127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “pretraining”

6,758 results

Tutorials

UniWAM: Unified World-Action Model

DGX agent

arXiv:2610.02054v1 Announce Type: new Abstract: Vision-language-action models benefit from the understanding and reasoning capabilities of pretrained vision-language models, but action-only supervisio

tutorialsarxiv-cs-ro

2 Oct 2026

Safety

Video Generation Models: A Survey of Post-Training and Alignment

DGX agent

arXiv:2610.00812v1 Announce Type: cross Abstract: Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamics

Search: “pretraining”

UniWAM: Unified World-Action Model

Video Generation Models: A Survey of Post-Training and Alignment

AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agents

DiffWAM: A Fast and Efficient Navigation World Action Model

DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents

Image Classifiers are Efficient Self-Supervised Video Representation Learners

Inductive Visual Logic for Few-Shot Out-Of-Distribution Adaptation in VLMs

PEG-Tab: Sampling-Time Record Repair and Release Control for Tabular Synthesis

PrefPI: Preference-Guided Steering into Out-of-Distribution Behaviors

Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse Imagination

Synthetic Data Characterization via Training Dynamics

T-Router: Learning Thalamic Routing for Reasoning with Parameter-Efficient Reinforcement Learning

VOSSA: Voiceprint Optimization for Streaming Speech Architectures

Adapting Linear-Time Architectures for Tabular In-Context Learning

CoRe-VLA: Preserving Cross-View Coordination in VLAs under Camera Shifts

GeoSET: Generalist Foundation Model for SAR-to-EO Image Translation

HiRAE: Hierarchical Representation Autoencoding with Residual Budgets

Interacting particle guidance for sampling reward-tilted generative priors

MoTIF-X: A Multimodal Tokenized Framework for Interpretable and Extensible Molecular Representation Learning

MVG-WAM: Multiple View Geometry-Aware World-Action Modeling for Robotic Manipulation

Principled MAP estimation for inverse problems: bridging the gap between convergence and performance

Reprogramming Vision-Language Models via Structured Prompt Reparameterization

Rethinking Soft Tokens for Parallel Decoding in Diffusion Language Models

Scalable Diffusion SBI for Compositional Inference under Simulator Misspecification

Scouting the Dynamics Gap: Test-Time Policy Adaptation via Action-Outcome Feedback

TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models

Trajectory Soup: Pushing the Compute-Scaling Frontier of LLM Mid-training via Diverse Trajectories

V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization

An End-to-End Latent-Rollout Approach for Pushing Few-Step ImageNet-256 Generation to FID 1.11 without Frechet Losses

CAESAR: Clustering via Autonomous Embedding-Space Agglomerative Reorganization

CARVE: Breaking Data Barriers in Chip Placement by Harnessing Reusable Expertise

Constrained Edit Fields for Training-Free Flow Editing

Continual Learning via Self-Probe Gradients

DimPO: Dimensionality Reduction for Attention using Preference Optimization

GeoCR: Learning a Generalist Cloud Removal Prior from Heterogeneous Observations

Hierarchical Response Preservation for Continual Adaptation of Zero-Shot Graph-Text Models

In-Token Learning for High-Fidelity Image Restoration via Diffusion Transformers

JET: Justification Evaluation in Transformer

LionMuon: Alternating Spectral and Sign Descent for Efficient Training

Patch Rebirth: Toward Fast and Transferable Model Inversion of Vision Transformers

Pre-registered tests of solid-state-physics-inspired LLM compression: a cluster-level negative result at small-language-model scale

Quantile Head for Vision-Language-Action Models

Representation Editing for Multimodal Test-Time Adaptation

SAMBAR: Selective Anchoring via Method of Multipliers for Balanced Knowledge Acquisition and Retention in Vision-Language-Action Models

Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity

Tilted Schrodinger Bridge Matching

Transferable Mass Spectrum Prediction via Reference-Guided Test-time Specialization

When Does Geometric View Synthesis Help Wine Label Retrieval? A Public One-Shot Benchmark Across Self-Supervised and Vision-Language Backbones