| MegaFold: System-Level Optimizations for Accelerating Protein Structure Prediction Models | Jun 24, 2025 | GPUProtein Folding | CodeCode Available | 2 |
| PocketVina Enables Scalable and Highly Accurate Physically Valid Docking through Multi-Pocket Conditioning | Jun 24, 2025 | BenchmarkingDrug Discovery | CodeCode Available | 2 |
| Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning | Jun 23, 2025 | GPULarge Language Model | CodeCode Available | 2 |
| SeerAttention-R: Sparse Attention Adaptation for Long Reasoning | Jun 10, 2025 | 4kGPU | CodeCode Available | 2 |
| Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos | Jun 5, 2025 | GPUSemantic Segmentation | CodeCode Available | 2 |
| ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS | May 29, 2025 | 3DGSGPU | CodeCode Available | 2 |
| QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design | May 22, 2025 | CPUGPU | CodeCode Available | 2 |
| Training Long-Context LLMs Efficiently via Chunk-wise Optimization | May 22, 2025 | 16kGPU | CodeCode Available | 2 |
| Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers | May 20, 2025 | GPUVideo Generation | CodeCode Available | 2 |
| UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Large Language Models | May 20, 2025 | GPULifelong learning | CodeCode Available | 2 |
| VRSplat: Fast and Robust Gaussian Splatting for Virtual Reality | May 15, 2025 | 3DGSGPU | CodeCode Available | 2 |
| GPU Performance Portability needs Autotuning | Apr 30, 2025 | GPU | CodeCode Available | 2 |
| STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow Prediction | Apr 28, 2025 | GPU | CodeCode Available | 2 |
| CaRL: Learning Scalable Planning Policies with Simple Rewards | Apr 24, 2025 | Autonomous DrivingCARLA longest6 | CodeCode Available | 2 |
| SG-Reg: Generalizable and Efficient Scene Graph Registration | Apr 20, 2025 | GPU | CodeCode Available | 2 |
| Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation | Apr 17, 2025 | GPUObject Recognition | CodeCode Available | 2 |
| Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images | Apr 13, 2025 | GPU | CodeCode Available | 2 |
| TorchFX: A modern approach to Audio DSP with PyTorch and GPU acceleration | Apr 11, 2025 | Audio Signal ProcessingBenchmarking | CodeCode Available | 2 |
| HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference | Apr 8, 2025 | CPUGPU | CodeCode Available | 2 |
| Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors | Apr 7, 2025 | GPU | CodeCode Available | 2 |
| GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration | Apr 3, 2025 | GPUQuantization | CodeCode Available | 2 |
| Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation | Apr 3, 2025 | Computational EfficiencyGPU | CodeCode Available | 2 |
| THEMIS: Towards Practical Intellectual Property Protection for Post-Deployment On-Device Deep Learning Models | Mar 31, 2025 | GPU | CodeCode Available | 2 |
| FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning | Mar 30, 2025 | 2kGPU | CodeCode Available | 2 |
| CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models | Mar 28, 2025 | GPUGSM8K | CodeCode Available | 2 |
