Xuelong Li

MTVCraft: Tokenizing 4D Motion for Arbitrary Character Animation

AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology Laboratory

HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models

Towards the Three-Phase Dynamics of Generalization Power of a DNN

Beyond Text-to-Image: Liberating Generation with a Unified Discrete Diffusion Model

Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance

UniARM: Towards a Unified Autoregressive Reward Model for Multi-Objective Test-Time Alignment

Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning

HAMLET: A Hierarchical and Adaptive Multi-Agent Framework for Live Embodied Theatrics

Morpheus: Learning to Jailbreak via Self-Evolving Metacognition

Group Verification-based Policy Optimization for Interactive Coding Agents

Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation

OpenFly: A COMPREHENSIVE PLATFORM FOR AERIAL VISION-LANGUAGE NAVIGATION

Riemannian Optimization on Relaxed Indicator Matrix Manifold

Towards Efficient Post-Training Quantization For Large Vision-Language Models Via Token-Wise Redundancy Elimination

Exploring the Potential of Encoder-free Architectures in 3D LMMs

Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning

CompassNav: Steering From Path Imitation to Decision Understanding In Navigation

Episodic Memory Representation for Long Video Understanding

HHW-Ego: DSLR-Quality Enhancement for Multi-Source Wearable Ego Imaging

Optimized Early-Exit Based Speculative Decoding via Pipeline Parallelism

VAR: Visual Attention Reasoning via Structured Search and Backtracking

RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration

Bridging Transformers and RWKV: Towards Efficient Multimodal Video Understanding

Metric-Solver: Sliding Anchored Metric Depth Estimation from a Single Image

Scale-Adapter: Reversed Distillation Adapter for Efficient Training of Large Video Diffusion Models

BRENA: Brain-inspired Hierarchical Neural Alignment Framework for Visual Decoding from EEG Signals

Thinking Before Coding: WebUI-to-Code Driven by Layout Reasoning and Consistency Rewards

Flow-IB: Information Bottleneck Meets Flow Matching for 32,768× Video Compression

Object-AVEdit: An Object-level Audio-Visual Editing Model

Adaptive Mixing of Non-Invariant Information for Generalized Diffusion Policy

Online Preference Alignment for Language Models via Count-based Exploration

KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills

Learn Beneficial Noise as Graph Augmentation

Discriminator-Guided Embodied Planning for LLM Agent

Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning

NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering

Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning

Debiased Deep Evidential Regression for Video Temporal Grounding

Towards Reliable LLM-based Robots Planning via Combined Uncertainty Estimation

CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs

Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models

Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration

FreeGaussian: Guidance-free Controllable 3D Gaussian Splats with Flow Derivatives

Think Small, Act Big: Primitive-level Skill Prompt Learning for Lifelong Robot Manipulation