Knowledge catalogue
arXiv:2610.05013v1 Announce Type: new Abstract: Lifelong physical agents must reason over extended interactions where past events continue to shape the world long after they disappear from view. Beyon
arXiv:2610.06450v1 Announce Type: new Abstract: Foundation models (FMs) are increasingly being developed for general time series and physiological signals, yet their transferability to downstream phys
arXiv:2610.04864v1 Announce Type: new Abstract: Long-video embedding requires capturing sparse query-relevant evidence under a limited visual-token budget. Uniform sampling can miss brief events in vi
arXiv:2610.06369v1 Announce Type: new Abstract: Integrating environmental sensor data with leaf imagery is widely reported to boost crop disease classification accuracy. In this work, we reveal that t
arXiv:2610.06196v1 Announce Type: new Abstract: Remote sensing images often carry composite degradations, in which haze, cloud, noise, blur, low light, and low resolution coexist. Restoring them requi
arXiv:2610.05690v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for literature search and synthesis. However, it is unclear whether they retrieve accurate bibliogr
arXiv:2610.05911v1 Announce Type: new Abstract: Multi-view panoptic segmentation assigns a semantic class and a scene-level instance ID to every pixel of an unordered set of images, and recent feed-fo
arXiv:2610.05418v1 Announce Type: cross Abstract: Most vision-language-action (VLA) models rely on current observations and lose task-relevant evidence once it leaves view, limiting performance on lon
arXiv:2606.16184v2 Announce Type: replace Abstract: Multi-shot long-form video generation remains challenging due to identity drift and compounding inconsistencies across shots. Existing methods encod
arXiv:2604.01554v2 Announce Type: replace-cross Abstract: Binary Function Similarity Detection (BFSD) is a core problem in software security, supporting tasks such as vulnerability analysis, malware c
arXiv:2610.05584v1 Announce Type: new Abstract: Extra inference compute is usually spent on sampling more reasoning chains. We study where inside an existing chain an additional continuation should be
arXiv:2610.04609v1 Announce Type: cross Abstract: Hierarchical control architectures are widely used to decompose complex control problems into interacting control levels and are particularly importan
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:2610.05353v1 Announce Type: cross Abstract: Fluorescence microscopy reveals where proteins localize, but only a limited number of proteins can be imaged in the same cell; generating these images
arXiv:2610.03980v1 Announce Type: new Abstract: Text-to-video (T2V) diffusion models can reproduce copyrighted, violent, or explicit content, which motivates concept erasure: removing designated conce
arXiv:2610.05790v1 Announce Type: new Abstract: Remote sensing foundation models (RSFMs) are commonly evaluated using aggregate metrics, which can hide systematic performance disparities across ecolog
arXiv:2610.05812v1 Announce Type: new Abstract: Process control of advanced semiconductor nodes is not only pushing the limits of metrology equipment requirements in terms of resolution and throughput
arXiv:2610.05897v1 Announce Type: new Abstract: Training a small projector between a frozen vision encoder and language model is an established approach to multimodal learning. As the parameter count
arXiv:2610.04337v1 Announce Type: cross Abstract: Calibrating microscopic traffic models for digital twins is an expensive black-box optimization problem: tuning car-following and lane-changing parame
arXiv:2610.05639v1 Announce Type: new Abstract: Autonomous robots operating over long periods must keep their environmental memory up to date as the world changes between visits. In semi-static enviro
For their Mistral Large 4 release, @MistralAI ran a blind Surge human eval, with our expert software engineers evaluating five frontier models on coding quality. Le Chonk ranked #1 among open-weight m
arXiv:2610.04139v1 Announce Type: new Abstract: Predicting future spatial states supports collision avoidance and timely decision-making in dynamic environments. However, existing vision-language mode
arXiv:2610.05993v1 Announce Type: new Abstract: Composed image retrieval (CIR) aims to retrieve a desired target image from a query consisting of a reference image and a modification text. This task e
arXiv:2610.04585v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPAs) for world modeling train an encoder so a predictor maps a current embedding and action to the next fram
arXiv:2610.04212v1 Announce Type: new Abstract: Graph Neural Operators (GNOs) provide flexible surrogate models for learning solution operators of partial differential equations (PDEs). However, stand
arXiv:2610.04033v1 Announce Type: cross Abstract: Information and infectious diseases spread through social networks, but the spreading probabilities driving them are hard to estimate without per-node
arXiv:2610.04390v1 Announce Type: cross Abstract: Simulation-free training of latent Stochastic Differential Equations (SDEs) relies on a variational posterior process whose one-time marginals are tra
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
arXiv:2606.13894v3 Announce Type: replace-cross Abstract: AdamW is a default optimizer for deep learning, but its moment states add two parameter-sized buffers to training memory, increasing the cost
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
arXiv:2610.04049v1 Announce Type: cross Abstract: We study nonnegative, non-monotone k-submodular maximization with kge2 labels under support constraints, and show how the certified approximation coef
arXiv:2610.04862v1 Announce Type: cross Abstract: Long-horizon problem solving and scientific research require computation to accumulate across successive attempts. Partial solutions, experimental fin
arXiv:2610.05387v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong performance on coding and reasoning benchmarks; however, their ability to solve graph-structured m
Google: Google DeepMind launches EmbeddingGemma 2, a 740M-parameter model to map code, images, video, and audio in a shared embedding space, under an Apache 2.0 license — EmbeddingGemma 2 is the most
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
Starting on October 9th, anyone using Google Gemini on a free plan will be limited to the Flash Lite model. Free users can currently choose from Gemini Flash Lite, Flash, and Pro, but now you'll need
EmbeddingGemma 2 is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs—and combinations thereof—into a single, unified 768-dimens
Hello llamas. I am posting this because I believe that, despite it being closed source models, the discussion will bring value to the local AI community. As many of you probably heard, GPT-6 Astra is
arXiv:2610.04715v1 Announce Type: cross Abstract: We present GPU-accelerated Bregman Douglas--Rachford splitting algorithm (BDRS) for discrete optimal transport problem in three input formats: an expl
arXiv:2610.05546v1 Announce Type: new Abstract: LiDAR-inertial odometry (LIO) is widely used for state estimation in ground-based autonomous mobile robots. However, the geometric constraints provided
arXiv:2505.08088v4 Announce Type: replace-cross Abstract: Vertical localization, particularly floor separation, remains a major challenge in indoor positioning systems operating in GPS-denied multisto
arXiv:2602.16961v2 Announce Type: replace-cross Abstract: The goal of L-step speculative decoding is to accelerate autoregressive decoding of a target model by using a cheaper draft model to generate
arXiv:2610.05337v1 Announce Type: new Abstract: We identify a mismatch between the physical role of transport fields in many PDEs and their usual role in neural operators: PDEs use them to select read
arXiv:2610.04255v1 Announce Type: cross Abstract: Robotic manipulation often requires inferring task-relevant states from past interactions when the current observation alone is insufficient to determ
arXiv:2610.04651v1 Announce Type: cross Abstract: Neural audio codecs compress waveforms into compact discrete tokens that underpin speech language models, real-time communication, and large-scale aud
arXiv:2610.04969v1 Announce Type: new Abstract: Optimization in machine learning is usually expressed through iterative rules that update model parameters using information from the loss landscape. In
arXiv:2610.06394v1 Announce Type: new Abstract: Human-object interaction (HOI) detection aims to localize human-object pairs and recognize their interactions. Traditional supervised methods perform st
Here's a benchmark that uses Lilypond https://x.com/aug5thmusic/status/2096030719156089029 GPT-6 Astra has the best result yet on the Bach Benchmark. Its chorale contains no voice-leading errors, and
arXiv:2610.04499v1 Announce Type: new Abstract: Radiology report generation (RRG) aims to convert medical images into diagnostic texts to assist in clinical decision-making and alleviate the workload
arXiv:2610.05077v1 Announce Type: new Abstract: Backtests of LLM trading agents often assume that every order fills at the closing price. We ask whether this choice changes only reported returns or al
arXiv:2610.04158v1 Announce Type: new Abstract: Recent studies on reinforcement learning (RL) report seemingly conflicting evidence about large language model (LLM) reasoning. Training on mathematics
A small thing I noticed: full-size screenshots use far more AI tokens than the model needs, so usage limits run out sooner. I built a free Firefox add-on, TokenSaver, that shrinks images before they a
arXiv:2610.06745v1 Announce Type: new Abstract: Hierarchical graphs embed in hyperbolic space with lower distortion than in Euclidean space owing to its negative curvature. However, their gradient-bas
I asked Opus 5.5 to make an interactive website companion for the latest @AcquiredFM Home Depot episode. It came out pretty nice! Water color illustrations all drawn by Claude, too: https://claude.ai/
I spent the last few weeks on a hobby research project and just made it public. The idea isn't new (product-key memory, Lample et al. 2019, and Meta's 'Memory Layers at Scale'): give a model a huge ta
On October 6 2026 Sophia Yang announced an “open‑source AI week.” She highlighted Monday’s event featuring @reflection_ai’s Beam and Tuesday’s unveiling of @MistralAI’s Mistral Large 4, indicating ant
Ideally I'd like to be able to run Qwen 3.8-Flash-Next with decent performance. I was thinking of just buying 2x Radeon AI R9700 (64GB VRAM), or maybe a DGX Spark but that was before the price hike. M
I wanted to build an offline bird/plant identifier that runs on a laptop with Ollama. Before building any UI, I tested it on 6 photos: Common Myna → gemma4:e2b said 'Jackdaw' (confidence: high). gemma
i was told we can't fundraise and grow at the same time. it turned out we grew monthly usage 400% during fundraising. we have never run this fast. while taking 60 investor calls a week, we shipped 20
arXiv:2610.04142v1 Announce Type: new Abstract: Modern training on a new task often starts from a previously trained model rather than from scratch, raising the question of how this initialization aff