Thinking with Images without Coordinates
cs.CV
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/mengcaopku/TiCO
Project page: https://mengcaopku.github.io/TiCO
Sources
- GPT-4 Technical Report
- Qwen2.5-VL Technical Report
- Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification
- Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning
- Pix2seq: A Language Modeling Framework for Object Detection
- See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning
- Video-R1: Reinforcing Video Reasoning in MLLMs
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
- Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
- High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
- OpenAI o1 System Card
- Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning
- Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search
- LLaVA-OneVision: Easy Visual Task Transfer
- Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey
- Evaluating Object Hallucination in Large Vision-Language Models
- Visual-RFT: Visual Reinforcement Fine-Tuning
- MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
- LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models