Knowledge catalogue
arXiv:2610.17845v1 Announce Type: new Abstract: Functional near-infrared spectroscopy (fNIRS) provides portable and spatially localized measurements of cortical hemodynamics, but differences in channe
arXiv:2610.18694v1 Announce Type: new Abstract: Vision-language models (VLMs) struggle with metric and multi-view relationships that remain implicit in RGB observations. Geometry foundation models rec
arXiv:2610.14852v1 Announce Type: new Abstract: Reinforcement learning (RL) is promising for spatial text-to-image generation, but existing work largely focuses on policy optimization, assuming accura
arXiv:2610.14541v1 Announce Type: new Abstract: Emerging strong Vision-Language Models (VLMs) have advanced navigation foundation models. However, these models still have unsatisfactory performance on
arXiv:2610.16455v1 Announce Type: new Abstract: 3D scene graph generation requires understanding both object semantics and metric spatial relations. However, existing open-vocabulary methods often str
arXiv:2610.17794v1 Announce Type: new Abstract: Contextual forecasting seeks to improve time series forecasting by incorporating forward-looking information, such as planned events, external condition
arXiv:2603.25072v2 Announce Type: replace Abstract: Video Large Language Models (VLMs) have achieved remarkable success in video understanding, but the significant computational cost from processing d
arXiv:2610.15064v1 Announce Type: new Abstract: The world has seen several threats that include resource depletion, food security, poverty and inequality, difficulties associated with urbanization, mi
arXiv:2610.14655v1 Announce Type: new Abstract: Pose Graph Optimization (PGO) is a classical and widely applied problem in state estimation for robotics, playing a fundamental role in localization, ma
arXiv:2610.17927v1 Announce Type: new Abstract: Autonomous navigation in real-world environments often requires long-horizon operation under partial observability and evolving goals. Existing mapless
arXiv:2610.17117v1 Announce Type: cross Abstract: Existing interpretability tools do not test whether a representation keeps the same content when only the phrasing changes. We treat each paraphrase p
arXiv:2610.15522v1 Announce Type: cross Abstract: Camera-based occupancy prediction provides geometric and semantic scene understanding for robot perception and has been adopted in autonomous vehicle
arXiv:2610.16861v1 Announce Type: new Abstract: This paper presents GpFlash, a Gaussian process library that is focused on fast training and posterior evaluations, minimal memory usage, and scalabilit
arXiv:2610.17321v1 Announce Type: cross Abstract: As demand for LLM inference grows and consumer GPUs grow more capable, edge deployment is becoming increasingly attractive. WebGPU is compelling in th
arXiv:2602.03945v2 Announce Type: replace Abstract: Simple row-wise predictors that score each row independently remain competitive with far more expressive architectures on tabular benchmarks, which
arXiv:2610.17062v1 Announce Type: new Abstract: We propose a mitigation to reward hacking in reinforcement learning. Our setup involves a misspecified reward function that gives rise to unintended beh
arXiv:2610.18471v1 Announce Type: new Abstract: Weight-space learning treats the weights of neural networks as data, processed by other models called metanetworks. A key challenge is that different we
arXiv:2505.02712v4 Announce Type: replace Abstract: Cellular reprogramming, the artificial transformation of one cell type into another, has been attracting increasing research attention due to its th
arXiv:2610.16272v1 Announce Type: new Abstract: Feed-forward reconstruction recovers camera poses and dense geometry from image sets whose views are assumed to come from a single scene. In practice, u
arXiv:2408.16717v4 Announce Type: replace Abstract: Due to the ongoing electrification of transportation systems, energy-based routing problems such as the Electric Vehicle Routing Problem (EVRP) are
arXiv:2405.03411v5 Announce Type: replace Abstract: Informed sampling techniques accelerate the convergence of sampling-based motion planners by biasing sampling toward regions of the state space that
arXiv:2610.18774v1 Announce Type: new Abstract: A robot needs a world model that predicts how its actions will change the scene and a policy that chooses those actions. Models are usually built and ev
arXiv:2607.08798v2 Announce Type: replace-cross Abstract: Adaptive volumetric finite element meshing traditionally requires iterative PDE solvers or heavily supervised, data-driven surrogates trained
arXiv:2610.18637v1 Announce Type: cross Abstract: A robot's world model must remember objects that leave the camera's view. FloWM, a learned world model, keeps them in a spatial grid of features that
arXiv:2610.15808v1 Announce Type: cross Abstract: Data flow underlies deep learning (DL) framework execution, including automatic differentiation and operator-fusion optimization. Bugs involving data
arXiv:2610.14809v1 Announce Type: new Abstract: Influence functions provide an efficient alternative to retraining for assessing the effects of removing or reweighting training data. For groups, howev
arXiv:2610.16489v1 Announce Type: new Abstract: Reinforcement learning (RL) can substantially improve the reasoning capabilities of large language models, but an effective training run requires consid
arXiv:2610.16817v1 Announce Type: new Abstract: Progressive depth growth builds large networks by starting with shallow models and inserting layers during training. Recent advances in large language m
arXiv:2506.10946v3 Announce Type: replace Abstract: Unlearning large language models (LLMs) is important due to copyright and privacy concerns. A key challenge is unintended forgetting, where removing
arXiv:2610.15829v1 Announce Type: new Abstract: Hard-margin SVM training is the distance problem between two convex hulls, which the Triangle Algorithm (TA) solves with a certified duality gap. We pro
arXiv:2610.16654v1 Announce Type: new Abstract: Flow matching models are typically trained to transport a Gaussian source to the data distribution, with source and target samples paired independently.
arXiv:2610.15856v1 Announce Type: new Abstract: DiffusionNFT (NFT) fine-tunes diffusion models toward task-specific rewards, but optimizing these rewards does not guarantee fidelity to the full prompt
arXiv:2610.18125v1 Announce Type: new Abstract: Training-free diffusion-based compression methods repurpose the generative priors of a diffusion or a flow model to compress data without retraining the
arXiv:2610.17348v1 Announce Type: new Abstract: Modeling 3D hair strands is challenging due to complex hairstyle geometry, scarce high-quality training data, and incomplete or noisy input observations
arXiv:2607.18360v2 Announce Type: replace-cross Abstract: GPTZero found 53 NeurIPS 2025 accepted papers with hallucinated citations, and venues now screen submissions with automated reference checkers
arXiv:2610.18369v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated promising capabilities for remote sensing reasoning, yet they frequently generate visually un
arXiv:2610.17948v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) have attracted increasing research attention due to their bidirectional attention and arbitrary order decoding.
arXiv:2610.15769v1 Announce Type: cross Abstract: Human demonstrations can capture task-relevant manipulation without using the target robot, but the recorded hand motions cannot directly serve as rob
arXiv:2610.15951v1 Announce Type: cross Abstract: Ransomware is a fast-escalating privacy threat causing significant financial and data losses worldwide. As attacks grow more sophisticated, traditiona
arXiv:2610.16261v1 Announce Type: cross Abstract: Mamba-based super-resolution models are efficient alternatives to Transformer-based restoration backbones, but their low-bit post-training quantizatio
arXiv:2610.15957v1 Announce Type: cross Abstract: Transformer models trained on symbolic music have become remarkably capable. However, it is yet unclear how they represent music structure, and whethe
arXiv:2610.14224v1 Announce Type: cross Abstract: LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a p
arXiv:2610.15431v1 Announce Type: new Abstract: Monocular depth estimation (MDE) has emerged as a cost-effective alternative to hardware-dependent 3D sensing modalities, yet predicting precise metric
arXiv:2610.15401v1 Announce Type: new Abstract: VLMs provide promising solutions to embodied reward design. Most current methods that train VLMs as reward regressors not only require extensive annotat
arXiv:2610.17370v1 Announce Type: new Abstract: Scientific discovery with language models requires finding the best valid solution within a finite computational budget. We study how feedback from this
arXiv:2610.17368v1 Announce Type: cross Abstract: Generative recommendation models have shown promising results by representing items as semantic IDs and generating these IDs autoregressively. We intr
arXiv:2610.15375v1 Announce Type: new Abstract: Zero-Shot Object Navigation (ZSON) requires an agent to locate target objects in unfamiliar environments without additional training for the test catego
arXiv:2610.18238v1 Announce Type: new Abstract: Vision-language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page
arXiv:2610.17694v1 Announce Type: new Abstract: We introduce HelpMeOut, an embodied AI benchmark for error-aware monitoring of household task execution. Existing embodied household benchmarks typicall
arXiv:2610.15781v1 Announce Type: new Abstract: Training-free pruning removes weights from pretrained large language models to reduce their deployment cost. However, existing approaches typically cons
arXiv:2610.16545v1 Announce Type: new Abstract: Feature caching has become a mainstream training-free strategy for accelerating video diffusion models by reusing intermediate outputs across denoising
arXiv:2610.15297v1 Announce Type: new Abstract: Recently, AutoRegressive Visual Generation (ARVG) models have emerged as a competitive paradigm for high-quality image synthesis. However, their substan
arXiv:2610.17684v1 Announce Type: new Abstract: High-fidelity surgical video generation is increasingly important for surgical education, simulation, and downstream AI training, as conventional simula
arXiv:2610.14123v1 Announce Type: cross Abstract: AI-assisted scientific discovery increasingly seeks to move beyond generating plausible ideas toward reproducible, constraint-aware workflows that can
arXiv:2604.03208v3 Announce Type: replace Abstract: World models are a promising path to zero-shot embodied control through planning. However, existing world model planners struggle on long-horizon, m
arXiv:2610.18196v1 Announce Type: cross Abstract: Hierarchical time series forecasting requires generating accurate predictions that are coherent across multiple levels of aggregation. Existing method
arXiv:2610.17933v1 Announce Type: new Abstract: Clinical screening for diabetic retinopathy proceeds in stages, yet most automated systems grade fundus images with a single black-box network. Three ga
arXiv:2610.18045v1 Announce Type: cross Abstract: High-fidelity three-dimensional turbulent flow fields are essential for scientific and engineering analyses, yet obtaining them through direct numeric
arXiv:2508.05570v2 Announce Type: replace-cross Abstract: In this paper, we study the bias and high-order error bounds of the Linear Stochastic Approximation (LSA) algorithm with Polyak-Ruppert (PR) a
arXiv:2601.07718v2 Announce Type: replace Abstract: Achieving robust humanoid locomotion in complex, unstructured environments requires transitioning from reactive proprioception to proactive percepti