Dromedary: towards helpful, ethical and reliable LLMs.
Repository Index
132,241 visible repositories in the index
97–120 of 186 · Most stars
[ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
- alignment
- reward
- reward-model
- rlhf
BoltzGen: Toward Universal Binder Design
- antibody-design
- antibody-engineering
- denovo-design
- drug-design
Automation for MS Rewards based on https://youtu.be/4qdPcMNaioA
A series of Houdini shelf tools that are geared towards game developers!
电报自动执行(签到、发送消息、点击键盘、AI回复等);个人、群组、频道消息监控、转发与自动回复。Automated Telegram tasks (check-ins, sending messages, keyboard clicks, AI replies, etc.); monitoring, forwarding, and auto-replying to private, group, and channel messages.
:memo: This repository recorded my NLP journey.
Official inference code for SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis
GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning
SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations (CVPR 2026 Findings)
- character-animation
- video-generation
- video2video
A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
- foundation-models
- multimodal
- representation-learning
- vision-language
A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding
AI-powered travel hacking and search with cash, points, miles, and award flights. Drop-in skills and MCP servers for Claude, Codex, and OpenCode.
- award-flights
- claude-code
- mcp
- opencode
Manipulate JSON-like data with NumPy-like idioms.
- json
- numpy
- data-analysis
- jagged-array
A highly configurable MQTT message router, where the routing targets are notification plugins, primarily written in Python.
- acquisition
- mosquitto
- mqtt
- mqtt-client
A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
Towards Large-Scale Emulation of IoT Firmware for Dynamic Analysis
[SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
- alignment
- large-language-models
- preference-alignment
- rlhf
Data Provinsi, Kota/Kabupaten, Kecamatan, dan Kelurahan/Desa di Indonesia
- indonesia
- dataset
[ECCV'22 Oral] Towards Grand Unification of Object Tracking
- multi-object-tracking-segmentation
- multiple-object-tracking
- object-tracking
- single-object-tracking
[IJCV 2022] Bridging Composite and Real: Towards End-to-end Deep Image Matting
- matting
- image-matting
- animal-matting
- composition
轻量级 LLM Post-training 框架,支持 SFT、RLVR、On-Policy KD、Guide KD 及混合训练;实现单轮/多轮 Guide 蒸馏、多教师蒸馏、Reward 混合训练与自动化数据分流👩🎓👨🎓