Knowledge catalogue
arXiv:2605.19723v1 Announce Type: cross Abstract: Mathematical reasoning is essential for problem-solving in education, science, and industry, serving as a crucial benchmark for evaluating artificial
arXiv:2605.19782v1 Announce Type: new Abstract: LLM discovery and optimization systems are increasingly applied across domains, implementing a common propose-evaluate-revise loop. Such optimization or
arXiv:2605.18878v1 Announce Type: cross Abstract: Hospital readmission within 30 days of discharge is a leading driver of morbidity, mortality, and avoidable healthcare expenditure in congestive heart
arXiv:2503.16309v2 Announce Type: replace-cross Abstract: Advanced navigation techniques in image-guided interventions and surgical robotics require the rapid and precise alignment of 3D preoperative
arXiv:2605.19744v1 Announce Type: new Abstract: Detecting anomalies in traffic scenes is crucial for ensuring safety in autonomous driving, yet collecting representative anomalous data remains challen
arXiv:2605.19095v1 Announce Type: cross Abstract: Schedule-Free Learning has shown promise as a practical anytime training method for machine learning, showing success across dozens of standard benchm
arXiv:2605.18971v1 Announce Type: cross Abstract: What determines the quality of a tabular foundation model? Unlike language or vision, tabular foundation models acquire their inductive biases almost
arXiv:2605.19213v1 Announce Type: new Abstract: Circular sample plots are a cornerstone of forest inventory, yet accurate measurement of tree diameter at breast height (DBH) and spatial location withi
arXiv:2605.06270v2 Announce Type: replace Abstract: Feed-forward 3D reconstruction models based on Vision Transformers can directly estimate scene geometry and camera poses from a small set of input i
arXiv:2605.19378v1 Announce Type: new Abstract: This paper systematically diagnoses the training failure modes of Token-Choice sparse Mixture-of-Experts (MoE) on video Diffusion Transformers. Starting
arXiv:2505.23747v2 Announce Type: replace-cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving
arXiv:2605.18791v1 Announce Type: cross Abstract: Existing spectral benchmarks are limited in scale, modality alignment, and evaluation scope, and typically focus on either specialized models or multi
arXiv:2605.19727v1 Announce Type: new Abstract: Existing 3D foundation models typically align point clouds to frozen vision-language spaces like CLIP, which achieve strong cross-modal retrieval by com
The future of biology shouldn’t stay behind black-box APIs. Especially when it touches personal health. Whether you’re @bryan_johnson measuring every biomarker, or @sytses openly sharing and analyzing
arXiv:2605.18826v1 Announce Type: cross Abstract: The attention interaction matrix QK^{op} contains two entangled computations: a skew-symmetric component that redistributes information between positi
arXiv:2605.18837v1 Announce Type: cross Abstract: Wearable devices enable continuous health monitoring from multimodal signals, but real-world deployment is hindered by limited labeled data and pervas
arXiv:2605.19762v1 Announce Type: new Abstract: Code has become a standard component of modern foundation language model (LM) training, yet its role beyond programming remains unclear. We revisit the
arXiv:2605.17046v1 Announce Type: cross Abstract: Autonomous AI coding agents are becoming a core tool for ML practitioners in industry and research alike. Despite this growing adoption, no standardiz
arXiv:2605.18700v1 Announce Type: new Abstract: Prior work on fine-grained image recognition (FGIR) has established the importance of the backbone selection, but has neglected the accuracy-vs-cost tra
arXiv:2605.16817v1 Announce Type: cross Abstract: Learned image compression has achieved competitive rate-distortion performance, but very-low-bitrate reconstruction remains difficult because the tran
arXiv:2605.16649v1 Announce Type: new Abstract: Recent diffusion-based video generators have achieved remarkable visual fidelity and prompt controllability, yet scaling them to ultra-high-resolution (
arXiv:2605.16823v1 Announce Type: new Abstract: Molecular representation learning has become a central approach in AI-driven drug discovery, yet existing molecular tokenizations such as SMILES remain
arXiv:2605.16579v1 Announce Type: new Abstract: Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attenti
arXiv:2603.12145v2 Announce Type: replace-cross Abstract: Translating complex reinforcement learning (RL) environments into high-performance implementations has traditionally required months of specia
arXiv:2605.17435v1 Announce Type: new Abstract: Biomedical question answering often requires decisions from retrieved literature whose relevance, quality, and support for candidate answers are uneven.
arXiv:2601.01593v2 Announce Type: replace Abstract: Manual font design is an intricate process that transforms a stylistic visual concept into a coherent glyph set. This challenge persists in automate
arXiv:2605.16736v1 Announce Type: new Abstract: Flow and diffusion models achieve high-fidelity, high-resolution image synthesis, but often require many function evaluations (NFEs) at sampling time. E
arXiv:2604.01674v2 Announce Type: replace Abstract: Model merging aims to integrate multiple expert models into a single model that inherits their complementary strengths without incurring the inferen
arXiv:2605.18180v1 Announce Type: cross Abstract: Wide neural networks in the feature-learning regime drive modern deep learning, and yet they remain far less studied than their kernel-regime counterp
arXiv:2605.16406v1 Announce Type: new Abstract: Night-time pedestrian detection remains challenging because labelled night-time data are limited and large illumination differences make daytime-only tr
arXiv:2605.16519v1 Announce Type: new Abstract: Accurate polyp segmentation in colonoscopy is essential for early colorectal cancer detection, yet real-world clinical environments pose persistent chal
arXiv:2605.16696v1 Announce Type: new Abstract: Face inpainting techniques recover missing or occluded facial regions in a visually realistic manner, but preserving the identity in the final output re
arXiv:2605.17165v1 Announce Type: new Abstract: Joint-Embedding Predictive Architectures (JEPA) are a promising framework for self-supervised video representation learning, yet the behavior of auxilia
arXiv:2605.17693v1 Announce Type: cross Abstract: Structure-based drug design has been accelerated by pocket-aware 3D generative models, yet most methods primarily fit the training distribution and ma
arXiv:2605.18462v1 Announce Type: new Abstract: Named entity recognition (NER) has been one of the essential preliminary steps in modern NLP applications. This report focuses on implementing the NER t
arXiv:2605.16928v1 Announce Type: cross Abstract: Long-context inference in large language models is bottlenecked by the quadratic cost of full attention. Existing efficient alternatives often rely ei
arXiv:2605.16349v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures achieve scalable capacity through sparse routing, yet the geometric structure of expert specialization remains po
arXiv:2605.17879v1 Announce Type: cross Abstract: Training frontier-scale foundation models involves coordinating tens of thousands of GPUs over multi-month runs, where even minor performance degradat
arXiv:2605.18601v1 Announce Type: new Abstract: Modern interactive video world models have achieved impressive visual fidelity, yet lack fine-grained multi-entity control and cross-entity, cross-world
arXiv:2605.16390v1 Announce Type: new Abstract: We investigate whether the training protocol can induce spatial locality in the early layers of a Vision Transformer (ViT) trained from scratch, without
arXiv:2605.16439v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have emerged as a critical and fast-growing extension of Large Language Models (LLMs) that enable multimodal reasoning t
arXiv:2605.16743v1 Announce Type: new Abstract: Cross-embodiment learning from human demonstrations is hindered by the visual gap between human and robot embodiments. While self-supervised learning (S
arXiv:2605.18541v1 Announce Type: new Abstract: Modeling hyperspectral imagery (HSI) across different sensors presents a fundamental challenge due to variations in wavelength coverage, band sampling,
arXiv:2410.13846v3 Announce Type: replace-cross Abstract: Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. M
arXiv:2509.15357v2 Announce Type: replace Abstract: Diffusion models have achieved strong results in text-to-image generation, but important limitations remain as prompts become more structured and mu
arXiv:2501.06933v3 Announce Type: replace Abstract: Nonlinear conservation laws govern a broad class of important physical systems in science and industry and are central to scientific machine learnin
arXiv:2605.16893v1 Announce Type: new Abstract: Recent studies introduce conditional memory modules that decouple knowledge storage from neural computation, enabling more direct knowledge access. Comp
arXiv:2605.16818v1 Announce Type: cross Abstract: Learning physical dynamics directly from incomplete observations is challenging because authentic occlusions are structured, sample-dependent, and oft
arXiv:2605.17907v1 Announce Type: cross Abstract: By sharing intermediate features, collaborative perception extends each agent's sensing beyond standalone limits, but real-world feature modality hete
arXiv:2605.17283v1 Announce Type: cross Abstract: Recent progress in formal theorem proving has benefited from large-scale proof generation and verifier-aware training, but agentic proving is rarely i
arXiv:2602.03352v2 Announce Type: replace Abstract: Reinforcement learning (RL) has shown strong promise for LLM-based machine translation, with recent methods such as GRPO demonstrating notable gains
arXiv:2605.18464v1 Announce Type: new Abstract: Contrastively trained vision-language models such as CLIP provide strong zero-shot transfer by aligning images and text in a shared embedding space. How
arXiv:2601.22664v4 Announce Type: replace Abstract: Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is
Running the same CNA search on base models (before instruction tuning) yields a structurally similar set of neurons, but ablating them produces almost no behavioral change. We read this as evidence th
arXiv:2605.16412v1 Announce Type: cross Abstract: Despite the central role of action in embodied intelligence, learning transferable action representations from visual transitions remains a fundamenta
arXiv:2605.18026v1 Announce Type: new Abstract: Roundabouts, characterized by frequent merging and yielding interactions, remain a safety-critical corner case for the development and testing of intell
arXiv:2605.18018v1 Announce Type: cross Abstract: We present SWIM (See What I Mean), a novel training strategy that aligns vision and language representations to enable fine-grained object understandi
arXiv:2605.17630v1 Announce Type: new Abstract: Here's a trimmed version under 1920 characters: Open-vocabulary segmentation models such as SAM3 achieve strong performance through concept-level text p
arXiv:2605.18039v1 Announce Type: new Abstract: Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, a
arXiv:2605.17842v1 Announce Type: new Abstract: Autoregressive language models execute Transformer layers sequentially, creating a latency bottleneck that is not removed by conventional tensor or pipe