[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Repository Index
142,273 visible repositories in the index
1–11 of 11 · Most stars
LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and medical agentic benchmarks.
HRM-Text is a 1B text generation model based on the HRM architecture, strengthened by task completion and latent space reasoning.
- large-language-models
- pretraining
- hierarchical-reasoning-model
- hrm
FireRed-Image-Edit is a powerful image editing foundation model achieving open-source state-of-the-art performance with precise instruction following, high-fidelity generation, superior identity consistency, and seamless multi-element fusion.
A privacy-first guardrail for LLMs and RAG pipelines. SurrogateShield detects, redacts, and reconstructs sensitive PII data on the fly while defending against adversarial attacks.
Open source guides/codes for mastering deep learning to deploying deep learning in production in PyTorch, Python, Apptainer, and more.
- pytorch
- deep-learning
- apptainer
- llamaindex
Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. Model-agnostic framework with CLI/API for creative writing, synthetic data generation, and dialogue simulation.
The project integrates the RAG and FAQ dual mechanisms, introduces intent recognition, dynamic adaptive retrieval, and the RAGAS automated evaluation system, achieving a transformation from empirical optimization to data-driven optimization.
[ICLR 2025] FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models
- mllm
- ifdl
[EMNLP'25 findings] An easy-to-use Graph RAG system using hierarchical knowledge.
- clustering
- graphrag
- large-language-models
- nlp
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.
- agentic-ai
- ai-safety
- fastapi
- langchain