Knowledge catalogue
arXiv:2606.24509v1 Announce Type: cross Abstract: Due to the wide use of graph-structured data in different fields of industry and science, the development of Graph Foundation Models (GFMs) has recent
arXiv:2606.24156v1 Announce Type: new Abstract: Visual token reduction has emerged as an effective strategy for accelerating Multimodal Large Language Models (MLLMs). Many existing methods prune token
arXiv:2606.18610v2 Announce Type: replace-cross Abstract: Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale. Action-conditioned video world
arXiv:2606.23897v1 Announce Type: cross Abstract: Prompt distillation compresses large vision-language models (VLMs) such as CLIP into lightweight student models by matching teacher predictions on unl
arXiv:2606.23754v1 Announce Type: cross Abstract: Deploying foundation models for robot control raises a central challenge: the expressive power that enables rich, multimodal perception also makes the
arXiv:2606.22497v1 Announce Type: new Abstract: Microscopic imaging provides essential visual evidence for studying plant biology and pathology at the cellular and subcellular levels. However, existin
arXiv:2505.24160v3 Announce Type: replace-cross Abstract: Medical image challenges have played a transformative role in advancing the field, catalyzing innovation and establishing new performance benc
arXiv:2606.23356v1 Announce Type: new Abstract: Machine learning models for remote sensing are trained and deployed on a static set of modalities. However, as we equip newer satellites with novel sens
arXiv:2606.20970v1 Announce Type: new Abstract: Omni-modal models can ingest video, audio, and text, but unified access to multiple modalities does not guarantee that a model uses the right evidence.
arXiv:2606.21885v1 Announce Type: new Abstract: Foundation models have achieved remarkable performance across medical question answering, imaging, and electronic health record (EHR) tasks, yet reliabl
arXiv:2606.20723v1 Announce Type: new Abstract: Chronic wound assessment remains a clinically challenging task that requires accurate interpretation of wound morphology, tissue composition, vascular c
arXiv:2508.18031v2 Announce Type: replace Abstract: Craniofacial reconstruction in forensics is one of the processes to identify victims of crime and natural disasters. Identifying an individual from
arXiv:2606.22158v1 Announce Type: new Abstract: Achieving human-like reasoning in Vision-Language Models (VLMs) remains a long-standing challenge. Recent approaches leverage Chain-of-Thought (CoT) rat
arXiv:2510.14656v2 Announce Type: replace-cross Abstract: This work proposes a two-stage physics-informed deep learning framework that combines neural-network-based sampling with statistical inference
Live Stream: Welcome to open source AI Lots of new folk are starting out on their journey with open models. Come join our livestream with all your questions about local models, open coding agents, and
arXiv:2410.02548v4 Announce Type: replace-cross Abstract: Flow Matching (FM) is a simulation-free method for learning a continuous, invertible flow that interpolates between two distributions, and in
arXiv:2606.21605v1 Announce Type: new Abstract: Vision foundation models have substantially advanced computer vision, enabling state-of-the-art performance in zero- and few-shot settings. They have be
arXiv:2510.18313v5 Announce Type: replace Abstract: Autonomous driving world models are expected to work effectively across three core dimensions: state, action, and reward. However, existing methods
arXiv:2606.22958v1 Announce Type: cross Abstract: Inference-time alignment of pretrained text-to-image models is typically performed along a single control axis, such as classifier-free guidance, atte
arXiv:2606.22248v1 Announce Type: new Abstract: Standard autoregressive Transformer decoders can often exhibit substantial forgetting under sequential fine-tuning on shifting curriculum distributions.
arXiv:2603.05963v2 Announce Type: replace Abstract: Recent advances in large-scale pretrained vision models have demonstrated impressive capabilities across a wide range of downstream tasks, including
arXiv:2606.21811v1 Announce Type: cross Abstract: End-to-end code agent training is resource-intensive and plateaus on the strategy-level reasoning needed to resolve code issues, since jointly optimiz
arXiv:2606.20878v1 Announce Type: new Abstract: Synthetic tabular data enables microdata sharing in regulated domains, yet deploying continuous-time generative models requires balancing analytical uti
arXiv:2606.22794v1 Announce Type: new Abstract: Mainstream Fast-Slow dual system vision-language-action models decouple a high-frequency action expert from a low-frequency vision-language model for ef
arXiv:2606.23243v1 Announce Type: new Abstract: Clinical audio diagnosis in low-resource settings requires models that identify conditions from minimal examples without large annotated corpora. We pro
arXiv:2606.20740v1 Announce Type: cross Abstract: Process Reward Models (PRMs) provide step-level verification for Large Language Model (LLM) reasoning, yet their training data acquisition remains a b
arXiv:2606.22430v1 Announce Type: cross Abstract: Because large language models (LLMs) are impressively successful in predicting text, it appears that they must have access to a 'world model' represen
Pretty remarkable what’s happening with open weights AI right now. We’re seeing models achieve SOTA results on specific tasks, and getting close to frontier on some areas of coding and other domains.
arXiv:2601.21817v3 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on open-ended tasks without ground-truth labels is increasingly done via the LLM-as-a-judge paradigm.
arXiv:2606.11219v1 Announce Type: cross Abstract: Audio language models (ALMs) are increasingly used for speech-based understanding, yet their ability to perform semantic reasoning beyond transcriptio
arXiv:2606.12273v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) offer an efficient alternative to autoregressive models through parallel decoding, yet existing post-training me
arXiv:2506.20040v3 Announce Type: replace-cross Abstract: Interpreting language models remains challenging due to the existence of residual stream, which linearly mixes and duplicates features across
arXiv:2606.11247v1 Announce Type: cross Abstract: Generative models are increasingly used to propose designs, data, and control actions for physical systems, yet many such systems are governed by hard
arXiv:2606.11542v1 Announce Type: cross Abstract: Modern pretrained self-supervised automatic speech recognition models are trained on large-scale audio data to encode speech into contextualized repre
arXiv:2606.12232v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faste
arXiv:2606.11477v1 Announce Type: cross Abstract: Correcting handwritten exams by hand is time-consuming and error-prone, particularly for large cohorts, while fully digital exams tend to force a dida
arXiv:2409.02426v5 Announce Type: replace-cross Abstract: Despite their empirical success across a wide range of generative tasks, the fundamental principles underlying the ability of diffusion models
arXiv:2606.11025v1 Announce Type: new Abstract: Recent work has demonstrated that online reinforcement learning (RL) can substantially improve the quality and alignment of flow matching models for ima
I asked 8 AI models (including Fable 5) for their world cup predictions. Going to keep an updated leaderboard based on match results to see which AI model performed the best! Launching tomorrow, right
In addition to transparency, I now believe frontier models should face mandatory third-party testing for cyber, bio, and autonomy risks—with the power to block or revoke deployment of models that pose
arXiv:2601.08379v2 Announce Type: replace-cross Abstract: Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their ou
arXiv:2606.10583v1 Announce Type: cross Abstract: We present NOVA, an autonomous symbolic regression framework that identifies interpretable car-following and lane-change structures from raw trajector
arXiv:2606.10581v1 Announce Type: new Abstract: Speech carries more information than just words: a child's voice, a fearful tone, or a noisy background should all lead a sufficiently competent spoken-
arXiv:2606.10868v1 Announce Type: new Abstract: Long-horizon autoregressive forecasting of oscillatory physical signals, such as seismograms, gravitational-wave strain, and similar wavefields is limit
arXiv:2606.08728v1 Announce Type: new Abstract: Mathematical reasoning has long served as a stringent test of machine intelligence; over the past decade, it has moved from a niche problem within NLP t
arXiv:2606.08088v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has recently become a key paradigm for improving the reasoning abilities of Large Language Models
arXiv:2606.07775v1 Announce Type: new Abstract: Recent breakthroughs in self-supervised learning (SSL), such as the Latent-Euclidean Joint-Embedding Predictive Architecture (LeJEPA), alongside success
arXiv:2606.08781v1 Announce Type: new Abstract: Document image binarization aims to separate foreground text from degraded backgrounds while preserving thin, broken, and low-contrast strokes. Although
arXiv:2606.08532v1 Announce Type: new Abstract: A scientific hypothesis is the first step in research and undergoes experimental validation, yet it also reflects a deep understanding of and reasoning
arXiv:2606.09718v1 Announce Type: cross Abstract: Diffusion models have demonstrated remarkable generative capabilities and have also emerged as powerful self-supervised representation learners, yet t
arXiv:2512.08724v3 Announce Type: replace Abstract: Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across se
arXiv:2507.00322v2 Announce Type: replace-cross Abstract: Despite remarkable advances in coding capabilities, language models (LMs) still struggle with simple syntactic tasks such as generating balanc
arXiv:2606.09311v1 Announce Type: new Abstract: Joint Embedding Predictive Architectures (JEPAs) have shown promising world modeling capabilities, enabling planning in latent space by optimizing actio
arXiv:2606.09813v1 Announce Type: cross Abstract: Embodied world models have emerged as a pivotal paradigm for visual robotic decision-making and interactive environment simulation. However, conventio
arXiv:2606.08400v1 Announce Type: cross Abstract: Graduate-level research reading report assessment creates a substantial labor burden for educators. While large language models (LLMs) hold great pote
arXiv:2606.09457v1 Announce Type: new Abstract: Embodied policies typically map current observations directly to actions, leaving candidate-action consequences implicit. World models provide predictiv
arXiv:2508.19857v3 Announce Type: replace Abstract: Many successful families of generative models leverage a low-dimensional latent distribution that is mapped to a data distribution. Though simple la
arXiv:2605.24890v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models commonly adapt pretrained Vision-Language Models (VLMs) to robot control by mapping visual observations and lang
arXiv:2606.08976v1 Announce Type: new Abstract: LLM-based RTL generation and reasoning is a promising direction for hardware design automation. High-quality benchmarks are critical infrastructure for
arXiv:2606.09511v1 Announce Type: new Abstract: Self-supervised data curation provides a pathway to scaling and improving the generalization capabilities of machine learning models. By leveraging self