Knowledge catalogue
arXiv:2605.15435v1 Announce Type: new Abstract: Standard deep-learning pipelines usually choose the network architecture before training and keep it fixed throughout optimization. In contrast, a model
arXiv:2605.15309v1 Announce Type: new Abstract: Despite remarkable progress, image generation is far from solved. The dominant metric, FID, conflates sample fidelity with mode coverage and is close to
arXiv:2511.04484v2 Announce Type: replace-cross Abstract: We study the repeated optimal stopping problem, in which the same optimal stopping instance with an unknown distribution is solved repeatedly
arXiv:2602.03922v3 Announce Type: replace Abstract: Standard sequence mixing layers used in language models struggle to balance efficiency and performance. Self-attention performs well on long context
arXiv:2605.15978v1 Announce Type: cross Abstract: Law enforcement reports contain structured fields and written narratives. However, many incident facts that are needed for review, police training, an
arXiv:2603.05377v2 Announce Type: replace-cross Abstract: Open-world navigation requires robots to make decisions in complex everyday environments while adapting to flexible task requirements. Convent
arXiv:2605.15553v1 Announce Type: cross Abstract: Sixth-generation mobile networks (6G) are approaching a structural inflection point. Five generations of vendor-led architectures have left operators
arXiv:2603.01290v3 Announce Type: replace Abstract: The 2026 Formula 1 technical regulations introduce a fundamental change to energy strategy: under a 50/50 internal combustion engine / battery power
arXiv:2605.16191v1 Announce Type: new Abstract: We present a case study for how AI coding systems can be used to generate novel scientific hypotheses. We combine a generic coding agent (Google's AntiG
arXiv:2605.15765v1 Announce Type: cross Abstract: Optimization problems with drones are widely studied in a variety of civilian tasks, mainly due to their ability to traverse rough terrains and to car
arXiv:2504.11320v3 Announce Type: replace-cross Abstract: Large language models now serve millions of users daily, with providers incurring costs exceeding $700,000 per day. Each request requires toke
arXiv:2506.00182v3 Announce Type: replace-cross Abstract: Will further scaling up of machine learning models continue to bring success? A significant challenge in answering this question lies in under
arXiv:2510.06194v2 Announce Type: replace-cross Abstract: The separation of overlapping objects presents a significant challenge in scientific imaging. While deep learning segmentation-regression algo
arXiv:2605.15353v1 Announce Type: cross Abstract: Inferring the structure of directed acyclic graphs (DAGs) from data is a central challenge in causal discovery, particularly in modern high-dimensiona
arXiv:2605.15963v1 Announce Type: new Abstract: Large vision-language models have significantly advanced GUI agents, enabling executable interaction across web, mobile, and desktop interfaces. Yet the
arXiv:2509.22739v3 Announce Type: replace-cross Abstract: Language models (LMs) are typically post-trained for desired capabilities and behaviors via weight-based or prompt-based steering, but the for
arXiv:2605.15391v1 Announce Type: cross Abstract: We present PanoWorld, a panoramic video world model that generates geometry-consistent 360egree video from a single image and a caption. Existing pano
arXiv:2605.16194v1 Announce Type: cross Abstract: LLM agents routinely serve as first (and sometimes only) readers of academic papers, skimming for sub-claims, extracting reproducibility steps, and ge
arXiv:2605.15509v1 Announce Type: new Abstract: While Isaac Lab provides massive parallel UAV simulation, OmniSafe and safe-control-gym provide constrained-RL benchmarks, and CBFKit provides control-b
arXiv:2605.15229v1 Announce Type: cross Abstract: Existing code benchmarks measure whether an agent can produce any test that reproduces a known bug, or whether it can produce a patch that fixes a des
arXiv:2605.15654v1 Announce Type: new Abstract: Real-world autonomous driving, particularly in urban environments with numerous corner cases, requires rigorous testing to ensure product safety and rob
arXiv:2605.15252v1 Announce Type: cross Abstract: Modern pedestrian dead reckoning (PDR) systems rely on fusing noisy and biased estimates of position, velocity, and calibrated orientation derived fro
arXiv:2605.15222v1 Announce Type: cross Abstract: Large language models (LLMs) can often generate functionally correct code, but their ability to produce efficient implementations for performance-crit
arXiv:2605.15647v1 Announce Type: new Abstract: Edge machine learning presents a unique set of constraints not encountered in cloud-scale model deployment: strict memory budgets, limited compute, and
arXiv:2605.15620v1 Announce Type: cross Abstract: We study risk-aware offline policy learning, aiming to learn a decision rule from logged data that is optimal under general risk criteria. This proble
arXiv:2605.15983v1 Announce Type: new Abstract: We formulate the Resource-Constrained Project Scheduling Problem (RCPSP) as optimal search over the reachability graph of a Timed Transition Petri Net w
arXiv:2605.15403v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models rely on balanced expert utilization to fully realize their scalability. However, existing load-balancing methods are lar
arXiv:2512.01843v2 Announce Type: replace Abstract: Driven by the growing capacity and training scale, Text-to-Video (T2V) generation models have recently achieved substantial progress in video qualit
arXiv:2605.15298v1 Announce Type: cross Abstract: Vision-language-action models have advanced rapidly, but robot trajectories alone provide limited coverage for learning broad physical understanding.
arXiv:2512.00242v3 Announce Type: replace-cross Abstract: Sheaf Neural Networks equip graph structures with a cellular sheaf: a geometric structure which assigns local vector spaces (stalks) and a lin
arXiv:2605.15567v1 Announce Type: new Abstract: This position paper argues for metacognition as a general design principle for creating more accurate, secure, and efficient AI. The metacognitive solut
arXiv:2605.15714v1 Announce Type: cross Abstract: This position paper argues that the machine learning community should prioritize early-stage quality assurance in annotation pipelines over the prevai
arXiv:2605.15253v1 Announce Type: new Abstract: Machine learning research increasingly bifurcates into two disconnected modes: benchmark-driven engineering that prioritizes metrics over understanding,
arXiv:2605.15622v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization, learning from finite differences of function evaluations without backpropagation, has recently regained attention in dee
arXiv:2605.15887v1 Announce Type: new Abstract: Robust aggregation is the core operation in Byzantine-tolerant federated learning. To ensure the quality of aggregation independently of data distributi
arXiv:2605.15363v1 Announce Type: new Abstract: Accurate forecasting of residual Physical Resource Blocks (PRBs) is critical for proactive network slice provisioning, energy-efficient operation, and s
arXiv:2509.01685v2 Announce Type: replace-cross Abstract: We consider sampling from a Gibbs distribution by evolving finitely many particles. We propose a preconditioned version of a recently proposed
arXiv:2508.08431v3 Announce Type: replace-cross Abstract: Spectral variability significantly impacts the accuracy and convergence of hyperspectral unmixing algorithms. Many methods address complex spe
arXiv:2605.15599v1 Announce Type: cross Abstract: Extreme low-data fine-grained classification is common in expert domains where labeling is expensive, yet practitioners still need principled guidance
arXiv:2605.15665v1 Announce Type: new Abstract: Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and
arXiv:2605.15507v1 Announce Type: cross Abstract: For a Gaussian source under mean-squared error (MSE), classical transform coding is rate--distortion (RD) optimal: the Karhunen--Loeve transform (KLT)
arXiv:2605.15246v1 Announce Type: new Abstract: Trajectory data is fundamental to modern urban intelligence, yet its sensitivity raises significant privacy concerns. Generative models such as Generati
arXiv:2605.06475v1 Announce Type: cross Abstract: We introduce a probabilistic approach for dating historical manuscript pages from visual features alone. Instead of aggregating centuries into classes
arXiv:2509.20349v3 Announce Type: replace Abstract: Accurate time-series forecasting for complex physical systems is the backbone of modern industrial monitoring and control, yet deep learning models
arXiv:2605.15529v1 Announce Type: cross Abstract: Process Reward Models (PRMs) provide step-level feedback for reasoning, but current PRMs usually output only a single reward score for each step. Down
arXiv:2407.02039v3 Announce Type: replace Abstract: Researchers are increasingly using language models (LMs) for text annotation. These approaches rely only on a prompt telling the model to return a g
arXiv:2605.15641v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as general planners in embodied intelligence, enabling high level coordination and low level task pla
arXiv:2605.16142v1 Announce Type: new Abstract: LLMs have shown impressive success in program synthesis, discovering programs that surpass prior solutions. However, these approaches rely on simple num
arXiv:2605.16238v1 Announce Type: new Abstract: Probabilistic forecasting of infectious diseases is crucial for public health but relies on labor-intensive manual model curation by expert modeling tea
arXiv:2605.15609v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) generate text by iteratively denoising masked token sequences. Although dLLMs can predict all masked positions i
arXiv:2605.15208v1 Announce Type: cross Abstract: Large Language Models are routinely compressed via post-training quantization to reduce inference costs and memory footprint for cloud and edge deploy
arXiv:2511.09884v2 Announce Type: replace Abstract: Mission critical (MC) applications such as defense operations, energy management, cybersecurity, and aerospace control require reliable, determinist
arXiv:2605.15370v1 Announce Type: cross Abstract: Accurate salt-body delineation is essential for seismic interpretation because salt structures distort wave propagation, complicate velocity-model bui
arXiv:2602.06824v2 Announce Type: replace-cross Abstract: Momentum methods, such as Polyak's Heavy Ball, are the standard for training deep networks but suffer from curvature-induced bias in stochasti
arXiv:2605.15908v1 Announce Type: cross Abstract: Natural images are continuous, yet most generative models synthesize them on discrete grids, limiting resolution-flexible generation. Continuous neura
arXiv:2512.04457v2 Announce Type: replace Abstract: Removing specific data influence from large language models (LLMs) remains challenging, as retraining is costly and existing approximate unlearning
arXiv:2403.13805v2 Announce Type: replace-cross Abstract: CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of c
arXiv:2603.18396v3 Announce Type: replace Abstract: Bus holding control is challenging due to stochastic traffic and passenger demand. While deep reinforcement learning (DRL) shows promise, standard a
arXiv:2605.15782v1 Announce Type: new Abstract: In this work, we address the problem of ensuring real-time safety in autonomous robot navigation, in spatially constrained dynamic environments, by util
arXiv:2605.15256v1 Announce Type: new Abstract: Current game world models simulate environments from a subjective, player-centric perspective. However, by treating the Non-Player Character (NPC) merel