Modality-Adaptive Decoding (MAD) is a training-free decoding method for MLLMs that adaptively weights modality-specific branches via self-assessed modality relevance, effectively reducing cross-modal hallucinations.
☆16Jun 22, 2026Updated 4 months ago
Alternatives and similar repositories for MAD
Users that are interested in MAD are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS 2025] AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding☆27Nov 3, 2025Updated last year
- ☆43Aug 24, 2026Updated 2 months ago
- ☆12Dec 4, 2024Updated last year
- Evaluation toolkit for action-conditioned world models☆18Sep 30, 2026Updated last month
- Repo for "STAR: Spectral Truncation and Rescale for Model Merging" [NAACL 2025]☆11Oct 22, 2026Updated 2 weeks ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- A benchmark dataset and simple code examples for measuring the perception and reasoning of multi-sensor Vision Language models.☆19Dec 27, 2024Updated last year
- ☆16Sep 29, 2026Updated last month
- ☆15Aug 4, 2026Updated 3 months ago
- ☆19Jun 6, 2025Updated last year
- ✨✨The Curse of Multi-Modalities (CMM): Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio☆55Jul 11, 2025Updated last year
- Code for "Beyond Individual Input for Deep Anomaly Detection on Tabular Data"☆17Nov 17, 2025Updated 11 months ago
- [ICLR 2025] Official implementation of "Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning"☆11Apr 21, 2025Updated last year
- [ICML 2024] Code release for "On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm"☆11Feb 20, 2025Updated last year
- Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity. NeurIPS, 2025.☆13Oct 12, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [ICML 2023] "Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?" by Ruisi Cai, Zhenyu Zhang, Zhangyang Wang☆16May 4, 2023Updated 3 years ago
- ☆14Aug 31, 2026Updated 2 months ago
- Official code website of the paper SPEGC☆14Jun 5, 2026Updated 5 months ago
- ☆20Apr 25, 2025Updated last year
- The official code of EOPSA: Efficient On-Policy Self-Distilled Safety Alignment☆26Nov 4, 2026Updated last week
- Official implementation of OPD-Aha for fine-grained visual perception and multimodal reasoning☆15Sep 16, 2026Updated last month
- ☆14May 9, 2024Updated 2 years ago
- SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation☆12Jul 6, 2026Updated 4 months ago
- Official implementation of the paper "Linear Model Merging Unlocks Simple and Scalable Multimodal Data Mixture Optimization".☆14Feb 16, 2026Updated 8 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆17Dec 11, 2025Updated 11 months ago
- The official repository of the ICML 2026 paper: Evaluating and Steering Modality Preferences in Multimodal Large Language Model☆12Mar 31, 2026Updated 7 months ago
- RA-Touch: Retrieval-Augmented Touch Understanding with Enriched Visual Data (ACM MM '25)☆15Sep 12, 2025Updated last year
- (COLING2025) SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding☆10Dec 18, 2024Updated last year
- [Interspeech 2026] Official Implementation of "ALARM: Audio–Language Alignment for Reasoning Models"☆16Jun 10, 2026Updated 5 months ago
- When Tone and Words Disagree: Towards Robust Speech Emotion Recognition under Acoustic-Semantic Conflict☆18Jan 7, 2026Updated 10 months ago
- Code Collection Repo for OAG-Bench [KDD'24]☆11Aug 29, 2024Updated 2 years ago
- Baba Is You simulation for Reinforcement Learning☆24Sep 8, 2019Updated 7 years ago
- Efficient and simple data mixing with on-policy proxies!☆22May 18, 2026Updated 5 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- EMNLP 2025☆14Nov 28, 2024Updated last year
- ☆11May 30, 2026Updated 5 months ago
- Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging. Arxiv, 2024.☆16Oct 28, 2024Updated 2 years ago
- A real-world multimodal VLM reasoning benchmark for industrial real-time safety assessment☆15Apr 30, 2026Updated 6 months ago
- [NeurIPS'24] Official Implementation for "Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?"☆11Nov 13, 2024Updated last year
- Unofficial Visual Prompt Tuning implementation☆17May 22, 2023Updated 3 years ago
- [TIP'2026] Official implementation of "AWM-Fuse: Multi-Modality Image Fusion for Adverse Weather via Global and Local Text Perception"☆14Oct 20, 2026Updated 3 weeks ago
Are these results useful?