Knowledge catalogue
arXiv:2606.23436v1 Announce Type: new Abstract: Unsupervised video object tracking aims to decompose dynamic scenes into persistent, object-centric entities without manual annotations. Many recent app
arXiv:2606.23069v1 Announce Type: new Abstract: Few-shot object detection aims to detect novel object categories from only a few labeled examples, avoiding costly large-scale annotation. Recent protot
arXiv:2606.21913v1 Announce Type: new Abstract: Cell segmentation is critical for computational pathology and biomedical discovery. While recent Vision Foundation Models (VFMs) have demonstrated remar
arXiv:2603.08305v2 Announce Type: replace Abstract: Text-conditioned generative models for volumetric medical imaging provide semantic control but lack explicit anatomical guidance, often resulting in
arXiv:2606.22823v1 Announce Type: new Abstract: Enzyme substrate interaction (ESI) prediction is a fundamental computational task for biocatalyst discovery and reaction screening in large biochemical
arXiv:2409.05755v3 Announce Type: replace Abstract: Over the past decade, Graph Neural Networks (GNNs) have achieved great success on machine learning tasks with relational data. However, recent studi
arXiv:2603.18985v2 Announce Type: replace-cross Abstract: Deep learning models have become the dominant approach for multivariate time series anomaly detection (MTSAD), often reporting substantial per
arXiv:2511.07272v2 Announce Type: replace Abstract: Overparameterized fully-connected neural networks have been shown to behave like kernel models when trained with gradient descent, assuming standard
arXiv:2606.21271v1 Announce Type: new Abstract: Sparse rewards pose a central challenge in reinforcement learning, since agents receive no informative signal until they reach their goal. Intrinsic-rew
arXiv:2606.20959v1 Announce Type: new Abstract: Large language models can store both outdated facts and newer superseding facts in their parameters, but standard prompting may still elicit the outdate
arXiv:2606.20638v1 Announce Type: cross Abstract: Large language models are increasingly deployed as long-lived agents that must adapt across users, tasks, domains, modalities, and feedback regimes wi
arXiv:2606.22840v1 Announce Type: new Abstract: We present RLM-Cascade, a proxy-layer system that applies speculative decoding at the response level to reduce LLM API costs without requiring model arc
arXiv:2606.22142v1 Announce Type: new Abstract: We present RoboLineage, an agent-native data lifecycle governance system for robot policy iteration. Modern robot policies improve through repeated data
arXiv:2606.21572v1 Announce Type: new Abstract: Large vision-language models contain several priors about the world and object interactions, making them useful critics during inference to steer robot
arXiv:2606.21406v1 Announce Type: cross Abstract: A central question in robot learning is how to acquire skills from the kinds of data that humans learn from: passive observation, embodied practice, a
arXiv:2511.23221v2 Announce Type: replace Abstract: In this paper, we challenge the conventional notion in 3DGS-SLAM that rendering quality is the primary determinant of tracking accuracy. We argue th
arXiv:2507.15232v2 Announce Type: replace-cross Abstract: Recent advances have sparked significant interest in the development of privacy-preserving Principal Component Analysis (PCA). However, many e
arXiv:2606.20666v1 Announce Type: cross Abstract: Associative memory models play a fundamental role in pattern retrieval, but their performance often degrades under adversarial perturbations and sever
arXiv:2606.22521v1 Announce Type: cross Abstract: We show that replacing the standard MSE denoising loss in diffusion models with a nonlinear transformation induced by an f-divergence yields a simple
arXiv:2606.20703v1 Announce Type: new Abstract: Label-free, image-based cellular mechanophenotyping in microfluidic devices provides a high-throughput method for single-cell profiling. However, while
arXiv:2602.03531v2 Announce Type: replace-cross Abstract: Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain le
arXiv:2603.02742v2 Announce Type: replace Abstract: Autonomous drone racing (ADR) demands state estimation that is simultaneously computationally efficient and resilient to the perceptual degradation
arXiv:2606.20734v1 Announce Type: new Abstract: Open Vocabulary Action Recognition (OVAR) enables the recognition of novel actions by leveraging vision-language representations, overcoming the limitat
arXiv:2606.21488v1 Announce Type: new Abstract: The vulnerability of ML models to adversarial examples has recently emerged as a major concern. While adversarial training is one of the most effective
arXiv:2606.20980v1 Announce Type: new Abstract: As Self-Driving Cars continue to expand internationally and use multi-modal systems such as VLMs as a cognitive backbone for their Action models; how we
arXiv:2606.21786v1 Announce Type: new Abstract: We introduce RocketPFN, a training-free pipeline for time series classification that combines random convolutional feature extraction (Rocket) with in-c
arXiv:2606.21264v1 Announce Type: new Abstract: Physically localizing unauthorized wireless devices remains a critical bottleneck in cyber-physical security operations, where rogue access points can p
arXiv:2606.21788v1 Announce Type: cross Abstract: Point-cloud goals provide a direct way to specify dexterous in-hand reorientation: instead of defining an object-specific pose frame or estimating 6D
arXiv:2606.18774v2 Announce Type: replace Abstract: We present RouteJudge, an online pairwise preference evaluation framework for LLM routing systems, with a public platform available at https://route
arXiv:2606.21755v1 Announce Type: new Abstract: Pre-Phase-A design of lunar micro-rovers is dominated by tightly coupled mobility, power, thermal, and mass trades, yet conceptual-design tooling for th
arXiv:2606.23221v1 Announce Type: new Abstract: Recent years have witnessed remarkable progress in image generation and editing, particularly regarding instruction following and visual fidelity. Howev
arXiv:2606.23344v1 Announce Type: new Abstract: Accurate document layout analysis remains a critical bottleneck for document parsing systems, due to the intricate coupling among heterogeneous document
arXiv:2511.20651v2 Announce Type: replace Abstract: Reinforcement learning (RL) has recently emerged as a promising approach for aligning text-to-image generative models with human preferences. A key
rumors of new models being delayed 🚨 SCOOP(s): - GPT-5.6 has been delayed and will no longer release this week. New target is ~mid-July. - DeepMind are not satisfied with the current state of 3.5 Pro
This IBM Research article discusses optimizing AI inference performance and costs by leveraging mixed hardware configurations, combining different types of processors and accelerators rather than rely
arXiv:2508.08048v2 Announce Type: replace Abstract: While video generation models excel at producing high-quality monocular videos, generating 3D stereoscopic and spatial videos for immersive applicat
arXiv:2606.23267v1 Announce Type: new Abstract: Flow matching has recently emerged as a strong paradigm for state-of-the-art text-to-image (T2I) generation, enabling high-quality generation with a sma
arXiv:2603.05497v3 Announce Type: replace Abstract: Traditional safety-critical control methods, such as control barrier functions, suffer from semantic blindness, exhibiting the same behavior around
arXiv:2606.20698v1 Announce Type: new Abstract: Safe control is a prerequisite for real-world embodied intelligence, for which safe reinforcement learning has emerged as a promising paradigm. However,
arXiv:2606.22144v1 Announce Type: new Abstract: Gastrointestinal cancers represent a growing health burden in the South Asian region, driven largely by rapid changes in socio-economic conditions & lif
arXiv:2606.21228v1 Announce Type: new Abstract: The capabilities of frontier Large Language Models (LLMs) continue to advance, with different providers increasingly specializing in distinct domains. T
Sakana AI's Fugu is a technical report describing an AI model or system, likely focusing on neural architecture design or evolutionary computation methods given Sakana AI's research focus. The report
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:2606.21108v1 Announce Type: new Abstract: Image forgery localization remains challenging due to diverse manipulation techniques and distribution shifts. Existing forgery localization models achi
arXiv:2606.22694v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain unreliable when spatial reasoning requires composing relations whose meanings depend on frames of reference. Existi
arXiv:2606.22601v1 Announce Type: cross Abstract: Gaussian Processes (GPs) are a powerful tool for Bayesian time-series modeling, yet their cubic computational cost remains a severe barrier for applic
arXiv:2606.22630v1 Announce Type: new Abstract: Diffusion policies have recently emerged as a powerful paradigm for representing complex action distributions in reinforcement learning (RL). However, t
arXiv:2606.22471v1 Announce Type: new Abstract: A key bottleneck in training generalist policies for bimanual dexterous manipulation is the lack of large-scale, high-quality datasets. Synthetic data g
arXiv:2606.22984v1 Announce Type: cross Abstract: Efficient sampling of the Boltzmann distribution in frustrated spin glasses is central to statistical mechanics and combinatorial optimization. Despit
arXiv:2606.20477v2 Announce Type: replace Abstract: We study how to train visually grounded vision-language models (VLMs) for radiology without manual spatial annotations. We introduce RefRad2D, a lar
arXiv:2606.21947v1 Announce Type: new Abstract: Vision Transformers have achieved remarkable success in many fields, yet their deployment on edge devices remains challenging due to their substantial c
arXiv:2606.20946v1 Announce Type: cross Abstract: Developing robust models for 3D visual grounding (3DVG), the localization of entities in a 3D scene described in natural language, is important for en
arXiv:2606.23607v1 Announce Type: new Abstract: Linear mode connectivity (LMC) provides a promising foundation for understanding and merging independently trained neural networks, but existing methods
arXiv:2606.19641v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving models are typically trained on offline human-demonstration datasets that provide limited state coverage and oft
arXiv:2606.23524v1 Announce Type: new Abstract: End-to-end OCR increasingly relies on autoregressive sequence models, where the quadratic cost of Transformer attention limits efficient transcription o
arXiv:2606.21756v1 Announce Type: cross Abstract: In this work, we present SemanticVessel, a dataset for fine-grained brain vessel segmentation in computed tomography angiography scans. Based on the d
arXiv:2606.23019v1 Announce Type: new Abstract: While Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, their reliance on 3D full attention creates a quadratic computat
arXiv:2505.17295v2 Announce Type: replace Abstract: We introduce ScanBot, a benchmark for instruction-conditioned, high-precision surface scanning with robot-mounted industrial laser profilers. Unlike
arXiv:2606.23101v1 Announce Type: new Abstract: ALS boresight calibration has relied for two decades on dedicated flight patterns over structured scenes containing planar surfaces of varied aspect and
arXiv:2606.21753v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) has achieved state-of-the-art photorealistic rendering, but the representation gap prevents these assets from being physi