[ICLR 2026π₯] SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense
β21Mar 24, 2026Updated 7 months ago
Alternatives and similar repositories for SHIELD
Users that are interested in SHIELD are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for Decoupled Vision-Language Attention for Dual-Path Causal Hallucination Mitigationβ12Nov 16, 2025Updated last year
- [CVPR 2026] CausalLens: Sensitivity-Guided Multi-Head Causal Intervention for Hallucination Mitigation in Large Vision-Language Modelsβ10Jun 6, 2026Updated 5 months ago
- Code for "Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models"β18Apr 30, 2026Updated 6 months ago
- [ACL 2026] Curated papers on video LLM hallucination, with benchmarks, mitigation methods, and an interactive browser. Updated monthly.β43Updated this week
- [ICLR 2026] Official code for "Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks"β29Sep 14, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer β’ AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- β15Nov 20, 2025Updated last year
- [NeurIPS 2025] The Indra Representation Hypothesis for Multimodal Alignmentβ32Feb 3, 2026Updated 9 months ago
- [NeurIPS 2025] Official code repository for the paper "On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Visioβ¦β11Oct 13, 2025Updated last year
- [CVPR 2025] Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attβ¦β86Oct 9, 2025Updated last year
- [ICCV 2025] ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Modelsβ53Jul 7, 2025Updated last year
- β15Apr 9, 2026Updated 7 months ago
- [CVPR 2025] Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attentionβ71Jul 16, 2024Updated 2 years ago
- [ICLR'26] SinkTrack: Attention Sink based Context Anchoring for Large Language Modelsβ18Apr 23, 2026Updated 6 months ago
- [ICLR 2026 Oral] πHallucination Begins Where Saliency Dropsβ70Feb 12, 2026Updated 9 months ago
- GPU virtual machines on DigitalOcean Gradient AI β’ AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- The official implementation of AAAI 26 Poster work ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLMβ16Aug 5, 2025Updated last year
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigationβ151Sep 11, 2025Updated last year
- MLLM hallucination, LVLM, LLM, Hallucination Mitigation, Training-free hallucination mitigationβ37Oct 22, 2026Updated 3 weeks ago
- AFNet(NeurIPS 2022)β20Nov 24, 2022Updated 3 years ago
- Official repo for ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Modelsβ31Mar 24, 2025Updated last year
- [ICLR 2026] Official implementation of "Enhancing Multi-Image Understanding Through Delimiter Token Scaling"β19Jul 10, 2026Updated 4 months ago
- A curated list of resources on on-policy distillationβ25Apr 13, 2026Updated 7 months ago
- [CVPR 2026 Highlight] Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decodingβ115Apr 9, 2026Updated 7 months ago
- up-to-date curated list of state-of-the-art Large vision language models hallucinations research work, papers & resourcesβ335Aug 28, 2026Updated 2 months ago
- 1-Click AI Models by DigitalOcean Gradient β’ AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Official repository for ICLR 2025 paper "Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs"β20Mar 18, 2025Updated last year
- Code for BlackSwanSuiteβ12Mar 26, 2025Updated last year
- β10Oct 27, 2025Updated last year
- [NeurIPS 2026]βοΈ Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning.β12May 7, 2026Updated 6 months ago
- β30Aug 22, 2023Updated 3 years ago
- [ICLR 2025] Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causalityβ67Jul 5, 2025Updated last year
- β34Apr 18, 2025Updated last year
- β15Aug 22, 2026Updated 2 months ago
- [ICCV 2025] Official repository of "Mitigating Object Hallucinations via Sentence-Level Early Intervention".β33Jul 2, 2026Updated 4 months ago
- End-to-end encrypted email - Proton Mail β’ AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Implementation of "RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse".β12May 29, 2026Updated 5 months ago
- Official Code for "Dreamweaver: Learning Compositional World Models from Pixels"β11Jun 12, 2025Updated last year
- SB-Bench: Stereotype Bias Benchmark for Large Multimodal Modelsβ15Jun 26, 2026Updated 4 months ago
- β38Oct 11, 2022Updated 4 years ago
- Evaluate robustness of adaptation methods on large vision-language modelsβ19Aug 23, 2023Updated 3 years ago
- [NeurIPS'22] What Makes a "Good" Data Augmentation in Knowledge Distillation -- A Statistical Perspectiveβ37Dec 15, 2022Updated 3 years ago
- Cross-Modal Retrieval with Partially Mismatched Pairs (IEEE TPAMI 2023, PyTorch Code)β23Sep 17, 2023Updated 3 years ago
Are these results useful?