Knowledge catalogue
arXiv:2606.20891v1 Announce Type: new Abstract: Filmmaking demands precise motion control and reference image compositing -- capabilities that existing methods treat separately. Point-track-conditione
arXiv:2606.22409v1 Announce Type: new Abstract: Robots operating in everyday environments must understand fine-grained human actions, intentions, and contextual cues from broad views where people occu
arXiv:2603.05035v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly served on shared accelerators where an adversary with read access to device memory can observe K
arXiv:2606.22741v1 Announce Type: new Abstract: Can one graph represent every kind of LLM agent's run? A trace records what each step did, never what it relied on, the state it read, and the results i
arXiv:2606.22053v1 Announce Type: new Abstract: Traditional evaluation of machine learning (ML) models typically focuses on achieving the maximum possible accuracy irrespective of the computational co
arXiv:2602.04548v2 Announce Type: replace Abstract: We develop a general mathematical framework to analyze scaling regimes and derive explicit analytic solutions for gradient flow (GF) in large learni
arXiv:2606.21253v1 Announce Type: new Abstract: Continual learning that is gradient-free, local, online, and append-only is attractive for edge and streaming deployment, but its value is usually argue
arXiv:2509.25665v2 Announce Type: replace Abstract: Sparse neural network methods typically assume that the target sparsity (or density) is fixed in advance, even though the relationship between netwo
arXiv:2606.21097v1 Announce Type: cross Abstract: Deploying highly capable personalized conversational agents in resource-constrained or privacy-sensitive environments remains a significant challenge.
arXiv:2606.22917v1 Announce Type: new Abstract: Learning instability is a long-standing problem across machine learning, but it is especially acute in the overparameterized regime that defines modern
arXiv:2509.09597v3 Announce Type: replace-cross Abstract: Graph alignment, the problem of identifying corresponding nodes across multiple graphs, is fundamental to numerous applications. Most existing
arXiv:2606.21368v1 Announce Type: new Abstract: Medical image re-identification (MedReID) enables longitudinal patient linkage but remains vulnerable to shortcut learning and often produces decisions
arXiv:2509.21489v3 Announce Type: replace Abstract: Graph foundation models face several fundamental challenges including transferability across diverse domains and data scarcity, which calls into que
arXiv:2603.06467v2 Announce Type: replace Abstract: Radiology foundation models (RFMs) have largely inherited the scale-first recipe of natural-image vision--language pre-training. This recipe is diff
arXiv:2606.23299v1 Announce Type: new Abstract: Configuring the hyperparameters of Mixed-integer programming (MIP) solvers is a high-dimensional, instance-dependent optimization problem where suboptim
arXiv:2606.23419v1 Announce Type: new Abstract: Autoregressive decoding with LLMs is primarily bottlenecked by GPU memory bandwidth, especially in edge-computing settings. While quantization is essent
arXiv:2606.20799v1 Announce Type: new Abstract: Generating visually consistent multi-shot videos remains an open challenge. As videos span more shots, inconsistencies can accumulate across shots, caus
arXiv:2606.22995v1 Announce Type: new Abstract: Group-based Reinforcement Learning (RL) has significantly enhanced Large Language Models (LLMs) in agentic scenarios. To achieve finer-grained policy up
arXiv:2606.20945v1 Announce Type: new Abstract: Self-attention is central to Transformer performance and is often the most expensive part of the Transformer at long context lengths because its pairwis
arXiv:2606.21915v1 Announce Type: new Abstract: Automated chest X-ray report generation requires precise cross-modal grounding to ensure clinically reliable descriptions. However, existing vision-lang
arXiv:2603.14109v2 Announce Type: replace Abstract: Millimeter-wave radar enables robust perception in visually degraded environments, yet radar-inertial estimation remains prone to drift: sparse body
arXiv:2512.24946v2 Announce Type: replace Abstract: Existing film-restoration methods frequently fail under fast motion, producing limb disappearance and structural distortion due to inaccurate motion
arXiv:2602.00032v3 Announce Type: replace-cross Abstract: Synthetic faces from text-to-image (T2I) models pervade digital media, yet their demographic biases under emotionally conditioned prompts rema
arXiv:2606.19636v2 Announce Type: replace Abstract: Math and science reasoning benchmarks rely on pass@k, the fraction of sampled chains that reach gold, as the canonical per-example difficulty signal
arXiv:2606.20631v1 Announce Type: cross Abstract: Agent skills externalise reusable agent-facing behavioural knowledge and guidance as persistent artefacts that can be discovered, activated, and inter
arXiv:2508.15555v4 Announce Type: replace-cross Abstract: HEAS is a Python framework that connects agent-based simulation, evolutionary search, and scenario-based evaluation in a single reproducible p
arXiv:2606.23615v1 Announce Type: new Abstract: We propose Hedgementation: a new benchmark to evaluate machine learning models for hedgerow mapping from remote sensing data at country scale and 10m^2
arXiv:2501.12191v2 Announce Type: replace-cross Abstract: Training deep neural networks (DNNs) on classification tasks can be performed with a number of different losses, but cross-entropy (CE) loss i
arXiv:2606.21633v1 Announce Type: new Abstract: Diffusion LLMs (dLLMs) improve GPU utilization over autoregressive decoding by generating multiple tokens per forward pass, but their KV cache still gro
arXiv:2606.22756v1 Announce Type: cross Abstract: We present HERCULES, an open-source simulator and data-collection pipeline for heterogeneous multi-robot autonomy. Built upon the Unreal Engine 5 (UE5
arXiv:2509.22645v2 Announce Type: replace Abstract: Class-Incremental Learning (CIL) aims to endow models with the ability to continuously adapt to evolving data streams. Recent advances in pre-traine
arXiv:2606.21174v1 Announce Type: new Abstract: Matched multi-omics can improve WSI-based biomarker and prognosis prediction, but most existing pipelines use omics as a paral lel feature stream or tex
arXiv:2606.20962v1 Announce Type: new Abstract: High-performing human-human teams learn intelligent and efficient communication and coordination strategies to maximize their joint utility. These teams
arXiv:2505.19061v2 Announce Type: replace Abstract: Motivated by Online Configuration Optimization in large, dynamic parameter spaces, this work studies the nonstochastic multi-armed bandit (MAB) prob
arXiv:2602.03448v2 Announce Type: replace Abstract: Multi-subject image generation aims to synthesize images that faithfully preserve the identities of multiple reference subjects while following text
arXiv:2606.20932v1 Announce Type: new Abstract: Sheaf Neural Networks (SNNs) generalize Graph Neural Networks (GNNs) by replacing scalar node signals with stalk-valued signals and by using restriction
arXiv:2606.22922v1 Announce Type: new Abstract: Applying machine learning techniques to solving long-standing mathematical conjectures can be particularly challenging due to their extreme reward spars
arXiv:2601.12879v2 Announce Type: replace Abstract: Extracting sparse circuits from billion-parameter transformers is constrained by O(2^n) search cost and pervasive feature reuse across co-active pat
arXiv:2508.05212v2 Announce Type: replace-cross Abstract: With the development of big data and machine learning, privacy concerns have become increasingly critical, especially when handling heterogene
arXiv:2606.22860v1 Announce Type: new Abstract: Recent advancements in generative imitation learning have significantly propelled the field of robotic manipulation. However, the majority of existing m
arXiv:2606.20189v2 Announce Type: replace Abstract: Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data
arXiv:2606.22556v1 Announce Type: new Abstract: Anomaly detection is essential for medical image analysis, where pathological regions often appear as rare deviations from normal anatomical structures.
arXiv:2606.20083v2 Announce Type: replace Abstract: Video world models are moving toward preserving an observed world under controllable camera and object motion while allowing its environmental state
arXiv:2606.23565v1 Announce Type: cross Abstract: LLM agents follow a practical execution loop in digital environments: they reason over structured states, invoke tools, inspect feedback, and revise a
arXiv:2606.22834v1 Announce Type: new Abstract: We present homographic navigation, a geometry-centric framework for guiding camera acquisition toward precise capture of planar regions. Rather than tre
arXiv:2606.21136v1 Announce Type: new Abstract: Learning accurate value functions plays a decisive role for reinforcement learning (RL) agents to solve long-horizon, complex tasks. Conventional tempor
arXiv:2606.21093v1 Announce Type: cross Abstract: Robotic inspection relies on accurate sensing to acquire high-fidelity geometric measurements for defect detection and metrology. While prior work has
arXiv:2606.22062v1 Announce Type: cross Abstract: Simulation-to-reality transfer, often called sim-to-real transfer, is a central challenge in robot learning. Yet, the tradeoff between measuring a sys
arXiv:2606.20726v1 Announce Type: new Abstract: We introduce a compact empirical model that quantifies how answer accuracy degrades as a function of frame budget B and temporal distance D in long vide
arXiv:2606.22177v1 Announce Type: cross Abstract: Self-supervised learning (SSL) models have become a central component of modern speech processing systems, as they enable the learning of rich acousti
arXiv:2606.21734v1 Announce Type: new Abstract: Understanding long videos requires fine-grained perception and multi-step, higher-order reasoning over complex, long-range spatio-temporal dynamics. Vis
arXiv:2603.19822v2 Announce Type: replace Abstract: Existing UAV vision-language navigation (VLN) benchmarks have enabled language-guided flight, but they largely focus on long, step-wise route descri
arXiv:2606.22486v1 Announce Type: new Abstract: Medical expert annotators are scarce, and blind reliance on artificial intelligence (AI) can be misleading, motivating approaches in which humans, parti
arXiv:2510.17525v3 Announce Type: replace Abstract: Safe and efficient robotic navigation among humans is essential for integrating robots into everyday environments. Most existing approaches focus on
arXiv:2606.22971v1 Announce Type: cross Abstract: Occupancy prediction at voxel-level granularity is essential for safe robotic navigation and interaction in complex environments. Existing occupancy d
arXiv:2606.22935v1 Announce Type: new Abstract: Deep neural networks have witnessed remarkable advancements in recent years and have become integral to various applications. However, alongside these d
arXiv:2606.23406v1 Announce Type: new Abstract: We present HyperQuant (Hadamard, optimallY Packing, Entropy Rice-coding), a unified post-training quantization pipeline for the weights and the KV cache
arXiv:2606.20642v1 Announce Type: cross Abstract: Asymptotic statistical theory is a challenging domain for AI-assisted formalization: its central results mix convergence statements, asymptotic expans
arXiv:2606.22042v1 Announce Type: new Abstract: Diffusion-based video editing has made significant progress; however, achieving precise and temporally consistent object-level control, especially in mu
arXiv:2606.23675v1 Announce Type: new Abstract: Generating human-object interactions (HOI) is central to character animation, robotics, AR/VR, and embodied AI. Recent HOI generation methods synthesize