Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Starred repositories
[ICML 2026] EchoRL: Reinforcement Learning via Rollout Echoing
[ICML 2026]Official implementation of the paper "The Geometry of Reasoning: Self-Evaluation via Layerwise Trajectory Evolution"
【ICML 2026 🔥】Knowledge injection method based on knowledge-oriented controls, achieving precision adaptation and powerful retention.
The official implementation of AAAI 26 Poster work ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
Official Repository of "Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding"
This repository provides a comprehensive library for parallel training and LoRA algorithm implementations, supporting multiple parallel strategies and a rich collection of LoRA variants. It serves …
[CVPR 2026] ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps
[TMLR 2025] Efficient Reasoning Models: A Survey
Papers list of empathy in LMs: theory, modeling, systems, emotion, evaluation.
A technical report / research paper repository for tool integrated reasoning.
🐉 Loong: Synthesize Long CoTs at Scale through Verifiers.
A Framework of Small-scale Large Multimodal Models
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
Code for the paper "Adapt - $\infty$: Scalable Lifelong Multimodal Instruction Tuning"
Writing AI Conference Papers: A Handbook for Beginners
Utilities intended for use with Llama models.
[CVPR 2024] Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation
Stanford NLP Python library for Representation Finetuning (ReFT)
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
⏰ Agenticly track worldwide conference deadlines (Website, Python Cli, Wechat Applet)
Tools for merging pretrained large language models.