ActivityForensics is the first large-scale benchmark for temporally localizing activity-level forgeries in videos, paired with a diffusion-based baseline called TADiff.
hub Mixed citations
Vidu: A highly consistent, dynamic and skilled text-to-video generator with diffusion models
Mixed citation behavior. Most common role is background (67%).
20
Pith papers citing it
Background
67% of classified citations
hub tools
citation-role summary
background 7
baseline 1
method 1
citation-polarity summary
representative citing papers
FreeSpec uses SVD-based spectral reconstruction to fuse global low-rank and local high-rank features, reducing content drift and preserving temporal dynamics in long video generation.
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.
Absorbing discrete diffusion models the conditional distributions of clean data; reparameterizing yields a time-independent RADD that unifies with AO-ARMs and reaches SOTA perplexity among diffusion models on zero-shot language benchmarks.
Delta Forcing improves temporal coherence in interactive autoregressive video generation by estimating transition consistency from teacher-generator latent deltas and balancing it against a monotonic continuity objective.
Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.
ARGen generates high-fidelity dynamic facial expression videos using affective semantic injection and adaptive reinforcement diffusion to improve emotion recognition models facing data scarcity and long-tail distributions.
Causal Forcing uses an autoregressive teacher for ODE initialization in diffusion distillation to close the causal attention gap and deliver better real-time video generation than Self Forcing.
Single-stage fine-tuning of a video model to generate actions as latent frames plus future states and values yields state-of-the-art robot policy performance on LIBERO, RoboCasa, and bimanual tasks.
The work introduces rCM, a score-regularized continuous-time consistency model that matches DMD2 quality on large models up to 14B parameters while improving diversity and enabling 1-4 step sampling.
Vidar shows that a video diffusion prior continuously pre-trained on 750K multi-view robot trajectories plus a label-free masked inverse dynamics adapter can generalize manipulation to new robot embodiments with 1% of typical demonstration data.
AnyPos automates task-agnostic action collection and inverse-dynamics modeling with arm/end-effector decoupling plus a direction-aware decoder, delivering 51% higher test accuracy and 30-40% better success rates on bimanual tasks.
Diffusion-APO synchronizes training noise with inference trajectories in video diffusion models to improve preference alignment and visual quality.
StableIDM stabilizes inverse dynamics models under manipulator truncation by combining robot-centric masking, directional spatial feature aggregation, and temporal dynamics refinement, yielding 12.1% higher strict action accuracy on AgiBot and 9.7-17.6% gains in real-robot tasks.
Wan releases open 1.3B and 14B video diffusion models claiming superior performance over open-source and commercial baselines across multiple tasks with consumer-grade efficiency.
The SAFE challenge shows measurable progress in detecting synthetic videos across different generators but persistent weaknesses against post-processing operations.
Mamoda2.5 is a 25B-parameter DiT-MoE unified AR-Diffusion model that reaches top video generation and editing benchmarks with 4-step inference up to 95.9x faster than baselines.
The paper offers the first focused review of MLLM-based video translation organized by a three-role taxonomy of Semantic Reasoner, Expressive Performer, and Visual Synthesizer, plus open challenges.
EchoTorrent combines multi-teacher distillation, adaptive CFG calibration, hybrid long-tail forcing, and VAE decoder refinement to enable few-pass autoregressive streaming video generation with improved temporal consistency and audio-lip sync.
A survey that organizes diffusion image-to-video methods into a taxonomy, distills core designs in condition encoding, temporal modeling, noise prior, and upsampling, and discusses applications plus challenges.
citing papers explorer
-
ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos
ActivityForensics is the first large-scale benchmark for temporally localizing activity-level forgeries in videos, paired with a diffusion-based baseline called TADiff.