| SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining | Mar 23, 2025 | 3DGSBenchmarking | CodeCode Available | 3 |
| ZO2: Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU Memory | Mar 16, 2025 | CPUGPU | CodeCode Available | 3 |
| LiteGS: A High-Performance Modular Framework for Gaussian Splatting Training | Mar 3, 2025 | 3DGSGPU | CodeCode Available | 3 |
| SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition | Feb 23, 2025 | Deep HashingGPU | CodeCode Available | 3 |
| Slamming: Training a Speech Language Model on One GPU in a Day | Feb 19, 2025 | GPULanguage Modeling | CodeCode Available | 3 |
| MetaDE: Evolving Differential Evolution by Differential Evolution | Feb 13, 2025 | Computational EfficiencyGPU | CodeCode Available | 3 |
| Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuray | Feb 7, 2025 | 4kGeneral Knowledge | CodeCode Available | 3 |
| Transolver++: An Accurate Neural Solver for PDEs on Million-Scale Geometries | Feb 4, 2025 | GPU | CodeCode Available | 3 |
| M+: Extending MemoryLLM with Scalable Long-Term Memory | Feb 1, 2025 | 16kGPU | CodeCode Available | 3 |
| How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks? | Jan 20, 2025 | Computed Tomography (CT)GPU | CodeCode Available | 3 |
| Dataset Distillation with Neural Characteristic Function: A Minmax Perspective | Jan 1, 2025 | Computational EfficiencyDataset Distillation | CodeCode Available | 3 |
| CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up | Dec 20, 2024 | 8kGPU | CodeCode Available | 3 |
| PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting | Dec 16, 2024 | 3D Reconstruction4k | CodeCode Available | 3 |
| HadaCore: Tensor Core Accelerated Hadamard Transform Kernel | Dec 12, 2024 | GPUMMLU | CodeCode Available | 3 |
| GraphNeuralNetworks.jl: Deep Learning on Graphs with Julia | Dec 9, 2024 | Deep LearningGPU | CodeCode Available | 3 |
| APOLLO: SGD-like Memory, AdamW-level Performance | Dec 6, 2024 | GPUQuantization | CodeCode Available | 3 |
| Pushing the Limits of Large Language Model Quantization via the Linearity Theorem | Nov 26, 2024 | GPULanguage Modeling | CodeCode Available | 3 |
| MobileMamba: Lightweight Multi-Receptive Visual Mamba Network | Nov 24, 2024 | GPUMamba | CodeCode Available | 3 |
| Nd-BiMamba2: A Unified Bidirectional Architecture for Multi-Dimensional Data Processing | Nov 22, 2024 | Computational EfficiencyCPU | CodeCode Available | 3 |
| REDUCIO! Generating 10241024 Video within 16 Seconds using Extremely Compressed Motion Latents | Nov 20, 2024 | GPUVideo Generation | CodeCode Available | 3 |
| Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension | Nov 20, 2024 | GPUMME | CodeCode Available | 3 |
| Data Generation for Hardware-Friendly Post-Training Quantization | Oct 29, 2024 | Data AugmentationGPU | CodeCode Available | 3 |
| Modular Duality in Deep Learning | Oct 28, 2024 | Deep LearningGPU | CodeCode Available | 3 |
| ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference | Oct 28, 2024 | CPU | CodeCode Available | 3 |
| Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss | Oct 22, 2024 | GPURepresentation Learning | CodeCode Available | 3 |
