Molmo2 delivers state-of-the-art open-weight video VLMs with new grounding datasets and training methods that outperform prior open models and match or exceed some proprietary ones on pointing and tracking tasks.
arXiv preprint arXiv:2504.15376 , year=
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 10roles
background 3representative citing papers
Look-Before-Move is a framework that converts narrative intent into Semantic Observation Contracts, uses Monte Carlo Viewpoint Search for feasible viewpoints, and applies Semantic Trajectory Grounding for coherent camera motion in dynamic 3D story worlds.
Proposes Spatial Narrative Score (SNS) evaluation for VLMs' camera motion understanding and introduces CaMo model achieving consistent performance on SNS and direct QA.
A training-free method reformulates camera control as geometric displacement fields applied via differentiable latent resampling, enabling control and bias probing in video diffusion models.
PNAPO augments preference data with prior noise pairs and uses straight-line interpolation to create a tighter surrogate objective for offline alignment of rectified flow models.
DMGD achieves better performance than fine-tuned SOTA methods in dataset distillation on ImageNet subsets by using semantic matching through conditional likelihood optimization and OT-based distribution matching in a training-free diffusion setup.
OmniShotCut treats shot boundary detection as structured relational prediction via a shot-query Transformer, uses fully synthetic transitions for training data, and releases OmniShotCutBench for evaluation.
HumanScore defines six metrics for kinematic plausibility, temporal stability, and biomechanical consistency to benchmark human motions in videos from thirteen state-of-the-art generation models, revealing gaps between visual appeal and physical fidelity.
CamReasoner uses structured O-T-A reasoning and RL on 56k samples to lift camera movement classification from 73.8% to 78.4% and VQA from 60.9% to 74.5% on Qwen2.5-VL-7B.
ViPE estimates camera intrinsics, motion, and dense near-metric depth from uncalibrated videos, outperforming baselines on TUM and KITTI while releasing annotations for 96M frames across real and generated videos.
citing papers explorer
-
Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds
Look-Before-Move is a framework that converts narrative intent into Semantic Observation Contracts, uses Monte Carlo Viewpoint Search for feasible viewpoints, and applies Semantic Trajectory Grounding for coherent camera motion in dynamic 3D story worlds.