Knowledge catalogue
arXiv:2603.27170v2 Announce Type: replace Abstract: Relative camera pose is a basic geometric cue for visual re-localization and scene understanding. When using images alone, visual evidence may not s
Enterprises and individual developers frequently run multiple AI inference models. The right architecture can simplify how the models are called while also providing centralized governance. In this po
arXiv:2610.04281v1 Announce Type: new Abstract: Lossless triangle mesh compression must preserve both vertex positions and connectivity. Octrees support learned point cloud geometry coding and progres
arXiv:2610.06469v1 Announce Type: new Abstract: Closed-loop evaluation of end-to-end driving requires continuous rollouts that reveal how earlier decisions affect subsequent driving. However, existing
arXiv:2610.04853v1 Announce Type: new Abstract: In weakly supervised Whole Slide Image (WSI) classification, feature extractors typically compress each image tile into a single global embedding. Conse
arXiv:2610.05810v1 Announce Type: cross Abstract: Machine learning (ML)-powered poisoning attack vectors are adversarial maneuvers whereby an attacker intentionally inserts, corrupts, or alters traini
arXiv:2412.12740v2 Announce Type: replace Abstract: Robots need to be able to understand their surroundings in order to operate safely and robustly, and to interact with the surrounding environment. R
With llama.cpp using a customized SYCL backend on Intel B70 (32GB), overclocking my DDR5 memory gave modest gains for MoE models which do not fit in VRAM. Both PP and TG increased after overclocking D
arXiv:2610.05732v1 Announce Type: new Abstract: LLM agents rely on long-term memory to retain and reuse information when performing tasks over long horizons. Existing methods provide limited support f
arXiv:2610.05010v1 Announce Type: new Abstract: Portrait aesthetic assessment assigns comparable scores according to how effectively human-centered images fulfill their photographic intent. These scor
arXiv:2610.04916v1 Announce Type: new Abstract: Urban navigation requires embodied agents to pursue long-horizon goals through local decisions based on egocentric observations. However, existing agent
arXiv:2610.03894v1 Announce Type: cross Abstract: A deployed LLM agent emits tool calls, queries, and code that can be silently wrong -- by the time the error surfaces, the action has run. Frontier ch
I’ve seen posts here raving about how good Qwen 3.8 27b is. The benchmarks look incredible, and all the online discourse seems to deem it the best local model. I have 32GB VRAM and run Unsloth’s Q6 ve
arXiv:2610.06401v1 Announce Type: cross Abstract: Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-ti
arXiv:2510.16444v2 Announce Type: replace Abstract: Who is being described, where are they, and what are they doing? Referring Atomic Video Action Recognition (RAVAR) answers these questions jointly b
arXiv:2610.04778v1 Announce Type: new Abstract: Patient world models are increasingly proposed for longitudinal prediction, intervention-aware reasoning, and clinical-trial simulation. Causal or clini
arXiv:2610.05715v1 Announce Type: new Abstract: Vision-language models (VLMs) can detect that an object has rotated across views, but cannot reliably tell by how much. We introduce OR-Bench, a fine-gr
arXiv:2602.04448v3 Announce Type: replace Abstract: Mixture-of-Experts (MoE) language models introduce unique challenges for safety alignment due to their sparse routing mechanisms, which can enable d
arXiv:2603.02348v2 Announce Type: replace Abstract: An agent meets a model as served: through an endpoint with a price card, a shared cache and other tenants, or on whatever hardware a self-hosted mod
arXiv:2610.06804v1 Announce Type: new Abstract: A language model can give a correct answer more probability than any single incorrect answer and still usually sample an incorrect one, because the inco
arXiv:2610.06257v1 Announce Type: new Abstract: Foundation models can generate scientific code, but authoring a scientific simulator (an executable program encoding hypotheses about how mechanisms gen
arXiv:2610.04017v1 Announce Type: new Abstract: Localizing behavior to individual components of a language model is a central goal of mechanistic interpretability. However, scoring components one at a
arXiv:2601.17657v4 Announce Type: replace Abstract: Robotic and autonomous systems need dense spatial cues, yet adding a dedicated depth estimator can duplicate visual processing already performed by
For the last few weeks most of my coding has been done locally with Qwen3.8-Flash-Next, so I gave it and Opus 5.5 the same high complexity feature to build on LlamaStash (a complex and large Rust proj
arXiv:2505.24033v3 Announce Type: replace-cross Abstract: We investigate whether hidden states from Structured State Space Models (SSMs) can be merged post hoc to support downstream reasoning. Inspire
https://huggingface.co/Dankpaws/Swift1.5-Qwen3.8-Flash-Next-MLX-4.7bpw I've had the 96GB Mac Studio with M5 Ultra for about a week now and wasn't satisfied with the results I was getting from the limi
arXiv:2610.05731v1 Announce Type: new Abstract: Earth observation (EO) data provide rich temporal supervision, yet existing remote sensing foundation models mainly exploit sequential observations thro
arXiv:2610.04945v1 Announce Type: new Abstract: Destructive single-cell measurements provide unpaired population snapshots rather than observations of the same cells across conditions. Local cell stat
arXiv:2407.21783v3 Announce Type: cross Abstract: Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It i
arXiv:2610.05453v1 Announce Type: cross Abstract: Multimodal models are increasingly shifting toward unified architectures that understand and generate text, images, and other modalities within a shar
arXiv:2507.09200v2 Announce Type: replace Abstract: The rapid proliferation of video in applications such as autonomous driving, surveillance, and sports analytics necessitates robust methods for dyna
arXiv:2610.06694v1 Announce Type: new Abstract: Graph foundation models aim to transfer across graphs, feature spaces, relational schemas, and prediction tasks, yet existing approaches typically gener
arXiv:2610.06494v1 Announce Type: new Abstract: Multi-structure segmentation of the uterus is important for computer-assisted screening, diagnosis, and treatment planning of uterine diseases, where ul
Someone who has always loved looking at the space between different AI techniques, this time I went a little deeper into the memory trade-offs between RNNs, Transformers and SSMs. I found it interesti
arXiv:2610.05025v1 Announce Type: new Abstract: Dual-system Vision-Language-Action (VLA) models improve real-time robotic control by pairing a slow, reasoning-capable generalist with a fast specialist
arXiv:2610.04925v1 Announce Type: new Abstract: Time-series forecasting informs critical decisions in energy dispatch, industrial operations, and environmental monitoring; understanding the patterns m
arXiv:2511.10542v2 Announce Type: replace-cross Abstract: Using 2.6 billion geolocated social-media posts (2014-2022) and a fine-tuned generative language model, we construct county-level indicators o
arXiv:2603.23478v2 Announce Type: replace Abstract: Affordance segmentation in 3D scenes requires an agent to ground implicit natural-language instructions into precise masks of fine-grained interacti
arXiv:2610.05425v1 Announce Type: new Abstract: Automated checks of radiology reports may rely on AI-generated checklists that leave findings unmentioned. We used reinforcement learning to train a vis
arXiv:2610.06616v1 Announce Type: new Abstract: The design of a video encoder determines when frames begin to interact and which frame-specific visual evidence remains accessible to the language model
arXiv:2610.05700v1 Announce Type: new Abstract: Recurrent sequence models must decide how strongly to overwrite their memory at each token. Read as Bayesian filtering, this write is the gain of a Kalm
arXiv:2610.05865v1 Announce Type: new Abstract: Feature pyramid methods, from FPN to BiFPN, have achieved strong performance in face detection by fusing multi-scale features. However, detecting faces
arXiv:2610.04303v1 Announce Type: new Abstract: Recursive computation repeatedly compresses or reuses intermediate states, creating a simple tension: information that must remain useful across longer
arXiv:2610.05273v1 Announce Type: new Abstract: Visual token pruning is an effective way to accelerate vision-language models and is especially useful for vision-language-action (VLA) inference, where
Zendesk launched a self‑service agent builder powered by Anthropic’s Claude, moving from proof of concept to early access in four months with a five‑person team. Within seven weeks of launch the platf
arXiv:2610.02970v1 Announce Type: new Abstract: Large language models (LLMs) have shown promising potential for biomedical named entity recognition (BioNER) through instruction following and in-contex
arXiv:2610.02598v1 Announce Type: new Abstract: Deploying LLMs on consumer-grade GPUs with insufficient memory to hold their weights can result in prohibitively slow inference, because decoding repeat
arXiv:2610.03078v1 Announce Type: new Abstract: Quantifying conversational dynamics requires reliable identification of interactional units and their temporal boundaries, but speech activity alone doe
arXiv:2610.02472v1 Announce Type: cross Abstract: Personalized LLM assistants must recover sparse evidence from long conversation histories across queries of varying complexity. We introduce APDMem (A
arXiv:2406.19892v5 Announce Type: replace Abstract: This article presents multilingual deep learning models for identifying web registers -- text varieties such as news reports and discussion forums -
arXiv:2610.03051v1 Announce Type: new Abstract: Social bees are important pollinators that support biodiversity and crop pollination globally and serve as important model systems for collective behavi
arXiv:2610.02462v1 Announce Type: cross Abstract: LLM compression reduces inference costs and memory requirements, but selecting a method and configuration remains largely empirical because comparable
arXiv:2610.02666v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models map visual observations and language instructions to continuous robot actions, but a diffusion-based action expert (
arXiv:2602.01124v4 Announce Type: replace Abstract: Dynamic graph representation learning requires capturing both structural relations and temporal evolution, yet existing approaches face a core trade
arXiv:2610.02945v1 Announce Type: new Abstract: Using frontier agent harnesses to tackle mathematical research problems has emerged as an effective means of advancing mathematics. However, solving fro
arXiv:2610.03622v1 Announce Type: new Abstract: The construction industry faces persistent labor shortages, low productivity that costs the global economy over $1.6 trillion annually, and one of the h
Disclosure: I made this. Sharing it here because it is fully local and small, and I want feedback from people who run models on their own machines. What it is: a 395M decision model (ModernBERT-large
deep agents just shipped a round of multimodal upgrades! 1. broader file support on OpenAI Responses: docx, pptx, xlsx, csv, json, markdown, not just pdfs 2. opt-in binary offloading to keep big files
arXiv:2610.03617v1 Announce Type: new Abstract: Image-text alignment is a core problem in computer vision with applications in caption evaluation, hallucination detection, data curation, and the bench
arXiv:2610.02351v1 Announce Type: new Abstract: ReAct-based agents typically rely on a single LLM policy to propose actions, interact with the environment, and decide when a task is complete. This cou