GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification
Paper • 2604.14258 • Published • 23
AI & ML interests
None defined yet.
Recent Activity
View all activity
zwq2018
submitted a
paper to Daily Papers 6 days ago
veggiebird
authored 10
papers about 1 month ago
ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?
Paper • 2311.16989 • Published
Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework
Paper • 2305.03268 • Published • 3
Retrieving Multimodal Information for Augmented Generation: A Survey
Paper • 2303.10868 • Published
How Much are LLMs Contaminated? A Comprehensive Survey and the LLMSanitize Library
Paper • 2404.00699 • Published
Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks
Paper • 2410.01428 • Published • 1
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
Paper • 2504.00993 • Published • 3
Multi-Agent Tool-Integrated Policy Optimization
Paper • 2510.04678 • Published • 31
OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
Paper • 2511.16334 • Published • 96
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
Paper • 2511.20785 • Published • 189
MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
Paper • 2603.15726 • Published • 185
LidongBing
authored a
paper about 2 months ago
Cyril666
authored 8
papers about 2 months ago
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
Paper • 2603.06569 • Published • 119
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
Paper • 2501.13106 • Published • 91
What Is a Good Caption? A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness
Paper • 2502.14914 • Published
MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources
Paper • 2509.21268 • Published • 104
N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models
Paper • 2512.16561 • Published • 20
Chain of Ideas: Revolutionizing Research in Novel Idea Development with LLM Agents
Paper • 2410.13185 • Published • 5
Focus on the Whole Character: Discriminative Character Modeling for Scene Text Recognition
Paper • 2407.05562 • Published
VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
Paper • 2501.00599 • Published • 46