👁 Image Submitted by 👁 Image Ruifeng Tan 1 BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting 👁 HKUSTGZ HKUSTGZ 29 2
👁 Image Submitted by 👁 Image Haotian Wang 8 UniT: Unified Geometry Learning with Group Autoregressive Transformer 👁 HKUSTGZ HKUSTGZ 21 1
👁 Image Submitted by 👁 Image Sicheng Feng 10 PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks 👁 HKUSTGZ HKUSTGZ 22 2
👁 Image Submitted by 👁 Image Sudong Wang 49 Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL 👁 HKUSTGZ HKUSTGZ 91 4
👁 Image 1 TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning 👁 HKUSTGZ HKUSTGZ 0
👁 Image Submitted by 👁 Image Zikai Zhou 9 Optimizing Few-Step Generation with Adaptive Matching Distillation 👁 HKUSTGZ HKUSTGZ 2
👁 Image Submitted by 👁 Image Haopeng Li 4 PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers 👁 HKUSTGZ HKUSTGZ 31 2
👁 Image Submitted by 👁 Image Haopeng Li 3 Mano: Restriking Manifold Optimization for LLM Training 👁 HKUSTGZ HKUSTGZ 25 3
👁 Image Submitted by 👁 Image ZhiFei Chen 9 A Mechanistic View on Video Generation as World Models: State and Dynamics 👁 HKUSTGZ HKUSTGZ 45 3
Submitted by 👁 Image Guibao SHEN 38 StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors 👁 HKUSTGZ HKUSTGZ 115 2
👁 Image Submitted by 👁 Image Yifan Shen 55 MedSAM3: Delving into Segment Anything with Medical Concepts 👁 HKUSTGZ HKUSTGZ 306 5
👁 Image Submitted by 👁 Image Wenxuan Song 7 Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process 👁 HKUSTGZ HKUSTGZ 182 1
👁 Image Submitted by 👁 Image Zhen Yang 7 Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention 👁 HKUSTGZ HKUSTGZ 41 1
👁 Image Submitted by 👁 Image Wenxuan Song 149 Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model 👁 HKUSTGZ HKUSTGZ 253 4
