Knowledge catalogue
arXiv:2609.24422v1 Announce Type: new Abstract: Hierarchical data is ubiquitous in the empirical sciences and is most commonly analyzed with generalized linear mixed-effects models (GLMMs). Bayesian i
arXiv:2609.22879v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a powerful paradigm for embodied intelligence, but fine-tuning them with reinforcement learning (RL)
arXiv:2609.23769v1 Announce Type: new Abstract: The disambiguation of semantically similar statutory text across jurisdictions is a retrieval problem that existing methods do not solve. This inter-con
arXiv:2609.24768v1 Announce Type: new Abstract: Professional photo finishing relies on both global adjustments and region-specific local edits guided by semantic masks, yet current automated methods h
arXiv:2609.22112v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated the ability to generate user-specific text with high stylistic fidelity. However, the personal data that
arXiv:2609.24397v1 Announce Type: new Abstract: The conventional testing process quickly fails when applied to ML-based systems such as obstacle detection in vehicles: if an obstacle is not detected i
arXiv:2609.23144v1 Announce Type: new Abstract: 3D scene graphs provide semantically rich and hierarchical representations for robot perception. However, existing systems do not maintain uncertainty a
arXiv:2609.23465v1 Announce Type: new Abstract: Long-horizon conversational memory is especially challenging in multi-actor settings, where relevant evidence is distributed across participants and con
arXiv:2609.23845v1 Announce Type: new Abstract: Decentralised federated learning removes the aggregation server but makes collaboration dependent on transient peer availability. In mobile and intermit
arXiv:2609.23127v1 Announce Type: new Abstract: Many real-world reinforcement learning (RL) problems evolve in continuous time, where decisions occur at irregular, event-driven intervals rather than a
arXiv:2609.23242v1 Announce Type: new Abstract: We study two-timescale decision systems in which a planning layer periodically supplies a continuation-value function to a real-time optimizer that allo
arXiv:2609.23386v1 Announce Type: new Abstract: Text-guided 3D building generation holds tremendous application potential, yet existing generative models typically output inseparable single meshes or
arXiv:2609.22106v1 Announce Type: cross Abstract: Accuracy of Low-bit quantization of linear layers is often dominated by a small number of outliers. Although existing methods, such as smoothing, rota
They just merged it https://github.com/Comfy-Org/ComfyUI/pull/16442 TL;DR: it's a prompt enhancer that you can use to improve Qwen Image 2.1 prompt Usage: Download these qwen3.5_9b_qwen_image , t2i fo
Upload a short file and ChatGPT reads all of it. Upload a long one, a contract, a thesis, a 200 page report, and most of it goes into a search index instead. Every answer is then built from whichever
arXiv:2609.23449v1 Announce Type: cross Abstract: Memory systems are becoming a core component of LLM agents, but constructing and maintaining memory remains expensive because it relies on repeated ca
arXiv:2609.24042v1 Announce Type: new Abstract: Edge deployment motivates forecasting models with compact parameter storage and low-bit representations. Deep equilibrium models (DEQs) obtain implicit
arXiv:2609.23880v1 Announce Type: new Abstract: Temporal Information Retrieval (TIR) has been increasingly critical given the rise of Retrieval-Augmented Generation (RAG). Since temporally mismatched
arXiv:2609.24538v1 Announce Type: new Abstract: Functional annotation of newly sequenced proteins remains a bottleneck in molecular biology: the number of sequences in public repositories grows far fa
Retrieval benchmarks sometimes feel benchmaxxed by models, so we wanted to find a way to tie it as close as possible to my objective: finding the article that answers a product question right. We work
arXiv:2609.22171v1 Announce Type: new Abstract: Precision healthcare, particularly for conditions like hypertension and cardiovascular disease, necessitates monitoring of dietary sodium intake. Howeve
You can finally downloads quants from: https://huggingface.co/IFM/K2-Horizon-MoVA-36B-A4B-GGUF https://preview.redd.it/cfhl43pps4rh1.png?width=2800&format=png&auto=webp&s=313eab309fb407a0a0e5da61e2a12
This LoRA can do a lot of good things such as detail enhancement, creative upscaling, photo restoration and quality improvements. It's a Image-to-Image(I2I) edit LoRA, so it will require image input,
Almost every single gen has this wispy, burned, piss-yellow ChatGPT-distilled thing going on. Background faces are absolutely abysmal. Even skin texture has this wispiness, like semen texture, and it'
Someone recommended that I try the ByteShape Qwen 3.8 27B IQ3-XXS GGUF after seeing my previous testing of the GSQ quant. So I did. And the result was… surprisingly bad. For context, I'm running: RTX
I've trained a preliminary lora to fix the image generation issues with Qwen Image 2.1 (also drastically improving edit quality). I've also been doing a lot of a/b testing with negative prompts and va
I didn't know my set up was outperforming nearly everyone until reading another discussion where people were struggling getting half of that speed with half the context on the same hardware. I benchma
arXiv:2609.23139v1 Announce Type: new Abstract: Most medical vision-language models (VLMs) excel at open-ended report generation and VQA but provide limited support for structured, fine-grained clinic
Github: https://github.com/OpenEuroLLM/ComplexKDA HuggingFace: https://huggingface.co/collections/openeurollm/complexkda Arxiv: https://arxiv.org/abs/2609.24797 Authors: Julien Siems*, Riccardo Grazzi
arXiv:2609.22959v1 Announce Type: cross Abstract: The medications prescribed to a patient often change during a hospital admission as clinicians start, stop, or continue therapies. We study whether mo
Julian Chokkattu / Wired: Rabbit launches OS3, a cloud AI agent that connects to local apps and files on Windows, Mac, and Linux and works via web, Telegram, iMessage, or its R1 device — Two years aft
Rabbit, the company behind the underwhelming R1 device, is rolling out a standalone AI agent that you don't need its hardware to use, as reported earlier by Wired. The startup says its new OS3 'agenti
arXiv:2601.03981v3 Announce Type: replace Abstract: To efficiently combat the spread of LLM-generated misinformation in the news domain, we present RADAR, a Retrieval-Augmented Detector with Adversari
arXiv:2609.24464v1 Announce Type: new Abstract: Using a Large Language Model (LLM) as the clusterer at production scale is hard: prompts cannot hold the entire label space, and per-document serial pro
arXiv:2609.24846v1 Announce Type: new Abstract: This paper presents a novel initialization method for range-aided simultaneous localization and mapping (RA-SLAM). The general SLAM problem has a well-k
arXiv:2609.22122v1 Announce Type: new Abstract: Cross-device hardware evaluation often assumes that if architecture rankings transfer across devices, a proxy device can support target-side model selec
arXiv:2609.22733v1 Announce Type: new Abstract: This paper develops the Rapidly-iterating kinoDynamic Grid (RDG) algorithm, an asymptotically near-optimal kinodynamic motion planning algorithm that pr
arXiv:2609.24969v1 Announce Type: new Abstract: As agents are deployed with increased autonomy, even extremely rare events along their stochastic output trajectories can occur and prove catastrophic.
arXiv:2609.22587v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models commonly predict action chunks, limiting their ability to react to environmental changes during execution. Existing
arXiv:2609.22135v1 Announce Type: new Abstract: Omni-modal large language models integrate text, audio, and image signals into a shared residual stream, where concepts such as emotion can be linearly
arXiv:2607.14293v2 Announce Type: replace-cross Abstract: Ionizing radiation from cosmic rays and gammas can induce discontinuous jumps in the environmental charge of superconducting qubits (charge ju
arXiv:2609.23826v1 Announce Type: new Abstract: Mitral regurgitation is the most common heart valve disorder worldwide, affecting over 2% of the global population, rising to at least 10% in adults ove
arXiv:2609.23141v1 Announce Type: cross Abstract: Real time plasma state estimation for control of Tokamak devices are challenging due to the stringent latency requirements of the plasma control syste
Victor M (@victormustar) tweeted on September 22, 2026 that the MiMo V2.6 release now includes an official Distill‑Qwen‑9B variant. The tweet expresses enthusiasm for this new model iteration and remi
arXiv:2609.23655v1 Announce Type: new Abstract: Imbalanced gradient magnitudes between the visual and language pathways of a vision-language model are often treated as a defect to be corrected. We tes
🚀 THE EDGE AI FAMILY HAS ARRIVED. Today we’re opening the doors to a new generation of open-source and open-weight edge AI models from Next GenAi. Meet Rebekah AI 1.8B. 🧠⚡ Small enough to run at the e
arXiv:2609.22591v1 Announce Type: new Abstract: Robot learning policies fail in characteristic ways: they stall in uncertain states, drift during contact-rich alignment, and miss targets by millimetre
arXiv:2609.24122v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is hard to monitor in production: exhaustive relevance labels do not exist for non-stationary multi-million-passage
arXiv:2609.23439v1 Announce Type: new Abstract: Non-prehensile manipulation is practical for relocating large, heavy, or geometrically ungraspable objects. Yet, long-horizon pushing of arbitrarily-sha
arXiv:2609.22090v1 Announce Type: new Abstract: An LLM producing the response pattern associated with a human psychological effect is not the same claim as the LLM possessing that bias. We present Psy
Recommended if you work on agent memory. Retrieval is the hardest memory problem in most harnesses because agents keep pulling stale context. AML tests this with a coding track of 150 software tasks,
arXiv:2609.23017v1 Announce Type: new Abstract: Automated pollen analysis supports veterinary cytology, but brightfield microscopy is costlier and more complex than lens-less digital in-line holograph
arXiv:2509.22650v3 Announce Type: replace Abstract: Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models,
arXiv:2406.03678v2 Announce Type: replace Abstract: On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensiv
arXiv:2501.08547v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) have been widely adopted for their ability to compute expressive node representations in graph datasets. However,
arXiv:2609.23286v1 Announce Type: new Abstract: 3D reconstruction from a lengthy video stream input poses a dilemma for feed-forward reconstruction models (FFRMs), that a whole-stream inference contex
arXiv:2609.24750v1 Announce Type: cross Abstract: The growing demand for real-time, data-driven decision-making in complex and dynamic systems is placing increasing pressure on traditional Operational
arXiv:2609.24249v1 Announce Type: cross Abstract: Neural networks, both convolution or transformer based, are essential for modern computer vision systems. However, they are vulnerable to small pertur
arXiv:2609.24103v1 Announce Type: new Abstract: In many real-world planning tasks, agents must tackle uncertainty about the environment's state and variability in the outcomes of any chosen policy. We
arXiv:2602.09300v2 Announce Type: replace Abstract: We consider the policy evaluation and control in a finite horizon reinforcement learning (RL) setting under an expectile-based objective. First, we