Knowledge catalogue
This post compares two high-end graphics cards—the AMD Radeon RX 7900 XTX and NVIDIA GeForce RTX 4070 Ti Super—across multiple demanding workloads including gaming, AI image generation with Comfy UI,
I am very proud of our team for releasing EDINET-Bench, and it is fantastic to see a Japanese financial dataset recognized at #ICLR2026 this week. We need more diverse, non-English datasets to evaluat
This post draws a humorous parallel between using images of salarymen eating ramen as a test case for AI image generation models in Eastern contexts and the Western 'Will Smith eating spaghetti' meme,
GDPval is one of the most important benchmarks of AI ability because it is based on human expertise. It compares expert human performance to AI performance using expert human judges who spend an avera
arXiv:2601.04588v2 Announce Type: replace Abstract: Segmentation of the left atrial (LA) wall and endocardium from late gadolinium-enhanced (LGE) MRI is essential for quantifying atrial fibrosis in pa
arXiv:2604.14263v1 Announce Type: cross Abstract: Accurate detection and segmentation of glomeruli in kidney tissue are essential for diagnostic applications. Traditional deep learning methods primari
arXiv:2604.15215v1 Announce Type: new Abstract: We present a novel hierarchical spatiotemporal action tokenizer for in-context imitation learning. We first propose a hierarchical approach, which consi
arXiv:2604.14635v1 Announce Type: new Abstract: We present a curated multi-platform LiDAR reference dataset from an instrumented ICOS forest plot, explicitly designed to support calibration, benchmark
arXiv:2601.16870v2 Announce Type: replace Abstract: Integrated control of wheelchairs and wheelchair-mounted robotic arms (WMRAs) has strong potential to increase independence for users with severe mo
arXiv:2604.15289v1 Announce Type: new Abstract: In recent years, reinforcement learning (RL) has shown remarkable success in robotics when a fast and accurate simulator is available for a given task.
NVIDIA released PhysicsNeMo, an open-source AI framework designed to speed up nuclear reactor design through physics-based simulations. The framework uses machine learning-based multiphysics emulators
arXiv:2604.15291v1 Announce Type: new Abstract: The reliability of a machine vision system for autonomous driving depends heavily on its training data distribution. When a vehicle encounters significa
arXiv:2601.07667v2 Announce Type: replace Abstract: Due to the prevalence of large language models (LLMs), key-value (KV) cache reduction for LLM inference has received remarkable attention. Among num
arXiv:2604.13812v1 Announce Type: new Abstract: Quantum circuit optimization is a central task in Quantum Computing, as current Noisy Intermediate Scale Quantum devices suffer from error propagation t
arXiv:2604.14882v1 Announce Type: cross Abstract: Rapid urbanization and continuous population growth have made municipal solid waste management increasingly challenging. These challenges highlight th
arXiv:2604.14534v1 Announce Type: new Abstract: Purpose. Athlete monitoring is constrained by small cohorts, heterogeneous biomarker scales, limited feasibility of repeated sampling, and the lack of r
arXiv:2601.21003v2 Announce Type: replace Abstract: Large Language Models usually put more emphasis on accuracy and therefore, will guess even when not certain about the prediction, which is especiall
arXiv:2603.10992v3 Announce Type: replace-cross Abstract: Building local surrogates to accelerate stationary point searches on potential energy surfaces spans decades of effort. Done correctly, surrog
arXiv:2604.15202v1 Announce Type: new Abstract: Coverage path planning on irregular hexagonal grids is relevant to maritime surveillance, search and rescue and environmental monitoring, yet classical
arXiv:2604.14171v1 Announce Type: new Abstract: Romanized Nepali, the Nepali language written in the Latin alphabet, is the dominant medium for informal digital communication in Nepal, yet it remains
arXiv:2604.15090v1 Announce Type: new Abstract: Any-Time Person Re-identification (AT-ReID) necessitates the robust retrieval of target individuals under arbitrary conditions, encompassing both modali
arXiv:2411.05472v2 Announce Type: replace Abstract: The paradigm shift toward structure-driven molecule generation has been propelled by advances in deep generative models, such as variational auto-en
arXiv:2604.14251v1 Announce Type: new Abstract: Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalat
arXiv:2604.14961v1 Announce Type: new Abstract: Contextual bandit algorithms suffer from high regret during cold-start, when the learner has insufficient data to distinguish good arms from bad. We pro
arXiv:2604.14602v1 Announce Type: new Abstract: Large language models (LLMs) frequently generate toxic content, posing significant risks for safe deployment. Current mitigation strategies often degrad
arXiv:2603.06431v2 Announce Type: replace-cross Abstract: Neural network methods for PDEs require reliable error control in function space norms. However, trained neural networks can typically only be
arXiv:2604.14692v1 Announce Type: new Abstract: Video understanding requires identifying and reasoning over semantically discriminative visual objects across frames, yet existing object-agnostic solut
arXiv:2602.08698v2 Announce Type: replace Abstract: This study examines the practical applications and methodological implications of Machine Translation in Indian Languages, specifically Bangla, Mala
arXiv:2604.14645v1 Announce Type: new Abstract: Convolutional neural networks (CNNs) often exhibit poor generalisation in limited training data scenarios due to overfitting and insufficient feature di
arXiv:2604.14169v1 Announce Type: new Abstract: In large-scale construction projects, the continuous evolution of decisions generates extensive records, most often captured in meeting minutes. Since d
arXiv:2604.14519v1 Announce Type: cross Abstract: Catastrophic forgetting remains a fundamental challenge in continual learning, in which models often forget previous knowledge when fine-tuned on a ne
arXiv:2604.13814v1 Announce Type: cross Abstract: Recent advances in artificial intelligence (AI) have shown promise in automating key aspects of Agile project management, yet their impact on team cog
arXiv:2604.13567v1 Announce Type: cross Abstract: Heart sound signals, phonocardiography (PCG) signals, allow for the automatic diagnosis of potential cardiovascular pathology. Such classification tas
arXiv:2509.01728v4 Announce Type: replace-cross Abstract: Recent advances in the development of robotic foundation models have led to promising end-to-end and general-purpose capabilities in robotic s
arXiv:2604.15267v1 Announce Type: cross Abstract: It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite tr
arXiv:2512.14098v3 Announce Type: replace Abstract: Any-to-Any models are an emerging class of multimodal models that accept combinations of text and multimodal data as input and generate them as outp
arXiv:2604.14214v1 Announce Type: new Abstract: Large Language Models utilizing reasoning techniques improve task performance but incur significant latency and token costs due to verbose generation. E
arXiv:2604.14545v1 Announce Type: new Abstract: Visual-inertial odometry (VIO) is widely used for mobile robot localization, but its long-term accuracy degrades without global constraints. Incorporati
Data Driven Agent Design with Evals & Hill Climbing Algorithms this is a mental model dump i’ve been thinking through + iterating on as we’re building self-improvement infra around agents: - mining Tr
arXiv:2602.22839v2 Announce Type: replace Abstract: Presentation generation requires deep content research, coherent visual design, and iterative refinement based on observation. However, existing pre
arXiv:2510.08483v2 Announce Type: replace Abstract: Parallel scaling has emerged as a powerful paradigm to enhance reasoning capabilities in large language models (LLMs) by generating multiple Chain-o
arXiv:2601.09240v2 Announce Type: replace Abstract: Satellite videos provide continuous observations of surface dynamics but pose significant challenges for multi-object tracking (MOT), especially und
arXiv:2411.00361v4 Announce Type: replace Abstract: Hierarchical reinforcement learning (HRL) enables agents to solve complex, long-horizon tasks by decomposing them into manageable sub-tasks. However
arXiv:2511.22521v2 Announce Type: replace Abstract: Document visual question answering requires models not only to answer questions correctly, but also to precisely localize answers within complex doc
arXiv:2509.03472v2 Announce Type: replace Abstract: Differentially-Private SGD (DP-SGD) and its adaptive variant DP-Adam are powerful techniques to protect user privacy when using sensitive data to tr
arXiv:2602.22699v2 Announce Type: replace-cross Abstract: SQL is the de facto interface for exploratory data analysis; however, releasing exact query results can expose sensitive information through m
arXiv:2604.15168v1 Announce Type: new Abstract: Autonomous drone racing demands robust real-time localization under extreme conditions: high-speed flight, aggressive maneuvers, and payload-constrained
arXiv:2604.14560v1 Announce Type: new Abstract: Video face restoration aims to enhance degraded face videos into high-quality results with realistic facial details, stable identity, and temporal coher
arXiv:2604.05541v2 Announce Type: replace Abstract: Reliable interpretation of echocardiography (Echo) is crucial for assessing cardiac function, which demands clinicians to synchronously orchestrate
arXiv:2604.13097v1 Announce Type: cross Abstract: Embodied agents increasingly rely on modular capabilities that can be installed, upgraded, composed, and governed at runtime. Prior work has introduce
arXiv:2410.01540v4 Announce Type: replace Abstract: Classical diffusion models typically rely on isotropic Gaussian noise, treating all regions uniformly and overlooking structural information importa
arXiv:2604.13959v1 Announce Type: new Abstract: As AI moves from data centers to robots and wearables, scaling ever-larger models becomes insufficient. Physical AI operates under tight latency, energy
arXiv:2604.14727v1 Announce Type: new Abstract: To quantify the geometric expressivity of transformers, we introduce a tropical geometry framework to characterize their exact spatial partitioning capa
arXiv:2604.14640v1 Announce Type: new Abstract: The proliferation of financial misinformation poses a severe threat to market stability and investor trust, misleading market behavior and creating crit
arXiv:2604.15115v1 Announce Type: new Abstract: Most existing Byzantine-robust federated learning (FL) methods suffer from slow and unstable convergence. Moreover, when handling a substantial proporti
arXiv:2603.24985v2 Announce Type: replace Abstract: Segmenting the left atrial wall from late gadolinium enhancement magnetic resonance images (MRI) is challenging due to the wall's thin geometry, low
arXiv:2604.14459v1 Announce Type: new Abstract: For humans, filler-gap dependencies require a shared representation across different syntactic constructions. Although causal analyses suggest this may
arXiv:2604.14734v1 Announce Type: new Abstract: Morphing is a challenge to face recognition (FR) for which several morphing attack detection solutions have been proposed. We argue that face recognitio
arXiv:2510.08055v2 Announce Type: replace Abstract: Large Language Model (LLM) inference in production must meet stringent service-level objectives for both time-to-first-token (TTFT) and time-between
arXiv:2604.14397v1 Announce Type: new Abstract: We study the task of automatically expanding WordNet-style lexical resources to new languages through sense generation. We generate senses by associatin