17 papers
GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training
Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2
Hybrid post-training combining supervised fine-tuning (SFT) and reinforcement learning (RL) is the standard paradigm for aligning large language models, yet fixed mixing schedules…
Full-4D: Generating Full-Scope 4D Scenes from a Single-View Video
Tingxi Chen, Ke Hao, Yabo Chen +6
Generating 4D scenes from a single-view video is inherently ill-posed: a single viewpoint lacks the information needed to recover a complete, dynamic scene with full coverage. Exis…
Hidden Failure Modes of Gradient Modification under Adam in Continual Learning, and Adaptive Decoupled Moment Routing as a Repair
Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2
Many continual-learning methods modify gradients upstream (e.g., projection, penalty rescaling, replay mixing) while treating Adam as a neutral backend. We show this composition ha…
WebExpert: domain-aware web agents with critic-guided expert experience for high-precision search
Yuelin Hu, Zhengxue Cheng, Ronghua Wu +5
Specialized web tasks in finance, biomedicine, and pharmaceuticals remain challenging due to missing domain priors: queries drift, evidence is noisy, and reasoning is brittle. We p…
TaCo: A Benchmark for Lossless and Lossy Codecs of Heterogeneous Tactile Data
Zhengxue Cheng, Yan Zhao, Keyu Wang +2
Tactile sensing is crucial for embodied intelligence, providing fine-grained perception and control in complex environments. However, efficient tactile data compression, which is e…
Entropy-Gated Selective Policy Optimization:Token-Level Gradient Allocation for Hybrid Training of Large Language Models
Yuelin Hu, Zhengxue Cheng, Wei Liu +1
Hybrid training methods for large language models combine supervised fine tuning (SFT) on expert demonstrations with reinforcement learning (RL) on model rollouts, typically at the…
MeetBench-XL: Calibrated Multi-Dimensional Evaluation and Learned Dual-Policy Agents for Real-Time Meetings
Yuelin Hu, Jun Xu, Bingcong Lu +4
Enterprise meeting environments require AI assistants that handle diverse operational tasks, from rapid fact checking during live discussions to cross meeting analysis for strategi…
OmniScaleSR: Unleashing Scale-Controlled Diffusion Prior for Faithful and Realistic Arbitrary-Scale Image Super-Resolution
Xinning Chai, Zhengxue Cheng, Yuhong Zhang +5
Arbitrary-scale super-resolution (ASSR) overcomes the limitation of traditional super-resolution (SR) methods that operate only at fixed scales (e.g., 4x), enabling a single model…
D3Grasp: Diverse and Deformable Dexterous Grasping for General Objects
Keyu Wang, Bingcong Lu, Zhengxue Cheng +2
Achieving diverse and stable dexterous grasping for general and deformable objects remains a fundamental challenge in robotics, due to high-dimensional action spaces and uncertaint…
PA-HOI: A Physics-Aware Human and Object Interaction Dataset
Ruiyan Wang, Lin Zuo, Zonghao Lin +5
The Human-Object Interaction (HOI) task explores the dynamic interactions between humans and objects in physical environments, providing essential biomechanical and cognitive-behav…
OmniVTLA: Vision-Tactile-Language-Action Models with Semantic-Aligned Tactile Sensing
Zhengxue Cheng, Yiqian Zhang, Anni Tang +5
Recent vision-language-action (VLA) models build upon vision-language foundations, and have achieved promising results and exhibit the possibility of task generalization in robot m…
Semantic and Temporal Integration in Latent Diffusion Space for High-Fidelity Video Super-Resolution
Yiwen Wang, Xinning Chai, Yuhong Zhang +4
Recent advancements in video super-resolution (VSR) models have demonstrated impressive results in enhancing low-resolution videos. However, due to limitations in adequately contro…
D-FCGS: Feedforward Compression of Dynamic Gaussian Splatting for Free-Viewpoint Videos
Wenkang Zhang, Yan Zhao, Qiang Wang +3
Free-Viewpoint Video (FVV) enables immersive 3D experiences, but efficient compression of dynamic 3D representation remains a major challenge. Existing dynamic 3D Gaussian Splattin…
DualComp: End-to-End Learning of a Unified Dual-Modality Lossless Compressor
Yan Zhao, Zhengxue Cheng, Junxuan Zhang +3
Most learning-based lossless compressors are designed for a single modality, requiring separate models for multi-modal data and lacking flexibility. However, different modalities v…
TacCompress: A Benchmark for Multi-Point Tactile Data Compression in Dexterous Hand
Yan Zhao, Yang Li, Zhengxue Cheng +2
Though robotic dexterous manipulation has progressed substantially recently, challenges like in-hand occlusion still necessitate fine-grained tactile perception, leading to the int…
Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs
Jie Ma, Ning Qu, Zhitao Gao +8
Knowledge graph-based retrieval-augmented generation seeks to mitigate hallucinations in Large Language Models (LLMs) caused by insufficient or outdated knowledge. However, existin…
Distillation-Supervised Convolutional Low-Rank Adaptation for Efficient Image Super-Resolution
Xinning Chai, Yao Zhang, Yuxuan Zhang +4
Convolutional neural networks (CNNs) have been widely used in efficient image super-resolution. However, for CNN-based methods, performance gains often require deeper networks and…