Knowledge catalogue
arXiv:2605.08389v1 Announce Type: cross Abstract: Zero-shot composed image retrieval (ZS-CIR) retrieves a target image from a reference image and a text modification without human-annotated CIR triple
Deep Agents ship with durable execution out of the box: every agent step is checkpointed, so you get observability, fault tolerance, and human-in-the-loop for free. But as agents run longer and contex
arXiv:2605.10569v1 Announce Type: new Abstract: Deep learning has become the dominant approach for creating high capacity, scalable models across diverse data modalities. However, because these models
arXiv:2605.08218v1 Announce Type: cross Abstract: This paper proposes latent visualization by optimization (LVO), a mechanistic interpretability technique that extends feature visualization by optimiz
arXiv:2505.05740v3 Announce Type: replace Abstract: This paper introduces the first globally optimal algorithm for the empirical risk minimization problem of two-layer maxout and ReLU networks, i.e.,
Deep learning hit a wall. Neurosymbolic AI rescued it. 🤩🤯🤩 Claude Code (still not AGI but biggest advance since GPT-4) is the most neurosymbolic thing I have ever seen in my life. 53 symbolic tools, 5
arXiv:2605.09890v1 Announce Type: cross Abstract: Differentially private stochastic gradient descent (DP-SGD) is a standard approach to privacy-preserving learning based on per-example clipping, subsa
arXiv:2509.25646v2 Announce Type: replace Abstract: Learning operators from data is central to scientific machine learning. While DeepONets are widely used for their ability to handle complex domains,
arXiv:2508.06248v4 Announce Type: replace Abstract: The generalization of deepfake detectors to unseen manipulation techniques remains a challenge for practical deployment. Although many approaches ad
arXiv:2605.10364v1 Announce Type: new Abstract: Modeling uncertainty in heavy-tailed time series remains a critical challenge for deep probabilistic forecasting models, which often struggle to capture
arXiv:2605.10279v1 Announce Type: new Abstract: DeepLog is an operational neurosymbolic framework that unifies logic and deep learning within standard PyTorch workflows. While existing neurosymbolic s
arXiv:2605.10488v1 Announce Type: cross Abstract: Agent-compiled knowledge bases provide persistent external knowledge for large language model (LLM) agents in open-ended, knowledge-intensive downstre
arXiv:2605.10564v1 Announce Type: new Abstract: End-to-end autonomous driving systems are increasingly integrating Vision-Language Model (VLM) architectures, incorporating text reasoning or visual rea
arXiv:2605.09679v1 Announce Type: cross Abstract: Medical vision-language models (VLMs) and AI agents have made significant progress in learning to analyze and reason about clinical images. However, e
arXiv:2605.08442v1 Announce Type: cross Abstract: Persistent memory attacks against LLM agents achieve high attack success rates against open-source models. In these attacks, malicious instructions in
arXiv:2605.09586v1 Announce Type: new Abstract: World models for deformable objects should recover not only geometry and appearance, but also underlying physical dynamics, interaction grounding, and m
arXiv:2605.09628v1 Announce Type: new Abstract: Depth super-resolution (DSR) aims to recover a high-resolution (HR) depth map from its low-resolution (LR) counterpart. With color image guidance, this
Delighted to announce our 3rd world modeling workshop! After NYC and Montreal, we are now headed to Chicago! - August 31st to September 2nd - CfP and details on the website: https://wm-booth.org - @yl
arXiv:2605.08396v1 Announce Type: new Abstract: The increasing complexity of modern computational environments often burdens researchers with infrastructure management, authentication protocols, and c
arXiv:2605.09269v1 Announce Type: new Abstract: Aligning Multimodal Large Language Models (MLLMs) requires reliable reward models, yet existing single-step evaluators can suffer from lazy judging, exp
arXiv:2605.08135v1 Announce Type: new Abstract: Equilibrium propagation (EP) is a biologically plausible alternative to backpropagation (BP), but its effectiveness can degrade in deeper and more chall
arXiv:2605.09065v1 Announce Type: new Abstract: Scene graphs (SGs) represent objects and their relationships as structured graphs, enabling applications in image generation, robotics, and 3D understan
arXiv:2605.09222v1 Announce Type: cross Abstract: Logs are ubiquitous in modern systems. Unfortunately, their unstructured nature in flat sequences limits understanding of execution behaviors, hinderi
arXiv:2604.01151v2 Announce Type: replace Abstract: As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human o
arXiv:2512.06673v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) are rapidly expanding from general video understanding to finer-grained understanding such as spatio-tempor
arXiv:2605.08794v1 Announce Type: cross Abstract: Modern generative models can be understood as probability transport from a simple base distribution to a target data distribution. Deterministic trans
arXiv:2603.08065v2 Announce Type: replace-cross Abstract: Structured pruning reduces LLM inference cost by removing low-importance architectural components. This can be viewed as learning a multiplica
arXiv:2605.10190v1 Announce Type: new Abstract: Open-vocabulary object detection (OVOD) aims to detect both seen and unseen categories, yet existing methods often struggle to generalize to novel objec
arXiv:2605.10184v1 Announce Type: cross Abstract: We develop a foundation model using 1.2m high resolution satellite images of the Netherlands. By combining a Convolutional Neural Network and a Vision
arXiv:2507.01008v3 Announce Type: replace Abstract: Development of dexterous manipulation hardware has primarily focused on hands and grippers. However, these end-effectors are often paired with bulky
arXiv:2605.09291v1 Announce Type: new Abstract: Discrete flow models (DFMs) are a class of flexible generative models for generating discrete data, and diffusion large language models (dLLMs) can be v
arXiv:2605.10863v1 Announce Type: new Abstract: Although Large Language Models (LLMs) have made remarkable progress, current preference optimization methods still struggle to align directional consist
arXiv:2605.09028v1 Announce Type: new Abstract: Machine learning-based Android malware detectors often fail in real-world deployment due to domain shift, where models trained on one data source perfor
arXiv:2605.08286v1 Announce Type: cross Abstract: We introduce a spectral-injection diagnostic for measuring which angular frequencies a trained equivariant force-field backbone preserves: inject a co
arXiv:2605.08614v1 Announce Type: new Abstract: Monitoring complex industrial assets relies on engineer-authored symbolic rules that trigger based on sensor conditions and prompt technicians to perfor
Did Jensen Huang catch conflict of interest disease from Sam? HUANG FOUNDATION SIGNS GPU COMPUTE DEAL WITH COREWEAVE $NVDA proxy says the charitable foundation tied to Jensen and Lori Huang entered an
arXiv:2605.09275v1 Announce Type: new Abstract: Direct diffusion modeling of high-resolution spatiotemporal fields is computationally challenging. Parameter-efficient primitives address this by repres
arXiv:2605.08568v1 Announce Type: new Abstract: Large language models (LLMs) have rapidly grown in scale, creating substantial memory and computational costs that hinder efficient deployment. Singular
arXiv:2502.06044v3 Announce Type: replace-cross Abstract: Hyperparameter tuning is a key component of machine learning procedures, but when validation data contain sensitive user information, search m
arXiv:2605.10015v1 Announce Type: cross Abstract: In this paper, we study the problem of sampling from a distribution under the constraint of differential privacy (DP). Prior works measure the utility
arXiv:2510.07136v2 Announce Type: replace-cross Abstract: We study spectral graph clustering under edge differential privacy. We propose a matrix shuffling mechanism that combines randomized edge flip
arXiv:2605.10647v1 Announce Type: new Abstract: Trajectories are nowadays valuable information for a wide range of applications. However they are also inherently sensitive, as they contain highly pers
arXiv:2410.02543v3 Announce Type: replace-cross Abstract: In a convergence of machine learning and biology, we reveal that diffusion models are evolutionary algorithms. By considering evolution as a d
Intelligent trust is not just a bonus for artificial intelligence systems, but a vital factor in their success. Although the AI train doesn’t seem to be slowing down any time soon, security concerns a
arXiv:2605.08167v1 Announce Type: cross Abstract: The increasing availability of advanced image editing tools has led to a significant rise in manipulated digital content, posing serious challenges fo
arXiv:2605.09331v1 Announce Type: new Abstract: Modern Large Language Model (LLM) training is fundamentally bottlenecked by pathologically flat saddle points in extreme high-dimensional landscapes. Mo
arXiv:2605.08249v1 Announce Type: new Abstract: Frozen vision foundation models do not merely extract features; they organize images through a learned coordinate system. We ask whether that coordinate
arXiv:2605.08446v1 Announce Type: new Abstract: We propose training Bayesian neural networks by directly minimizing the Bethe free energy rather than maximizing a variational lower bound. On tree-stru
arXiv:2605.05284v2 Announce Type: replace-cross Abstract: Evolutionary computation has long promised to deliver both high-performance optimization tools as well as rigorous scientific simulations of D
arXiv:2605.09696v1 Announce Type: new Abstract: Discovering governing equations from observational data remains a fundamental challenge in scientific modeling, particularly when the underlying mathema
arXiv:2602.13759v2 Announce Type: replace Abstract: We study eigendecomposition on SO(n) under streaming observations C_k = C_{sig} + sigma_k^2 I + E_k, where the isotropic background sigma_k^2 I may
arXiv:2605.08882v1 Announce Type: new Abstract: Flow Matching has recently emerged as a popular class of generative models for simulating a target distribution mu_1 from samples drawn from a source di
arXiv:2605.09302v1 Announce Type: cross Abstract: We study posterior sampling for inverse problems in discrete state spaces using discrete diffusion models as generative priors. While continuous diffu
arXiv:2605.09697v1 Announce Type: new Abstract: In many real-world computer vision applications, including medical imaging and industrial inspection, binary classification tasks are characterized by a
arXiv:2602.05214v2 Announce Type: replace Abstract: Disentangled representation learning aims to capture the underlying explanatory factors of observed data, enabling a principled understanding of the
arXiv:2605.09881v1 Announce Type: cross Abstract: Mechanistic interpretability seeks to reverse engineer a trained neural network by identifying the minimal subset of internal components. We perform a
arXiv:2605.08293v1 Announce Type: new Abstract: 3D semantic scene understanding has broad applications in digital twins, autonomous driving, smart agriculture, and embodied perception. However, dense
arXiv:2605.09719v1 Announce Type: cross Abstract: Large-scale 3D vision-language models (VLMs) like LLaVA-3D offer strong spatial reasoning but are difficult to deploy due to high computational costs.
arXiv:2605.08104v1 Announce Type: new Abstract: This paper explores the application of the Soft Actor-Critic (SAC) algorithm within a Distributional Reinforcement Learning setting and introduces an im
arXiv:2605.08237v1 Announce Type: new Abstract: In grokking, a model first fits the training data while test accuracy remains low, and only later begins to generalize. We ask whether this transition c