11 citations · 13 across the 9 of their papers we have counts for
10 papers
PhysMAS: Physics-Grounded Multi-Agent Synthesis of Compositional 4D Gaussians
Jiang Qin, Chunji Lv, Yangguang Wei +6
Efficient, fully automatic, and physically plausible 4D Gaussian synthesis is an important goal for dynamic scene generation. Recent physics-based methods couple 3D Gaussians with…
PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning
Chunji Lv, Yangguang Wei, Junlin Liu +6
Large language model agents have shown strong potential in complex interactive tasks, yet their reinforcement learning (RL) is often hindered by sparse rewards, as a long multi-tur…
Astro: Activation-guided Structured Regularization for Outlier-Robust LLM Post-Training Quantization
Xi Chen, Ming Li, Junxi Li +5
Weight-only post-training quantization (PTQ) is crucial for efficient Large Language Model (LLM) deployment but suffers from accuracy degradation caused by weight and activation ou…
DeepFaith: A Domain-Free and Model-Agnostic Unified Framework for Highly Faithful Explanations
Yuhan Guo, Lizhong Ding, Shihan Jia +6
Explainable AI (XAI) builds trust in complex systems through model attribution methods that reveal the decision rationale. However, due to the absence of a unified optimal explanat…
ITPNet: Towards Instantaneous Trajectory Prediction for Autonomous Driving
Rongqing Li, Changsheng Li, Yuhang Li +5
Trajectory prediction of agents is crucial for the safety of autonomous vehicles, whereas previous approaches usually rely on sufficiently long-observed trajectory to predict the f…
DREAM: Domain-agnostic Reverse Engineering Attributes of Black-box Model
Rongqing Li, Jiaqi Yu, Changsheng Li +3
Deep learning models are usually black boxes when deployed on machine learning platforms. Prior works have shown that the attributes (e.g., the number of convolutional layers) of a…
Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?
Xi Chen, Kaituo Feng, Changsheng Li +4
Low-rank training has emerged as a promising approach for reducing memory usage in training Large Language Models (LLMs). Previous methods either rely on decomposing weight matrice…
On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving
Kaituo Feng, Changsheng Li, Dongchun Ren +2
End-to-end motion planning models equipped with deep neural networks have shown great potential for enabling full autonomous driving. However, the oversized neural networks render…
Learning to Generate Parameters of ConvNets for Unseen Image Data
Shiye Wang, Kaituo Feng, Changsheng Li +2
Typical Convolutional Neural Networks (ConvNets) depend heavily on large amounts of image data and resort to an iterative optimization algorithm (e.g., SGD or Adam) to learn networ…
Shared Growth of Graph Neural Networks via Prompted Free-direction Knowledge Distillation
Kaituo Feng, Yikun Miao, Changsheng Li +2
Knowledge distillation (KD) has shown to be effective to boost the performance of graph neural networks (GNNs), where the typical objective is to distill knowledge from a deeper te…