KejiaZhang-Robust / TARSLinks
TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
☆23Updated 3 months ago
Alternatives and similar repositories for TARS
Users that are interested in TARS are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2025] Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models☆52Updated 3 months ago
- Official implementation of "Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation" (CVPR 202…☆40Updated 7 months ago
- Official repo for "Spotlight on Token Perception for Multimodal Reinforcement Learning"☆45Updated 2 months ago
- [NeurIPS 2025] Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO☆73Updated 2 months ago
- [ICCV 2025] Dynamic-VLM☆28Updated last year
- Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."☆50Updated last year
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆84Updated 2 months ago
- ☆23Updated 7 months ago
- Official PyTorch implementation of RACRO (https://www.arxiv.org/abs/2506.04559)☆19Updated 6 months ago
- VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection☆20Updated 7 months ago
- DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding☆65Updated 7 months ago
- ☆18Updated 2 months ago
- ☆33Updated last month
- Github repository for "Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas" (ICML 2025)☆67Updated 8 months ago
- ☆46Updated last year
- Codes for ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding [ICML 2025]]☆44Updated 5 months ago
- Preference Learning for LLaVA☆58Updated last year
- Official repository of the video reasoning benchmark MMR-V. Can Your MLLMs "Think with Video"?☆36Updated 6 months ago
- ☆12Updated last year
- Github repository for "Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging" (ICML 2025)☆86Updated 3 months ago
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆16Updated last year
- More reliable Video Understanding Evaluation☆13Updated 3 months ago
- ☆17Updated last year
- A Comprehensive Benchmark for Robust Multi-image Understanding☆17Updated last year
- Official Repo for SvS: A Self-play with Variational Problem Synthesis strategy for RLVR training☆50Updated 3 weeks ago
- The official repo for "VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search" [EMNLP25]☆35Updated 4 months ago
- The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".☆15Updated 4 months ago
- This repo contains code for the paper "Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM"☆16Updated 2 months ago
- [NeurIPS'25] The official code of "PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning"☆27Updated 3 months ago
- The codebase for our EMNLP24 paper: Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Mo…☆85Updated 11 months ago