Knowledge catalogue
arXiv:2602.07533v2 Announce Type: replace Abstract: Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative mod
arXiv:2606.26828v1 Announce Type: new Abstract: Accurate seedling detection during early growth stages is essential for timely replanting and effective crop management in precision agriculture. Howeve
arXiv:2606.26333v1 Announce Type: new Abstract: Reinforcement learning in large or sparse-reward environments suffers from slow temporal-difference reward propagation, as value information spreads onl
arXiv:2606.26392v1 Announce Type: new Abstract: Reinforcement learning (RL) for locomotion frequently converges to locally optimal but undeployable behaviors, such as vibrating limbs or scooting on th
arXiv:2606.26520v1 Announce Type: cross Abstract: Mammalian cell-culture processes underpin the manufacture of many biopharmaceuticals, yet keeping a run on track is hard: critical process parameters
arXiv:2606.27325v1 Announce Type: new Abstract: Recent advances in action-conditioned world models show promising progress in modeling complex interactions and forecasting future states under diverse
now seems like a good day to remind people we have an apache 2.0 coding model you can run with 20 gigs of ram locally for free forever. https://huggingface.co/CohereLabs/North-Mini-Code-1.0-w4a16 Its
arXiv:2606.26403v1 Announce Type: new Abstract: Foundation-model research increasingly needs data about people: user state, personal histories, relationships, contact-like fields, documents, and longi
arXiv:2606.27084v1 Announce Type: new Abstract: Reliable organ localization in abdominal CT can provide spatial priors for downstream trauma analysis. We propose CT-3GDINO, a lightweight 3D detector t
arXiv:2606.26822v1 Announce Type: new Abstract: Federated Learning (FL) has become a foundational paradigm for privacy-preserving distributed intelligence, yet its scalability remains fundamentally co
arXiv:2606.26341v1 Announce Type: new Abstract: Many robotics problems, including trajectory optimization, inverse kinematics, and contact-rich motion planning, reduce to nonlinear programs (NLPs). Ma
SITUATION EXPLAINED: 70% of frontier model queries could run locally for free. @ClementDelangue, co-founder and CEO of @huggingface: 'There was an interesting study from Stanford published last year s
arXiv:2606.26487v1 Announce Type: cross Abstract: Large language models (LLMs) are attractive for context-aware time series forecasting because they can integrate heterogeneous textual signals, yet th
arXiv:2606.26511v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) gives agents access to accumulated knowledge, but has no model of time. When a fact changes (e.g., a function is
arXiv:2606.26664v1 Announce Type: cross Abstract: Existing homomorphic encryption (HE)-based GNN systems adopt a graph-centric paradigm that couples per-query cost to global graph size, limiting evalu
arXiv:2606.25156v1 Announce Type: new Abstract: Modern large language models based on softmax scaled-dot-product attention are constrained by their training sequence length: as the key-value sequence
arXiv:2606.25253v1 Announce Type: new Abstract: Highlights provide a concise summary of the main contributions of an academic paper and help readers quickly understand its focus. However, many journal
b9786 is a release of llama.cpp, a tool for LLM inference in C/C++ . Llama.cpp is a free and open-source tool that allows users to run AI models locally on Windows, Linux, and macOS . The b9786 releas
B9787 is a build release of llama.cpp, an open-source C/C++ implementation for LLM inference created by Georgi Gerganov. The llama.cpp project enables large language model inference with minimal setup
Release b9789 of llama.cpp includes a fix for quantizing mixture-of-experts models with MTP (multi-token prediction) . Binaries are provided for multiple platforms including macOS, Linux, Android, and
arXiv:2606.25556v1 Announce Type: new Abstract: Stepwise group-based RL is an attractive way to train long-horizon LLM agents without a learned critic: it reuses multiple sampled rollouts to estimate
arXiv:2606.25508v1 Announce Type: new Abstract: Histopathological tissue segmentation is essential for computer-aided diagnosis, yet weakly supervised methods often suffer from noisy pseudo-labels gen
arXiv:2606.25524v1 Announce Type: cross Abstract: Large language models (LLMs) reach high accuracy in mathematical reasoning, but individual traces on the same problem diverge; some arrive at the corr
arXiv:2512.05394v2 Announce Type: replace Abstract: Latent diffusion models pair VAEs with diffusion backbones, and the structure of VAE latents strongly influences the difficulty of diffusion trainin
arXiv:2606.25354v1 Announce Type: new Abstract: Test-time scaling improves language-model reasoning, but existing approaches often face a difficult trade-off: long chain-of-thought sampling remains si
arXiv:2606.24941v1 Announce Type: cross Abstract: Reviewing recorded interviews for affective cues such as composure, hesitation and agitation is slow and subjective, and cloud services that could aut
arXiv:2506.21091v2 Announce Type: replace Abstract: Stereo matching has become an increasingly important component of modern autonomous systems. Developing deep learning-based stereo matching models t
arXiv:2606.25941v1 Announce Type: cross Abstract: Increasing demand for precise and reliable control in complex scenarios has led to the development of increasingly sophisticated controllers, includin
arXiv:2606.26037v1 Announce Type: cross Abstract: Federated learning has emerged as the foremost approach for decentralized model training with privacy preservation. The global class imbalance and cro
arXiv:2606.25115v1 Announce Type: new Abstract: On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights. This memory is hard-bounded and
arXiv:2606.24889v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems, despite low overall word error rates, produce residual lexical errors that disproportionately affect semanti
arXiv:2507.00028v2 Announce Type: replace-cross Abstract: The representation of urban trajectory data plays a critical role in effectively analyzing spatial movement patterns. Despite considerable pro
arXiv:2606.25368v1 Announce Type: new Abstract: Visual anomaly detection is often deployed with only normal training images. Most one-class detectors map test patches or features to a normal reference
One animation. Different visual styles. This workflow uses Seedance 2.0 in ComfyUI with reference images to explore different looks while preserving the same motion and camera movement. In this exampl
arXiv:2606.18008v2 Announce Type: replace Abstract: Visual attribution is a fundamental tool for interpreting modern vision and vision-language models, particularly when their decisions must be inspec
arXiv:2606.25533v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for enhancing large language models with external knowledge. By coupling retri
Seedance 2.0 Mini is live in ComfyUI. Same cinematic toolkit. Same nodes. Lower cost per run. → 480p + 720p output → Multi-shot sequences with coherent pacing → Stable character identity across shots
Mark Gurman / Bloomberg: Sources: Apple plans to skip higher-end M6 chips and launch its next Pro and Max chips in 2027 as part of the M7 lineup, to boost on-device AI capabilities — Apple Inc. is mak
arXiv:2606.25224v1 Announce Type: new Abstract: Learning-based automated coaching systems for complex motor tasks such as high-performance driving remain limited in the ability to be adaptive by their
arXiv:2606.25328v1 Announce Type: cross Abstract: Large speech foundation models have shown strong potential for speech deepfake detection, but direct fine-tuning is limited by a mismatch between self
arXiv:2606.24958v1 Announce Type: new Abstract: Collective behavior arises when locally interacting units produce coordinated global organization, from synchronization in dynamical systems to task-rel
arXiv:2606.25627v1 Announce Type: new Abstract: Distributed intelligent systems increasingly need to train across data silos without centralizing raw data. Federated learning keeps data local but can
arXiv:2606.25456v1 Announce Type: new Abstract: Brain-Computer Interface (BCI) based on electroencephalography (EEG) enables direct interaction between the brain and external environments and has sign
Ollama v0.30.11 is a release candidate from the v0.30 series (June 2026) , which pairs the new MLX engine on Apple Silicon with continued llama.cpp improvements for enhanced compatibility across Mac a
We just crossed 100M annual run-rate. I know many AI companies are capturing much more $ these days, but still proud of the milestone! Maximizing short-term revenue has never been our priority. In fac
arXiv:2606.25208v1 Announce Type: new Abstract: A companion study introduced joint durability into the dimensional design of the Theo Jansen walking linkage and found its classical 'holy numbers' Pare
This X/Twitter broadcast by Clem Delangue (CEO of Hugging Face) likely provides an introduction to running open source AI models locally on personal machines, covering topics such as benefits of local
who wants to help eyal poke holes in this approach to run LLM inference... in browser? Looking for peer reviewers 🧪 Built an LLM inference engine in pure WebGPU/WGSL. Runs in browser and Node, on-devi
arXiv:2606.25964v1 Announce Type: cross Abstract: Small (sim2B) GUI-grounding agents are attractive for on-device deployment, accessibility tooling, and low-cost iteration, but at this scale they face
arXiv:2606.23964v1 Announce Type: cross Abstract: Self-supervised learning in fluorescence microscopy often relies on 2D projections, despite the inherently three-dimensional nature of cells. We prese
arXiv:2606.24140v1 Announce Type: new Abstract: Discrete flow matching (DFM) provides a principled framework for generative modeling on discrete state spaces via continuous-time Markov chain dynamics.
arXiv:2606.24834v1 Announce Type: new Abstract: LLM-based dialogue assistants have become mainstream tools for software developers, yet current evaluation benchmarks focus exclusively on functional co
arXiv:2606.24292v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive vision-language understanding, yet still struggle with fine-grained perception in
arXiv:2606.24118v1 Announce Type: new Abstract: Visual grounding in documents is a crucial ability for Large Multimodal Models (LMMs) in areas such as document understanding, deep research and documen
The search results do not contain specific information about the b9777 release. Based on the available information about llama.cpp releases, b9777 is an intermediate build release from the llama.cpp p
Build b9784 is a release of llama.cpp, a C/C++ project that enables large language model inference with minimal setup on a wide range of hardware. The release includes pre-compiled binaries for multip
arXiv:2606.24633v1 Announce Type: new Abstract: Human demonstrations for robot imitation learning often contain mistakes and corrective behaviors, such as imprecise grasps, object misalignment, unstab
Creator seungho__yeo ( IG ) built an entire anime-inspired 2D motion sequence - storyboard to final render inside Comfy. seungho__yeo created this workflow while creator whatzuwant ( IG ) created the
arXiv:2606.24579v1 Announce Type: new Abstract: Parametric knowledge in Large Language Models is not equally accessible across languages. As a result, standard inference techniques often struggle to s
arXiv:2606.24506v1 Announce Type: cross Abstract: Emerging LLM services increasingly host many sparse MoE models, yet most models receive sparse requests and remain cold. This creates a GPU memory pro