Explore shared collections
Curated reading lists shared by the community. Save any into your own collections.
3D Gaussian Splatting
7 papers · shared by gsplat_notes
Key papers on 3D Gaussian Splatting for fast, high-quality scene reconstruction and rendering.
CVPR 2024GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis
ICLR 2024DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
CVPR 20244D Gaussian Splatting for Real-Time Dynamic Scene Rendering
Diffusion Models for Generation
6 papers · shared by scorefield
Foundational and recent diffusion models for image and data generation.
CVPR 2022High-Resolution Image Synthesis With Latent Diffusion Models
NeurIPS 2021Diffusion Models Beat GANs on Image Synthesis
ICLR 2021Denoising Diffusion Implicit Models
Learning from Human Preferences
6 papers · shared by kl_penalty
Aligning models with human preferences: RLHF, DPO, and preference optimization.
NeurIPS 2022Training language models to follow instructions with human feedback
NeurIPS 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Model
NeurIPS 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback
LLM Agents and Tool Use
6 papers · shared by agentroute
LLM-based agents: planning, tool use, and multi-step reasoning.
ICML 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
ICML 2024Improving Factuality and Reasoning in Language Models through Multiagent Debate
ICCV 2023LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models
Mixture-of-Experts
6 papers · shared by top2gating
Mixture-of-Experts architectures for scaling models efficiently.
ICML 2022GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
NeurIPS 2021Scaling Vision with Sparse Mixture of Experts
NeurIPS 2022Mixture-of-Experts with Expert Choice Routing
Retrieval-Augmented Generation
6 papers · shared by chunk_norris
Retrieval-augmented generation: grounding language models in external knowledge.
AAAI 2024Benchmarking Large Language Models in Retrieval-Augmented Generation
NeurIPS 2023LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
ICLR 2021Retrieval-Augmented Generation for Code Summarization via Hybrid GNN
State Space Models and Mamba
5 papers · shared by hippo_init
State space models and Mamba: efficient sequence modeling beyond attention.
NeurIPS 2024VMamba: Visual State Space Model
ICLR 2023Hungry Hungry Hippos: Towards Language Modeling with State Space Models
NeurIPS 2022On the Parameterization and Initialization of Diagonal State Space Models
Vision-Language Models
6 papers · shared by clip_notes
Vision-language and multimodal models that connect images and text.
ICML 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
ICML 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
ICLR 2024MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models