Knowledge catalogue
arXiv:2605.03790v1 Announce Type: new Abstract: With advances in multimodal research and deep learning, Multimodal Large Language Models (MLLMs) have emerged as a powerful paradigm for a wide range of
arXiv:2502.11336v2 Announce Type: replace Abstract: Detecting texts generated by Large Language Models (LLMs) could cause grave mistakes due to incorrect decisions, such as undermining students' acade
arXiv:2605.01208v1 Announce Type: new Abstract: Vision-language model based graphical user interface (GUI) agents have shown strong interaction capabilities. However, they often behave unfaithfully, r
arXiv:2605.03588v1 Announce Type: new Abstract: We introduce a general framework for training flow matching models on Riemannian symmetric spaces, a large class of manifolds that includes the sphere,
arXiv:2605.02916v1 Announce Type: new Abstract: The development of AI-assisted Early Intensive Behavioral Intervention (EIBI) for Autism Spectrum Disorder (ASD) is severely constrained by data scarcit
arXiv:2604.14607v2 Announce Type: replace Abstract: We study the overall process of automatic formalization of GDPR provisions using large language models, within a human-in-the-loop verification fram
arXiv:2605.02913v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these syst
arXiv:2605.00831v1 Announce Type: cross Abstract: The rise of million-token, agent-based applications has placed unprecedented demands on large language model (LLM) inference services. The long-runnin
arXiv:2605.03377v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) achieve strong performance on node classification tasks but remain difficult to interpret, particularly with respect to whi
arXiv:2605.03690v1 Announce Type: new Abstract: We present a method for finding hierarchy-aware embeddings of knowledge graphs (KGs) using graph neural networks (GNNs) enriched with a semantic loss de
arXiv:2605.01423v1 Announce Type: cross Abstract: The escalating data scale in High-Energy Physics (HEP) fuels a growing aspiration for higher analytical efficiency. While Large Language Models (LLMs)
I usually avoid commenting too much on industry deals, but this one is fascinating. Certainly seems like a blow to the idea that Grok will remain a frontier model. Our agreement with @SpaceX means we
Introducing Factory Describe your idea in one sentence and Factory builds the first draft of the production for you. It plans the scenes, chooses the models, generates the assets, and wires everything
It's time to build NYC's physical AI community. We're hosting a small dinner in NYC for engineers and people building across robotics, autonomous systems, and world models. It's a pretty unique and sp
arXiv:2605.04035v1 Announce Type: new Abstract: We propose HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups. Our method em
arXiv:2605.03059v1 Announce Type: new Abstract: Medical experts often manually segment images to obtain diagnostic statistics and discard the resulting annotations. We aim to train segmentation models
arXiv:2605.03620v1 Announce Type: cross Abstract: Syndrome-based neural decoding (SBND) has emerged as a promising deep learning approach for soft-decision decoding of high-rate, short-length codes. H
arXiv:2605.01293v1 Announce Type: new Abstract: Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing
Tim Harford compares large language models to tricksters, arguing that LLMs excel at generating plausible-sounding text without necessarily ensuring accuracy or truthfulness. The article likely explor
arXiv:2605.02335v1 Announce Type: cross Abstract: Large Language Models (LLMs) have transformed agent-agent and human-agent interaction by enabling software, physical, and simulation agents to communi
arXiv:2505.16120v2 Announce Type: replace Abstract: The emergence of Large Language Models (LLMs) has reshaped agent systems. Unlike traditional rule-based agents with limited task scope, LLM-powered
arXiv:2605.03228v1 Announce Type: cross Abstract: As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that
arXiv:2604.05081v2 Announce Type: replace Abstract: We introduce MedGemma 1.5 4B, the latest model in the MedGemma collection. MedGemma 1.5 expands on MedGemma 1 by integrating additional capabilities
arXiv:2605.03343v1 Announce Type: new Abstract: Medical image super-resolution (MedSR) is essential for improving diagnostic precision across diverse imaging modalities such as MRI, CT, X-ray, Ultraso
arXiv:2603.06194v2 Announce Type: replace Abstract: Reinforcement learning (RL) for large language models (LLMs) has shown strong performance in single-turn tasks, but extending it to multi-turn inter
arXiv:2605.03359v1 Announce Type: new Abstract: Recent trends in sparse-view 3D reconstruction have taken two different paths: feed-forward reconstruction that predicts pixel-aligned point maps withou
Rivian CEO RJ Scaringe confirmed that the company is developing undisclosed variants of the R2, hinting at both a pickup truck and an 'R2X' performance model shortly after starting volume production o
arXiv:2605.03799v1 Announce Type: new Abstract: This preprint presents a systematic, research-oriented practicum that guides the reader through the entire modern NLP pipeline: from tokenisation and ve
arXiv:2507.15143v3 Announce Type: replace Abstract: This paper investigates the feasibility of human mobility in extreme urban morphologies characterized by high-density vertical structures and linear
arXiv:2605.01797v1 Announce Type: new Abstract: Integration of Answer Set Programming (ASP) with neural networks has emerged as a promising tool in Neuro-symbolic AI. While existing approaches extend
arXiv:2605.03769v1 Announce Type: new Abstract: Matrix-based optimizers have demonstrated immense potential in training Large Language Models (LLMs), however, designing an ideal optimizer remains a fo
arXiv:2605.03869v1 Announce Type: new Abstract: We investigate the effectiveness of adaptive zeroth-order (ZO) optimization for memory-constrained fine-tuning of large language models (LLMs). Contrary
arXiv:2605.02907v1 Announce Type: new Abstract: Softmax attention maps every query--key interaction into a probability distribution, but the underlying structure remains largely unexplored. We define
arXiv:2508.17466v3 Announce Type: replace-cross Abstract: This paper presents a deep learning framework designed to enhance the grasping capabilities of quadrupeds equipped with arms, with a focus on
arXiv:2603.20562v2 Announce Type: replace Abstract: Large language models (LLMs) are now widely used as judges, yet their decisions can change under presentation choices that should be irrelevant. We
arXiv:2605.03929v1 Announce Type: cross Abstract: Stem retrieval, the task of matching missing stems to a given audio submix, is a key challenge currently limited by models that discard temporal infor
arXiv:2605.03357v1 Announce Type: new Abstract: Mean Field Games (MFGs) provide a powerful framework for modeling the collective behavior of large populations of interacting agents. In this paper, we
arXiv:2605.03510v1 Announce Type: new Abstract: Human languages expand vocabularies by combining existing morphemes rather than inventing arbitrary forms. Communicative efficiency shapes lexical syste
arXiv:2605.03260v1 Announce Type: new Abstract: Model Predictive Path Integral (MPPI) control is a powerful sampling-based strategy for nonlinear autonomous systems. However, its performance is often
arXiv:2605.03626v1 Announce Type: new Abstract: To address module fragmentation, uninterpretable mappings, and deployment constraints in RAW-domain demosaicing, color correction, and detail enhancemen
arXiv:2605.03244v1 Announce Type: new Abstract: Movie scripts pose a fundamental challenge for automatic summarization due to their non-linear, cross-cut narrative structure, which makes surface-level
arXiv:2503.06917v5 Announce Type: replace Abstract: We study zeroth-order optimization where solutions must minimize a cost d(s) while maintaining high probability under a complex generative prior L(s
arXiv:2510.09768v2 Announce Type: replace Abstract: We present an empirical study in the geometric task of learning interatomic potentials, which shows equivariance matters even more at larger scales;
arXiv:2605.03723v1 Announce Type: new Abstract: The rise of large language models (LLMs) has created an urgent need to distinguish between human-written and LLM-generated text to ensure authenticity a
arXiv:2508.18983v3 Announce Type: replace Abstract: The Mixture of Experts (MoE) architecture has emerged as a key technique for scaling Large Language Models by activating only a subset of experts pe
arXiv:2605.03371v1 Announce Type: new Abstract: Cross-scene hyperspectral image (HSI) classification stands as a fundamental research topic in remote sensing, with extensive applications spanning vari
Stop token maxxing 🛑 Our CEO @ashashutosh sat down with @a16z General Partner Peter Levine to discuss why we’re moving beyond the vector database: '85% of an agent’s work isn't the model; it's the und
arXiv:2605.03780v1 Announce Type: cross Abstract: Transformers are effective at inferring the latent task from context via two inference modes: recognizing a task seen during training, and adapting to
arXiv:2605.03712v1 Announce Type: cross Abstract: Training-free conditional diffusion provides a flexible alternative to task-specific conditional model training, but existing samplers often allocate
arXiv:2605.01134v1 Announce Type: new Abstract: The dominant noun-based modeling paradigm has fundamentally constrained AI development, precluding any adequate representation of the future as an open
arXiv:2605.03314v1 Announce Type: new Abstract: In single-stream autoregressive interfaces, the same tokens both update the model state and constitute an irreversible public commitment. This coupling
This article explains how retrieval quality directly impacts large language model performance in retrieval-augmented generation (RAG) systems, emphasizing that even advanced LLMs cannot produce better
arXiv:2605.02960v1 Announce Type: new Abstract: Production LLM workloads increasingly serve discriminative tasks, such as classification, recommendation, and verification, whose answers are read from
5.5 instant comes to ChatGPT today! imo it is a pretty big upgrade, i really like using it. Excited that we're updating the default model in ChatGPT today! 5.5 instant is a substantial improvement in
arXiv:2605.01920v1 Announce Type: cross Abstract: Large language models are increasingly used within larger systems ('LLM agents'). These make a sequence of LLM calls, each call providing the LLM with
arXiv:2605.02350v1 Announce Type: new Abstract: We study the complexity of smoothed agnostic learning of halfspaces on {pm 1}^n under the uniform distribution in the model of itet{KM25} where each inp
arXiv:2603.29895v2 Announce Type: replace-cross Abstract: We present a new theory of categorization based on an information-theoretic rational analysis. To evaluate this theory, we investigate how wel
arXiv:2605.01034v1 Announce Type: new Abstract: As large language models grow increasingly capable, concerns about their safe deployment have intensified. While numerous alignment strategies aim to re
arXiv:2510.18232v2 Announce Type: replace Abstract: Generating high-quality synthetic text under differential privacy (DP) is critical for training and evaluating language models without compromising
arXiv:2605.02849v1 Announce Type: new Abstract: Diffusion models provide a powerful generative prior for perceptual reconstruction at ultra-low bitrates, but effective video compression requires contr