THU-KEG / LongWriter-VLinks
LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models
☆18Updated 2 months ago
Alternatives and similar repositories for LongWriter-V
Users that are interested in LongWriter-V are comparing it to the libraries listed below
Sorting:
- This repo contains code for the paper "Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM"☆14Updated 2 months ago
- Official implementation of the paper "MMInA: Benchmarking Multihop Multimodal Internet Agents"☆44Updated 4 months ago
- The official repo for "VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search"☆25Updated last month
- Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models☆36Updated last week
- Official implementation of ECCV24 paper: POA☆24Updated 10 months ago
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆16Updated 6 months ago
- PyTorch implementation of StableMask (ICML'24)☆13Updated last year
- Code for paper: Long cOntext aliGnment via efficient preference Optimization☆14Updated 4 months ago
- ☆16Updated 11 months ago
- official code for "BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning"☆35Updated 5 months ago
- [ICLR 2025] Weighted-Reward Preference Optimization for Implicit Model Fusion☆13Updated 3 months ago
- Codes for ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding☆35Updated last month
- [NAACL 2025] Source code for MMEvalPro, a more trustworthy and efficient benchmark for evaluating LMMs☆24Updated 9 months ago
- ☆60Updated 4 months ago
- ☆13Updated 6 months ago
- Evaluation framework for paper "VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?"☆57Updated 8 months ago
- [ICML 2025] VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models☆27Updated 2 weeks ago
- ☆50Updated 3 weeks ago
- ☆29Updated 2 months ago
- Official Implementation of Muddit [Meissonic II]: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model.☆60Updated 3 weeks ago
- Large Language Models Can Self-Improve in Long-context Reasoning☆70Updated 7 months ago
- A Recipe for Building LLM Reasoners to Solve Complex Instructions☆18Updated this week
- Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"☆16Updated last month
- Official code and dataset for our EMNLP 2024 Findings paper: Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Kn…☆19Updated 6 months ago
- ☆18Updated 3 months ago
- Ruler: A Model-Agnostic Method to Control Generated Length for Large Language Models☆36Updated 8 months ago
- The code for "VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by VIdeo SpatioTemporal Augmentation" [CVPR2025]☆16Updated 4 months ago
- This is the implementation of CounterCurate, the data curation pipeline of both physical and semantic counterfactual image-caption pairs.☆18Updated last year
- ☆40Updated 2 weeks ago
- Control LLM☆16Updated 2 months ago