Knowledge catalogue
arXiv:2604.08539v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has emerged as the de facto Reinforcement Learning (RL) objective driving recent advancements in Multimodal
arXiv:2506.17212v2 Announce Type: replace Abstract: Articulated objects are common in the real world, yet modeling their structure and motion remains a challenging task for 3D reconstruction methods.
arXiv:2604.07427v1 Announce Type: new Abstract: Modern text-to-image (T2I) models generate high-fidelity visuals but remain indifferent to individual user preferences. While existing reward models opt
arXiv:2512.23994v3 Announce Type: replace-cross Abstract: Text-to-audio-video (T2AV) generation is central to applications such as filmmaking and world modeling. However, current models often fail to
arXiv:2604.06176v1 Announce Type: cross Abstract: We present an empirical study of embedding-based retrieval under realistic conversational settings, where queries are short, dialogue-like, and weakly
arXiv:2603.04759v2 Announce Type: replace Abstract: The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse do
arXiv:2604.07674v1 Announce Type: new Abstract: Foundation models have achieved remarkable results in medical image analysis. However, its large network architecture and high computational complexity
arXiv:2604.06422v1 Announce Type: cross Abstract: Understanding when Vision-Language Models (VLMs) will behave unexpectedly, whether models can reliably predict their own behavior, and if models adher
🚀Deep Agents deploy Today we’re launching Deep Agents deploy in beta. Deep Agents deploy is the fastest way to deploy a model agnostic, open source agent harness in a production ready way. Open harnes
Anthropic's unreleased frontier model, Claude Mythos (internally codenamed 'Capybara'), was exposed through two separate leaks within the same week in late March/early April 2026. The Mythos model...
Hi r/LocalLLaMA. I'm on the team at Blockway (disclosure: this is our model). Two weeks ago we posted the Volundr 32B Preview here, and you were blunt about what was wrong with it. This is v1, and mos
model : add Kolibri-1 (Aleph-Alpha) support (#30673) model : add Kolibri-1 (Aleph-Alpha) support Kolibri-1 is a bilingual German/English MoE reasoning model with 78B parameters and 3.46B active per to
Reflection AI's Beam is an open-weight model for agentic coding and long-horizon tasks. This post shows how to deploy Beam on AWS: start with an Amazon SageMaker JumpStart real-time endpoint, or use A
arXiv:2610.21783v1 Announce Type: new Abstract: We study how vision-language models (VLMs) can learn to think and actively explore in 3D space. Instead of providing multi-view images, videos, or 3D re
arXiv:2610.22355v1 Announce Type: new Abstract: Generative visual verifiers play a crucial role in advancing multimodal intelligence. To enhance the robustness of visual verifiers in complex multimoda
Beam is an open model built by Reflection. Beam takes text as input and generates text as output. This release includes the instruction-tuned model in BF16, FP8, and NVFP4 numerics. Beam uses a sparse
arXiv:2610.14479v1 Announce Type: cross Abstract: While language therapy is the primary treatment for post-stroke aphasia, limited clinical resources often restrict patient access to proper care. Addr
arXiv:2505.21710v2 Announce Type: replace Abstract: This study evaluates the effectiveness of ChatGPT, an advanced AI model for natural language processing, in identifying targeting and inappropriate
arXiv:2610.19231v1 Announce Type: new Abstract: Transformer language models develop attention heads that specialize in syntactic relations, for example, attending from verbs to their subjects. Do thes
arXiv:2610.19364v1 Announce Type: new Abstract: Dynamic graph learning models how entities and their relations evolve from historical observations to predict future graph states. Existing methods do n
arXiv:2610.20598v1 Announce Type: new Abstract: Achieving general spatial intelligence requires a unified understanding of both static 3D and dynamic 4D. However, we find that existing models struggle
arXiv:2610.19281v1 Announce Type: new Abstract: Understanding neural scaling laws is increasingly important for theory and practice, yet first-principles explanations remain limited even in simple set
arXiv:2610.19250v1 Announce Type: new Abstract: Reduced-order models (ROMs) make model predictive control (MPC) of high-dimensional nonlinear systems tractable, but the resulting modeling error can le
arXiv:2610.20462v1 Announce Type: new Abstract: Foundation models have shown strong generalization across scientific domains, but their use in power systems remains largely task-specific. We investiga
arXiv:2610.18343v1 Announce Type: cross Abstract: Post-training quantisation reduces the memory cost of large language models, but it remains unclear whether compression preserves language skills of r
arXiv:2610.18946v1 Announce Type: cross Abstract: Physical-layer spoofing attacks pose a critical threat to wireless localization systems by manipulating channel state information (CSI). Detecting suc
arXiv:2610.18755v1 Announce Type: cross Abstract: Reinforcement learning (RL) from unit tests is the common recipe for post-training code models, but a unit test only asks whether the final program pa
arXiv:2610.20071v1 Announce Type: new Abstract: MeanFlow predicts interval-average velocities, but conventional few-step sampling ties the interval queried from the model to the duration of the state
arXiv:2610.16260v1 Announce Type: new Abstract: Current ASR models perform well on general benchmarks but still struggle with acoustically ambiguous words. Visual context can aid recognition in screen
arXiv:2610.20136v1 Announce Type: new Abstract: Vision-language models (VLMs) are moving onto edge devices, but little is known about how much energy they draw on single-board computers with NPU or GP
arXiv:2610.15708v1 Announce Type: new Abstract: Coding agents based on frozen language models can improve their performance by refining the external context they rely on, without updating model weight
arXiv:2610.16127v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly explored in the Architecture, Engineering, and Construction (AEC) domain, yet their reliability in regul
£299.99 Lenovo IdeaCentre Mini (Snapdragon X1-26-100, 32GB, CPU only): - Qwen3.6 35B A3B coder: reads ~118 tok/s, writes 24.5, ~30 with MTP - Qwen3-Next 80B A3B: 17-18 tok/s writes with MTP How I got
arXiv:2610.20588v1 Announce Type: new Abstract: Scaling up transformers has produced models with broad capabilities, deployed across heterogeneous hardware and fluctuating workloads. Yet, model famili
arXiv:2610.17625v1 Announce Type: new Abstract: For video generation in dynamic world modeling, observed static and dynamic content should be efficiently reused to provide conditions for repeated gene
arXiv:2610.15314v1 Announce Type: new Abstract: A deception detector is only as useful as the trust its alarms deserve. Like a polygraph, detectors that read a language model's internal activations ca
arXiv:2610.16630v1 Announce Type: new Abstract: Accurate long-term air quality forecasting is challenging due to long-range transport, meteorological variability, and nonlinear chemical reactions unde
arXiv:2610.16737v1 Announce Type: cross Abstract: Video-to-robot pipelines for quadrupedal imitation insert a learned lifting stage, either a monocular depth model or a per-clip 3D reconstruction, to
arXiv:2610.14159v1 Announce Type: cross Abstract: Reward design remains a major bottleneck for reinforcement learning in robotic manipulation. Handcrafted dense rewards can compensate for the limited
arXiv:2610.16433v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) provide general-purpose forecasting capabilities, yet their forecasts can remain misaligned with the temporal char
arXiv:2610.15836v1 Announce Type: cross Abstract: When told that robins have sesamoid bones, people are far more prone to extend the property to sparrows than to whales. This behavior, called category
arXiv:2610.15846v1 Announce Type: new Abstract: Movable agents, such as autonomous vehicles and robots, should be able to autonomously adapt their pre-trained object recognition models to new environm
arXiv:2610.14748v1 Announce Type: new Abstract: Inspired by the great success of foundation models in the development of artificial general intelligence, Graph Foundation Models (GFMs) have recently a
arXiv:2610.17201v1 Announce Type: new Abstract: Multi-player interactive world models aim to simulate shared environments from multiple players' perspectives, but achieving robust generation while sca
arXiv:2610.14335v1 Announce Type: new Abstract: Latent world-model planning has shown promising results in goal-conditioned robotic manipulation, but remains challenging for long-horizon planning due
arXiv:2610.17936v1 Announce Type: new Abstract: Dynamic 3D Gaussian Splatting (3DGS) provides an efficient framework for dynamic scene reconstruction. Most existing approaches model scene dynamics wit
arXiv:2610.15106v1 Announce Type: new Abstract: Latent recursion repeatedly processes internal representations through the same neural network. Recent work has shown this approach to be effective on s
tl;dr: new qwen finetune that simultaneously pushes the frontiers of small model capability and reasoning efficiency. Hey everyone, We publish two post-trained versions of Qwen 3.8 27B called Sabi-Noe
arXiv:2610.15467v1 Announce Type: new Abstract: Image-computable low-level image saliency has shaped perceptual psychology and computer science, but is limited by its inability to capture human high-l
arXiv:2610.16878v1 Announce Type: new Abstract: Autoregressive electronic health record (EHR) foundation models predict the next event token in patient trajectories: sequences of structured medical ev
arXiv:2610.15124v1 Announce Type: new Abstract: Foundation models need to support diverse inference budgets, yet training a separate model for each budget duplicates pretraining effort. Elastic models
arXiv:2610.16990v1 Announce Type: new Abstract: Tabular data generation aims to synthesize realistic samples from limited observations while faithfully capturing the underlying data distribution. Tabu
arXiv:2610.16383v1 Announce Type: new Abstract: Elite athletics throwing provides a structured biomechanical action sequence together with an objective continuous outcome, namely throw distance, makin
arXiv:2601.17673v2 Announce Type: replace Abstract: Unified remote sensing multimodal models exhibit a pronounced spatial reversal curse: Although they can accurately recognize and describe object loc
arXiv:2610.15429v1 Announce Type: new Abstract: How do we tell a world model what information to preserve? We study this question through the lens of spectral representation learning. We introduce Spe
arXiv:2610.15394v1 Announce Type: new Abstract: Structured pruning is typically formulated as identifying which model dimensions to remove, often within the model's original representation. However, t
tests : consolidate context state tests into test-llama-context (#30023) tests : consolidate the context state tests into test-llama-context test-save-load-state, test-recurrent-state-rollback and tes
arXiv:2610.12936v1 Announce Type: new Abstract: Vision-language-action (VLA) models provide a unified framework for visual understanding, language grounding, and robot control, yet anticipating how th
I built a spotlight search for windows. It has an embedding model and a MoE models to go with it. The MoE It's 2 Qwen 3.5 4B models, I fine tuned one for coding work and another for agentic work, and
gguf's: https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf 'MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 35B-A3B variant, with 35B-A3B being the first MoE model in