @agrimsingh @unprofeshme and i joked about the idea of running
We just published the demo video from our latest @DBOS_Inc user group! Big thanks to Adrian Lyjak from @llama_index for walking through the DBOS integration with LlamaAgents, an open-source Python fra
We just wrapped recording with @jerryjliu0 of @llama_index 👀 His thesis: the AI framework era is over. Scaffolding collapses into the model. Context quality = moat that survives. Frontier models still
This post likely reflects on the historical costs of traditional media production and distribution, possibly comparing past spending on storytelling (such as television or film production) to modern,
arXiv:2605.07367v1 Announce Type: cross Abstract: Cameras and LiDAR degrade in rain, fog, and snow, while millimeter-wave radar remains largely unaffected. We align a radar encoder to frozen SigLIP vi
arXiv:2605.07522v1 Announce Type: new Abstract: Accurate weather forecast reporting enables individuals and communities to better plan daily activities and agricultural operations. However, the curren
arXiv:2602.12852v2 Announce Type: replace Abstract: Deep Research systems based on web agents have shown strong potential in solving complex information-seeking tasks, yet their search efficiency rema
arXiv:2605.06761v1 Announce Type: new Abstract: The web is complex, open-ended, and constantly changing, making it challenging to scale training data for visual web agents. Existing data collection at
📣We're calling for ambassadors! Whether you're a developer with great technical taste or a local community leader who loves bringing people together, we'd love to have you join us. Visit the website b
Hugging Face is releasing two open-source Small Language Models (SLMs) this week, with one achieving state-of-the-art accuracy while being up to 93x smaller than comparable models, and the other outpe
OpenAI announced the acquisition of Tomoro, a company that will add 150 experienced Forward Deployed Engineers and Deployment Specialists to OpenAI's team. This acquisition appears focused on expandin
We’ve temporarily suspended new free-tier account creation on Comfy Cloud due to a recent abuse incident targeting high-cost video generation models. Importantly, - All existing paid accounts and cred
what i have been saying for 6 years. maybe now you will believe it? 📁 Fei-Fei Li, former Google Chief Scientist, says the industry is dangerously fixated on language models. Most of the real economy i
arXiv:2605.07896v1 Announce Type: cross Abstract: The rapid convergence of artificial intelligence (AI) toward conversational chatbot interfaces marks a critical moment for the industry. This paper ar
arXiv:2605.07915v1 Announce Type: new Abstract: Tokenizers are a crucial component of latent diffusion models, as they define the latent space in which diffusion models operate. However, existing toke
What will we be like when he is gone? Can we return to mutual respect? Can we believe we are all on the same team as Obama and McCain did? Can we imagine the mutual respect of those two, competitors b
arXiv:2605.07260v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models route each token to a small subset of experts, but whether the routes selected by a trained top-k router are
arXiv:2605.06868v1 Announce Type: new Abstract: Fixed-budget nonconvex optimization can fail not because local descent is unstable, but because it is too stable: after reaching a nearby stationary poi
arXiv:2605.07969v1 Announce Type: new Abstract: Diffusion models perform remarkably well on high-dimensional data such as images, often using only a modest number of reverse-time steps. Despite this p
arXiv:2605.06723v1 Announce Type: new Abstract: Language models often generate reasoning before giving a final answer, but the visible answer does not reveal when the model's answer preference became
arXiv:2605.06772v1 Announce Type: new Abstract: As large language models (LLMs) show increasing promise on research-level physics reasoning tasks and agentic AI becomes more common, a practical questi
arXiv:2602.09229v3 Announce Type: replace Abstract: Cosine similarity normalizes both sides; dot product normalizes neither. We propose a 2x2 framework that independently controls query-side and docum
arXiv:2605.07756v1 Announce Type: cross Abstract: Modern deep models are often pretrained on large-scale data with missing labels using composite objectives, where the relative weights of multiple los
arXiv:2605.06731v1 Announce Type: cross Abstract: Personalized LLM agents maintain persistent cross-session state to support long-horizon collaboration. Yet, this persistence introduces a subtle but c
arXiv:2605.07313v1 Announce Type: new Abstract: Memory-agent evaluations report fixed-snapshot accuracy or retrieval quality, but these scores do not show whether evidence remains usable as irrelevant
arXiv:2605.07120v1 Announce Type: new Abstract: Template tasks have emerged as a clean testbed for asking whether transformers reason with abstract symbols rather than concrete token names. We study t
arXiv:2605.07114v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a central paradigm for improving the reasoning capabilities of large language model
arXiv:2605.07984v1 Announce Type: cross Abstract: We study planning site formation in language models -- where internal representations of structurally-constrained future tokens form during the forwar
Which has better odds? Generative AI earning $1.6 trillion/year or the roulette wheel landing on zero? One estimate of how much annual revenue AI needs to “make sense”: 1.6 trillion. That’s four times