Knowledge catalogue
arXiv:2604.19300v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) have recently achieved strong performance across various audio-centric tasks. However, hallucination, where models
arXiv:2510.04800v3 Announce Type: replace Abstract: Recent progress in large language models demonstrates that hybrid architectures--combining self-attention mechanisms with structured state space mod
arXiv:2604.19043v1 Announce Type: new Abstract: Efficient construction of models capturing the preconditions and effects of actions is essential for applying AI planning in real-world domains. Extensi
arXiv:2604.18878v1 Announce Type: new Abstract: We introduce LegalBench-BR, the first public benchmark for evaluating language models on Brazilian legal text classification. The dataset comprises 3,10
Props to @augmentcode for being one of the first to ship Kimi K2.6 to their users. Open models are now the frontier. Support for Kimi K2.6 is now here in Augment Code! We teamed up with @Kimi_Moonshot
arXiv:2510.06133v2 Announce Type: replace Abstract: Diffusion large language models (dLLMs) generate text through iterative denoising. In commonly adopted parallel decoding schemes, each step confirms
arXiv:2604.16363v1 Announce Type: cross Abstract: Text-to-image models are commercially valuable assets often distributed under restrictive licenses, but such licenses are enforceable only when violat
arXiv:2604.16940v1 Announce Type: new Abstract: Supervised Fine-Tuning (SFT) accelerates taskspecific large language models (LLMs) development, but the resulting proliferation of finetuned models incu
arXiv:2604.17585v1 Announce Type: new Abstract: Salient object detection (SOD) requires modeling both long-range contextual dependencies and fine-grained structural details, which remains challenging
arXiv:2604.16980v1 Announce Type: new Abstract: Background: Large language models (LLMs) are increasingly proposed for diagnostic support, but few evaluations use real-world multimodal inpatient data,
arXiv:2604.18092v1 Announce Type: new Abstract: Small language models fine-tuned for graph property estimation have demonstrated strong in-distribution performance, yet their generalization capabiliti
arXiv:2604.18564v1 Announce Type: new Abstract: Video world models have achieved remarkable success in simulating environmental dynamics in response to actions by users or agents. They are modeled as
Please don’t trust your chatbot for medical advice. 🙏 Remember how I used to say that large language models are “frequently wrong, never in doubt”, and how I warned three years ago on 60 Minutes that
arXiv:2506.02541v2 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) can recognize individuals in images and disclose sensitive personal information about them, raising criti
arXiv:2602.14466v2 Announce Type: replace Abstract: With natural language generation becoming a popular use case for language models, the Bias Benchmark for Question-Answering (BBQ) has grown to be an
arXiv:2604.16429v1 Announce Type: cross Abstract: We introduce Mosaic, a probabilistic weather forecasting model that addresses two principal sources of spectral degradation in ML-based weather predic
arXiv:2604.18518v1 Announce Type: new Abstract: Uniform Discrete Diffusion Model (UDM) has recently emerged as a promising paradigm for discrete generative modeling; however, its integration with rein
arXiv:2602.19946v4 Announce Type: replace Abstract: Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following. But do they perform well as
arXiv:2604.15822v1 Announce Type: cross Abstract: Automated classification of electrocardiogram (ECG) signals is a useful tool for diagnosing and monitoring cardiovascular diseases. This study compare
arXiv:2604.15911v1 Announce Type: new Abstract: Video diffusion models have rapidly become the dominant paradigm for high-fidelity generative video synthesis, but their practical deployment remains co
arXiv:2604.15380v1 Announce Type: cross Abstract: We present an exascale workflow for materials discovery using atomistic graph foundation models built on HydraGNN. We jointly train on 16 open first-p
arXiv:2505.19563v4 Announce Type: replace Abstract: Mathematical reasoning has long been a key benchmark for evaluating large language models. Although substantial progress has been made on math word
arXiv:2604.15756v1 Announce Type: new Abstract: Vision-language models (VLMs) such as CLIP exhibit strong Out-of-distribution (OOD) detection capabilities by aligning visual and textual representation
arXiv:2603.13966v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models are increasingly evaluated across multiple simulation benchmarks, yet adding each benchmark to an evaluation pip
arXiv:2505.10846v3 Announce Type: replace Abstract: This paper presents AutoRAN, the first framework to automate the hijacking of internal safety reasoning in large reasoning models (LRMs). At its cor
arXiv:2604.14156v1 Announce Type: new Abstract: Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work ha
arXiv:2604.13392v1 Announce Type: new Abstract: Tabular data remains prevalent in high-stakes domains such as healthcare and finance, where predictive models are expected to provide both high accuracy
arXiv:2604.14973v1 Announce Type: cross Abstract: A vision foundation model outputs an embedding vector for an image, which can be affected by common editing operations (e.g., JPEG compression, bright
arXiv:2604.13803v1 Announce Type: new Abstract: Vision-language models are increasingly deployed in high-stakes settings, yet their susceptibility to sycophantic manipulation remains poorly understood
arXiv:2512.10877v4 Announce Type: replace Abstract: Discrete diffusion models (DMs) have achieved strong performance in language and other discrete domains, offering a compelling alternative to autore
arXiv:2510.14232v2 Announce Type: replace-cross Abstract: Competitive programming has become a rigorous benchmark for evaluating the reasoning and problem-solving capabilities of large language models
arXiv:2603.10652v2 Announce Type: replace-cross Abstract: In real-world deployment, vision-language models often encounter disturbances such as weather, occlusion, and camera motion. Under such condit
arXiv:2604.12978v1 Announce Type: new Abstract: Optical character recognition (OCR) has advanced rapidly with the rise of vision-language models, yet evaluation has remained concentrated on a small cl
Parcae is a stable looped language model that matches the quality of a Transformer twice its size — a 770M model reaching 1.3B-level performance. We introduce the first scaling laws for looping and sh
arXiv:2604.12652v1 Announce Type: cross Abstract: Reinforcement learning (RL) can improve the prompt following capability of text-to-image (T2I) models, yet obtaining high-quality reward signals remai
arXiv:2604.12371v1 Announce Type: new Abstract: We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms
arXiv:2512.00412v4 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical
arXiv:2604.12481v1 Announce Type: new Abstract: Text-to-image (T2I) generative models achieve impressive visual fidelity but inherit and amplify demographic imbalances and cultural biases embedded in
arXiv:2604.11840v1 Announce Type: new Abstract: Large language models are increasingly used as agents in social, economic, and policy simulations. A common assumption is that stronger reasoning should
As of April 2026, Latent Space published a curated ranking of the top locally-runnable AI models, providing a research-based overview of the best open-weight or self-hostable models available at that
arXiv:2604.11540v1 Announce Type: new Abstract: Current large language models require hundreds of billions of parameters yet struggle with domain-specific reasoning and tool coordination in materials
arXiv:2510.01544v2 Announce Type: replace Abstract: Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning rem
arXiv:2604.10985v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new
arXiv:2604.11177v1 Announce Type: new Abstract: We benchmark how internal reasoning traces, which we call thought streams, affect video scene understanding in vision-language models. Using four config
arXiv:2604.09920v1 Announce Type: new Abstract: Vision foundation models (VFMs) offer the promise of zero-shot object detection without task-specific training data, yet their performance in complex ag
arXiv:2604.09656v1 Announce Type: cross Abstract: Despite there now being more than 1,000 FDA-authorised AI medical devices, formal equity assessments -- whether model performance is uniform across pa
arXiv:2604.09651v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are emerging as a cornerstone for robotics, with flow-matching policies like pi_0 showing great promise in generatin
arXiv:2601.08209v3 Announce Type: replace Abstract: In domains such as materials science, biomedicine, and finance, high-stakes deployment of large language models (LLMs) requires injecting private, d
arXiv:2604.04385v3 Announce Type: replace-cross Abstract: This paper localizes the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected co
arXiv:2604.09629v1 Announce Type: new Abstract: Humor generation poses a significant challenge for Large Language Models (LLMs), because their standard training objective - predicting the most likely
arXiv:2604.09688v1 Announce Type: new Abstract: Recent large-scale generative models enable high-quality 3D synthesis. However, the public accessibility of pre-trained weights introduces a critical vu
arXiv:2509.22403v2 Announce Type: replace Abstract: Mobility Foundation Models (MFMs) have advanced the modeling of human movement patterns, yet they face a ceiling due to limitations in data scale an
arXiv:2604.10976v1 Announce Type: cross Abstract: Generalized linear mixed-effects models (GLMMs) are widely used to analyze grouped and hierarchical data. In a GLMM, each response is assumed to follo
arXiv:2602.03402v3 Announce Type: replace Abstract: Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerabl
arXiv:2307.01139v2 Announce Type: replace-cross Abstract: Instruction finetuning is a popular paradigm to align large language models (LLM) with human intent. Despite its popularity, this idea is less
arXiv:2604.11663v1 Announce Type: new Abstract: Large Language Models (LLMs) have been shown to generate harmful content. However, the underlying causes of such behavior remain under explored. We prop
arXiv:2604.08561v1 Announce Type: new Abstract: We investigate how successful bias mitigation reshapes the embedding space of encoder-only and decoder-only foundation models, offering an internal audi
arXiv:2604.08564v1 Announce Type: new Abstract: Auto-regressive models (ARMs) have established a dominant paradigm in language modeling. However, their strictly sequential decoding paradigm imposes fu
arXiv:2604.09151v1 Announce Type: new Abstract: Accurate segmentation of surgical instruments in robotic-assisted surgery is critical for enabling context-aware computer-assisted interventions, such a
arXiv:2604.09425v1 Announce Type: new Abstract: Vision Language Models (VLMs) have achieved remarkable success by integrating visual encoders with large language models (LLMs). While VLMs process dens