Knowledge catalogue
arXiv:2609.32270v1 Announce Type: cross Abstract: We study the generalization of spectral gradient descent (SpecGD) in overparameterized matrix classification with corrupted labels. Each input combine
arXiv:2609.33236v1 Announce Type: new Abstract: Training-free online video anomaly detection (VAD) with frozen multimodal language models faces two coupled challenges: extracting reliable current-wind
arXiv:2609.32634v1 Announce Type: new Abstract: Reinforcement Fine-Tuning~(RFT) has emerged as a promising paradigm for improving Vision-Language-Action~(VLA) policies, yet sparse task-level outcomes
arXiv:2603.02231v2 Announce Type: replace Abstract: Large-scale wave field reconstruction requires precise solutions but faces challenges with computational efficiency and accuracy. The physics-based
arXiv:2609.32685v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) provide a learning-based framework for solving partial differential equations (PDEs), yet their training beha
arXiv:2609.32146v1 Announce Type: new Abstract: A quadrilateral block decomposition of a planar domain is judged by whether it is complete, whether its elements are well shaped, and how many of its ve
arXiv:2609.33127v1 Announce Type: new Abstract: Offline-to-Online Reinforcement Learning (O2O RL) has emerged as a practical paradigm that pre-trains the policy using static offline datasets and subse
arXiv:2609.34021v1 Announce Type: new Abstract: Test-Time Training (TTT) adapts models to incoming test samples (e.g. out-of-distribution, (OOD)) when conventional fine-tuning is infeasible. Existing
arXiv:2609.35011v1 Announce Type: new Abstract: Price stability remains a pillar in monetary policy practices and carries a special importance within monetary unions. Mainstream economics tried to lev
arXiv:2609.31641v1 Announce Type: new Abstract: Scalar rounding decisions interact through matrix multiplication. We study deterministic product-aware rounding after scales, clipping bounds, and grids
arXiv:2609.32333v1 Announce Type: new Abstract: Regional-to-global distillation uses crop-conditioned guidance to improve full-image understanding. The challenge is to effectively transfer the teacher
arXiv:2609.34222v1 Announce Type: new Abstract: Payload forces must be accommodated during locomotion, while leash forces can specify desired motion. We investigate whether a shared three-dimensional
arXiv:2609.35698v1 Announce Type: new Abstract: We study adversarial imitation learning (AIL), in which an agent learns to imitate expert demonstrations by optimizing a policy against an adversarial r
arXiv:2609.34497v1 Announce Type: new Abstract: Flow policies can model rich action distributions, but their iterative sampling limits decision speed. Adjoint matching uses the critic's action gradien
arXiv:2609.34061v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models integrate pretrained Vision-Language Models (VLMs) with action heads for robot control. Common action heads have d
arXiv:2609.31668v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) process multimodal inputs by converting text, images, and videos into token sequences that are subsequently pro
arXiv:2609.32836v1 Announce Type: cross Abstract: Radiomap blind prediction aims to infer radiomaps from observable representations of the propagation environment and base station configuration withou
arXiv:2609.34179v1 Announce Type: cross Abstract: Retrieval-augmented generation systems are extensively instrumented with metrics, benchmarks, traces, and automated judges, but these tools do not dec
arXiv:2609.32819v1 Announce Type: cross Abstract: Raising the update-to-data (UTD) ratio breaks off-policy critics in two ways grouped as 'plasticity loss': collapsing representations and growing valu
arXiv:2609.32416v1 Announce Type: cross Abstract: Code-as-Policy agents accomplish long-horizon embodied tasks by generating and executing code, yet continually improving them with teachers that are s
arXiv:2609.32155v1 Announce Type: new Abstract: Sequential manipulation requires a robot to track what has already happened, even when the current scene no longer reveals it. Policies with explicit hi
arXiv:2609.35200v1 Announce Type: cross Abstract: Memory-dependent manipulation requires robots to make decisions using information that is no longer available to their current sensors, such as recall
arXiv:2609.35034v1 Announce Type: cross Abstract: Off-policy evaluation, which estimates evaluation policy performance from logged data, is key for recommender ranking policies. However, logged clicks
arXiv:2609.31771v1 Announce Type: new Abstract: Many planning and control tasks for tendon-driven continuum robots (TDCRs) require the complete Cartesian backbone geometry. We present a reduced Cartes
arXiv:2609.32888v1 Announce Type: new Abstract: Gradient-based data selection methods such as LESS score each candidate by the alignment between its gradient and a target validation gradient, and reco
arXiv:2505.12027v2 Announce Type: replace Abstract: In recent years, large language models (LLMs) have demonstrated remarkable capability to generalize across diverse natural language processing tasks
arXiv:2609.31816v1 Announce Type: new Abstract: What should a compressed representation preserve when the information of interest lies in relationships among elements rather than in the elements thems
arXiv:2609.33304v1 Announce Type: new Abstract: Personal Graphical User Interface (GUI) agents rely on interaction history to infer what a user wants from ambiguous instructions and to anticipate recu
arXiv:2609.33725v1 Announce Type: cross Abstract: Continually adapting models to new tasks requires retaining earlier knowledge under limited memory and computation. Experience replay addresses this c
arXiv:2609.33217v1 Announce Type: new Abstract: Generative models learn visual structure through denoising, yet their internal states are entangled with both noise level and network depth, making it d
arXiv:2609.32263v1 Announce Type: new Abstract: Multimodal test-time adaptation (TTA) aims to adapt a pretrained multimodal model online to distribution shift across modalities using unlabeled test da
arXiv:2609.32129v1 Announce Type: new Abstract: Pretrained robot policies offer strong manipulation skills but are typically limited to single-agent settings, where a robot acts in isolation. In this
arXiv:2609.32187v1 Announce Type: new Abstract: Cross-channel modeling is central to multivariate time-series forecasting, yet channels that are statistically related, predictively useful, and actuall
arXiv:2609.34563v1 Announce Type: new Abstract: Latent visual reasoning (LVR) enables multimodal large language models (MLLMs) to perform intermediate computation in continuous latent tokens rather th
arXiv:2609.35439v1 Announce Type: cross Abstract: World-action models use predicted visual futures to condition robot actions, yet execution feedback can invalidate parts of a prediction while leaving
arXiv:2609.33989v1 Announce Type: cross Abstract: Reward models (RMs) are a key component of large language model post-training, providing reward signals for subsequent reinforcement learning. However
arXiv:2609.33221v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is a powerful technique for aligning large language models (LLMs) with human preference. However, it o
arXiv:2609.32236v1 Announce Type: new Abstract: Generative models, such as diffusion and flow-based models, have shown strong promise for robot policy learning by capturing complex and multimodal acti
arXiv:2609.33872v1 Announce Type: cross Abstract: Robotic manipulation policies are advancing rapidly with increasing reliance on vision-language models for end-to-end decision making. However, reliab
arXiv:2512.22318v3 Announce Type: replace Abstract: When do role-specific training counts improve knowledge-graph error ranking? We evaluate fifteen from-scratch predictors, nine development-selected
arXiv:2609.34556v1 Announce Type: cross Abstract: Transformers process tokens without any inherent notion of order, making positional encoding a fundamental requirement rather than an architectural re
arXiv:2609.31698v1 Announce Type: new Abstract: Most existing MEG and EEG (M/EEG) visual decoding methods align brain signals with a single global embedding extracted from a pretrained visual encoder,
arXiv:2609.33669v1 Announce Type: cross Abstract: Residual policy adaptation provides a lightweight way to modify a strong reference policy, but a shared scale and a fixed subgroup partition can hide
arXiv:2603.09160v2 Announce Type: replace Abstract: Dense image captioning is critical for vision-language pretraining and for text-to-image generation, but scaling expert-quality annotations is prohi
arXiv:2609.34929v1 Announce Type: new Abstract: Language models are increasingly used to sample from a specified distribution, for instance, to simulate survey respondents or generate synthetic data.
arXiv:2609.33126v1 Announce Type: new Abstract: Group-relative reinforcement learning (RL) relies on reward variation among sampled responses to estimate informative relative advantages. As language m
arXiv:2609.35292v1 Announce Type: new Abstract: Recent representation alignment (REPA) methods accelerate diffusion transformer training by aligning projections of the transformer's hidden states with
arXiv:2609.33667v1 Announce Type: new Abstract: Attributing and controlling model behavior during training requires identifying each example's contribution quickly enough to act before the next update
arXiv:2609.33239v1 Announce Type: cross Abstract: Diffusion policies represent multimodal action distributions, but an advantage-weighted update does not specify how to sample from the resulting targe
arXiv:2609.34044v1 Announce Type: new Abstract: Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive. Training-free token pr
arXiv:2609.32698v1 Announce Type: new Abstract: Recent vision-language-action (VLA) policies demonstrate promising generalization across diverse short-horizon tasks. However, they remain unreliable on
arXiv:2609.32966v1 Announce Type: new Abstract: Reinforcement learning (RL) trains representations on data selected by the agent's policy, which then uses the resulting returns to guide its next choic
arXiv:2609.35432v1 Announce Type: new Abstract: Vision-language-action (VLA) and world-action (WAM) models map observations and instructions directly to robot actions. This directness ties a policy to
arXiv:2609.34294v1 Announce Type: new Abstract: Unsupervised visible-infrared person re-identification (USL-VI-ReID) learns person representations that can be compared across modalities without identi
arXiv:2609.33082v1 Announce Type: new Abstract: Developmental screening videos show how children perform specific behaviors, but clinical records usually contain outcomes rather than descriptions of w
arXiv:2609.32340v1 Announce Type: new Abstract: Reinforcement Learning (RL) has proven effective in aligning flow-based generative models with human preferences. Recently, Flow-GRPO has emerged as an
arXiv:2609.35225v1 Announce Type: cross Abstract: Sign language translation and generation share the goal of bidirectional alignment between text and sign representations. However, existing approaches
arXiv:2609.33575v1 Announce Type: new Abstract: Vision-Language-Action models are increasingly effective for robotic manipulation, yet most predict actions directly from current observations without e
arXiv:2607.11196v2 Announce Type: replace Abstract: Deploying object-centric models for real-world scene understanding typically requires complex pipelines to achieve both robust scene decomposition a
arXiv:2609.31965v1 Announce Type: cross Abstract: Mathematical expressions and the numerical behavior they produce are two views of the same underlying function, and connecting them is central to scie