Qing Li

MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning

When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations

Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation

MVR: Multi-view Video Reward Shaping for Reinforcement Learning

STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement Learning

AdaReP: Plug-and-Play Acceleration for World Model Predictive Control using Adaptive Re-Planning

GUI Knowledge Bench: Revealing the Knowledge Gap Behind VLM Failures in GUI Tasks

On the Effect of Positional Encoding for In-context Learning in Transformers

Towards the Decisive Factor of Symbolic Generalization of DNNs

LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Augmentations and Constraints

Towards the Mysteries of Convergent Interaction Representations through DNNs

COIN: Chain Of INteraction Benchmark: When Reasoning meets Embodied interaction

Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

NEP: Autoregressive Image Editing via Next Editing Token Prediction

Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning

MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge

Falcon: Fast Visuomotor Policies via Partial Denoising

LongViTU: Instruction Tuning for Long-Form Video Understanding

Task-oriented Sequential Grounding in 3D Scenes