PKU-Alignment / safe-soraLinks
SafeSora is a human preference dataset designed to support safety alignment research in the text-to-video generation field, aiming to enhance the helpfulness and harmlessness of Large Vision Models (LVMs).
☆31Updated 10 months ago
Alternatives and similar repositories for safe-sora
Users that are interested in safe-sora are comparing it to the libraries listed below
Sorting:
- Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).☆38Updated last year
- [ICML2025] The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation☆112Updated 8 months ago
- [CVPR 2025 (Oral)] Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key☆61Updated 3 weeks ago
- ☆84Updated 2 months ago
- ☆44Updated 5 months ago
- Empowering Unified MLLM with Multi-granular Visual Generation☆124Updated 5 months ago
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation☆120Updated 2 weeks ago
- PhysGame Benchmark for Physical Commonsense Evaluation in Gameplay Videos☆45Updated last month
- [ICML 2024] On Discrete Prompt Optimization for Diffusion Models - Google☆56Updated 10 months ago
- Code and Data for "GenAI Arena: An Open Evaluation Platform for Generative Models" [NeurIPS 2024]☆21Updated 9 months ago
- [CVPR 25] A framework named B^2-DiffuRL for RL-based diffusion model fine-tuning.☆30Updated 2 months ago
- ☆37Updated last month
- code for "Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization"☆55Updated 10 months ago
- Multimodal RewardBench☆41Updated 4 months ago
- Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"☆33Updated 4 months ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?☆51Updated 3 weeks ago
- [NeurIPS 2024] Efficient Large Multi-modal Models via Visual Context Compression☆60Updated 4 months ago
- PyTorch implementation of DiffMoE, TC-DiT, EC-DiT and Dense DiT☆113Updated 2 months ago
- RichHF-18K dataset contains rich human feedback labels we collected for our CVPR'24 paper: https://arxiv.org/pdf/2312.10240, along with t…☆136Updated last year
- Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning☆191Updated 2 months ago
- ☆152Updated last week
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆75Updated 3 months ago
- ElasticTok: Adaptive Tokenization for Image and Video☆70Updated 7 months ago
- [ICLR 2025] AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark☆111Updated 3 weeks ago
- [ICML 2025 Spotlight] Direct Discriminative Optimization: Supercharging Diffusion/Autoregressive with GAN-type Discrimination☆47Updated this week
- [IROS'25 Oral & NeurIPSw'24] Official implementation of "MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simula…☆91Updated last week
- Official implementation of "Self-Improving Video Generation"☆66Updated 2 months ago
- ☆52Updated 9 months ago
- [NeurIPS 2024] Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning☆69Updated 4 months ago
- [arXiv] Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs☆32Updated last month