Official code for paper "Reasoning Fails Where Step Flow Breaks" (ACL 2026)
☆19Apr 19, 2026Updated 6 months ago
Alternatives and similar repositories for step-saliency
Users that are interested in step-saliency are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2026 Oral] 🎉Hallucination Begins Where Saliency Drops☆69Feb 12, 2026Updated 9 months ago
- [ACM MM25] MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models☆14Aug 8, 2025Updated last year
- [ICLR 26] CoTA++: Understanding the Repeat Curse in dMLLMs from an Information Flow Perspective☆40Oct 27, 2026Updated 2 weeks 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
- [CVPR2026] Official code for "See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in …☆17Aug 20, 2026Updated 2 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.
- Official Repository for "Continuous Chain of Thought Enables Parallel Exploration and Reasoning"☆17Feb 22, 2026Updated 8 months ago
- Procedural Knowledge at Scale Improves ReasoningThis repository contains the minimal, end-to-end pipeline for reproducing the paper resul…☆21Apr 1, 2026Updated 7 months ago
- ☆24May 21, 2026Updated 5 months ago
- This repository contains the code for the paper "LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Sig…☆27Apr 15, 2026Updated 7 months ago
- [CVPR 2025] Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Att…☆86Oct 9, 2025Updated last year
- [SIGIR 2025] Class Activation Values: Lucid and Faithful Visual Interpretations for CLIP-based Text-Image Retrievals.☆11Aug 3, 2025Updated last year
- [EMNLP main 2026]Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models☆18Oct 29, 2026Updated 2 weeks ago
- [NeurIPS 2025] Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats☆12Dec 5, 2025Updated 11 months ago
- ☆27Oct 12, 2026Updated last month
- 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.
- [AAAI-25]Code for SEAL☆16Sep 25, 2025Updated last year
- [ICLR 2025] Code for Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models☆26Apr 14, 2025Updated last year
- Efficient multi-token attribution for reasoning language models — Python package, CLI, and HTML token traces☆44Updated this week
- ☆15Aug 6, 2026Updated 3 months ago
- [NeurIPS 2025] Official repository for “FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models”☆34Dec 9, 2025Updated 11 months ago
- A replication of "Toy Models of Superposition," a groundbreaking machine learning research paper published by authors affiliated with Ant…☆10Dec 30, 2023Updated 2 years ago
- [CVPR 2025] PPAP: Probabilistic Prompt Distribution Learning for Animal Pose Estimation☆12Jun 16, 2026Updated 4 months ago
- The offical repo for "Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing"☆22Feb 3, 2026Updated 9 months ago
- [NeurIPS 2025] More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models☆84May 31, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆16Apr 10, 2026Updated 7 months ago
- [ICML 2024] Official implementation for "HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding"☆117Dec 4, 2024Updated last year
- Official code for **Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity** (PruneSI…☆14Mar 25, 2026Updated 7 months ago
- Relabeling of the POPE benchmark☆14May 16, 2025Updated last year
- Code and data repository for two papers (ACL & EMNLP 2024) on the topic of collapse in model editing.☆10Dec 20, 2024Updated last year
- ICA Lens: compact ICA-based interpretability tools for exploring LLM activations. Code release for the paper.☆60Updated this week
- [ACM MM-24] Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization☆13Oct 8, 2024Updated 2 years ago
- recursive rag with r1 reasoning☆11Feb 26, 2025Updated last year
- ☆18May 7, 2026Updated 6 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆16Jul 10, 2023Updated 3 years ago
- Implementation for ACL 2024 paper "Meta-Task Prompting Elicits Embeddings from Large Language Models"☆12Jul 25, 2024Updated 2 years ago
- Implementation for the paper "Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning"☆11Jan 10, 2025Updated last year
- ScienceVision: Can AI Observe and Reason Like a Scientist?☆18Nov 7, 2026Updated last week
- PreAct: Computer-Using Agents that Get Faster on Repeated Tasks (arXiv:2606.17929). Compile successful runs into verified state-machine p…☆19Jun 17, 2026Updated 4 months ago
- Code of "MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards"☆16Jul 7, 2026Updated 4 months ago
- MLLM hallucination, LVLM, LLM, Hallucination Mitigation, Training-free hallucination mitigation☆37Oct 22, 2026Updated 3 weeks ago
Are these results useful?