XPENG AI

non-profit

https://xpeng-ai.github.io

AI & ML interests

LLM, VLM, Omni Model, Agent, VLA

Recent Activity

ShiyuHuang updated a Space about 12 hours ago

XPENG-AI/README

Skywalker0410 authored a paper 4 days ago

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

ShiyuHuang authored a paper 4 days ago

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

View all activity

Papers

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments

View all Papers

updated a Space about 12 hours ago

XPENG AI

authored a paper 4 days ago

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

Paper • 2609.11412 • Published 5 days ago • 44

authored a paper 4 days ago

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

Paper • 2609.11412 • Published 5 days ago • 44

submitted a paper to Daily Papers 4 days ago

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

Paper • 2609.11412 • Published 5 days ago • 44

updated a model 4 days ago

XPENG-AI/X-AuT

Automatic Speech Recognition • 0.9B • Updated 4 days ago • 94 • 5

published a Space 4 days ago

XPENG AI

updated a model 4 days ago

XPENG-AI/X-AuT

Automatic Speech Recognition • 0.9B • Updated 4 days ago • 94 • 5

published a model 4 days ago

XPENG-AI/X-AuT

Automatic Speech Recognition • 0.9B • Updated 4 days ago • 94 • 5

authored 2 papers 5 days ago

LD4WAM: Learning Latent Dynamics from Human Videos for World Action Models

Paper • 2608.22403 • Published 23 days ago • 1

OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining

Paper • 2609.07398 • Published 8 days ago • 74

submitted a paper to Daily Papers 3 months ago

AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding

Paper • 2606.06155 • Published Jun 4 • 10

authored 4 papers 3 months ago

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning

Paper • 2604.14922 • Published Apr 16 • 7

SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework

Paper • 2605.20373 • Published May 19

AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding

Paper • 2606.06155 • Published Jun 4 • 10

A3D: Adaptive Affordance Assembly with Dual-Arm Manipulation

Paper • 2601.11076 • Published Jan 16

submitted a paper to Daily Papers 4 months ago

OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments

Paper • 2605.18758 • Published Apr 3 • 17

authored a paper 5 months ago

UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling

Paper • 2604.19734 • Published Apr 21 • 34

authored 2 papers about 1 year ago

DreamPolish: Domain Score Distillation With Progressive Geometry Generation

Paper • 2411.01602 • Published Nov 3, 2024 • 11

GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Paper • 2507.01006 • Published Jul 1, 2025 • 257

authored a paper over 1 year ago

MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models

Paper • 2501.02955 • Published Jan 6, 2025 • 44