Dream.exe evaluates 8 video generation models on 101 manipulation tasks by converting generated videos into executable robot trajectories in a simulator, finding measurable success rates that visual metrics do not predict.
hub Canonical reference
Kling-Omni Technical Report
Canonical reference. 93% of citing Pith papers cite this work as background.
46
Pith papers citing it
Background
93% of classified citations
abstract
We present Kling-Omni, a generalist generative framework designed to synthesize high-fidelity videos directly from multimodal visual language inputs. Adopting an end-to-end perspective, Kling-Omni bridges the functional separation among diverse video generation, editing, and intelligent reasoning tasks, integrating them into a holistic system. Unlike disjointed pipeline approaches, Kling-Omni supports a diverse range of user inputs, including text instructions, reference images, and video contexts, processing them into a unified multimodal representation to deliver cinematic-quality and highly-intelligent video content creation. To support these capabilities, we constructed a comprehensive data system that serves as the foundation for multimodal video creation. The framework is further empowered by efficient large-scale pre-training strategies and infrastructure optimizations for inference. Comprehensive evaluations reveal that Kling-Omni demonstrates exceptional capabilities in in-context generation, reasoning-based editing, and multimodal instruction following. Moving beyond a content creation tool, we believe Kling-Omni is a pivotal advancement toward multimodal world simulators capable of perceiving, reasoning, generating and interacting with the dynamic and complex worlds.
hub tools
citation-role summary
background 13
baseline 1
citation-polarity summary
years
2026 46representative citing papers
PaSBench-Video benchmark shows no tested MLLM exceeds 20% on strict proactive safety metrics, with recall correlated 0.64 to false-positive rate on safe clips.
Introduces TASLE benchmark and MSLoc baseline for temporal localization and explanation of manipulated segments in long videos.
Future Forcing constructs a future query proxy from historical pre-RoPE statistics to score and merge KV tokens, improving subject consistency by up to 1.49 on VBench-Long for 60s AR video generation.
What-If World is a new paired-prompt benchmark showing that nine state-of-the-art video generation models achieve at most 52% on causal intervention tests and cluster near 28% for open-source systems.
LongAV-Compass is a new benchmark and evaluation framework for minute-scale audio-visual generation across T2AV, I2AV, and V2AV with multi-dimensional assessment.
Soap2Soap uses a multi-agent system with dual-bridge consistency via JSON screenplays and visual anchors plus batch keyframe generation to achieve better long-term consistency in cinematic video remaking than commercial APIs.
StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
Echo-Forcing decouples stable anchors, compressed history, and recent dynamics in video diffusion KV caches using hierarchical memory, scene recall frames, and difference-aware decay to support interactive long video generation under bounded cache.
CaC presents a new spatiotemporal concentrating reward model for video anomalies, built on a novel large-scale dataset and three-stage training with RL and IoU rewards, claiming 25.7% accuracy gains and 11.7% anomaly reduction.
AV-Phys Bench shows that current joint audio-video models lack robust physical commonsense, with major drops on transitions and deliberate anti-physics prompts.
AniMatrix generates anime videos by structuring artistic production rules into a controllable taxonomy and training the model to prioritize those rules over physical realism, achieving top scores from professional animators on prompt understanding and artistic motion.
RaG unifies generative recommendation and video generation via semantic IDs and Video Generation Agents with cross-domain rewards, reporting 1.87% ad revenue lift in a 400M-user industrial deployment.
GIVE uses paired depth-box and orientation-box geometry streams plus a graphics pipeline to train models for consistent object-level geometric edits like translate, rotate, and scale in videos.
A training-free framework that reorders shot generation and maintains per-entity visual memory improves cross-shot character, object, and scene consistency over narrative-order memory baselines.
MakeupMirror reports 60% better facial similarity and 50% less skin tone change than Stable-Makeup using geometry, region, and tone controls in diffusion models.
REINS uses supervised PCA on safety-labeled activations to find a linear direction that, when added to hidden states at roughly 50% depth in video diffusion transformers, redirects generations from unsafe to safe content across multiple models.
SpecLoR rectifies the amplitude spectrum of lookahead-estimated clean latents to natural-video priors during early ODE sampling steps, cutting physical artifacts with only four extra NFEs.
Dexterity-BEV creates 3D vertex-based inputs and BEV-aligned outputs to reduce spatial-temporal misalignments in end-to-end robot policies trained on diverse datasets and embodiments.
Introduces dimension-disentangled influence estimation to prune or reweight training samples for MVRMs, outperforming global scalar filtering in alignment with ground truth.
SmartDirector generates cinematic videos via Director-Gen for low-res keyframe-conditioned output followed by Director-SR refinement using high-res keyframes, trained on curated movie sequences.
VISTA introduces a new synthetic triplet dataset and diffusion-transformer framework with style adapter that jointly models style, content, and motion to achieve state-of-the-art video style transfer.
MiVE repurposes VLMs as multiscale feature extractors integrated into a unified self-attention Diffusion Transformer for reference-guided video editing, claiming top human preference scores over prior methods.
OmniHumanoid factorizes transferable motion learning from embodiment-specific adaptation to enable scalable cross-embodiment video generation without paired data for new humanoids.
citing papers explorer
-
Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation?
Dream.exe evaluates 8 video generation models on 101 manipulation tasks by converting generated videos into executable robot trajectories in a simulator, finding measurable success rates that visual metrics do not predict.
-
PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning
PaSBench-Video benchmark shows no tested MLLM exceeds 20% on strict proactive safety metrics, with recall correlated 0.64 to false-positive rate on safe clips.
-
Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
Introduces TASLE benchmark and MSLoc baseline for temporal localization and explanation of manipulated segments in long videos.
-
Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation
Future Forcing constructs a future query proxy from historical pre-RoPE statistics to score and merge KV tokens, improving subject consistency by up to 1.49 on VBench-Long for 60s AR video generation.
-
What-If World: A Causal Benchmark for General World Models in Embodied Scenarios
What-If World is a new paired-prompt benchmark showing that nine state-of-the-art video generation models achieve at most 52% on causal intervention tests and cluster near 28% for open-source systems.
-
LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV
LongAV-Compass is a new benchmark and evaluation framework for minute-scale audio-visual generation across T2AV, I2AV, and V2AV with multi-dimensional assessment.
-
Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration
Soap2Soap uses a multi-agent system with dual-bridge consistency via JSON screenplays and visual anchors plus batch keyframe generation to achieve better long-term consistency in cinematic video remaking than commercial APIs.
-
StreamingEffect: Real-Time Human-Centric Video Effect Generation
StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
-
Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation
Echo-Forcing decouples stable anchors, compressed history, and recent dynamics in video diffusion KV caches using hierarchical memory, scene recall frames, and difference-aware decay to support interactive long video generation under bounded cache.
-
CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
CaC presents a new spatiotemporal concentrating reward model for video anomalies, built on a novel large-scale dataset and three-stage training with RL and IoU rewards, claiming 25.7% accuracy gains and 11.7% anomaly reduction.
-
Do Joint Audio-Video Generation Models Understand Physics?
AV-Phys Bench shows that current joint audio-video models lack robust physical commonsense, with major drops on transitions and deliberate anti-physics prompts.
-
AniMatrix: An Anime Video Generation Model that Thinks in Art, Not Physics
AniMatrix generates anime videos by structuring artistic production rules into a controllable taxonomy and training the model to prioritize those rules over physical realism, achieving top scores from professional animators on prompt understanding and artistic motion.
-
Recommendation as Generation: Unifying Personalized Video Generation and Recommendation at Industrial Scale
RaG unifies generative recommendation and video generation via semantic IDs and Video Generation Agents with cross-domain rewards, reporting 1.87% ad revenue lift in a 400M-user industrial deployment.
-
Geometry-Instructed Video Editing
GIVE uses paired depth-box and orientation-box geometry streams plus a graphics pipeline to train models for consistent object-level geometric edits like translate, rotate, and scale in videos.
-
GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling
A training-free framework that reorders shot generation and maintains per-entity visual memory improves cross-shot character, object, and scene consistency over narrative-order memory baselines.
-
MakeupMirror: Improving Facial Attribute Preservation in Diffusion Models for Makeup Transfer
MakeupMirror reports 60% better facial similarity and 50% less skin tone change than Stable-Makeup using geometry, region, and tone controls in diffusion models.
-
Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering
REINS uses supervised PCA on safety-labeled activations to find a linear direction that, when added to hidden states at roughly 50% depth in video diffusion transformers, redirects generations from unsafe to safe content across multiple models.
-
SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation
SpecLoR rectifies the amplitude spectrum of lookahead-estimated clean latents to natural-video priors during early ODE sampling steps, cutting physical artifacts with only four extra NFEs.
-
Dexterity-BEV: Aligning 3D World and Actions for Generalizable Robot Policies Learning
Dexterity-BEV creates 3D vertex-based inputs and BEV-aligned outputs to reduce spatial-temporal misalignments in end-to-end robot policies trained on diverse datasets and embodiments.
-
Refining Multidimensional Video Reward Models via Disentangled Influence Functions
Introduces dimension-disentangled influence estimation to prune or reweight training samples for MVRMs, outperforming global scalar filtering in alignment with ground truth.
-
SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control
SmartDirector generates cinematic videos via Director-Gen for low-res keyframe-conditioned output followed by Director-SR refinement using high-res keyframes, trained on curated movie sequences.
-
VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformers
VISTA introduces a new synthetic triplet dataset and diffusion-transformer framework with style adapter that jointly models style, content, and motion to achieve state-of-the-art video style transfer.
-
MiVE: Multiscale Vision-language features for reference-guided video Editing
MiVE repurposes VLMs as multiscale feature extractors integrated into a unified self-attention Diffusion Transformer for reference-guided video editing, claiming top human preference scores over prior methods.
-
OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation
OmniHumanoid factorizes transferable motion learning from embodiment-specific adaptation to enable scalable cross-embodiment video generation without paired data for new humanoids.
-
From Priors to Perception: Grounding Video-LLMs in Physical Reality
Video-LLMs fail physical reasoning due to semantic prior dominance rather than perception deficits; a new programmatic adversarial curriculum and visual-anchored reasoning chain enable substantial gains via standard LoRA fine-tuning.
-
ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control
ExoActor uses exocentric video generation to implicitly model robot-environment-object interactions and converts the resulting videos into task-conditioned humanoid control sequences.
-
How Far Are Video Models from True Multimodal Reasoning?
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
-
Human Cognition in Machines: A Unified Perspective of World Models
The paper introduces a unified framework for world models that fully incorporates all cognitive functions from Cognitive Architecture Theory, highlights under-researched areas in motivation and meta-cognition, and proposes Epistemic World Models as a new category for scientific discovery agents.
-
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation
OmniShow unifies text, image, audio, and pose conditions into an end-to-end model for high-quality human-object interaction video generation and introduces the HOIVG-Bench benchmark, claiming state-of-the-art results.
-
InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation
InsEdit adapts a video diffusion backbone for text-instruction video editing via Mutual Context Attention, achieving SOTA open-source results with O(100K) data while also supporting image editing.
-
ImVideoEdit: Image-learning Video Editing via 2D Spatial Difference Attention Blocks
ImVideoEdit learns video editing from 13K image pairs by decoupling spatial modifications from frozen temporal dynamics in pretrained models, matching larger video-trained systems in fidelity and consistency.
-
A Definition and Roadmap for World Models
A perspective article defining world models as finite-resource compression of physical state transitions and outlining a roadmap toward physical AGI via unified representations and interactive simulators.
-
Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization
Disco-LoRA proposes disentangling content-style and content-motion via dual-LoRA with statistical regularization to enable multi-concept video customization.
-
EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis
EchoStyle is a text-driven framework for arbitrary-length video stylization that creates the V-Style20k dataset through reverse synthesis and adds init-follow-mode with sliding windows to reduce style drift and motion issues.
-
Bernini: Latent Semantic Planning for Video Diffusion
Bernini is a framework that uses an MLLM planner to output semantic representations for a DiT renderer to generate or edit videos, reporting SOTA benchmark performance.
-
EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation
EasyVFX decouples VFX generation via frequency-aware Mixture-of-Experts and test-time training to achieve realistic effects with limited resources.
-
AdaptiveLoad: Towards Efficient Video Diffusion Transformer Training
AdaptiveLoad cuts computational imbalance in video DiT training from 39% to 18.9% and raises throughput 27.2% via memory-compute constraints and a custom LayerNorm-Modulate kernel.
-
A3D: Agentic AI flow for autonomous Accelerator Design
A3D is an agentic AI system that automates end-to-end hardware accelerator design for complex applications like LAMMPS and QMCPACK with no human intervention.
-
A Systematic Post-Train Framework for Video Generation
A post-training pipeline for video generation models combines SFT, RLHF with novel GRPO, prompt enhancement, and inference optimization to improve visual quality, temporal coherence, and instruction following.
-
On Semiotic-Grounded Interpretive Evaluation of Generative Art
SemJudge uses a Hierarchical Semiosis Graph based on Peircean theory to evaluate deeper artistic meaning in generative art and aligns better with human judgments than prior metrics.
-
Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation
Delta Forcing constrains unreliable teacher supervision in autoregressive video models using an adaptive trust region based on latent trajectory deltas to improve consistency without losing event responsiveness.
-
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
Matrix-Game 3.0 delivers 720p real-time video generation at 40 FPS with minute-scale memory consistency by combining residual self-correction training, camera-aware memory injection, and DMD-based autoregressive distillation on a 5B model.
-
OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization
OmniFysics is an omni-modal network using a dynamic physical data engine and evolutive tuning to improve performance on multimodal benchmarks and physics-oriented tasks.
-
Toward Native Multimodal Modeling: A Roadmap
A roadmap that defines architectural nativity for multimodal models and categorizes them into Multi-to-Text, Multi-to-Target, and Multi-to-Multi types while outlining an industrial pipeline toward unified transformer-based native multimodal modeling.
-
LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation
This review organizes literature on large multimodal models and object-centric vision into four themes—understanding, referring segmentation, editing, and generation—while summarizing paradigms, strategies, and challenges like instance permanence and consistent interaction.
- SignVerse-2M: A Two-Million-Clip Pose-Native Universe of 55+ Sign Languages