Publications (18)
Reciprocal polarization imaging of complex media
Zhineng Xie, Guowu Huang, Weihao Lin +5
The vectorial evolution of polarized light interaction with a medium can reveal its microstructure and anisotropy beyond what can be obtained from scalar light interaction. Anisotr…
When Liquid Meets Frequency-Selective Rasorber: Wideband and Switchable 3-D Frequency-Selective Rasorber
Xiangkun Kong, Xuemeng Wang, Xin Jin +4
In this paper, a switchable 3-D frequency selective rasorber (FSR) with wide absorption bands without lumped components or commercial magnetic absorbers is presented and investigat…
Design of Switchable Frequency-Selective Rasorber with A-R-A-T or A-T-A-R Operating Modes
Xiangkun Kong, Xin Jin, Xuemeng Wang +4
This work presents a switchable frequency-selective rasorber (SFSR) with two operating modes. Switching from transmission to reflection can be achieved by appropriately adding feed…
Multi-Level Decoupled Relational Distillation for Heterogeneous Architectures
Yaoxin Yang, Peng Ye, Weihao Lin +4
Heterogeneous distillation is an effective way to transfer knowledge from cross-architecture teacher models to student models. However, existing heterogeneous distillation methods…
Band-Notched Frequency-Selective Absorber with Polarization Rotation Function
iangkun Kong, Xin Jin, Xuemeng Wang +5
This paper presents the theoretical analysis, design, simulations, and experimental verification of a novel band-notched frequency-selective absorber (BFSA) with polarization rotat…
Boosting Residual Networks with Group Knowledge
Shengji Tang, Peng Ye, Baopu Li +5
Recent research understands the residual networks from a new perspective of the implicit ensemble model. From this view, previous methods such as stochastic depth and stimulative t…
HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction
Shengji Tang, Weicai Ye, Peng Ye +4
Reconstructing 3D scenes from multiple viewpoints is a fundamental task in stereo vision. Recently, advances in generalizable 3D Gaussian Splatting have enabled high-quality novel…
Multi-body dynamic evolution sequence-assisted PSO for interval analysis
Xuanlong Wu, Peng Zhong, Weihao Lin
When the exact probability distribution of input conditions cannot be obtained in practical engineering problems, interval analysis methods are often used to analyze the upper and…
Robust quantitative single-exposure laser speckle imaging with true flow speckle contrast in the temporal and spatial domains
Chenge Wang, Zili Cao, Xin Jin +4
A systematic and robust laser speckle contrast imaging (LSCI) method and procedure is presented, covering the LSCI system calibration, static scattering removal, and measurement no…
Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale
Shengji Tang, Weihao Lin, Peng Ye +9
Large Language Models (LLMs) have rapidly advanced, with Gemini-3-Pro setting a new performance milestone. In this work, we explore collective intelligence as an alternative to mon…
SpVOS: Efficient Video Object Segmentation with Triple Sparse Convolution
Weihao Lin, Tao Chen, Chong Yu
Semi-supervised video object segmentation (Semi-VOS), which requires only annotating the first frame of a video to segment future frames, has received increased attention recently.…
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Lei Bai, Zongsheng Cao, Yang Chen +50
The paper introduces Agents-A1, a 35B mixture-of-experts agent model that attains trillion-parameter-level performance by extending the length of reasoning horizons and integrating…
Liquid Reconfigurable Stealth Window Constructed by Metamaterial Absorber
Xiangkun Kong, Weihao Lin, Xuemeng Wang +3
In this paper, a liquid reconfigurable stealth window constructed by metamaterial absorber at microwave band is proposed. The stealth window consists of an anti-reflection glass wi…
Wisdom of the Crowd: Reinforcement Learning from Coevolutionary Collective Feedback
Wenzhen Yuan, Shengji Tang, Weihao Lin +8
Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), but its reliance on expensive human-labeled data or complex rewar…
Efficient Architecture Search via Bi-level Data Pruning
Chongjun Tu, Peng Ye, Weihao Lin +5
Improving the efficiency of Neural Architecture Search (NAS) is a challenging but significant task that has received much attention. Previous works mainly adopted the Differentiabl…
A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement
Shengji Tang, Jianjian Cao, Weihao Lin +7
Existing multi-LLM collaboration systems often encounter scalability challenges when integrating new LLMs and tasks, leading to suboptimal performance. To address this, we propose…
S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning
Weihao Lin, Shengji Tang, Chong Yu +2
Recently, differentiable mask pruning methods optimize the continuous relaxation architecture (soft network) as the proxy of the pruned discrete network (hard network) for superior…
Enhanced Sparsification via Stimulative Training
Shengji Tang, Weihao Lin, Hancheng Ye +4
Sparsification-based pruning has been an important category in model compression. Existing methods commonly set sparsity-inducing penalty terms to suppress the importance of droppe…