Physics-IQ benchmark reveals that generative video models exhibit limited physical understanding unrelated to their visual quality.
hub Canonical reference
Vbench++: Comprehensive and versatile bench- mark suite for video generative models
Canonical reference. 75% of citing Pith papers cite this work as background.
28
Pith papers citing it
Background
75% of classified citations
hub tools
citation-role summary
background 6
dataset 1
method 1
citation-polarity summary
representative citing papers
DRIVE-CHOREO uses three LLM agents to create a unified position-aware token sequence co-compressed with multi-view video, achieving SOTA BEV mAP of 21.6 and +2.4 NDS improvement on nuScenes.
WorldJen is a new benchmark for generative video models that uses VLM-judged multi-dimensional Likert questionnaires validated against human preferences to achieve perfect tier agreement.
WorldMark is the first public benchmark that standardizes scenes, trajectories, and control interfaces across heterogeneous interactive image-to-video world models.
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.
CoMoVi co-generates 3D human motions and 2D videos synchronously in a single diffusion denoising loop using 3D-to-2D projection and dual-branch diffusion with 3D-2D cross attentions.
VACE unifies reference-to-video generation, video-to-video editing, and masked video-to-video editing in one Diffusion Transformer framework using a Video Condition Unit for inputs and a Context Adapter for task injection.
EffectivePresentationScorer evaluates paper-to-video talks for instructional quality by checking clear explanation of ideas, prerequisite concepts, and links to contributions, finding that current systems cover topics but fail to teach.
MAVEN introduces a multi-agent system for refining prompts in multicultural text-to-video generation and releases a benchmark of 243 prompts and 972 videos showing improved cultural relevance via parallel agent specialization.
CVG improves compositional faithfulness in frozen text-to-video diffusion models by steering early denoising steps with gradients from a classifier trained on the model's own cross-attention features.
PhyMotion scores generated human videos by grounding recovered 3D poses in a physics simulator across kinematic, contact, and dynamic axes, yielding stronger human correlation and larger RL post-training gains than prior 2D rewards.
LIVEditor-14B applies a new sparse attention method (ISA) that prunes context and uses query-sharpness routing to cut attention latency ~60% with no loss in editing quality on standard benchmarks.
EgoIn uses a fine-tuned vision-language model to infer transition steps and a conditioning module plus auxiliary supervision to generate coherent egocentric video sequences of object state changes.
Reward Forcing combines EMA-Sink tokens and Rewarded Distribution Matching Distillation to deliver state-of-the-art streaming video generation at 23.1 FPS without copying initial frames.
SteadyDancer is an I2V framework using condition reconciliation, synergistic pose modulation, and staged training to achieve robust first-frame preservation and coherent motion control in human image animation.
RAPO++ is a three-stage prompt optimization framework combining retrieval-augmented refinement, closed-loop test-time scaling, and LLM fine-tuning to enhance text-to-video generation quality.
LongLive is a causal autoregressive video generator that produces up to 240-second interactive videos at 20.7 FPS on one H100 GPU after 32 GPU-days of fine-tuning from a 1.3B short-clip model.
Genie Envisioner unifies robotic policy learning, simulation, and evaluation inside one instruction-conditioned video diffusion framework using GE-Base, GE-Act, and GE-Sim.
RIGVid shows that filtered AI-generated videos can serve as effective supervision for complex robotic manipulation tasks without any real demonstrations.
MAGI-1 is a 24B-parameter autoregressive video world model that predicts denoised frame chunks sequentially with increasing noise to enable causal, scalable, streaming generation up to 4M token contexts.
VBench-2.0 is a benchmark suite that automatically evaluates video generative models on five dimensions of intrinsic faithfulness: Human Fidelity, Controllability, Creativity, Physics, and Commonsense using VLMs, LLMs, and anomaly detection methods.
Vega unifies video understanding and generation via shared vocabulary and hybrid autoregressive-diffusion architecture, reporting strong results on VBench and VideoMME.
A decoupled-control autoregressive video model using Fast-Slow Memory training, dynamic projection, and staged camera control to produce stable long-horizon outputs with human and viewpoint guidance.
Physics-IQ Verified refines 57.6% of samples and 34.8% of prompts from the original benchmark and produces moderate ranking shifts (Kendall's τ = 0.46) across six image-to-video models.
citing papers explorer
-
A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talks
EffectivePresentationScorer evaluates paper-to-video talks for instructional quality by checking clear explanation of ideas, prerequisite concepts, and links to contributions, finding that current systems cover topics but fail to teach.