Optimal Transport Depth Up-Scaling
arXiv:2508.08011v2 Announce Type: replace Abstract: Pre-training Large Language Models (LLMs) from scratch at larger scales yields remarkable performance but incurs substantially high training costs.
Knowledge catalogue
arXiv:2508.08011v2 Announce Type: replace Abstract: Pre-training Large Language Models (LLMs) from scratch at larger scales yields remarkable performance but incurs substantially high training costs.
arXiv:2610.11074v1 Announce Type: new Abstract: We establish near-optimal regret bounds for budget-constrained online learning against arbitrary classes of budget-pacing experts in the adversarial set
arXiv:2610.10975v1 Announce Type: cross Abstract: Muon has motivated a growing family of optimizers that compose multiple matrix normalizations, but these methods remain fragmented and lack a unified
arXiv:2610.11294v1 Announce Type: new Abstract: Presolve strongly affects mixed-integer programming (MIP) performance, yet learning-based methods only optimize parameter configurations and cannot expr
arXiv:2610.12461v1 Announce Type: new Abstract: Recent 3D world models generate photorealistic, explorable scenes that remain frozen in time. OuroWorld is a mask-free framework that turns any static 3
arXiv:2610.12345v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) adapts pretrained large language models (LLMs) to downstream tasks, but the required concepts can receive substantially dif
arXiv:2610.11547v1 Announce Type: new Abstract: NeRF and Gaussian splatting methods have been successfully applied on X-ray scenes where the views are too sparse for 3D reconstruction via classical me
arXiv:2610.11201v1 Announce Type: cross Abstract: Dynamic sparse attention limits the KV pages selected by each query, but a small support does not necessarily yield efficient GPU work. Query unions s
arXiv:2610.11572v1 Announce Type: new Abstract: Adapting a pre-trained 3D Gaussian Splatting (3DGS) road scene to a new time of day requires learning appearance changes from a few anchor images while
arXiv:2610.11498v1 Announce Type: new Abstract: Video diffusion and flow models require many sequential evaluations, making generation computationally expensive. Few-step distillation reduces this cos
arXiv:2602.19661v3 Announce Type: replace Abstract: Temporal information in structured electronic health records (EHRs) is often lost in sparse one-hot or count-based representations, while sequence m
arXiv:2610.11329v1 Announce Type: new Abstract: Pathology vision-language models (VLMs) have shown strong visual perception ability, but their robustness in the language domain remains poorly characte
arXiv:2610.11771v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies typically predict actions at fixed time intervals, coupling the route a robot follows with its execution pace. Thi
arXiv:2610.11011v1 Announce Type: new Abstract: Gaussian splatting has emerged as a flexible representation for 3D reconstruction from posed images. However, existing methods are optimized primarily u
arXiv:2606.17924v2 Announce Type: replace-cross Abstract: Current Vision-Language-Action (VLA) models face a trade-off between efficient action generation and explicit deliberation. Directly decoding
arXiv:2610.12081v1 Announce Type: new Abstract: Continuing the Perception Test challenge series, we organised the fourth edition as a workshop at the European Conference on Computer Vision (ECCV) 2026
arXiv:2610.11669v1 Announce Type: new Abstract: Holistic and semantics-aware co-speech gesture generation has advanced rapidly, yet evaluation remains behind: objective metrics do not consistently ref
arXiv:2610.11791v1 Announce Type: new Abstract: Generating physically plausible videos for solid-gas dynamics is challenging as different phases exhibit distinct dynamics yet remain coupled through ph
arXiv:2610.10630v1 Announce Type: cross Abstract: Training a compact model often needs far more memory than storing it, because the optimizer keeps its own records of past gradients. For a hyperdimens
arXiv:2610.11275v1 Announce Type: new Abstract: Phoneme-level models transcribe or generate speech as a sequence of phonemes, the smallest sound units that distinguish words. These models enable fine-
arXiv:2610.11646v1 Announce Type: new Abstract: German is a morphologically rich language whose syllable structure is exceptionally well-predicted by the Knuth--Liang hyphenation algorithm. We ask whe
arXiv:2603.13228v3 Announce Type: replace-cross Abstract: Recent progress in text-conditioned human motion generation has been largely driven by diffusion models trained on large-scale human motion da
arXiv:2610.12123v1 Announce Type: new Abstract: Generating a plausible robot action does not establish that current observations justify its execution. Motivated by exploratory observations of high-co
arXiv:2610.11167v1 Announce Type: cross Abstract: Vertical-domain few-shot classification remains challenging for small language models, as limited supervision makes it difficult to acquire domain-spe
arXiv:2610.10786v1 Announce Type: new Abstract: Planning is increasingly important for long-horizon agents, where successful execution requires coordinating subgoals, tool use, and intermediate outcom
arXiv:2610.11382v1 Announce Type: cross Abstract: World models in end-to-end autonomous driving predict future scene evolution to provide foresight for trajectory planning. Existing methods mainly stu
arXiv:2610.12285v1 Announce Type: new Abstract: Learning to predict how the world evolves can provide vision-language-action (VLA) policies with predictive context for long-horizon control, but its ef
arXiv:2609.32382v2 Announce Type: replace Abstract: We present our system for the PlurVA-LLM 2026 Shared Task Track-1, which focuses on pluralistic value alignment in the contexts of China, Indonesia,
arXiv:2610.11168v1 Announce Type: cross Abstract: Robotic manipulation often contains repeated motions whose local observations look similar at different phases. When these phases require different ac
arXiv:2610.11342v1 Announce Type: new Abstract: Synergistically capturing intricate local structures and global contextual dependencies has become a critical challenge in point cloud representation le
arXiv:2610.11612v1 Announce Type: new Abstract: This paper addresses multiview RGB-D point cloud registration, aiming to estimate global rigid poses for unordered RGB-D scans and align them in a metri
arXiv:2610.11423v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student model by aligning its policy with a teacher model on trajectories generated by the student model itself. T
arXiv:2405.04118v4 Announce Type: replace-cross Abstract: Modern AI systems such as self-driving cars and game-playing agents can achieve superhuman performance, but often lack human-like generalizati
arXiv:2610.11857v1 Announce Type: new Abstract: 3D scene inpainting aims to recover missing or occluded regions in edited 3D scenes, while ensuring geometric and textural consistency. Existing approac
arXiv:2610.12137v1 Announce Type: cross Abstract: Unauthorized model distillation, in which a model is trained on the outputs of a proprietary large language model (LLM), is a growing threat to model
arXiv:2610.10909v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) threaten the privacy of machine learning (ML) training data by determining whether a sample was used to train a ta
arXiv:2610.11803v1 Announce Type: new Abstract: Self-improving learning systems adapt data selection, optimization, and auxiliary symbolic components, inducing nonstationary objectives outside standar
arXiv:2610.12410v1 Announce Type: cross Abstract: LLM developers post-train their models to exhibit prosocial values and behavioral traits, which are enumerated in an alignment target. However, while
arXiv:2610.11975v1 Announce Type: new Abstract: Learned simulators for deformable linear objects (DLOs) such as cables have to predict the motion of cables they were not trained on and stay stable ove
arXiv:2610.12332v1 Announce Type: cross Abstract: Randomized controlled trials (RCTs) identify treatment effects without confounding but are often small, whereas observational studies (OBS) are large
arXiv:2512.16545v3 Announce Type: replace-cross Abstract: Cu NPs have a broad applicability, yet their synthesis is sensitive to subtle changes in reaction parameters. This sensitivity, combined with
arXiv:2610.11185v1 Announce Type: new Abstract: Single-cell trajectory inference maps transcriptomic measurements onto developmental continua, yet configurations that fit the data equally well can ass
arXiv:2610.12325v1 Announce Type: new Abstract: Do LLM scientific agents rely only on their initial task context, or do they adapt their decisions in response to experimental feedback? We study this q
arXiv:2610.10978v1 Announce Type: cross Abstract: When a field that an authority contract needs exists only in unstructured evidence, a model can sense it. We admit the model's output only as an obser
arXiv:2610.11833v1 Announce Type: new Abstract: Neural networks trained on modular addition tasks often develop Fourier-structured representations that support exact generalization. While prior work h
arXiv:2610.11592v1 Announce Type: new Abstract: Current frontier LLMs can theoretically process long contexts with 1M tokens or more. But to what extent can they go beyond simple retrieval and perform
arXiv:2610.11922v1 Announce Type: cross Abstract: Project Greenhouse represents our exploration of a simple thesis: We believe that it is possible to build fully open and sovereign models for agentic
arXiv:2610.11015v1 Announce Type: new Abstract: As voice agents gain more popularity commercially, the user simulators used to evaluate the deployed agents are also being developed to include more rea
arXiv:2510.10931v3 Announce Type: replace Abstract: While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this sett
arXiv:2610.11544v1 Announce Type: new Abstract: While predicting prosody from text is an established task in the field, the opposite direction, predicting text that fits a given prosodic pattern, rema
arXiv:2610.12397v1 Announce Type: new Abstract: We study whether persistent out-of-distribution (OOD) degradation can be predicted before it is directly observed using only source-side training dynami
arXiv:2610.11460v1 Announce Type: cross Abstract: Prototypes in classification models are almost always vectors, and a vector has no readable form. This paper asks what happens when a prototype is an
arXiv:2610.11486v1 Announce Type: cross Abstract: Sparse identification of nonlinear dynamics (SINDy) is a data-driven framework for discovering governing dynamics from time-series data by identifying
arXiv:2610.11914v1 Announce Type: new Abstract: High-resolution socioeconomic variables are important for applications such as urban planning, public health, disaster response, and resource allocation
arXiv:2610.12010v1 Announce Type: new Abstract: Predictive representation learning from photoplethysmography (PPG) can violate causal information access even with causal attention, as normalization, n
arXiv:2610.12423v1 Announce Type: new Abstract: We present Pumpire, a unified benchmark for evaluating metric point-pair distance estimation capability of both image- and video-level 3D foundation mod
arXiv:2610.10653v1 Announce Type: new Abstract: Scientific multimodal learning commonly assumes that paired views are comparably informative. Powder X-ray diffraction (PXRD) makes this mismatch explic
arXiv:2610.11261v1 Announce Type: cross Abstract: Variational quantum algorithms are often limited by barren plateaus: gradients vanish as circuit size and depth increase, making quantum neural networ
arXiv:2610.12135v1 Announce Type: new Abstract: Learning to tackle long-horizon, goal-conditioned tasks requires an agent to reason over extended timescales and act across a broad range of states. In
arXiv:2610.12200v1 Announce Type: cross Abstract: Classical CUSUM relies on the log-likelihood ratio of the underlying distributions, which cannot generally be computed from finite pre- and post-chang