Z1zs / MMNeuronLinks
Official implementation of "MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model". Our codes are borrowed from Tang's language specific neurons implementation and nrimsky's logit lens implementation.
☆20Updated 8 months ago
Alternatives and similar repositories for MMNeuron
Users that are interested in MMNeuron are comparing it to the libraries listed below
Sorting:
- [2025-TMLR] A Survey on the Honesty of Large Language Models☆58Updated 8 months ago
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆43Updated 3 months ago
- Code for "CREAM: Consistency Regularized Self-Rewarding Language Models", ICLR 2025.☆25Updated 6 months ago
- ☆120Updated 5 months ago
- Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆52Updated 3 months ago
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆153Updated last week
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆64Updated last month
- ☆46Updated 4 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆61Updated last year
- FeatureAlignment = Alignment + Mechanistic Interpretability☆29Updated 5 months ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆79Updated 9 months ago
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆41Updated 9 months ago
- ☆96Updated last month
- Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."☆45Updated 10 months ago
- [EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".☆80Updated 7 months ago
- [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.☆80Updated 6 months ago
- [ICLR 2025] Pad: Personalized alignment of llms at decoding-time☆15Updated 5 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆41Updated last year
- ☆61Updated 5 months ago
- ☆147Updated 3 months ago
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆174Updated 2 months ago
- Official Repository of LatentSeek☆60Updated 2 months ago
- An Efficient LLM Fine-Tuning Factory Optimized for MoE PEFT☆111Updated 5 months ago
- Code and data for "Timo: Towards Better Temporal Reasoning for Language Models" (COLM 2024)☆24Updated 10 months ago
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"☆76Updated 8 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆114Updated last year
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆84Updated 6 months ago
- Code for ACL 2024 paper "Soft Self-Consistency Improves Language Model Agents"☆24Updated 11 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆80Updated 2 months ago
- Large Language Models Can Self-Improve in Long-context Reasoning☆72Updated 9 months ago