22 citations · 71 across the 41 of their papers we have counts for
42 papers
HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
Shenzhi Wang, Shixuan Liu, Jing Zhou +8
Vision-language models (VLMs) show strong multimodal capabilities but still struggle with fine-grained vision-language reasoning. We find that long chain-of-thought (CoT) reasoning…
Beyond Short-Horizon: VQ-Memory for Robust Long-Horizon Manipulation in Non-Markovian Simulation Benchmarks
Honghui Wang, Zhi Jing, Jicong Ao +4
The high cost of collecting real-robot data has made robotic simulation a scalable platform for both evaluation and data generation. Yet most existing benchmarks concentrate on sim…
UltraStar: Semantic-Aware Star Graph Modeling for Echocardiography Navigation
Teng Wang, Haojun Jiang, Chenxi Li +6
Echocardiography is critical for diagnosing cardiovascular diseases, yet the shortage of skilled sonographers hinders timely patient care, due to high operational difficulties. Con…
MOVE: A Simple Motion-Based Data Collection Paradigm for Spatial Generalization in Robotic Manipulation
Huanqian Wang, Chi Bene Chen, Yang Yue +7
Imitation learning method has shown immense promise for robotic manipulation, yet its practical deployment is fundamentally constrained by the data scarcity. Despite prior work on…
VA-Adapter: Adapting Ultrasound Foundation Model to Echocardiography Probe Guidance
Teng Wang, Haojun Jiang, Yuxuan Wang +4
Echocardiography is a critical tool for detecting heart diseases, yet its steep operational difficulty causes a shortage of skilled personnel. Probe guidance systems, which assist…
Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception
Yulin Wang, Yang Yue, Huanqian Wang +11
Human vision is highly adaptive, efficiently sampling intricate environments by sequentially fixating on task-relevant regions. In contrast, prevailing machine vision models passiv…
BAPE: Learning an Explicit Bayes Classifier for Long-tailed Visual Recognition
Chaoqun Du, Yulin Wang, Shiji Song +1
Bayesian decision theory advocates the Bayes classifier as the optimal approach for minimizing the risk in machine learning problems. Current deep learning algorithms usually solve…
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Shenzhi Wang, Le Yu, Chang Gao +15
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs), while its mechanis…
CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning
Yang Yue, Yulin Wang, Chenxin Tao +3
Humans can develop internal world models that encode common sense knowledge, telling them how the world works and predicting the consequences of their actions. This concept has eme…
EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance
Yang Yue, Yulin Wang, Haojun Jiang +3
Echocardiography is crucial for cardiovascular disease detection but relies heavily on experienced sonographers. Echocardiography probe guidance systems, which provide real-time mo…
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Yang Yue, Zhiqi Chen, Rui Lu +4
Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated notable success in enhancing the reasoning performance of large language models (LLMs), particularly…
Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition
Yulin Wang, Haoji Zhang, Yang Yue +4
This paper presents a comprehensive exploration of the phenomenon of data redundancy in video understanding, with the aim to improve computational efficiency. Our investigation com…
Bridging the Divide: Reconsidering Softmax and Linear Attention
Dongchen Han, Yifan Pu, Zhuofan Xia +6
Widely adopted in modern Vision Transformer designs, Softmax attention can effectively capture long-range visual information; however, it incurs excessive computational cost when d…
A Unified Interaction Control Framework for Safe Robotic Ultrasound Scanning with Human-Intention-Aware Compliance
Xiangjie Yan, Shaqi Luo, Yongpeng Jiang +6
The ultrasound scanning robot operates in environments where frequent human-robot interactions occur. Most existing control methods for ultrasound scanning address only one specifi…
Advancing Generalization in PINNs through Latent-Space Representations
Honghui Wang, Yifan Pu, Shiji Song +1
Physics-informed neural networks (PINNs) have made significant strides in modeling dynamical systems governed by partial differential equations (PDEs). However, their generalizatio…
DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
Yang Yue, Yulin Wang, Bingyi Kang +5
MLLMs have demonstrated remarkable comprehension and reasoning capabilities with complex language and visual data. These advances have spurred the vision of establishing a generali…
OStr-DARTS: Differentiable Neural Architecture Search based on Operation Strength
Le Yang, Ziwei Zheng, Yizeng Han +3
Differentiable architecture search (DARTS) has emerged as a promising technique for effective neural architecture search, and it mainly contains two steps to find the high-performa…
Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators
Yifan Pu, Zhuofan Xia, Jiayi Guo +9
This paper identifies significant redundancy in the query-key interactions within self-attention mechanisms of diffusion transformer models, particularly during the early stages of…
UltraSeP: Sequence-aware Pre-training for Echocardiography Probe Movement Guidance
Haojun Jiang, Teng Wang, Zhenguo Sun +8
Echocardiography is an essential medical technique for diagnosing cardiovascular diseases, but its high operational complexity has led to a shortage of trained professionals. To ad…
Structure-aware World Model for Probe Guidance via Large-scale Self-supervised Pre-train
Haojun Jiang, Meng Li, Zhenguo Sun +5
The complex structure of the heart leads to significant challenges in echocardiography, especially in acquisition cardiac ultrasound images. Successful echocardiography requires a…
Rethinking the Architecture Design for Efficient Generic Event Boundary Detection
Ziwei Zheng, Zechuan Zhang, Yulin Wang +3
Generic event boundary detection (GEBD), inspired by human visual cognitive behaviors of consistently segmenting videos into meaningful temporal chunks, finds utility in various ap…
DyFADet: Dynamic Feature Aggregation for Temporal Action Detection
Le Yang, Ziwei Zheng, Yizeng Han +4
Recent proposed neural network-based Temporal Action Detection (TAD) models are inherently limited to extracting the discriminative representations and modeling action instances wi…
Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing
Huanqian Wang, Yang Yue, Rui Lu +5
Large Language Models (LLMs) have demonstrated great potential as generalist assistants, showcasing powerful task understanding and problem-solving capabilities. To deploy LLMs as…
Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis
Zanlin Ni, Yulin Wang, Renping Zhou +6
The field of image synthesis is currently flourishing due to the advancements in diffusion models. While diffusion models have been successful, their computational intensity has pr…