Knowledge catalogue
Clem Delangue discusses a resurgence of interest in decentralized intelligence systems and approaches, suggesting a shift away from centralized AI models toward more distributed architectures. The pos
arXiv:2606.18729v2 Announce Type: replace-cross Abstract: Data valuation quantifies the intrinsic quality of individual samples to enable principled data curation, quality control, and robust learning
arXiv:2606.24498v1 Announce Type: new Abstract: Grounding deictic gestures in natural images is fundamental to AR and human-robot collaboration, providing a basis for seamless spatial interaction. Whi
This workflow template demonstrates how to use the Seedance 2.0 R2V (Rank-to-Video) model within ComfyUI, likely enabling users to generate or process video content based on seed values and ranking pa
arXiv:2606.24842v1 Announce Type: new Abstract: In the big-world regime, agents cannot be universally capable and their ability is inevitably specialized across a world model in pieces. Consequently,
arXiv:2606.21623v1 Announce Type: new Abstract: Instruction-conditioned trajectory prediction is an emerging problem in autonomous driving, where a model predicts the future ego trajectory not only fr
arXiv:2606.20955v1 Announce Type: new Abstract: Dynamic average estimation is a critical problem in multi-agent systems, enabling agents to collaboratively estimate time-varying signals using only loc
arXiv:2606.23079v1 Announce Type: new Abstract: Neural world models coupled with model predictive control (MPC) replan at every environment step to bound accumulated prediction error, but this incurs
arXiv:2606.21177v1 Announce Type: cross Abstract: Segmenting the temporomandibular joint (TMJ) disc from MRI is essential for accurate diagnosis of internal derangement, yet it remains unreliable in p
arXiv:2606.18319v2 Announce Type: replace Abstract: Air Traffic Control Operators (ATCOs) are vital in ensuring the safe, orderly, and efficient flow of air traffic, yet training capacity is constrain
At @aiDotEngineer World's Fair next week? Come join us Tuesday night 🏓 We're co-hosting an evening at SPIN with @TheoryVC and @ollama. Talk shop with the people building the next-generation of local a
The search results do not contain specific details about the b9769 release. Based on the available information about llama.cpp and its release patterns, here is a knowledge base entry: Release b9769 o
Release b9770 of llama.cpp addresses server functionality by fixing remote preset handling and adding tests (PR #24938). The release includes pre-built binaries for multiple platforms including macOS,
llama.cpp release b9771 addresses Vulkan optimization by making mul_mm ALIGNED a spec constant, reducing shader variant explosion and binary size. This release is part of the ongoing development of ll
Release b9773 of llama.cpp adds Vulkan support for the GET_ROWS_BACK operation . The release includes pre-built binaries for multiple platforms including macOS, Linux, Windows, and Android with variou
The b9774 release of llama.cpp adds Vulkan backend support for multiple operations including SQR, SQRT, SIN, COS, CLAMP, LEAKY_RELU, and NORM functions, along with fixes for non-contiguous tensor hand
b9775 is a release of llama.cpp published on June 23, 2026 , featuring 'server: check draft context creation error' improvements . The release includes pre-built binaries across multiple platforms inc
arXiv:2606.21497v1 Announce Type: new Abstract: Modern deep neural network architectures are trained via backpropagation, which requires errors to be sequentially propagated through all layers before
arXiv:2409.15493v4 Announce Type: replace-cross Abstract: Persistent semantic monitoring of indoor spaces such as warehouses, hospitals, and offices requires a robot to repeatedly monitor an environme
GitHub Copilot App now supports Bring Your Own Key (BYOK) functionality, allowing users to integrate local and third-party AI models including Ollama, Foundry, and any OpenAI-compatible or Anthropic-c
arXiv:2606.22019v1 Announce Type: new Abstract: Subliminal learning lets a student inherit a teacher's hidden trait from distillation data that never names it. We ask when such transfer can be audited
Comfy is a project with an active social media presence on TikTok, as promoted through ComfyUI's X account. The post encourages users to follow or explore Comfy's TikTok channel for content related to
arXiv:2606.20300v2 Announce Type: replace Abstract: Few-shot anomaly detection remains challenging due to limited training data. Multi-modal anomaly detection (MAD) offers a viable solution, leveragin
arXiv:2606.21982v1 Announce Type: new Abstract: Few-step distillation for video diffusion models has attracted significant attention, driven by the urgent demand for efficient deployment in real-world
arXiv:2606.21752v1 Announce Type: cross Abstract: Histopathologic cancer detection is challenging due to tissue variability, staining differences, and subtle visual distinctions between disease classe
arXiv:2606.22804v1 Announce Type: new Abstract: Long, continuous video streams are an increasingly critical driver of multimedia intelligence. Existing efforts often handle long videos with a sample-e
This entry references a creator's Instagram account (a01demort) shared by ComfyUI, likely highlighting a digital artist or content creator who works with or showcases ComfyUI, a node-based generative
arXiv:2207.14273v2 Announce Type: replace Abstract: We present Curve Distillation, CuDi, for efficient and controllable exposure adjustment without the requirement of paired or unpaired data during tr
arXiv:2606.20765v1 Announce Type: cross Abstract: Deep learning for 3D medical image segmentation requires extensive manual annotations, a major bottleneck in volumetric medical imaging. Active learni
arXiv:2606.21212v1 Announce Type: new Abstract: Causal discovery is critical for understanding complex data-generating mechanisms, yet traditional algorithms often struggle with highly non-linear and
arXiv:2606.21158v1 Announce Type: new Abstract: Singular learning theory characterises the complexity of a deep network through the geometry of its loss singularities. The local learning coefficient (
arXiv:2603.14418v2 Announce Type: replace Abstract: Label variability is a major challenge for prostate lesion segmentation. In multi-site datasets, annotations often reflect centre-specific contourin
arXiv:2606.22040v1 Announce Type: new Abstract: Sit-to-stand (STS) transitions impose significant joint-loading demands on elderly individuals, making them a primary target for lower-limb exoskeleton
arXiv:2606.22285v1 Announce Type: new Abstract: Localizing document tampering is extremely challenging, as manipulations are crafted to appear visually consistent and often leave only subtle traces th
arXiv:2504.08061v2 Announce Type: replace Abstract: Traffic prediction is difficult due to the complex interplay of temporal evolution, spatial interactions, and delayed spatio-temporal propagation ov
arXiv:2606.20811v1 Announce Type: cross Abstract: We study the problem of system identification in heterogeneous settings, where different systems may follow distinct underlying dynamics. Existing clu
arXiv:2606.22496v1 Announce Type: cross Abstract: Large language models (LLMs) offer a natural-language interface for interpreting Internet of Things (IoT) sensor data in smart environments; however,
arXiv:2606.21646v1 Announce Type: new Abstract: Compositional diffusion planners aim to solve long-horizon robotic tasks using short training trajectories. Yet, current approaches often rely on the he
arXiv:2606.21674v1 Announce Type: new Abstract: We present ENLIGHT, a fast and training free framework for low-light image enhancement based on direct optimization of a perceptual objective. Unlike de
arXiv:2606.21384v1 Announce Type: new Abstract: Multimodal medical imaging fuses complementary anatomical and functional information, yet modalities frequently disagree in pathologically heterogeneous
arXiv:2606.22744v1 Announce Type: new Abstract: Predictive coding networks (PCNs) offer a biologically-plausible, local-learning alternative to back-propagation of errors (backprop). Nevertheless, the
arXiv:2302.14062v2 Announce Type: replace-cross Abstract: We address quality assessment for neural network based ASR by providing explanations that help increase our understanding of the system and ul
arXiv:2606.22510v1 Announce Type: new Abstract: While federated learning enables collaborative modelling on decentralised data, standard methods merely fit historical observations. This purely observa
arXiv:2606.22466v1 Announce Type: new Abstract: Federated learning (FL) is an emerging distributed machine learning paradigm that enables local devices to jointly train a global model while keeping da
arXiv:2507.18219v3 Announce Type: replace Abstract: Federated Graph Learning (FGL) is a distributed learning paradigm that enables collaborative training over large-scale subgraphs located on multiple
arXiv:2606.21373v1 Announce Type: new Abstract: Recent indoor occupancy prediction methods adopt Gaussian primitives as a sparse 3D representation for computational efficiency. However, their training
arXiv:2606.23293v1 Announce Type: new Abstract: 6D pose estimation is a key task in computer vision and embodied AI, widely used in robotic manipulation, augmented reality, etc. Existing methods direc
arXiv:2603.06467v2 Announce Type: replace Abstract: Radiology foundation models (RFMs) have largely inherited the scale-first recipe of natural-image vision--language pre-training. This recipe is diff
arXiv:2606.22834v1 Announce Type: new Abstract: We present homographic navigation, a geometry-centric framework for guiding camera acquisition toward precise capture of planar regions. Rather than tre
arXiv:2606.19538v2 Announce Type: replace-cross Abstract: Convolutional networks, recurrent networks, and transformers each encode different inductive biases -- locality, sequential memory, and conten
arXiv:2509.22307v2 Announce Type: replace Abstract: Lightweight 3D medical image segmentation remains constrained by a fundamental extit{``efficiency / robustness conflict''}, particularly when proces
arXiv:2603.05663v2 Announce Type: replace Abstract: Video Temporal Grounding (VTG) localizes the temporal boundaries of query-relevant moments in long videos, making video-language-model prohibitively
Krea 2 is back and this time the weights are OPEN. This open source release ships with two models designed to work together — @krea_ai 2 RAW and Krea 2 Turbo. RAW is for training, Turbo is for inferen
Krea x Comfy: Founders Live A special live conversation with our guests Victor Perez (CEO, Krea), Miguel Lara (Krea Team), and ComfyAnonymous (Co-Founder, Comfy Org), hosted by Purz & Julien. Today at
This appears to be a live broadcast event featuring the founders of Krea and Comfy discussing their projects and potentially their collaboration or integration. The session likely covers updates on Co
arXiv:2606.20627v1 Announce Type: cross Abstract: Planning with world models is bottlenecked by compounding prediction errors and the difficulty of defining optimizable goals. Visual targets provide p
Live Stream: Welcome to open source AI Lots of new folk are starting out on their journey with open models. Come join our livestream with all your questions about local models, open coding agents, and
arXiv:2606.21821v1 Announce Type: new Abstract: Understanding the causal structure of a language model's thought process is a problem of significant importance for both transparency and safety. In thi
arXiv:2410.02548v4 Announce Type: replace-cross Abstract: Flow Matching (FM) is a simulation-free method for learning a continuous, invertible flow that interpolates between two distributions, and in
arXiv:2606.21968v1 Announce Type: new Abstract: Vision-Language Models (VLMs) struggle as query-relevant objects become smaller. To address this, recent training-free approaches dynamically retrieve a