Knowledge catalogue
arXiv:2610.06704v1 Announce Type: new Abstract: Dynamic World (DW) maps land use and land cover globally at 10 m from Sentinel-2 (S2) imagery, but only for cloud-free observations, which limits where
arXiv:2610.06080v1 Announce Type: cross Abstract: Gaussian-process limits are powerful in describing overparameterized machine learning models, yet their validity in structured tensor-network architec
This is an update. I posted LocalMind here many moons ago from another account, when it was a Gemma chat in a tab. LocalMind is a static web page that runs models on your GPU through WebGPU. It has no
Google LLC today released EmbeddingGemma 2, an open multimodal embedding model small enough to run on a smartphone. The release takes the EmbeddingGemma line beyond text, which was all the first versi
arXiv:2610.05564v1 Announce Type: cross Abstract: Text embedding models trained with contrastive learning learn to follow task instructions from instruction-paired data, while instruction-tuned LLMs a
arXiv:2610.04441v1 Announce Type: new Abstract: Large language models can intervene in reinforcement learning through both reward design and action selection, yet aggregate performance offers an incom
arXiv:2610.05023v1 Announce Type: new Abstract: We introduce Self-Saliency, a method for training Vision-Language Models (VLMs) to increase the alignment between their visual attention and the image r
arXiv:2610.03771v1 Announce Type: new Abstract: We propose a fine-tuning method for flow-matching diffusion models aimed at realistic artificial light modeling without the need for a large training da
Mistral 4 is pretty good at lawyer bench and cyber security bench, but give it's European heritage, one can only assume it's also good at regulation bench Meet Mistral Large 4, aka Le Chonk. • 1T para
arXiv:2610.04456v1 Announce Type: new Abstract: Deep learning models for crop leaf disease recognition routinely report near-perfect accuracy yet are typically trained and evaluated on a single datase
arXiv:2610.05872v1 Announce Type: new Abstract: A long-standing goal of AI is a model that can continually learn and improve itself. On post-trained models, supervised finetuning (SFT) on new data oft
arXiv:2610.04572v1 Announce Type: new Abstract: Precise constraint satisfaction is a prerequisite to deploying learned models in many areas, motivating methods that repair raw neural predictions with
arXiv:2610.05129v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) provide a natural way to make video anomaly detection more explainable. However, their final decisions do not a
arXiv:2610.05318v1 Announce Type: new Abstract: Analog in-memory computing is a promising platform for on-device execution of large language models because it performs matrix--vector multiplications (
arXiv:2610.04690v1 Announce Type: cross Abstract: Self-supervised learning (SSL) is standard for speech representation learning, but mainstream models are designed around single-speaker audio, limitin
Implements the EmbeddingGemma2Model architecture on the MLX runner: 24-layer bidirectional text encoder with PLE, shared gemma4 vision/audio towers, mean-pool + L2 output. /api/embed accepts per-item
arXiv:2610.04756v1 Announce Type: cross Abstract: Self-evolving large language model (LLM) systems repeatedly propose, evaluate, and incorporate updates to prompts, skills, or other persistent artifac
arXiv:2610.02369v1 Announce Type: cross Abstract: Human-computer interaction (HCI) is in the middle of a transition: large language models can now generate functional user interfaces (UIs) on demand f
arXiv:2610.03252v1 Announce Type: new Abstract: Generative models of human-object interaction are bounded by the data that exists: everyday activities involve several objects, but most captured datase
arXiv:2610.02444v1 Announce Type: cross Abstract: Large language models often solve a theorem forward yet fail to disprove a closely related false one: a falsification gap that supervised fine-tuning
arXiv:2610.02687v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in enterprise, scientific, and medical applications, where agents must incorporate domain-specifi
arXiv:2610.02949v1 Announce Type: new Abstract: Instruction tuning has become a common paradigm for applying large language models (LLMs) to biomedical named entity recognition (BioNER). However, exis
arXiv:2610.03591v1 Announce Type: new Abstract: Understanding and assessing natural hazards is essential for disaster preparedness and risk reduction. Recent advances in large language models have spu
arXiv:2610.02564v1 Announce Type: cross Abstract: We develop a closure modeling framework for identifying missing components of dynamical systems using Kernel Ridge Regression (KRR). The framework add
Hi everyone, thank you so much for all the interest in my model. It's more than I expected. Here is a short summary of the trial and error I went through while building Apex-2. 1. GPUs were always the
arXiv:2610.03636v1 Announce Type: cross Abstract: Camera-controlled video models are rapidly advancing toward long generation horizons and complex camera control. A key failure mode is 3D inconsistenc
arXiv:2610.02260v1 Announce Type: new Abstract: Flow matching models excel at generative modeling, and many downstream applications require their samples to satisfy prescribed constraints, such as obs
arXiv:2610.03001v1 Announce Type: new Abstract: Extracellular electrophysiology records a different set of neurons in every session. Neural foundation models embed each neuron and each session into th
arXiv:2610.03015v1 Announce Type: cross Abstract: Accurate 3D detection is essential for mobile embodied agents, while Vision Foundation Models (VFMs) offer transferable visual and geometric priors. Y
arXiv:2610.03054v1 Announce Type: new Abstract: Clustered Federated Learning (FL) partitions a client population into groups of similar local distributions and trains one specialized model per cluster
arXiv:2609.32791v2 Announce Type: replace Abstract: Reinforcement mid-training lets language models learn internal thoughts from unlabeled text, but efficient token-level credit assignment remains cha
arXiv:2610.02478v1 Announce Type: new Abstract: Reinforcement learning for large language models typically maximizes expected return, adding up the probabilities of all successful trajectories. Howeve
arXiv:2610.02397v1 Announce Type: new Abstract: Electric utilities and grid operators increasingly rely on machine-learning models to forecast next-day demand, and those models learn from meter data t
arXiv:2610.03632v1 Announce Type: cross Abstract: Physical fidelity has received increasing attention in world models and video generation, yet how video representations encode physical information re
Whenever I feed codebases into local models (Qwen, DeepSeek R1) or API models, the biggest annoyance is prompt pollution: - Lockfiles (`Cargo.lock`, `package-lock.json`) burning 30,000+ tokens for zer
So I tried that miracle engine everyone is talking about. Asked the IQ3_S model to express its opinion on a post from this sub to measure the tps on a long-ish generation: Can you help with the follow
model: support nimble decision model (#29844) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52332773 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Si
model: add support for clef decision model (text-only) (#29831) init support for clef (text only) more static graph clean up nits nits 2 Update gguf-py/gguf/constants.py Co-authored-by: Sigbjørn Skjær
Workflow & Hardware The workflow was originally based on Pixaroma’s ComfyUI workflow. I made some modifications and added Sol Attn optimization and Comfy Kitchen Sink, including the very useful Model
Seattle-based artificial intelligence research firm Allen Institute for AI announced a development framework for large language models Thursday that significantly improves how mixture-of-experts large
Editor’s note: AI21 Labs is a leading global AI lab with a long track record of building foundation models, most notably the Jamba family, and today focuses on specialized LLMs and agent optimization
arXiv:2610.00685v1 Announce Type: new Abstract: With the rapid adoption of large language models (LLMs) and parameter-efficient fine-tuning (PEFT) methods, the risk of backdoor attacks has become more
arXiv:2610.01054v1 Announce Type: cross Abstract: In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requir
arXiv:2610.01133v1 Announce Type: cross Abstract: Scaling reasoning typically spends more compute on reinforcement learning (RL) or on inference. We show that a completed RL training history can yield
arXiv:2610.01304v1 Announce Type: cross Abstract: Federated LLM fine-tuning enables large models to be adapted using private and geographically distributed data at the network edge, creating recurring
arXiv:2610.01820v1 Announce Type: cross Abstract: When the system model is not fully known, measurement error and limited excitation can leave several models consistent with the same finite data. A co
arXiv:2610.00394v1 Announce Type: new Abstract: This paper studies forking, a generalization failure discovered in NanoGPT autoresearch. Under data replay, models with an over-encoding n-gram memory b
arXiv:2610.01378v1 Announce Type: new Abstract: Attributing model behavior to synthetic training data requires knowing what produced each training item before estimating what that item caused. A wavef
arXiv:2604.01997v2 Announce Type: replace Abstract: Gait analysis provides an objective characterization of locomotor function and is widely used to support diagnosis and rehabilitation monitoring acr
arXiv:2610.02036v1 Announce Type: new Abstract: AI agents can each make locally valid decisions yet jointly produce an invalid result. We call this the global coherence problem: a failure of shared st
arXiv:2610.01522v1 Announce Type: new Abstract: Many scientific and machine learning systems, from molecular dynamics to diffusion models and beyond, are governed by stochastic dynamics with low-dimen
arXiv:2610.01905v1 Announce Type: new Abstract: Online vectorized HD map construction is essential for scaling safe autonomous driving and requires accurate, real-time inference. Prior methods typical
arXiv:2610.00007v1 Announce Type: cross Abstract: Named-entity recognition (NER) is increasingly wanted on-device (no API, low latency, data kept local). The practitioner's question is not the leaderb
arXiv:2610.01320v1 Announce Type: new Abstract: Generative modeling has shown strong promise for multivariate time mseries (MTS) forecasting, especially scale to high-dimensional settings. Diffusion-b
arXiv:2610.01554v1 Announce Type: new Abstract: Wanda (Sun et al., 2024) prunes large language models by scoring weights independently within each linear projection, although queries and keys interact
arXiv:2610.00940v1 Announce Type: cross Abstract: We propose ReHoPER, an inference-only, zero-shot method that improves large language models' reasoning by generating and answering intermediate questi
arXiv:2609.12822v2 Announce Type: replace Abstract: Blinded physician evaluation has been considered by many to be the gold standard for assessing clinical reasoning in large language models (LLMs). T
arXiv:2610.01799v1 Announce Type: new Abstract: Skill evolution offers a promising way to improve large language model agents without updating their parameters, but its use in formal theorem proving r
arXiv:2610.00417v1 Announce Type: new Abstract: Repeated training on model-generated data can degrade later models. One possible response is to use provenance when deciding which generated examples to
arXiv:2610.00106v1 Announce Type: cross Abstract: Deep learning and large language models (LLMs) are rapidly gaining adoption in semiconductor design, driving demand for training datasets. Most effort