Houqiang Li

21

Papers

153

Total Citations

Papers (21)

EG4D: Explicit Generation of 4D Object without Score Distillation

TinySAM: Pushing the Envelope for Efficient Segment Anything Model

Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models

DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models

Long-term Temporal Context Gathering for Neural Video Compression

SmartEraser: Remove Anything from Images using Masked-Region Guidance

RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusion

Revisiting Open-Set Panoptic Segmentation

Active Perception Meets Rule-Guided RL: A Two-Phase Approach for Precise Object Navigation in Complex Environments

Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling

OPTICAL: Leveraging Optimal Transport for Contribution Allocation in Dataset Distillation

Towards Practical Real-Time Neural Video Compression

Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters

SUF: Stabilized Unconstrained Fine-Tuning for Offline-to-Online Reinforcement Learning

KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding

InstructDiffusion: A Generalist Modeling Interface for Vision Tasks

Generative Latent Coding for Ultra-Low Bitrate Image Compression

Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation

Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning

S3R-GS: Streamlining the Pipeline for Large-Scale Street Scene Reconstruction

From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning