Involution Without Export Is Wasted Effort
A week in Beijing and Shanghai with the people building AI in China some quotes from the article: ByteDance/Doubao is the only major lab keeping its flagship closed, because it is the only one that al
Knowledge catalogue
A week in Beijing and Shanghai with the people building AI in China some quotes from the article: ByteDance/Doubao is the only major lab keeping its flagship closed, because it is the only one that al
arXiv:2610.09444v1 Announce Type: new Abstract: Forecasting future 3D occupancy from surround-view cameras is essential for autonomous driving, yet existing approaches rely on dense voxel or bird's-ey
On-device personal AI requires models and agent software that can operate within fixed hardware limits. Developers also need ways to keep those systems improving after deployment. Model builders are r
arXiv:2610.10528v1 Announce Type: cross Abstract: Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Long
arXiv:2610.10225v1 Announce Type: new Abstract: Whole slide image (WSI) analysis in computational pathology follows a multiple instance learning (MIL) pipeline where patch embeddings are extracted ind
arXiv:2610.10448v1 Announce Type: cross Abstract: MemoCare is an interactive mobile system for automated multimodal cognitive screening. A React Native application combines spoken responses, temporal
arXiv:2610.09952v1 Announce Type: new Abstract: Recent advances in generative image models have made many manipulated images highly realistic, raising the need for detectors that are not only accurate
arXiv:2610.09020v1 Announce Type: new Abstract: Modern neural networks are often miscalibrated, with a tendency to overconfidence. Existing train-time calibration methods largely modify task losses or
In my attempt to combat powerty; as electricity cost a ton these days and it is hot as hell, I consolidated 2 machines into one, so my 2 crappy machines now are one, and that means a bit less power an
Next YC Paper Club: Inference Inference is no longer just: y = model.forward(x) It has now become as complex and important as training. The difference between naive inference and well tuned could be 1
arXiv:2610.10385v1 Announce Type: new Abstract: Embedding tables are among the largest components of modern language models. Most compression methods fix a coding geometry such as coordinate blocks, l
arXiv:2610.09383v1 Announce Type: new Abstract: Sparse-view 3D coronary reconstruction commonly relies on cross-view correspondence and triangulation, which are vulnerable to vessel overlap and foresh
arXiv:2610.10239v1 Announce Type: new Abstract: Scientific dynamics forecasting is often framed as an architecture choice, although deployment is also determined by observed history, rollout feedback,
arXiv:2610.08954v1 Announce Type: new Abstract: Video large language models (Vid-LLMs) excel at diverse video-language tasks by reasoning over selected frames. However, frame selection for long videos
arXiv:2505.12224v5 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have recently advanced robotic manipulation by translating natural-language instructions and visual observations
arXiv:2610.09454v1 Announce Type: new Abstract: Robotic manipulation videos are increasingly used as visual plans for embodied agents, but optimizing purely for visual plausibility often fails to capt
arXiv:2610.10199v1 Announce Type: new Abstract: Emerging legislation requires large language models (LLMs) to be audited for compliance with regulatory standards, particularly fairness. Such black-box
arXiv:2610.09384v1 Announce Type: new Abstract: Language models are routinely fine-tuned under a fixed context, such as a generic system prompt, persona or domain-specific instruction, yet the learned
arXiv:2610.10411v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model inference by using a low-cost draft model to propose tokens that the full-size target model veri
arXiv:2610.08883v1 Announce Type: cross Abstract: Finding low-energy configurations of interacting particles and approximating probability distributions lead to the minimization of potential-interacti
arXiv:2610.09785v1 Announce Type: new Abstract: World models can enable autonomous ultrasound scanning by predicting the outcomes of probe motions from local observations. Learning this action--observ
arXiv:2610.10190v1 Announce Type: cross Abstract: We analyze the first-order deterministic diffusion sampler of Karras et al. (2022), termed EDM, in 2-Wasserstein distance by separating two sources of
USA Today Co., along with the several local newspapers it owns, is suing OpenAI over claims that the company copied 'hundreds of thousands' of articles to train its AI models, as reported earlier by R
What's Changed README: add oxi to community integrations by @maziluiosif in #18739 server: hide duplicate and downgrade guards from list by @dhiltgen in #18874 New Contributors @maziluiosif made their
arXiv:2610.09027v1 Announce Type: cross Abstract: Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images. Can an adversarial input cont
arXiv:2610.09535v1 Announce Type: new Abstract: Real-world applications require 6D pose estimation to be accurate, fast, and scalable to unseen objects. This paper introduces WAPR, a zero-shot wide-an
arXiv:2610.09313v1 Announce Type: new Abstract: Vision-language models (VLMs) often miss small objects in large images. We ask three questions: what limits them, which of these limits better models ca
arXiv:2610.09718v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models acquire broad manipulation capabilities via large-scale pretraining, yet eliciting them through language requires
It's on the official Tencent Github page now: https://github.com/Tencent-Hunyuan/Prism Looks like they started uploading bits of it two weeks ago, but its still beta. But I think its odd its on an ind
arXiv:2610.07116v1 Announce Type: new Abstract: Deformable-object manipulation is essential for robotic tasks such as folding laundry and handling food, where robots must control shape changes as well
arXiv:2610.07271v1 Announce Type: new Abstract: Linkage algorithms for hierarchical clustering (HC) are a powerful and efficient framework for constructing clustering trees, yet it is often unclear wh
arXiv:2610.07457v1 Announce Type: cross Abstract: Fine-grained mixed-precision quantization promises efficient large language model inference, but local precision choices can conflict with regular GPU
arXiv:2610.07323v1 Announce Type: cross Abstract: Security evaluation of learning-based systems requires more than just testing the system against a fixed collection of attacks. It requires adaptive m
arXiv:2607.17669v2 Announce Type: replace Abstract: Drone-based object detection technology has advanced rapidly, becoming increasingly sophisticated and efficient. Recently, research trends have expa
Wanted to share a local memory engine I built called Hillock. The main problem I had with standard local RAG was that running document parsing and vector search chewed up so much VRAM that my actual O
Every time I try, I'm met with this: error message: Error: max retries exceeded: Get 'https://dd20bb891979d25aebc8bec07b2b3bbc.r2.cloudflarestorage.com/ollama/docker/registry/v2/blobs/sha256/00/001e5d
arXiv:2610.06897v1 Announce Type: new Abstract: Localizing latent structures in the activation space of language models (LMs) is central to understanding and controlling their behavior. Yet, localized
arXiv:2610.07340v1 Announce Type: cross Abstract: Protein-molecule virtual screening is increasingly cast as a problem of representation learning in a shared embedding space. Existing methods rely on
Follow up update of this post here I added mask support to the reference strength node. You can now increase or reduce attention to a selected part of a reference instead of adjusting the whole photo.
arXiv:2512.20007v3 Announce Type: replace-cross Abstract: Models with intractable normalizing constants are widely used in statistics and machine learning. Assessing the adequacy of such models poses
arXiv:2610.07816v1 Announce Type: new Abstract: Small language models (SLMs) are attractive as local agent controllers because they reduce remote inference, latency, and deployment footprint, yet stru
arXiv:2610.08268v1 Announce Type: cross Abstract: Pervasive intelligent applications are increasingly deployed on mobile and Internet of Things (IoT) edge devices. Consequently, Large Language Models
I am sure people need it you know? There are plenty of embedding models on ollama, but only for local deployment. Which is a shame. I wish ollama would make embedding and rerankers available on ollama
arXiv:2610.07197v1 Announce Type: new Abstract: Exact unlearning requires a deployed predictor to match one rebuilt without the information named by a deletion request. Existing general-purpose exact
https://x.com/haoailab/status/2107591980591227227 https://github.com/hao-ai-lab/FastVideo https://haoailab.com/FastVideo/cookbook/minimax-h3/ https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-Com
arXiv:2610.07399v1 Announce Type: new Abstract: Federated deep clustering seeks to learn clustering-friendly representations from decentralized unlabeled data while preserving client privacy. However,
arXiv:2610.08388v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suffer from hallucinations on know
arXiv:2610.07550v1 Announce Type: cross Abstract: Random access (RA) is one of the most foundational medium access control (MAC) layer scheduling schemes for handling unpredictable data traffic from m
arXiv:2610.07729v1 Announce Type: new Abstract: Visual tokens are a major source of inference cost in vision-language models, yet simple image downsampling remains a surprisingly strong compression ba
arXiv:2610.08538v1 Announce Type: cross Abstract: Probabilistic load forecasting has been widely studied for power-system operation and planning, but customer- and transformer-level forecasting introd
arXiv:2610.07243v1 Announce Type: new Abstract: Breast cancer is the leading cause of cancer-related mortality among women in Sub-Saharan Africa, where delayed diagnosis results from limited radiology
Since Minimax H3 does such a good job of taking a source or two of a character and doing an animation with them while maintaining the character's integrity, it has me thinking that it could be used to
On October 7, 2026, Clement Delangue noted that Microsoft’s Windows launch—highlighted by Satya Nadella and others—demonstrated the growing excitement around local AI solutions such as llamacpp. The e
EmbeddingGemma 2 came out this week. It maps images and text into one 768-dim space, so you can search photos by describing them. I ported its text and vision towers to ruNNtime, a WebGPU inference li
arXiv:2610.07037v1 Announce Type: new Abstract: AlphaFold 3-style cofolding models predict biomolecular complexes with high structural accuracy, yet a large fraction of their outputs are physically in
arXiv:2610.08020v1 Announce Type: cross Abstract: Classical force fields (FFs) remain the workhorse for large-scale simulations even as machine-learned interatomic potentials (MLIPs) approach ab initi
arXiv:2610.08176v1 Announce Type: new Abstract: Decentralized learning is highly sensitive to communication topology under non-IID data. Adaptive peer-selection methods can exploit local model informa
arXiv:2610.07326v1 Announce Type: new Abstract: Universal object localization in X-ray security inspection is critical for automated threat detection in safety-critical venues. However, unlike everyda
Thursday, October 8 — 15:00–19:00 UTC Access is free and the API is OpenAI-compatible. During those 4 hours, everyone will be asked to use it actively at the same time—coding, chatting, agents, long c
Hi everyone, I’m exploring AI filmmaking and looking for good AI video-generation models that are either free, open-source/open-weight, or affordable. I’m particularly interested in models who allow u