DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal Reasoning
cs.CV
Submitted: 2026-09-18
Updated: 2026-09-18
Code: https://github.com/HIT-leaderone/DRT
Terminology
Sources
- Qwen3-VL Technical Report
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Learning Adaptive Reasoning Paths for Efficient Visual Reasoning
- DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models
- ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy
- Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy
- SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning
- On the Optimal Reasoning Length for RL-Trained Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts
- Chain of Draft: Thinking Faster by Writing Less
- Qwen3 Technical Report
- Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring
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