A Stealthy Inference Cost Attack in Edge Serving of LVLMs

[CVPR 2026 Hightlight] OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer

[NeurIPS 2025] Hybrid Latent Reasoning via Reinforcement Learning

Codura is an intelligent code assistant designed to supercharge your IDE with context-aware code completion, inline explanations, test case generation, and refactoring suggestions. Powered by large…

🚀 Lightweight Redis GUI 🌐Full platform support🔥为爱发电💞

A LLM-based Agent that predict its tasks proactively.

This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025

[USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

Explore the Multimodal “Aha Moment” on 2B Model

Witness the aha moment of VLM with less than $3.

Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’

[NAACL 2025 Oral] From redundancy to relevance: Enhancing explainability in multimodal large language models

[NeurIPS 2024] Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models

[ECCV 2024] ControlCap: Controllable Region-level Captioning

[EMNLP'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records

Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.

A curated list of Meachine learning Security & Privacy papers published in security top-4 conferences (IEEE S&P, ACM CCS, USENIX Security and NDSS).

[ICLR'24] Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

Code for ICLR 2025 Paper: Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs

[CVPR 2024 Highlight] Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

[EMNLP'24] MedAdapter: Efficient Test-Time Adaptation of Large Language Models Towards Medical Reasoning

[ECCV 2024] FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification

Aligning pretrained language models with instruction data generated by themselves.

[ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting."

Large-Scale Visual Representation Model

[NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'

A very powerful and easy-to-use number precision calculation and formatting library.