[NeurIPS 2024] RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models

Kolors Team

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

An self-improving embodied conversational agent seamlessly integrated into the operating system to automate our daily tasks.

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2…

🙌 OpenHands: Code Less, Make More

Multilingual Medicine: Model, Dataset, Benchmark, Code

A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.

Cool Papers - Immersive Paper Discovery

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Shared task on Large-Scale Radiology Report Generation @ BioNLP ACL'24

"Discharge Me!" Challenge @ BioNLP ACL'24

Paper collections of the continuous effort start from World Models.

Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

Tools for merging pretrained large language models.

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

Minimalistic large language model 3D-parallelism training

Friends don't let friends make certain types of data visualization - What are they and why are they bad.

TextStarCraft2,a pure language env which support llms play starcraft2

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Retrieved Sequence Augmentation for Protein Representation Learning

WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.

Tools to download and cleanup Common Crawl data

[ACL 2024] Progressive LLaMA with Block Expansion.

Representation Engineering: A Top-Down Approach to AI Transparency

Machine Theory of Mind Reading List. Built upon EMNLP Findings 2023 Paper: Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models

[NeurlPS D&B 2024] Generative AI for Math: MathPile

Extract full next-token probabilities via language model APIs

[Arxiv-2024] CheXagent: Towards a Foundation Model for Chest X-Ray Interpretation