Skip to main content
Search

# Text-to-Video Generation

12 related articles

Subscribe to updates
  1. arXiv

    EmoReward stops emotional video RL from trusting fixed rewards: last run's traces set the next run's weights

    Emotional video generation has no single correct target, and fixed fusion of visual, motion and text-alignment rewards captures emotional intent poorly. EmoReward distills reward traces from one completed training run into per-emotion-regime reliability estimates, converts them into bounded weight multipliers, and combines them with current-video instance gates in the next run without updating any reward-model parameters. On HunyuanVideo 1.5 with DanceGRPO, FlowGRPO and SAGE-GRPO, VideoAlign Overall rises under all three algorithms, including SAGE-GRPO with EmoReward moving from -0.8269 to -0.2624.

  2. arXiv

    PixVid moves video generation back to pixels: one token per frame, camera control lands on the next frame

    PixVid converts a pretrained latent video diffusion model into a frame-wise pixel-space generator: it keeps the diffusion transformer, replaces the VAE decoder with a convolutional detailer head, and finetunes from Wan2.1-14B. It reaches VBench totals of 85.09 at 960p and 84.78 at 480p, above Wan2.1's 84.05 and PixelUMM's 83.72, and keeps 98% of source motion on fast clips versus 83% for an identically finetuned latent model.

  3. arXiv

    Video models learn physics from executable code, not guesses: PhysOPSD beats 80K-sample fine-tuning with 3K samples

    PhysOPSD uses executable simulation code as privileged context for on-policy self-distillation in video generation: the student sees only text, while the teacher additionally sees a physics draft rendered from the simulation, so the model learns physically plausible motion without changing its inference interface. On the UniVideo (13B) and OmniWeaving (8.3B) backbones it trains on 3K samples and scores higher on VideoPhy-2 overall and PhyGround than supervised fine-tuning with 80K samples and offline reinforcement learning with 21K samples, while VBench general quality is maintained or slightly improved.

  4. arXiv

    VA-TDM swaps four-step supervision for a velocity-field adversarial game: 45.53% human preference against the many-step teacher on 33B MiniMax-H3

    Few-step diffusion distillation has long relied on estimating the student score, yet at intermediate steps that score is hard to track and the estimated distribution can differ from the one used to update the student. VA-TDM instead supervises velocity fields built from the student's own sampling process, uses a learned critic to compare student and teacher fields and turns their disagreement into generator feedback, unifying score distillation, Fisher matching and moment matching. On four-step SD3.5-Medium it raises GenEval from TDM's 0.61 to 0.67; on 33B MiniMax-H3 at the same 4-NFE budget it wins 61.33% of human comparisons against Fast-H3 and reaches a 45.53% preference rate against the 100-NFE teacher, versus 24.67% for Fast-H3.

  5. Gemini

    Gemini Omni 1.2 Flash goes generally available: 15-second clips at $0.07 per second for 720p

    Gemini Omni 1.2 Flash is now generally available through the Gemini API and Gemini for business, extending native video generation from 10 seconds in Omni 1.1 to 15 seconds and allowing durations from 3 to 15 seconds in one-second increments. It adds multi-turn conversational editing, so a clip can be refined turn by turn, swapping a product or background or changing lighting and aspect ratio without regenerating the whole clip; 720p video costs $0.07 per second, 30% below Omni 1.1. In the official example, given the same static studio poster and five-layer animation prompt, 1.2 follows the reference image more closely than 1.1.

  6. arXiv

    Joint text-to-video post-training stops sharing one reward: prompt and generator get separate credit, lifting a matched LTX-2.5 control from 61.47 to 64.46

    FlowCred splits the single terminal reward of joint text-to-video post-training into prompt-level credit and prompt-conditioned generator residuals, lifting a strictly matched joint-training control on LTX-2.5 from 61.47 to 64.46 on T2V-CompBench without increasing decoded-video or reward-model-call budgets.

  7. arXiv

    Diffusion sampling drops the single global guidance scale: per-token allocation lifts VBench total by up to 0.75

    Classifier-free guidance for flow-matching models has applied one shared scale to all latent tokens, even though their velocity predictions evolve differently during sampling. TrajCFG maps historical changes in guided velocity direction to bounded per-token scales, giving stronger guidance to larger directional changes and weaker guidance to more consistent directions, and fuses adjacent-step with interval-normalized longer-span feedback without extra model evaluations. Across text-to-video, image-to-video, text-to-audio-video, text-to-image and image-to-3D generation it improves on base samplers; on text-to-video it raises VBench Total by 0.30 to 0.75 points over the strongest evaluated baseline on each of three backbones.

  8. arXiv

    DuoMatching adds joint-marginal distribution matching to few-step video generation, with over 80% overall human preference against every baseline

    DuoMatching introduces a unified joint-marginal distribution matching framework: beyond existing joint DMD, it applies direct frame-level marginal supervision from an image generator, uses LatentBridge to resolve the video-image latent mismatch, and uses Latent Variation Sampling to spread frame-level supervision across temporal segments; in causal and bidirectional few-step video generation it improves visual quality, composition and semantic alignment while largely preserving motion dynamics, with human overall preference above 80% against all evaluated baselines.

  9. arXiv

    First survey of post-training and alignment for video generation unifies four method families and reports dimension-wise cross-benchmark evidence

    This TMLR survey presents the first comprehensive review of post-training and alignment for video generation models, distinguishing implicit from explicit alignment by how alignment signals are enforced and organizing methods into supervised fine-tuning, self-training and distillation, preference- and reward-based methods, and inference-time methods, while reviewing datasets, benchmarks, and evaluation practices and discussing open challenges such as scalable reward design, long-horizon temporal consistency, stability-expressiveness trade-offs, and safety-aware generation.

  10. arXiv

    PreviewDiff puts a multimodal critic inside the denoising loop, beating Best-of-N at matched compute on SDXL and LTX-Video

    PreviewDiff introduces a training-free test-time search method that decodes partial previews at selected denoising checkpoints, asks a multimodal judge to score and critique them, and uses the resulting natural-language feedback to branch over semantic prompt edits and locally re-noised latent continuations that are scored and selectively rolled forward, consistently outperforming budget-matched Best-of-N and scalar-search baselines on image and video generation benchmarks.