Lists (2)
Stars
A paper list of some recent works about Token Compress for Vit and VLM
Toolkit for Prompt Compression
[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.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …
Advancing AI by embracing human-likeness for better AI understanding, human–AI collaboration, and social simulation, bridging technology and genuine human experience.
Learning to Compress Prompts with Gist Tokens - https://arxiv.org/abs/2304.08467
[R]einforcement [L]earning from [M]odel-rewarded [T]hinking - code for the paper "Language Models That Think, Chat Better"
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
Official PyTorch implementation for "Large Language Diffusion Models"
Implementation of paper Data Engineering for Scaling Language Models to 128K Context
Open source traditional chinese handwriting dataset.
[ACL 2024] Long-Context Language Modeling with Parallel Encodings
Oh my tmux! My self-contained, pretty & versatile tmux configuration made with 💛🩷💙🖤❤️🤍
A jailbreak prompt that can universally attack strong leading LLMs.
Let your Claude able to think
An end-to-end signature verification system to extract, clean and verify signatures in documents. Signatures are detected using YOLOv5. Noise is cleaned using a CycleGAN approach and verified. Kera…
[TIP'24] Official PyTorch implementation of Concept Activation-Guided Contrast Learning.
A high-throughput and memory-efficient inference and serving engine for LLMs
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.
SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
Automatic architecture search and hyperparameter optimization for PyTorch
[EMNLP 2023] Enabling Large Language Models to Generate Text with Citations. Paper: https://arxiv.org/abs/2305.14627
NASLib is a Neural Architecture Search (NAS) library for facilitating NAS research for the community by providing interfaces to several state-of-the-art NAS search spaces and optimizers.
Automated Deep Learning: Neural Architecture Search Is Not the End (a curated list of AutoDL resources and an in-depth analysis)