几篇论文实现代码：
《Doob’s Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling》(NeurIPS 2024) GitHub: github.com/plainerman/Variational-Doob
《Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models》(ECCV 2024) GitHub: github.com/AoiDragon/HADES [fig3]
《PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-To-Speech Using Natural Language Descriptions》(2024) GitHub: github.com/line/promptttspp
《IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation》(2024) GitHub: github.com/YangLing0818/IterComp [fig1]
《ElasticTok: Adaptive Tokenization for Image and Video》(2024) GitHub: github.com/LargeWorldModel/ElasticTok [fig2]
《Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis》(2024) GitHub: github.com/YangLing0818/Trans4D
《OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction》(2024) GitHub: github.com/EnVision-Research/OmniBooth
《HART: Efficient Visual Generation with Hybrid Autoregressive Transformer》(2024) GitHub: github.com/mit-han-lab/hart
《DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads》(2024) GitHub: github.com/mit-han-lab/duo-attention [fig4]
《TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data》(2024) GitHub: github.com/ermongroup/TEOChat
《ToolGen: Unified Tool Retrieval and Calling via Generation》(2024) GitHub: github.com/Reason-Wang/ToolGen
《Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement》(2024) GitHub: github.com/Arvid-pku/Godel_Agent [fig5]
《Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians》(2024) GitHub: github.com/google-research/Splat-SLAM [fig6]
《Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving》(2024) GitHub: github.com/Robot-K/Hint-AD
《Splat-MOVER: Multi-Stage, Open-Vocabulary Robotic Manipulation via Editable Gaussian Splatting》(2024) GitHub: github.com/StanfordMSL/Splat-MOVER
《All-In-One Medical Image Restoration via Task-Adaptive Routing》(2024) GitHub: github.com/Yaziwel/All-In-One-Medical-Image-Restoration-via-Task-Adaptive-Routing
《Doob’s Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling》(NeurIPS 2024) GitHub: github.com/plainerman/Variational-Doob
《Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models》(ECCV 2024) GitHub: github.com/AoiDragon/HADES [fig3]
《PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-To-Speech Using Natural Language Descriptions》(2024) GitHub: github.com/line/promptttspp
《IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation》(2024) GitHub: github.com/YangLing0818/IterComp [fig1]
《ElasticTok: Adaptive Tokenization for Image and Video》(2024) GitHub: github.com/LargeWorldModel/ElasticTok [fig2]
《Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis》(2024) GitHub: github.com/YangLing0818/Trans4D
《OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction》(2024) GitHub: github.com/EnVision-Research/OmniBooth
《HART: Efficient Visual Generation with Hybrid Autoregressive Transformer》(2024) GitHub: github.com/mit-han-lab/hart
《DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads》(2024) GitHub: github.com/mit-han-lab/duo-attention [fig4]
《TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data》(2024) GitHub: github.com/ermongroup/TEOChat
《ToolGen: Unified Tool Retrieval and Calling via Generation》(2024) GitHub: github.com/Reason-Wang/ToolGen
《Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement》(2024) GitHub: github.com/Arvid-pku/Godel_Agent [fig5]
《Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians》(2024) GitHub: github.com/google-research/Splat-SLAM [fig6]
《Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving》(2024) GitHub: github.com/Robot-K/Hint-AD
《Splat-MOVER: Multi-Stage, Open-Vocabulary Robotic Manipulation via Editable Gaussian Splatting》(2024) GitHub: github.com/StanfordMSL/Splat-MOVER
《All-In-One Medical Image Restoration via Task-Adaptive Routing》(2024) GitHub: github.com/Yaziwel/All-In-One-Medical-Image-Restoration-via-Task-Adaptive-Routing
