VLMs formulate differentiable rewards from task-specific rules to enable test-time online LoRA optimization of VGMs, delivering 16.7-point gains on symbolic and general video reasoning benchmarks over VLM-as-solver and Best-of-N baselines.
Mmgr: Multi-modal generative reasoning
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 6years
2026 6roles
background 2polarities
background 2representative citing papers
WBench is a benchmark with 289 test cases and 1,058 turns for evaluating interactive world models using 22 automated metrics validated against human judgments.
CollabVR improves video reasoning performance by coupling vision-language models and video generation models in a closed-loop step-level collaboration that detects and repairs generation failures.
Fine-tuning a video generator on a new 17K reasoning-video dataset improves Chain-of-Frame reasoning, and adding learnable visual/textual reasoning tokens yields further gains on external benchmarks.
VideoRLVR uses SDE-GRPO optimization, dense decomposed rewards, and Early-Step Focus to train video diffusion models on verifiable reasoning tasks, outperforming supervised fine-tuning and other video generators on Maze, FlowFree, and Sokoban.
Fine-tuning VLMs to output action sequences for puzzles causes emergent internal visual representations that improve performance when integrated into reasoning.
citing papers explorer
-
VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization
VLMs formulate differentiable rewards from task-specific rules to enable test-time online LoRA optimization of VGMs, delivering 16.7-point gains on symbolic and general video reasoning benchmarks over VLM-as-solver and Best-of-N baselines.
-
WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation
WBench is a benchmark with 289 test cases and 1,058 turns for evaluating interactive world models using 22 automated metrics validated against human judgments.
-
CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models
CollabVR improves video reasoning performance by coupling vision-language models and video generation models in a closed-loop step-level collaboration that detects and repairs generation failures.
-
OpenCoF: Learning to Reason Through Video Generation
Fine-tuning a video generator on a new 17K reasoning-video dataset improves Chain-of-Frame reasoning, and adding learnable visual/textual reasoning tokens yields further gains on external benchmarks.
-
Video Models Can Reason with Verifiable Rewards
VideoRLVR uses SDE-GRPO optimization, dense decomposed rewards, and Early-Step Focus to train video diffusion models on verifiable reasoning tasks, outperforming supervised fine-tuning and other video generators on Maze, FlowFree, and Sokoban.
-
Do multimodal models imagine electric sheep?
Fine-tuning VLMs to output action sequences for puzzles causes emergent internal visual representations that improve performance when integrated into reasoning.