| XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX | Dec 19, 2023 | DiversityGPU | CodeCode Available | 2 |
| Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving | Dec 19, 2023 | Autonomous DrivingGPU | CodeCode Available | 1 |
| Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning | Dec 18, 2023 | Domain AdaptationGPU | —Unverified | 0 |
| GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis | Dec 18, 2023 | GPUInductive Bias | —Unverified | 0 |
| PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU | Dec 16, 2023 | CPUGPU | CodeCode Available | 5 |
| RetailKLIP : Finetuning OpenCLIP backbone using metric learning on a single GPU for Zero-shot retail product image classification | Dec 16, 2023 | GPUimage-classification | —Unverified | 0 |
| Opara: Exploiting Operator Parallelism for Expediting DNN Inference on GPUs | Dec 16, 2023 | GPUScheduling | CodeCode Available | 1 |
| FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices with A Simple Super-Resolution Pipeline | Dec 15, 2023 | GPUKnowledge Distillation | —Unverified | 0 |
| Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models | Dec 15, 2023 | BenchmarkingCode Summarization | CodeCode Available | 1 |
| Data-Efficient Multimodal Fusion on a Single GPU | Dec 15, 2023 | GPUImage Retrieval | CodeCode Available | 1 |
| LiteVSR: Efficient Visual Speech Recognition by Learning from Speech Representations of Unlabeled Data | Dec 15, 2023 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | —Unverified | 0 |
| A parallelized cellular Potts model that enables simulations at tissue scale | Dec 14, 2023 | GPU | CodeCode Available | 0 |
| MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Training | Dec 14, 2023 | GPU | CodeCode Available | 1 |
| A Sparse Cross Attention-based Graph Convolution Network with Auxiliary Information Awareness for Traffic Flow Prediction | Dec 14, 2023 | AttributeDecoder | —Unverified | 0 |
| Context-PEFT: Efficient Multi-Modal, Multi-Task Fine-Tuning | Dec 14, 2023 | GPUparameter-efficient fine-tuning | —Unverified | 0 |
| Dataset Distillation via Adversarial Prediction Matching | Dec 14, 2023 | Dataset DistillationGPU | CodeCode Available | 0 |
| Efficient-NeRF2NeRF: Streamlining Text-Driven 3D Editing with Multiview Correspondence-Enhanced Diffusion Models | Dec 13, 2023 | GPU | —Unverified | 0 |
| Contractive error feedback for gradient compression | Dec 13, 2023 | Federated LearningGPU | —Unverified | 0 |
| EZ-CLIP: Efficient Zeroshot Video Action Recognition | Dec 13, 2023 | Action RecognitionGPU | CodeCode Available | 1 |
| CBQ: Cross-Block Quantization for Large Language Models | Dec 13, 2023 | GPUQuantization | —Unverified | 0 |
| Memory-Efficient Reversible Spiking Neural Networks | Dec 13, 2023 | GPU | CodeCode Available | 1 |
| DTL: Disentangled Transfer Learning for Visual Recognition | Dec 13, 2023 | GPUTransfer Learning | CodeCode Available | 1 |
| Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI | Dec 13, 2023 | DiversityGPU | CodeCode Available | 1 |
| LLM in a flash: Efficient Large Language Model Inference with Limited Memory | Dec 12, 2023 | CPUGPU | —Unverified | 0 |
| Neural Video Fields Editing | Dec 12, 2023 | GPUVideo Editing | —Unverified | 0 |