Knowledge catalogue
arXiv:2610.21152v1 Announce Type: new Abstract: Training humanoid whole-body vision-language-action (VLA) policies requires costly robot demonstrations with aligned robot-view observations and control
arXiv:2610.21176v1 Announce Type: cross Abstract: Large language models (LLMs) reproduce a human working-memory signature on the N-back task: performance declines as memory load N increases, and error
arXiv:2610.20951v1 Announce Type: new Abstract: Decision models answer typed questions about an input with one probability per option, computed in a single forward pass without generating text. Like t
arXiv:2610.21282v1 Announce Type: cross Abstract: Spatial augmented reality (SAR) augments physical environments with projected content, but most systems assume that the projector pose, target region,
arXiv:2610.21140v1 Announce Type: new Abstract: Contact-rich robotic tasks require coordinated motion and impedance under uncertain interaction dynamics and physical constraints. While recent methods
arXiv:2610.21007v1 Announce Type: new Abstract: Data selection reallocates training support across visual concepts, including objects, attributes, color, texture, and backgrounds. Different allocation
arXiv:2610.22276v1 Announce Type: new Abstract: Spatial intelligence lets an agent perceive and act in the physical world, and many of its judgments must be made at interaction rates: which spatial re
arXiv:2610.21743v1 Announce Type: new Abstract: Direct pairwise AUC-surrogate training is attractive because it trains toward the ranking metric used at test time, especially under class imbalance. Th
arXiv:2610.22100v1 Announce Type: new Abstract: Byte-level language models such as the Byte Latent Transformer (BLT) run their large global model once per patch and start a patch where a small model's
arXiv:2610.22363v1 Announce Type: new Abstract: We introduce P^{3}-WAM, a unified world action model for egocentric dexterous manipulation that learns 3D perception, action-conditioned prediction, and
arXiv:2610.20973v1 Announce Type: new Abstract: Geo-foundation models (GFMs) are typically evaluated by downstream task predictive performance, revealing little about which physical features they are
arXiv:2610.20873v1 Announce Type: new Abstract: Vehicles that lose control at the handling limit through icing, hydroplaning, or an abrupt evasive maneuver fall outside the operating envelope of produ
arXiv:2610.22150v1 Announce Type: new Abstract: In Rhetorical Structure Theory (RST), each edge of a discourse tree carries a nuclearity label, marking which span holds the central content, and a rela
arXiv:2610.21539v1 Announce Type: new Abstract: Diffusion models (DMs) have steadily demonstrated outstanding performance in high-fidelity, controllable generation across diverse scenarios, following
arXiv:2610.21240v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) decompose language model activations into sparse features, but prompt transformations designed to preserve the underlying r
arXiv:2610.22120v1 Announce Type: new Abstract: Knowing the layout of the physical world matters for many applications, yet the sensors we rely on for it (e.g., cameras and LiDAR) can fail in darkness
arXiv:2512.15756v2 Announce Type: replace-cross Abstract: Human-imposed design conventions can restrict the alternatives represented in scientific training data and shape the search preferences learne
arXiv:2610.21850v1 Announce Type: new Abstract: Generating 3D assets with explicit parts requires two properties at once: geometric detail inside each part and structural coherence across the whole ob
arXiv:2610.21950v1 Announce Type: cross Abstract: Tabular foundation models based on prior-data fitted networks (PFNs) predict on a new data set in a single forward pass, but they cannot report which
arXiv:2610.20766v1 Announce Type: new Abstract: Imagined speech decoding from EEG offers a promising route toward naturalistic brain-computer interfaces. Traditional closed-set classifiers treat seman
arXiv:2507.19839v2 Announce Type: replace-cross Abstract: The modality gap is intrinsic to multimodal alignment, where embeddings from different modalities remain partially separated in a shared repre
arXiv:2610.22352v1 Announce Type: new Abstract: Single image 3D generation aims to dress a given 3D mesh with relightable materials while faithfully preserving the visual details of a reference image.
arXiv:2610.22242v1 Announce Type: cross Abstract: Tabular foundation models (TFMs) now outperform gradient-boosted trees in classification and regression. Yet in survival analysis, which predicts when
arXiv:2610.21286v1 Announce Type: new Abstract: We investigate whether variation in information density across chain-of-thought (CoT) reasoning steps predicts answer correctness and can serve as a con
arXiv:2610.21922v1 Announce Type: new Abstract: Many vision-language-action policies rely on action-labeled robot demonstrations and lack an explicit mechanism for predicting future visual states. The
arXiv:2610.21735v1 Announce Type: new Abstract: Object manipulation often requires combining non-prehensile actions with grasping. However, existing approaches typically develop these capabilities sep
arXiv:2610.16837v1 Announce Type: cross Abstract: Syntactic language models (SLMs) that generate sentences along with their syntactic tree structures have shown promise in both syntactic generalizatio
arXiv:2610.15371v1 Announce Type: cross Abstract: Gnani-Evon-v3.3-30B-A3B is a long-context hybrid Mamba-Transformer mixture-of-experts model for reasoning, instruction following, and tool use in Engl
arXiv:2610.14693v1 Announce Type: new Abstract: Explicit point correspondence is attractive for adapting video generators: it describes how visible surfaces move, but can overwrite the appearance prio
arXiv:2509.18369v2 Announce Type: replace Abstract: Adapting vision-language models in low-resource languages remains challenging, as they often produce fluent text about the wrong objects. This stems
arXiv:2610.19802v1 Announce Type: new Abstract: Negative guidance of diffusion models generates samples that avoid an undesired condition, specified either by reference samples or by a conditional sco
arXiv:2610.19966v1 Announce Type: new Abstract: The number of attention heads in a transformer is usually set by convention or grid search. We test a simple heuristic for setting it in advance: estima
arXiv:2610.14465v1 Announce Type: cross Abstract: Structured knowledge retrieval acquires task-relevant evidence from structured knowledge sources for downstream tasks. Existing methods rely on uncons
arXiv:2610.20597v1 Announce Type: cross Abstract: Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from
arXiv:2610.19880v1 Announce Type: new Abstract: Unsupervised temporal action localization (UTAL) aims to identify action categories and localize their temporal boundaries without annotation supervisio
arXiv:2610.19957v1 Announce Type: new Abstract: World action models (WAMs) jointly predict future visual states and robot actions, but processing dense future-frame tokens incurs substantial inference
arXiv:2610.19247v1 Announce Type: new Abstract: Transformers are intuitively considered to be efficient at copying from their inputs. We actually show that the ability of LLMs to copy in context can b
arXiv:2610.19343v1 Announce Type: cross Abstract: A training-data quality gate changes both which examples survive within regions of the input space and how training mass is distributed across those r
arXiv:2610.19600v1 Announce Type: new Abstract: Recent vision-language-action (VLA) models have shown strong performance on local robot manipulation, yet their success does not readily translate to lo
arXiv:2610.17124v1 Announce Type: cross Abstract: Full-duplex spoken language models (FD-SLMs) support simultaneous listening and speaking, but often lag behind half-duplex spoken language models (HD-
arXiv:2610.20158v1 Announce Type: new Abstract: Self-supervised joint embedding learning aligns representations of augmented views while regularizing their distribution to prevent collapse. Regulariza
arXiv:2610.19466v1 Announce Type: new Abstract: Chest X-Ray (CXR) is a primary modality for diagnosing pulmonary diseases, yet the overlap of bony structures often obscures critical radiographic findi
arXiv:2610.20124v1 Announce Type: new Abstract: Human mesh recovery (HMR) provides a geometric foundation for understanding human motion, but accurately reconstructing both body motion and fine hand a
arXiv:2610.20598v1 Announce Type: new Abstract: Achieving general spatial intelligence requires a unified understanding of both static 3D and dynamic 4D. However, we find that existing models struggle
arXiv:2506.04713v4 Announce Type: replace Abstract: A key challenge in Few-Shot Recognition (FSR) is the scarcity of labeled task-specific data for training. Contemporary methods mitigate this challen
arXiv:2610.19224v1 Announce Type: new Abstract: Surface navigation on the Moon is subject to extreme illumination contrast and deployment-time perceptual disturbances. While modular navigation pipelin
arXiv:2610.19635v1 Announce Type: new Abstract: Gaze coordinates attention in human interaction through coupled eye, head, and eyelid motion. A humanoid robot must choose where to look while generatin
arXiv:2610.20286v1 Announce Type: new Abstract: The Platonic Representation Hypothesis (PRH) holds that increasingly capable models converge toward a common representation. However, recent studies hav
arXiv:2610.20073v1 Announce Type: new Abstract: Accurate nuclei segmentation underpins quantitative computational pathology, yet remains challenging due to morphological variability, weak boundaries,
arXiv:2610.20220v1 Announce Type: new Abstract: Autoregressive generation underlies real-time, causal video synthesis and is the backbone of video world models. Today's dominant approach distills a bi
arXiv:2610.20409v1 Announce Type: new Abstract: We develop a self-supervised reinforcement learning algorithm that learns to build towers of up to eight cubes from scratch, without prior data, rewards
arXiv:2610.18547v1 Announce Type: new Abstract: People often tackle difficult problems by thinking more deeply or exploring more possibilities. Similarly, recursive reasoners, which reason by repeated
arXiv:2610.19592v1 Announce Type: new Abstract: The ability to generate proteins with desired functions is a central goal of computational biology. Although natural language can express diverse design
arXiv:2610.14699v1 Announce Type: new Abstract: The design of high-affinity, target-specific protein binders is central to the development of modern therapeutics. However, existing protein-generation
arXiv:2610.20552v1 Announce Type: new Abstract: We present KinoGen, a framework that synthesizes customizable humanoid loco-manipulation references through kinematically grounded video generation. Kin
arXiv:2610.20102v1 Announce Type: new Abstract: We investigate two aspects of multilingual pre-training with limited data, namely how language exposure is distributed across English, Dutch, and Chines
arXiv:2610.17439v1 Announce Type: new Abstract: The success of autonomous research systems relies on the quality of the scientific hypotheses they generate. Recent studies report that human reviewers
arXiv:2610.15158v2 Announce Type: replace Abstract: We study neuro-symbolic natural language inference (NLI) with independently translated propositional representations of the premise and hypothesis.
arXiv:2610.19782v1 Announce Type: new Abstract: Population health stratification frameworks, such as the Italian DM77, organize patients by clinical need and care pathways but offer limited guidance o
arXiv:2610.20365v1 Announce Type: new Abstract: AI agent communities sustain lexical persistence, popular terms spread, recur, and achieve broad adoption, but whether they also develop the temporal se