This is the official repo for AdaIAT: Adaptively Increasing Attentions to Generated Text Tokens to Alleviate Hallucinations in Detail Caption (CVPR 2026)
☆13Apr 26, 2026Updated 6 months ago
Alternatives and similar repositories for AdaIAT
Users that are interested in AdaIAT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆15Nov 20, 2025Updated 11 months ago
- Code for "Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models"☆18Apr 30, 2026Updated 6 months ago
- Code for Decoupled Vision-Language Attention for Dual-Path Causal Hallucination Mitigation☆12Nov 16, 2025Updated last year
- [ICML 2026] Official implementation of Vision-aligned Latent Reasoning for Multi-modal Large Language Model (VaLR)☆22Apr 30, 2026Updated 6 months ago
- Code for paper: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models☆62Dec 18, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- The official implementation of AAAI 26 Poster work ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM☆16Aug 5, 2025Updated last year
- This is official code implementation of the <Why Does RL Generalize Better Than SFT? A Data-Centric Perspective on VLM Post-Training> in …☆16Apr 5, 2026Updated 7 months ago
- [EMNLP 2025 Oral] 🎉 Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs☆15Dec 10, 2025Updated 11 months ago
- CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts (ECCV2026)☆17Aug 4, 2026Updated 3 months ago
- Official codes of "Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs"☆20Sep 22, 2026Updated last month
- ☆24May 21, 2026Updated 5 months ago
- ☆34Apr 18, 2025Updated last year
- ☆18Aug 20, 2026Updated 2 months ago
- Code for ICML 2026 -- MEDSIGHT: Towards Grounded Visual Comprehension in Medical Large Vision-Language Models☆15Jul 2, 2026Updated 4 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.
- [ICLR 2026🔥] SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense☆21Mar 24, 2026Updated 7 months ago
- ☆13Sep 14, 2026Updated 2 months ago
- [ICCV 2025] ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models☆53Jul 7, 2025Updated last year
- MLLM hallucination, LVLM, LLM, Hallucination Mitigation, Training-free hallucination mitigation☆37Oct 22, 2026Updated 3 weeks ago
- The official code for paper "LARA: Latent Action Representation Alignment for Vision-Language-Action Models"☆11Aug 3, 2026Updated 3 months ago
- [ACL 2025] Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence☆20Jun 10, 2025Updated last year
- ☆14Jan 14, 2026Updated 10 months ago
- [NeurIPS'26] VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning☆19Oct 14, 2026Updated last month
- Official implementation of "Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models". (ECCV 2026 Spotlig…☆13Jul 3, 2026Updated 4 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆11Jul 24, 2024Updated 2 years ago
- CVPR 2025☆11Aug 8, 2025Updated last year
- ☆10Feb 27, 2026Updated 8 months ago
- ☆12Jun 4, 2026Updated 5 months ago
- [NeurIPS 2026]⭐️ Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning.☆12May 7, 2026Updated 6 months ago
- [ICML’25] Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models☆11Jun 9, 2025Updated last year
- Code for AAAI 2026: Enhancing Medical Large Vision-Language Models via Alignment Distillation☆12Apr 8, 2026Updated 7 months ago
- ☆16Sep 29, 2024Updated 2 years ago
- Official implementation of RP-OPSD for multimodal large language models☆13Aug 13, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ICLR 2026☆30May 13, 2026Updated 6 months ago
- The official repo of paper: "Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward"☆16Oct 17, 2025Updated last year
- [ICML 2026]Official PyTorch implementation of "SpecPL: Disentangling Spectral Granularity for Prompt Learning"☆13May 29, 2026Updated 5 months ago
- [ICLR'26] How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images☆19Apr 28, 2026Updated 6 months ago
- An implementation of the hallucination mitigation method "REVIS" introduced in "Sparse Latent Steering to Mitigate Object Hallucination i…☆16Feb 12, 2026Updated 9 months ago
- This repository contains the implementation of AlignVLM paper, which proposes a novel method for vision language alignment☆14May 23, 2025Updated last year
- ☆21May 20, 2026Updated 5 months ago
Are these results useful?