hrlics / HoPELinks
[NeurIPS 2025] HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models
☆24Updated 2 months ago
Alternatives and similar repositories for HoPE
Users that are interested in HoPE are comparing it to the libraries listed below
Sorting:
- ☆33Updated 2 months ago
- CoRL 2025☆23Updated 5 months ago
- Official implementation of CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding.☆47Updated 4 months ago
- ☆39Updated last week
- Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies☆55Updated 2 months ago
- Official implementation of ICCV 2025 paper "EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds".☆44Updated 7 months ago
- Code for "AffordanceLLM: Grounding Affordance from Vision Language Models"☆14Updated last year
- Multi-SpatialMLLM Multi-Frame Spatial Understanding with Multi-Modal Large Language Models☆167Updated 4 months ago
- Imitation Learning; Robotics; Policy; VLA;☆30Updated this week
- Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image☆65Updated last month
- This repository is the official implementation of MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expre…☆75Updated 3 weeks ago
- [ICLR 2026] Official implemetation of the paper "Policy Contrastive Decoding for Robotic Foundation Models"☆22Updated last week
- The official implementation of "DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation". (arXiv 2601.22153)☆118Updated last week
- [ICCV 2025] Official PyTorch Implementation of "Learning Self-supervised Part-aware 3D Hybrid Representations of 2D Gaussians and Superqu…☆61Updated last month
- [ICCV 2025] Official repo of "EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow"☆26Updated 3 months ago
- Official Release of "Mixture of Horizons in Action Chunking"☆40Updated 2 months ago
- ☆47Updated 2 weeks ago
- Code implementation of the paper "World-in-World: World Models in a Closed-Loop World" (ICLR'26 Oral)☆124Updated last month
- EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments☆25Updated 8 months ago
- Codes of Paper "Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding"☆20Updated last year
- Official implementation of “4D LangVGGT: 4D Language-Visual Geometry Grounded Transformer”☆78Updated 2 months ago
- EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory☆62Updated 3 weeks ago
- [CVPR 2025] Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning☆55Updated 10 months ago
- SPAgent, a spatial intelligence agent designed to operate in the physical and spatial world.☆98Updated 2 weeks ago
- [NeurIPS 2025]"DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling"☆93Updated last month
- Public implementation of Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modeling☆26Updated 2 months ago
- [NeurIPS 2025 Spotlight] MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning☆76Updated 4 months ago
- [AAAI 2025] GFlow: Recovering 4D World from Monocular Video☆65Updated 9 months ago
- Project page for Neural Shell Texture Splatting (ICCV 2025)☆33Updated 3 months ago
- Thinking in 360°: Humanoid Visual Search in the Wild☆114Updated 2 weeks ago