Knowledge catalogue
arXiv:2609.34866v1 Announce Type: new Abstract: Most post-training quantization pipelines fit each weight matrix to its pretrained counterpart, one matrix at a time. Whether that proxy tracks what an
arXiv:2609.33086v1 Announce Type: new Abstract: Current approaches to aligning language models often make it hard to know what behavior is being rewarded or to change that reward in a targeted way. In
arXiv:2609.35348v1 Announce Type: new Abstract: Estimating probability densities from a finite set of samples typically requires dataset-specific model fitting. We introduce PRODiGI, a pretrained data
arXiv:2609.33649v1 Announce Type: new Abstract: Learning mappings between probability distributions arises naturally when inputs and outputs are represented by populations of samples rather than indiv
arXiv:2605.05660v2 Announce Type: replace Abstract: Multi-objective optimization (MOO) has received growing attention in applications that require learning under multiple criteria. However, most exist
arXiv:2609.35568v1 Announce Type: new Abstract: High-performance kernels underpin efficient accelerator execution but require expert tuning and lengthy manual optimization cycles. LLM coding agents pr
arXiv:2609.32761v1 Announce Type: new Abstract: Reconstruct where the images provide evidence, and generate where they do not: recent success of spatial world models such as Atlas (World Labs Team, 20
arXiv:2609.33387v1 Announce Type: new Abstract: Machine learning plays an increasingly vital role in engineering, but the corresponding increase in compute time is not without environmental cost. Phys
arXiv:2609.33984v1 Announce Type: new Abstract: Linear forecasters have shown competitive accuracy against Transformer-based models in long-term time series forecasting. We study how classical station
arXiv:2609.35449v1 Announce Type: new Abstract: With limited annotation budgets, choosing which images to label determines how much a model improves. Data-selection methods that use features from a se
arXiv:2609.32653v1 Announce Type: cross Abstract: The ability of vision-language models (VLMs) to abstain from unanswerable questions is as important as their ability to answer answerable ones accurat
arXiv:2609.34412v1 Announce Type: new Abstract: Natural-language manipulation instructions specify qualitative relations, whereas continuous controllers require state-evaluable task quantities, differ
arXiv:2609.34994v1 Announce Type: cross Abstract: Most music-generation systems are still framed and evaluated primarily as producers of complete outputs, whereas composition often proceeds through su
arXiv:2609.33447v1 Announce Type: cross Abstract: Guideline documents are published as unstructured PDFs whose evidence is locked in visual structures---tables, flowcharts, and graded recommendations-
arXiv:2609.34809v1 Announce Type: new Abstract: Vision-language models (VLMs) can answer simple visual questions, but often struggle when one question requires several visual judgments. We study this
arXiv:2609.31656v1 Announce Type: new Abstract: Data quality is a major bottleneck for the reliable deployment of graph neural networks (GNNs) in real-world graph mining tasks. Among various sources o
arXiv:2609.34716v1 Announce Type: new Abstract: Clinical CT and UHRCT cannot resolve individual trabeculae, whereas synchrotron radiation microCT (SR{mu}CT) provides 3.2{mu}m high-resolution reference
arXiv:2609.35375v1 Announce Type: new Abstract: Scaling up robotic manipulation is primarily bottlenecked by the scarcity of real-world robot data. While recent approaches leverage human video demonst
arXiv:2609.34679v1 Announce Type: new Abstract: Bipartite matching is a fundamental problem in game theory and market design. Classical approaches such as Gale--Shapley assume complete preferences and
arXiv:2609.35491v1 Announce Type: new Abstract: Few-step autoregressive video generation commonly relies on Distribution Matching Distillation (DMD), requiring a bidirectional diffusion teacher and an
arXiv:2609.34850v1 Announce Type: cross Abstract: Soft preference targets specify supervision strength, and reward objectives convert that strength into learned reward signals. A central design questi
arXiv:2609.34371v1 Announce Type: new Abstract: On-policy distillation (OPD) specializes pretrained video diffusion models through teacher supervision along the student's own generation trajectory. Al
arXiv:2609.35203v1 Announce Type: new Abstract: Nuclei instance segmentation is a core task in digital pathology, yet high-accuracy models rely on large vision transformer (ViT) encoders whose inferen
arXiv:2609.34414v1 Announce Type: new Abstract: Predicting the next state is a core paradigm of World Models for modeling physical dynamics, emphasizing prediction fidelity. As World Models evolve int
arXiv:2609.35426v1 Announce Type: new Abstract: Reinforcement Learning-based post-training of Large Language Models (LLM) has been successfully applied to improve their reasoning capabilities. Existin
arXiv:2609.34198v1 Announce Type: new Abstract: Language-model judges compare agent upgrades with their predecessors, but a fixed judge can make version-dependent mistakes. We analyze 35 public coding
arXiv:2609.32273v1 Announce Type: new Abstract: Accurate delineation of whole tumor (WT), tumor core (TC), and enhancing tumor (ET) from multimodal magnetic resonance imaging remains challenging under
arXiv:2609.34207v1 Announce Type: cross Abstract: Functional data are intrinsically infinite-dimensional, and often exhibit phase variation, where corresponding events occur at different times across
arXiv:2609.34149v1 Announce Type: new Abstract: Current methods for egocentric view action recognition often face challenges in perceiving dynamic hand movements relying solely on geometrical or physi
arXiv:2609.32296v1 Announce Type: new Abstract: Efficient sampling from Boltzmann distributions is central to modelling complex physical systems. Markov Chain Monte Carlo (MCMC) methods suffer from cr
arXiv:2609.35770v1 Announce Type: new Abstract: Realistic and editable animal fur reconstruction from multi-view images is challenging due to fine-scale detail, self-occlusion and obfuscation, and, un
arXiv:2609.33650v1 Announce Type: new Abstract: Word-level forced alignment estimates when each transcript word occurs in an audio recording. It underpins text-based media editing, subtitling, speech-
arXiv:2609.04742v1 Announce Type: cross Abstract: Running an unfamiliar nuclear-physics code is rarely difficult because of the physics alone. One must find and build the program, learn its input conv
arXiv:2609.31749v1 Announce Type: new Abstract: We built an ordinary stacking ensemble for AI-generated image detection -- three open detectors producing five scores, fused by a gradient-boosted meta-
arXiv:2609.33981v1 Announce Type: new Abstract: Exploration--exploitation is a central trade-off in bandit learning. While classical algorithms such as upper confidence bound methods and Thompson Samp
arXiv:2609.34362v1 Announce Type: new Abstract: World Action Models (WAMs) augment robot action generation with future visual supervision. Existing WAMs commonly fuse main and wrist observations into
arXiv:2609.32158v1 Announce Type: new Abstract: Moving obstacles can block a previously clear route while a quadruped robot executes a motion command. We investigate whether predicting changing cleara
arXiv:2609.31715v1 Announce Type: new Abstract: Agentic recognition requires visual perception to move beyond static scene understanding and produce structured scene representations that support the p
arXiv:2609.35189v1 Announce Type: new Abstract: Post-training foundation video models on heterogeneous reward-weighted data usually assume that all data categories induce compatible updates. This assu
arXiv:2609.34233v1 Announce Type: new Abstract: Humanoid avatars extend human physical presence beyond the body, enabling people to participate in social, service, and labor activities through remotel
arXiv:2609.31901v1 Announce Type: new Abstract: Constrained general-sum dynamic games are a popular formulation for highly interactive multi-agent planning problems. In recent years, Generalized Nash
arXiv:2609.31755v1 Announce Type: new Abstract: Panoramic 360^irc scene understanding increasingly relies on icosphere transformers, but a state-of-the-art spherical model loses more than half of its
arXiv:2609.32596v1 Announce Type: new Abstract: Feed-forward models regress dense 3D point trajectories directly from monocular video, yet the residual after global alignment is substantial and lacks
arXiv:2609.32154v1 Announce Type: new Abstract: In this paper, we present a Goal-Aware Uncertainty-Guided Exploration (GAUGE) framework for planner-conditioned active calibration of opaque quadruped v
arXiv:2609.32131v1 Announce Type: new Abstract: 2D Gaussian-based image representation is becoming increasingly popular, and our work proposes a new approach to steganography by embedding information
arXiv:2609.34825v1 Announce Type: new Abstract: Gaussian neural networks (GaNNs) are proposed as a novel regularization mechanism for neural networks. From a Bayesian perspective standard regularizati
arXiv:2609.33969v1 Announce Type: new Abstract: Immersive video communication requires photorealistic, render-efficient, and compact dynamic scene representations. 3D Gaussian Splatting (3DGS) offers
arXiv:2609.34550v1 Announce Type: new Abstract: Vision-Language-Action (VLA) fine-tuning pairs images with actions at every step, yet typically provides only a task-level language instruction, leaving
arXiv:2407.07670v2 Announce Type: replace-cross Abstract: We investigate the generalization performance of online stochastic gradient descent (SGD) for overparameterized two-layer neural networks unde
arXiv:2609.35226v1 Announce Type: new Abstract: Early detection of oral cancer via photographic imaging presents a promising avenue for large-scale oral cavity screening. However, the development of r
arXiv:2504.02272v2 Announce Type: replace Abstract: Domain generalization (DG) aims to improve the generalizability of computer vision models toward distribution shifts. The mainstream DG methods pred
arXiv:2609.32941v1 Announce Type: new Abstract: Inferring quantities of interest (QoI) from data is a central task in Science and Engineering. In such contexts, we often have access to both quantitati
arXiv:2609.34824v1 Announce Type: new Abstract: Under a shared-factor model, the conditional law of the next image patch factors into a posterior over the shared scene factor and a residual kernel giv
arXiv:2609.35341v1 Announce Type: new Abstract: Evaluating semantic similarity between videos is a fundamental challenge in computer vision, essential for tasks ranging from out-of-distribution (OOD)
arXiv:2609.34633v1 Announce Type: new Abstract: Long-term memory supports the self-evolution of LLM agents by retaining experience and skills across tasks and enabling their retrieval, reuse, and revi
arXiv:2609.34579v1 Announce Type: new Abstract: Single-image novel view synthesis remains challenging because the underlying 3D geometry is highly ambiguous. Recent diffusion-based approaches produce
arXiv:2609.34398v1 Announce Type: new Abstract: Critical mineral discovery is a positive-only problem: deposits are observed as sparse locations, while unlabeled regions are not reliable negatives, an
arXiv:2609.32510v1 Announce Type: new Abstract: Cloud removal methods are typically specialized to individual datasets and input configurations, limiting reuse across sensors, spectral bands, and obse
arXiv:2609.35527v1 Announce Type: new Abstract: Embedding structured objects into Euclidean spaces has enabled a wide range of successful machine learning applications. Such objects include words, doc
arXiv:2609.34148v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are far more reliable at recognizing what appears in a video than at reasoning about its spatial and temporal properties,