Topics — The twenty-eight kinds of claim this anthology files against — the primary axis of both the practice registry and the reading list, and the same twenty-eight for each (ADR-026). The filing rule is the point: take a domain topic when the claim is ABOUT the domain; a claim merely discovered in one still takes its kind. The axis organizes the record, it does not bound it: content the list cannot place is evidence the list is short (ADR-059).
Vision and graphics — neural rendering, reconstruction, perception, visual foundation models.
102 of 737 LIT documents. Back to the full index.
| # | Title | Summary | Status |
|---|---|---|---|
| LIT-064 v3 | Instant Neural Graphics Primitives with a Multiresolution Hash Encoding | Müller et al. (2022), ARXIV-2201.05989. Real-time neural rendering. | Active |
| LIT-072 v2 | Simple Open-Vocabulary Object Detection with Vision Transformers | Minderer et al. (2022), ARXIV-2205.06230. Open vocabulary detection. | Active |
| LIT-086 v4 | K-Planes: Explicit Radiance Fields in Space, Time, and Appearance | Fridovich-Keil et al. (2023), ARXIV-2301.10241. Hybrid representation scheme. | Active |
| LIT-094 v2 | Neural Scene Graphs for Dynamic Scenes | Ost et al. (2020), ARXIV-2011.10379. Dynamic scene representation. | Rejected — too domain-specific for a general training list |
| LIT-096 v2 | Segment Anything | Kirillov et al. (2023), ARXIV-2304.02643. Universal segmentation model. | Active |
| LIT-107 v4 | MiDaS v3.1 — A Model Zoo for Robust Monocular Relative Depth Estimation | Birkl et al. (2023), ARXIV-2307.14460. Improved depth estimation. | Active |
| LIT-108 v3 | 3D Gaussian Splatting for Real-Time Radiance Field Rendering | Kerbl et al. (2023), ARXIV-2308.04079. Real-time neural rendering. | Active |
| LIT-109 v3 | NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction | Wang et al. (2022), ARXIV-2212.05231. Accelerated surface reconstruction. | Active |
| LIT-111 v3 | OnePose: One-Shot Object Pose Estimation without CAD Models | Sun et al. (2022), ARXIV-2205.12257. Category-level pose estimation. | Active |
| LIT-113 v3 | Gaussian Shell Maps for Efficient 3D Human Generation | Abdal et al. (2023), ARXIV-2311.17857. Shell-based surface representation. | Active |
| LIT-215 v2 | V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning | Assran et al. (2025), ARXIV-2506.09985. The JEPA objective at internet scale: over 1M hours of video, action-free, then post-trained into an action-conditioned world model on under 62 hours of unlabelled robot video. 77.3 on Something-Something v2, 39.7 recall-at-5 on Epic-Kitchens-100, 84.0 on PerceptionTest once aligned to an 8B LLM — and zero-shot pick-and-place on Franka arms in labs that contributed no training data. | Active |
| LIT-216 v3 | Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture | Assran et al. (2023), ARXIV-2301.08243. I-JEPA: predict the representations of target blocks from a context block in the same image, rather than the pixels or an augmentation-invariant embedding. No hand-crafted augmentations, and the masking strategy is the design choice that does the work — large semantic targets, a spatially distributed context. A ViT-Huge/14 trains on ImageNet in under 72 hours on 16 A100s. | Active |
| LIT-218 v2 | Video models are zero-shot learners and reasoners | Wiedemer et al. (2025), ARXIV-2509.20328. The argument is an analogy and it is stated as one: large generative models on web-scale data made language models generalist, the same primitives now describe video models, so vision may be about to follow. Veo 3 is shown solving segmentation, edge detection, image editing, affordance recognition, tool-use simulation and early visual reasoning (mazes, symmetry) that it was never trained on. | Active |
| LIT-384 | VGGT: Visual Geometry Grounded Transformer | Wang et al. (2025), ARXIV-2503.11651. One feed-forward pass infers camera parameters, point maps, depth maps and 3D point tracks together, from one view or hundreds, in under a second — beating methods that post-process with geometry optimisation. The claim that matters is that the specialisation into separate tasks was never necessary. | Active |
| LIT-385 | DUSt3R: Geometric 3D Vision Made Easy | Wang et al. (2023), ARXIV-2312.14132. Reconstruct from uncalibrated, unposed images by regressing pointmaps, with no camera intrinsics or extrinsics supplied. The inversion is the content: pixel matches and relative and absolute camera come back OUT of the 3D output, where the classical pipeline demands them as inputs before it can triangulate anything. | Active |
| LIT-386 | SuperGlue: Learning Feature Matching with Graph Neural Networks | Sarlin et al. (2019), ARXIV-1911.11763. Match two sets of local features by learning the matcher rather than hand-designing it: a graph neural network predicts assignment costs and a differentiable optimal transport step solves them, finding correspondences and rejecting unmatchable points in one operation. Replaces “hand-designed heuristics” with priors over geometry learned end to end — and still consumes keypoints somebody else detected. | Active |
| LIT-387 | LoFTR: Detector-Free Local Feature Matching with Transformers | Sun et al. (2021), ARXIV-2104.00680. Drop the keypoint detector: establish dense matches coarsely and refine them, with self and cross attention producing descriptors conditioned on BOTH images. The argument is that the detector is the binding constraint — it cannot produce repeatable interest points in low-texture regions, which is exactly where matching is hard. | Active |
| LIT-421 | Gradient-based learning applied to document recognition | LeCun et al. (1998), Proceedings of the IEEE. The paper MNIST comes from. In this record it is cited for the dataset alone, and almost always in one role: the small convex-ish problem where a claim about influence, attribution or retraining can be checked against ground truth. | Active |
| LIT-422 | ImageNet: A large-scale hierarchical image database | Deng et al. (2009), CVPR. The database itself — millions of images organised on the WordNet noun hierarchy. Almost nothing in this record is measured on it: an “ImageNet” number here is nearly always ILSVRC (LIT-423), the thousand-class challenge built from a slice of it. | Active |
| LIT-423 | ImageNet Large Scale Visual Recognition Challenge | Russakovsky et al. (2014), ARXIV-1409.0575. The thousand-class challenge built on a slice of LIT-422’s database, and the instrument almost every “ImageNet top-1” number in this record is actually measured on — including the human-error figure those numbers are read against. | Active |
| LIT-424 | Learning Multiple Layers of Features from Tiny Images | Krizhevsky (2009), University of Toronto technical report. The source of CIFAR-10 and CIFAR-100 — 32×32 labelled images drawn from the Tiny Images collection. Sixty-nine documents here measure something on it, which makes it the record’s most-used instrument after ILSVRC. | Active |
| LIT-435 | NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis | Mildenhall et al. (2020), ARXIV-2003.08934. The coordinate network the record’s one scene-representation practice exists to replace. An MLP maps a 5D coordinate — position and viewing direction — to density and view-dependent colour; differentiable volume rendering means posed images are the only supervision needed. | Active |
| LIT-475 | Dropout Reduces Underfitting | Liu, Xu, Jin, Shen and Darrell (2023), ARXIV-2303.01500. Dropout applied only for the first stretch of training and then switched off lowers training loss and raises test accuracy on models too small to overfit — the regime where standard dropout costs up to 6 points. The mechanism is measured: early dropout reduces the angle between mini-batch gradients and the whole-dataset gradient. | Active |
| LIT-488 | gen2seg: Generative Models Enable Generalizable Instance Segmentation | Khangaonkar and Pirsiavash (2025), ARXIV-2505.15263. Finetune Stable Diffusion or MAE end-to-end — encoder and decoder — for category-agnostic instance segmentation on indoor furnishings and cars only, and the model segments people, animals, x-rays and impressionist paintings. It approaches SAM across five domains on 0.3% of the annotated masks, and beats it ~3× on fine structures. The controls are the argument: the same backbone under a standard segmentation head scores near zero. | Active |
| LIT-494 v2 | GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting | Dong, Wang, Zheng, Chen, Lu and Tang (2025), ARXIV-2501.15619. Replaces the fixed grid of a VQ image tokenizer with K 2D Gaussians whose feature coefficient is quantized while position, rotation and scale stay continuous. Reports rFID 1.61 on ImageNet-1K against LlamaGen’s 2.19 with a 16× smaller codebook. The paper’s own word for the result is semi-discrete, and the comparison is at equal token count rather than equal rate — each token carries five floats the baselines’ tokens do not. | Active |
| LIT-511 | Image-GS: Content-Adaptive Image Representation via 2D Gaussians | Zhang et al. (2024), ARXIV-2407.01866 — the 2D descendant of LIT-108, and the paper that does the rate accounting LIT-494 skipped. Anisotropic colored 2D Gaussians, spawned by image-gradient magnitude and grown where error persists, decoded at 0.3K MACs per pixel against C3’s 3K at comparable bitrate. Beats six neural image representations at matched model size across the bitrate range, and beats JPEG below 0.244 bpp. Read as NOTE-256. | Active |
| LIT-550 | Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains | Tancik, Srinivasan, Mildenhall et al. (2020), ARXIV-2006.10739. A plain MLP on low-dimensional coordinates learns high frequencies so slowly that in practice it never does. In the NTK picture this is because the kernel’s eigenvalues fall off fast with frequency. Mapping the input through sinusoids makes the kernel stationary, with a bandwidth set by the frequencies. Random Gaussian frequencies beat NeRF’s positional encoding on all seven tasks, and only their scale matters. | Active |
| LIT-551 | Implicit Neural Representations with Periodic Activation Functions | Sitzmann, Martel et al. (2020), ARXIV-2006.09661. An MLP with sin activations fits images, video, audio and signed distance functions, and, unlike ReLU networks, their derivatives, because a SIREN’s derivative is itself a SIREN. It trains only with a specific initialization: weights U(±√(6/n)) keep every pre-activation near N(0,1), and the first layer is scaled by ω₀ = 30. The initialization’s activation statistics are verified. Its role in earlier periodic networks’ failures is asserted, not ablated. | Active |
| LIT-554 | Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion | Chen, Marti Monso, Du, Simchowitz, Tedrake, Sitzmann (2024), ARXIV-2407.01392. Train a causal sequence model to denoise tokens that each carry an independent noise level. One model then samples autoregressively, like next-token prediction, and supports guidance over a whole horizon, like full-sequence diffusion. Video rollouts stay stable past 1,000 frames where teacher forcing diverges, shown qualitatively only. On D4RL mazes it beats Diffuser using its own generated actions. A convolutional RNN, not a transformer, at small scale. | Active |
| LIT-559 | Alias-Free Generative Adversarial Networks | Karras et al. (2021), ARXIV-2106.12423. StyleGAN3: fine detail in GAN images sticks to pixel coordinates (“texture sticking”) because the generator aliases. Treat every feature map as a bandlimited continuous signal. Low-pass filter around each nonlinearity at 2× temporary upsampling, feed Fourier features instead of a constant, drop noise inputs. The generator becomes translation-equivariant (EQ-T 63 dB), or also rotation-equivariant (StyleGAN3-R, EQ-R 40 dB), at StyleGAN2’s FID. | Active |
| LIT-560 | Analyzing and Improving the Image Quality of StyleGAN | Karras et al. (2019), ARXIV-1912.04958. StyleGAN2 traces StyleGAN’s droplet artifacts to instance normalization and replaces it with weight demodulation (FID unchanged, artifacts gone). It traces its phase artifacts to progressive growing and replaces growing with a fixed output-skip generator and residual discriminator (FFHQ FID 4.34 → 3.31). It runs R1 only every 16 minibatches at no cost, and adds path-length regularization, which trades FID against smoothness on less structured data. | Active |
| LIT-561 | A Style-Based Generator Architecture for Generative Adversarial Networks | Karras, Laine, Aila (2018), ARXIV-1812.04948. StyleGAN: a mapping network turns the latent z into an intermediate w, and w modulates every synthesis layer through AdaIN. Per-layer noise inputs supply stochastic detail, and mixing two w’s across layers regularizes the model toward scale-specific control. Built on progressive growing. FFHQ FID goes from 8.04 (Progressive GAN) to 4.40, most of it from tuning (5.25) and the mapping network and styles (4.85). Also introduced the FFHQ dataset and the perceptual path length metric. | Active |
| LIT-562 | Projected GANs Converge Faster | Sauer, Chitta, Müller, Geiger (2021), ARXIV-2111.01007. Feed real and generated images through a frozen ImageNet-pretrained EfficientNet, mix its multi-scale features with fixed random 1×1 and 3×3 convolutions, and put a small discriminator on each scale. FID reaches StyleGAN2’s best on LSUN-Church after 1.1M images instead of 88M, and beats it on 22 datasets. A later analysis (LIT-563) shows part of the gain is in FID’s perceptual null space: at equal FID, humans and a CLIP-feature distance prefer StyleGAN2. | Active |
| LIT-564 | Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks | Zhu, Park, Isola, Efros (2017), ARXIV-1703.10593. Learn G: X → Y and F: Y → X from unpaired collections, with adversarial losses in each domain and a cycle-consistency loss that makes F(G(x)) ≈ x and G(F(y)) ≈ y. The cycle term turns an under-constrained mapping into a usable one for colour and texture changes (horse → zebra, photo ↔ painting, summer ↔ winter). The authors report that it fails on geometric changes. Its own ablation has a one-directional cycle beating the full model on labels → photo. | Active |
| LIT-566 | SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis | Podell et al. (2023), ARXIV-2307.01952. SDXL: a 2.6B-parameter UNet latent diffusion model, 3× Stable Diffusion’s, with two text encoders (CLIP ViT-L and OpenCLIP ViT-bigG) and pooled-text conditioning. It is conditioned on each training image’s original size and crop, trained on multiple aspect ratios, and followed by an optional refiner applied SDEdit-style. The one quantitative ablation is size conditioning on class-conditional ImageNet. The headline comparisons are user studies. | Active |
| LIT-573 | FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space | Black Forest Labs (2025), ARXIV-2506.15742. The only paper describing FLUX.1: a 12B rectified-flow transformer in a 16-channel VAE latent, with double-stream then 38 single-stream blocks, fused feed-forward layers and 3D RoPE. Kontext fine-tunes it for editing by appending context-image latents to the sequence, offset by a “virtual time step” in RoPE. The evidence is human preference against other systems and a reconstruction table. It has no ablations. | Active |
| LIT-587 | An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale | Dosovitskiy et al. (2020), ARXIV-2010.11929. Cut the image into fixed patches, linearly embed them, and feed the sequence to an unmodified transformer encoder. The result is not that the architecture is better — it is that at enough pre-training data the convolutional prior stops paying for itself, and below that threshold it still does. | Active |
| LIT-588 v2 | Learning Transferable Visual Models From Natural Language Supervision | Radford et al. (2021), ARXIV-2103.00020. Train an image encoder and a text encoder to match 400M (image, text) pairs contrastively, then build a classifier for any label set by embedding its class names. The most durable result is not the zero-shot accuracy — it is that supervised adaptation which raises ImageNet by 9.2% buys no average robustness. | Active |
| LIT-590 | Momentum Contrast for Unsupervised Visual Representation Learning | He et al. (2019), ARXIV-1911.05722. Reframes contrastive learning as dictionary look-up and asks for a dictionary that is both large and consistent: a queue makes it large independently of the batch, and an EMA-updated key encoder makes it consistent. The momentum ablation is the result that propagated — at m=0 it does not train at all. | Active |
| LIT-591 | A Simple Framework for Contrastive Learning of Visual Representations | Chen et al. (2020), ARXIV-2002.05709. Strips contrastive learning to augment, encode, project, NT-Xent — no memory bank, no special architecture — and then ablates each piece. The two findings that outlived the method: the augmentation pair is the pretext task, and the projection head is a sacrificial layer you throw away. | Active |
| LIT-593 | Exploring Simple Siamese Representation Learning | Chen & He (2020), ARXIV-2011.10566. Strips a joint-embedding method to nothing: no negatives, no large batch, no momentum encoder — shared weights, a predictor on one side, a stop-gradient on the other. It works, which makes stop-gradient the candidate for the load-bearing piece, and contradicts BYOL’s account of its own method. | Active |
| LIT-594 | Bootstrap your own latent: A new approach to self-supervised Learning | Grill et al. (2020), ARXIV-2006.07733. Learns a representation with no negatives at all: an online network predicts a slow EMA copy of itself under a different augmentation. 74.3% ImageNet linear. Why it does not collapse is a hypothesis in the paper, not a result, and LIT-593 disputes which part is doing the work. | Active |
| LIT-595 | VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning | Bardes et al. (2021), ARXIV-2105.04906. Three explicit terms — a hinge keeping each embedding dimension’s standard deviation above a threshold, an invariance term, and a decorrelation term — applied to each branch separately. Needs no weight sharing, batch norm, stop-gradient or memory bank, and the variance term transplants into other methods and improves them. | Active |
| LIT-596 | Barlow Twins: Self-Supervised Learning via Redundancy Reduction | Zbontar et al. (2021), ARXIV-2103.03230. Removes every asymmetry — no predictor, no stop-gradient, no moving average — and prevents collapse in the objective instead: drive the cross-correlation matrix between the two branches’ outputs toward the identity. 73.2% ImageNet linear, and unlike its neighbours it wants a very high-dimensional output. | Active |
| LIT-598 | Unsupervised Learning of Visual Features by Contrasting Cluster Assignments | Caron et al. (2020), ARXIV-2006.09882. Predict one view’s cluster code from another view’s representation instead of comparing features pairwise, with an equipartition constraint doing the anti-collapse work. 75.3% ImageNet linear — and multi-crop, which is the part that transplants into other methods for 2-4 points. | Active |
| LIT-599 v3 | DINOv2: Learning Robust Visual Features without Supervision | Oquab et al. (2023), ARXIV-2304.07193. The thesis is that existing self-supervised objectives already produce general-purpose features if the data is curated enough, so the contribution is a retrieval-based curation pipeline and the engineering to scale it — not a new objective. Frozen features, no finetuning, competitive with the best open weakly-supervised models. | Active |
| LIT-601 | Masked Autoencoders Are Scalable Vision Learners | He et al. (2021), ARXIV-2111.06377. Mask 75% of the patches, run the encoder on the visible quarter only, and reconstruct pixels with a small decoder you then throw away. 3x faster pretraining, 87.8% with ViT-Huge on ImageNet-1K alone. The 75% ratio, five times BERT’s 15%, is found by a sweep, and the paper explains it with an argument about the signal’s redundancy. | Active |
| LIT-605 v2 | Sigmoid Loss for Language Image Pre-Training | Zhai et al. (2023), ARXIV-2303.15343. Replace CLIP’s softmax with a pairwise sigmoid, so the loss never needs a global view of the similarity matrix — no all-gathers, only a per-device block in memory, and better results below 16k batch. Then trains at batch size one million and finds the benefit saturated at 32k. | Active |
| LIT-611 v2 | GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium | Heusel et al. (2017), ARXIV-1706.08500. Where FID comes from — and it comes from a subsection of a paper about two time-scale update rules and Nash equilibria. Fit a Gaussian to Inception activations for each distribution and take the Wasserstein-2 distance between them. Validated by monotonicity under six synthetic corruptions. | Active |
| LIT-614 | Improved Techniques for Training GANs | Salimans et al. (2016), ARXIV-1606.03498. Where the Inception Score comes from — exp(E_x KL(p(y|x) ‖ p(y))), proposed as a cheap stand-in for a Mechanical Turk study it correlates with, on 50k samples because part of what it measures is diversity. The incumbent LIT-611 displaced, and the paper that first tied generative evaluation to ImageNet class structure on purpose. | Active |
| LIT-615 | Demystifying MMD GANs | Bińkowski et al. (2018), ARXIV-1801.01401. Where KID comes from, and where the case against comparing FID numbers comes from. The plug-in FID estimator is biased, no unbiased estimator of FID exists, and at d=2048 with 50,000 samples it reliably returns the wrong ordering between two models with a standard deviation small enough to hide it. KID is the squared MMD in the same Inception features, with a cubic kernel and a simple unbiased estimator. | Active |
| LIT-618 v2 | LTX-Video: Realtime Video Latent Diffusion | HaCohen et al., Lightricks (2024), ARXIV-2501.00103. It trades latent size for speed: a 32×32×8 VAE with 128 channels (1:192) moves patchification into the autoencoder, and the decoder does the last denoising step. It generates 5s of 768×512 video in about 2s on an H100 at 20 steps. The denoising decoder, the central idea, is supported by one internal preference study with no reported numbers. | Active |
| LIT-619 v2 | Wan: Open and Advanced Large-Scale Video Generative Models | Wan Team, Alibaba (2025), ARXIV-2503.20314. The open Wan2.1 video models, 1.3B and 14B, and the full recipe behind them. The recipe covers data curation, a 127M causal 3D VAE compressing 4×8×8, a cross-attention DiT trained by rectified flow on an image-then-video resolution curriculum, the 2D context parallelism it needs, and a mask-conditioned image-to-video variant. The abstract claims video scaling laws in data and model size, but the report plots no scaling curve. | Active |
| LIT-620 v2 | HunyuanVideo: A Systematic Framework For Large Video Generative Models | Kong et al., Tencent Hunyuan (2024), ARXIV-2412.03603. A 13B open video model: FLUX-style dual-then-single-stream transformer, a multimodal LLM as text encoder, a from-scratch causal 3D VAE. It fits the line’s only explicit video compute-optimal scaling law, on a proxy model that differs from the shipped one in objective, text encoder and conditioning. It reports no controlled ablations. | Active |
| LIT-621 v2 | Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models | Blattmann et al., LMU Munich and NVIDIA (2023), ARXIV-2304.08818. Video LDM turns a pretrained image latent diffusion model into a video model by inserting temporal layers and fine-tuning the decoder on video. Starting from the image model halves driving-scene FVD against end-to-end training (534 against 1155). The paper counts 2.2B of the text-to-video model’s 3.1B parameters as trained, and that count leaves out the spatial layers and decoder it also fine-tuned. The abstract describes training only temporal layers. | Active |
| LIT-622 v2 | CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer | Yang, Teng et al., Tsinghua and Zhipu AI (2024), ARXIV-2408.06072. The first widely used open DiT for text-to-video. It has a MAGVIT-style causal 3D VAE, one sequence over text and video with modality-specific adaLN, and full 3D attention. Full 3D attention beats factorized attention at 1.1× to 2.3× the forward time, rising with resolution. The architecture ablations are absent from the first arXiv version and present in the third, and the 2B model ships the position encoding they rejected. | Active |
| LIT-623 v2 | Language Model Beats Diffusion — Tokenizer is Key to Visual Generation | Yu et al., Google and CMU (2023), ARXIV-2310.05737. MAGVIT-v2 is a causal 3D-CNN tokenizer with lookup-free quantization. The causal design lets images and video share one tokenizer, though no experiment uses the video tokenizer for images, and LFQ lets generation keep improving as the vocabulary grows, where VQ turns worse. The title’s “beats diffusion” holds only with guidance, and the “language model” is a masked, MaskGIT-style one. | Active |
| LIT-624 v3 | Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model | Step-Video Team, StepFun (2025), ARXIV-2502.10248. A 30B text-to-video DiT on a 16×16×8 VAE that reconstructs as well as HunyuanVideo’s 8×8×4 on its own benchmark, though not on Open-Sora 2.0’s, so the model covers 204 frames. It also applies DPO to video (a 55/45 preference score, ties split) and runs at 32% MFU. It reaches parity with Movie Gen and loses to the strongest commercial model it names, despite the abstract’s “state-of-the-art”. | Active |
| LIT-625 v2 | Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets | Blattmann, Dockhorn, Kulal et al., Stability AI (2023), ARXIV-2311.15127. Video LDM’s architecture is held fixed, and the paper studies what the data does. Curating 4× fewer clips beats the uncurated set, and the advantage survives high-quality fine-tuning. It is the only controlled video-curation study in this line. One of its own filters lost the ablation and was kept anyway. | Active |
| LIT-626 v2 | Movie Gen: A Cast of Media Foundation Models | The Movie Gen team, Meta (2024), ARXIV-2410.13720. A 30B video model built from a Llama 3-style transformer, flow matching and an 8×8×8 temporal autoencoder, with the most controlled ablations in the video line. At 5B, flow matching beats diffusion and video captions beat frame captions. The “LLaMa3 scaling laws” claim rests on image-only runs at four sizes. | Active |
| LIT-627 v2 | Video Diffusion Models | Ho, Salimans et al., Google (2022), ARXIV-2204.03458. The first diffusion model for video: a U-Net factorized into space and time and trained jointly on videos and still frames. Adding eight still frames per video cuts FVD from 202 to 58 at fixed model, batch and steps, though not at fixed frames per step. The abstract’s explanation, lower gradient variance, is never measured. | Active |
| LIT-628 | Better plain ViT baselines for ImageNet-1k | Beyer, Zhai and Kolesnikov (2022), ARXIV-2205.01580. Four pages that move a plain ViT-S/16 on ImageNet-1k from 66.8% to 80.0% with five changes, none of them novel and none of them a regulariser. The original recipe scores 66.8 / 67.2 / 67.1 at 90 / 150 / 300 epochs — it cannot use more training at all. The belief the abstract names is that ViT needs sophisticated regularisation at this scale; the answer is that standard augmentation is sufficient. | Active |
| LIT-629 v3 | Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion | Huang et al., Adobe Research and UT Austin (2025), ARXIV-2506.08009. Self Forcing trains an autoregressive video model on its own rollouts, conditioning on self-generated context and scoring the whole clip with a distribution-level loss. On Wan2.1-1.3B it beats teacher-forced and diffusion-forced training under every objective tried, and holds quality where they degrade frame by frame. It reaches 17 fps at 0.69s latency on one H100. The comparison against slower models is confounded by a 14B teacher. | Active |
| LIT-631 v3 | From Slow Bidirectional to Fast Autoregressive Video Diffusion Models | Yin et al., MIT and Adobe (2024), ARXIV-2412.07772. CausVid distills a bidirectional video DiT into a 4-step block-causal student with distribution matching, cutting first-frame latency from 219s to 1.3s at 9.4 fps. The controlled result is that a bidirectional teacher makes a better causal student than a causal one. The authors attribute this to error accumulation, but the causal teacher is also the weaker model, and the ablation does not separate the two. The paper does not claim real time, and it reports that the student flickers more and is less diverse. | Active |
| LIT-632 v2 | Make-A-Video: Text-to-Video Generation without Text-Video Data | Singer et al., Meta AI (2022), ARXIV-2209.14792. An unCLIP text-to-image model is extended into video with identity-initialized temporal layers trained on video whose captions are discarded. Text alignment comes entirely from images. That limits it: it “can not learn associations between text and phenomenon that can only be inferred in videos”. The paper has no ablations, and its title describes the training signal, not the data. | Active |
| LIT-633 v2 | AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning | Guo et al., CUHK, Shanghai AI Lab and Stanford (2023), ARXIV-2307.04725. Stable Diffusion 1.5 is frozen and only zero-initialized temporal “motion modules” are trained. The modules then plug into community checkpoints fine-tuned from the same base, with no tuning. Transfer is measured by one table against two baselines not built for the task. The first version’s limitations section, which reports failure on stylized checkpoints, was dropped from the second. | Active |
| LIT-634 v2 | Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k | The Open-Sora team, HPC-AI Tech (2025), ARXIV-2503.09642. An 11B video model initialized from FLUX, with most of its compute at 256px and a 768px text/image-to-video stage that is short in iterations but takes 37% of the compute. The “$200k” is one final diffusion-model run at an assumed H200 rental rate. It excludes data, captioning, failed runs, and the FLUX and HunyuanVideo-VAE weights it starts from. A 4×32×32 autoencoder is a further efficiency experiment, and the model adapted to it is unconverged and weaker. | Active |
| LIT-635 v2 | Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning | Girdhar et al., Meta GenAI (2023), ARXIV-2311.10709. Text-to-video is factored into generating an image and then a video conditioned on it, on a frozen text-to-image model. The report runs controlled human-preference ablations of the factorization, zero terminal SNR, low-then-high resolution training and a fine-tune on 1.6K clips filtered on motion, aesthetics and CLIP score together. Movie Gen builds on this recipe. Freezing the image layers beats fine-tuning them only narrowly (55/58). | Active |
| LIT-637 v2 | Imagen Video: High Definition Video Generation with Diffusion Models | Ho et al., Google (2022), ARXIV-2210.02303. VDM scaled into a seven-model, 11.6B cascade producing 128 frames at 1280×768. It is the first report to add a separate image-text corpus (60M internal pairs plus LAION-400M) to joint training, and it asserts the benefit without an ablation. Its tested results are that v-prediction beats ε-prediction for video super-resolution, and that distillation to 8 steps is 18× faster at a small metric cost under constant guidance and none under oscillating guidance. | Active |
| LIT-643 | One-step Diffusion with Distribution Matching Distillation | Yin et al., MIT and Adobe (2023), ARXIV-2311.18828. DMD distills a diffusion model into a one-step generator by descending an approximate KL(p_fake ‖ p_real), whose gradient is the difference of a frozen “real” score and an online “fake” score. It adds an LPIPS regression loss onto precomputed teacher ODE outputs. It reaches 2.62 FID on ImageNet-64 and 11.49 on zero-shot COCO-30k. The ablation that makes the regression loss look necessary ran its no-regression arm at a different learning rate, and its mode-collapse evidence is qualitative. | Active |
| LIT-646 | Improved Distribution Matching Distillation for Fast Image Synthesis | Yin et al., MIT and Adobe (2024), ARXIV-2405.14867. DMD2 drops DMD’s regression loss. It stabilizes training by updating the fake score five times per generator step, adds a GAN loss on real images, and trains multi-step students on their own simulated inputs. The ImageNet ablation is clean: removing the loss costs 2.62 → 3.48 FID, and the update rule restores 2.61. The student is slightly less diverse than its teacher (LPIPS diversity 0.61 against 0.64). The paper does not attribute this to the reverse KL. | Active |
| LIT-652 v2 | Video generation models as world simulators | Brooks, Peebles et al., OpenAI (2024), no arXiv id. Sora is a latent diffusion transformer over spacetime patches of a video autoencoder’s latents. It is trained jointly on images and videos at their native durations, resolutions and aspect ratios, with captions from a DALL-E 3-style recaptioner. The report withholds model and implementation details, and it has no table, number, metric or baseline. Every claim, including the scaling comparison and the square-crop ablation, is shown by example videos only. The video reports filed after it cite it and benchmark against it, and it supplies no measurement of its own. | Active |
| LIT-657 | Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution | Dehghani, Mustafa et al., Google DeepMind (2023), ARXIV-2307.06304. Packs patches from several images into each fixed-length sequence, with per-example attention masks and pooling. A ViT can then take any aspect ratio and a sampled resolution per image. It leads ViT at each of 12 compute-matched budgets, and matches the best ViT with 4x less compute. The paper attributes the gain chiefly to seeing about 5x more images, not to aspect ratio. The one test that isolates aspect ratio is a linear probe on fairness attributes. | Active |
| LIT-658 | FiT: Flexible Vision Transformer for Diffusion Model | Lu et al. (2024), ARXIV-2402.12376. A DiT variant trained on images without cropping or upsampling. Large images are only resized down to at most 256² pixels at native aspect ratio, and sequences are padded to 256 tokens. Table 3 isolates this pipeline change on DiT-B/2 at 400K steps. At a square 256² output, FID moves 44.83 → 43.34 and sFID worsens 8.49 → 11.11. At 160×320 and 224×448, FID falls from 91.32 and 109.1 to 50.51 and 52.55, but the fixed model never trained on those shapes. | Active |
| LIT-661 | Photorealistic Video Generation with Diffusion Models | Gupta, Yu et al., Stanford and Google (2023), ARXIV-2312.06662. A latent video diffusion transformer over a causal image-and-video encoder. It alternates per-frame spatial attention with local spatiotemporal windows. Two single-run ablations bear on the record’s video practices. Adding a separate corpus of ~970M image-text pairs to ~89M text-video pairs takes zero-shot UCF-101 FVD from 598.8 to 344.5 at 419M (Table 5), with compute not stated. And windowed attention matches full self-attention on UCF-101 (FVD 55.3–59.6 against 59.9) while training 1.7x faster (Table 3b). | Active |
| LIT-662 | Vision Transformers Need Registers | Darcet, Oquab, Mairal and Bojanowski (2023), ARXIV-2309.16588. 107 documents in this record say “ViT” and none held this. Large trained ViTs put high-norm outlier tokens on background patches — 2.37% of tokens in DINOv2 ViT-g — which hold little local information and a lot of global information. The model is using redundant patches as scratch space. Append a few tokens whose only job is to be scratch space and the artifacts vanish. | Active |
| LIT-663 | DINOv3 | Siméoni et al. (2025), ARXIV-2508.10104. The finding the record needs is not the model: train a self-supervised ViT long enough and its dense features rot while its global metrics keep improving. Segmentation mIoU declines after ~200k iterations and for the 7B falls below its early levels, while ImageNet classification rises monotonically throughout. Gram anchoring — pull the student’s patch Gram matrix towards an early teacher’s — repairs it, and it is a different defect from the register artifacts. | Active |
| LIT-664 | Emerging Properties in Self-Supervised Vision Transformers | Caron et al. (2021), ARXIV-2104.14294. The origin of the DINO line, which 31 documents here reference and 12 practices touch. Self-supervised ViT features carry explicit semantic segmentation that supervised ViTs and convnets do not show as clearly, and reach 78.3% ImageNet top-1 with a plain k-NN — no finetuning, no linear probe, no augmentation. Collapse is avoided by centering and sharpening the teacher output alone, with no predictor. | Active |
| LIT-687 v2 | Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think | Martin Garcia, Knaebel, Schmidt, de Geus, Hermans and Leibe (WACV 2025), ARXIV-2409.11355. Marigold’s “dismal” few-step depth came from the DDIM scheduler’s leading timestep spacing. The spacing hands a pure-noise input a timestep that claims an almost clean one. Switching to trailing spacing makes one step usable (NYUv2 AbsRel 5.7). The fixed single step is still behind the 50-step, 10-member ensemble on all five depth sets. What beats that ensemble everywhere is end-to-end fine-tuning as a one-step model with a task loss, and it works nearly as well from plain Stable Diffusion. | Active |
| LIT-691 | Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation | Ke, Obukhov, Huang, Metzger, Daudt and Schindler (CVPR 2024), ARXIV-2312.02145. Marigold fine-tunes Stable Diffusion v2’s U-Net on 74K synthetic images to denoise a depth latent conditioned on the image latent, with the VAE frozen. It samples 50 DDIM steps and ensembles 10 runs, and ranks first on average across five zero-shot depth benchmarks. Its step-count curve, one step at ≈34% NYUv2 AbsRel, was measured under diffusers’ default leading spacing, which the paper never names. That is the scheduler bug LIT-687 corrects. The claim that a generative prior is what helps is not tested. | Active |
| LIT-703 | Improved Precision and Recall Metric for Assessing Generative Models | Kynkäänniemi, Karras, Laine, Lehtinen and Aila (2019), ARXIV-1904.06991. The definitions SOTA-425 rests on: build a k-NN hypersphere approximation of each distribution’s manifold in a feature space, then precision is the fraction of generated samples inside the real manifold and recall the fraction of real samples inside the generated one. The features are VGG-16 fc2, not Inception — the record had this wrong. Its Figure 4 is the demonstration: two StyleGAN setups at FID 16.9 and 16.7 where one produces good samples at low variety and the other is “practically all images broken”, and the FID-optimised configuration has visible facial distortion. | Active |
| LIT-706 | Scaling Language-Image Pre-training via Masking | Li et al. (2022), ARXIV-2212.00794 — FLIP. Train CLIP with 50–75% of image patches removed and the image encoder run on the rest: the saved compute buys more pairs per hour and a 2–4× larger batch at the same memory, which outweighs the information lost per image. ViT-L/16 on LAION-400M reaches its CLIP reproduction’s accuracy more than 3× faster. The accuracy gain at a fixed schedule is 1–2 points at L and nothing at B/16, and at equal batch size masking 50% buys nothing — the batch is doing the work. | Active |
| LIT-712 | Axiomatic Attribution for Deep Networks | Sundararajan, Taly and Yan (ICML 2017), ARXIV-1703.01365. Integrated Gradients: attribute a prediction to input features by integrating the gradient along the straight line from a baseline x′ to the input, times (x − x′). Its case is axiomatic, not empirical. It satisfies Sensitivity and Implementation Invariance, which gradients, DeconvNets and Guided Backprop (Sensitivity) and DeepLift and LRP (Implementation Invariance) each break, and its attributions sum to F(x) − F(x′). It is the unique symmetry-preserving path method. No experiment measures whether its maps are faithful. The only comparison with another method is visual (Figure 2). The baseline is a free choice that changes the answer. | Active |
| LIT-713 v2 | Sanity Checks for Saliency Maps | Adebayo, Gilmer, Muelly, Goodfellow, Hardt and Kim (NeurIPS 2018), ARXIV-1810.03292. Two randomization tests for any explanation method. Compare its maps on the trained model against the same architecture with weights re-initialized (top-down, or one layer at a time), and against a model trained on permuted labels. A method whose maps survive either cannot support model debugging or explain what the model learned from data. Gradients and GradCAM pass. Guided Backprop and Guided GradCAM are invariant to the higher layers’ weights. Integrated Gradients and gradient⊙input get no verdict. Their maps keep the input’s structure (rank correlation with absolute values and SSIM stay high), while their sign decorrelates at once. The lesson that travels is the negative one: judging a saliency map by how it looks is not a test. | Active |
| LIT-715 | Surya: Foundation Model for Heliophysics | Roy et al. (2025), ARXIV-2508.14112. A 366M-parameter transformer pretrained on full-resolution (4096²) multi-instrument SDO imagery to forecast the next frame, then rollout-tuned, forecasts solar dynamics zero-shot. With LoRA fine-tuning it beats task-specific baselines on four downstream heliophysics tasks. | Deferred — seeded from the abstract and a skim on 2026-09-25; not read in full |
| LIT-723 | Swin Transformer: Hierarchical Vision Transformer using Shifted Windows | Liu, Lin, Cao, Hu et al. (2021), ARXIV-2103.14030. A vision transformer with a hierarchical feature pyramid and self-attention confined to shifted local windows, linear in image size rather than quadratic. Nine documents here run experiments on it and none said what it is. Its ablation is the reason to hold it: every design element is measured on three tasks, and the absolute position embedding this record recommends elsewhere helps ImageNet classification (+0.4 top-1) while hurting COCO detection (−0.2 box AP) and ADE20K segmentation (−0.6 mIoU). | Active |
| LIT-727 v4 | Striving for Simplicity: The All Convolutional Net | Springenberg, Dosovitskiy, Brox and Riedmiller (2014), ARXIV-1412.6806, ICLR 2015 workshop. Guided backpropagation’s defining paper, and so the referent for SOTA-430’s headline failure case — the method whose maps stay “visually and quantitatively similar” after the weights above the lowest layers are destroyed. The masking rule is stated here in one sentence: zero the gradient wherever either the top gradient or the bottom activation is negative. The paper is about an architecture; guided backprop arrives in §4.2 as a tool for analysing it, and the property later found to be its defect is presented here as its advantage. | Active |
| LIT-728 v2 | Visualizing and Understanding Convolutional Networks | Zeiler and Fergus (2013), ARXIV-1311.2901. Two attribution families start here and the record depends on both. The deconvnet is the approach guided backprop (LIT-727) is explicitly “a new variant of”, and so is the antecedent of SOTA-430’s headline failure case. Occlusion sensitivity — slide a grey square, watch the class probability — is the perturbation-based family LIT-725 names as its own origin, and LIT-725’s infidelity is its quantitative descendant. Also an early depth-against-parameters ablation: removing the fully connected layers costs little, removing them and two middle conv layers is “dramatically worse”. | Active |
| LIT-730 | A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations | Nie, Zhang and Patel (2018), ARXIV-1805.07039, ICML 2018. The third mechanism, and the one SOTA-430’s headline failure row needed. Theorem 1: in a random three-layer CNN, guided backpropagation recovers the input, s_k^GBP(x) ≈ x, regardless of the class label. Theorem 2: saliency map and DeconvNet in the same network are N(0, I) — noise. So GBP and DeconvNet are doing (partial) image recovery, “unrelated to the decision-making of neural networks”, and the two causes are the backward ReLU and a CNN’s local connections. Four arms test it, including removing local connections and an adversarial attack that changes the class while barely changing the input. | Active |
| LIT-731 | SmoothGrad: removing noise by adding noise | Smilkov, Thorat, Kim, Viégas and Wattenberg (2017), ARXIV-1706.03825. The smoothing eight held documents name — averaging the gradient over n noisy copies of the input, with 10–20% noise and n ≈ 50, past which “there was little apparent change”. Its own evidence is entirely qualitative and it says so: “since quantitative evaluation of a map remains an unsolved problem, we again focus on qualitative evaluation.” And its §3.1 visualization lessons contain informal statements of two things this record spent two days building accounts for: the signed-versus-absolute ambiguity, and the input multiplier putting the input’s own edges into the map. | Active |
| LIT-732 | Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization | Selvaraju, Cogswell, Das, Vedantam, Parikh and Batra (2016; ICCV 2017, IJCV 2019), ARXIV-1610.02391. The referent behind both halves of SOTA-430’s verdict table — GradCAM, which passes the randomization test, and Guided GradCAM, which fails it, are both defined here, and the second is defined as the pointwise product of the first with guided backpropagation. Grad-CAM reads one layer: gradients of the class logit into the last conv feature maps, global-average-pooled into per-channel weights. Also carried: a 2016 human study in which guided backprop, the best-looking method, comes last of four — 44.44% against Deconvolution’s 53.33% — a number its authors did not gloss until v4 in December 2019, fourteen months after LIT-713 made the same point another way. | Active |
| LIT-743 | Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation | Bahmani et al. (2025), ARXIV-2509.19296 — Lyra. Train a 3D Gaussian Splatting decoder on the latents of a frozen camera-controlled video diffusion model (GEN3C), supervised only by that model’s own RGB decodings along six camera trajectories per image, with no real multi-view data. Decoding latents rather than pixels is what makes 726 views per scene fit in memory. Single image to 3D beats the reported numbers of ZeroNVS, ViewCrafter, Wonderland and Bolt3D on RealEstate10K, DL3DV and Tanks-and-Temples, and adding real multi-view data to the synthetic supervision does not help. | Active |
| LIT-745 | SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features | Tschannen et al. (2025), ARXIV-2502.14786. Keep SigLIP’s architecture and sigmoid loss, and add a captioning-and-grounding decoder loss (LocCa) throughout, self-distillation and masked prediction for the last 20% of training, a 90/10 English/multilingual mix with de-biasing filters, and distillation through active data selection for the smallest models. It beats SigLIP at every size and resolution compared on zero-shot classification, retrieval, VLM transfer, dense probing and localization (RefCOCO val, L/256: 67.3 → 86.0). None of the ingredients is ablated, so the gains cannot be credited to any one of them. | Active |
| LIT-747 | Perceiver: General Perception with Iterative Attention | Jaegle et al. (2021), ARXIV-2103.03206 — the Perceiver. A learned latent array of N=512 queries cross-attends to the raw input (50,176 ImageNet pixels), so attention costs O(MN) rather than O(M²), and a deep latent transformer then runs at O(N²) per layer, independent of input size. With 2D Fourier-feature positions and no convolution it reaches 78.0% top-1 on ImageNet without pretraining, unchanged when the pixels are permuted, while ViT-B-16 and ResNet-50 given the same features fall to 61.7 and 39.4. The same architecture runs on audio, video and point clouds. | Active |
| LIT-751 | ”Principal Components” Enable A New Language of Images | Wen, Zhao et al. (2025), ARXIV-2503.08685 — Semanticist. A ViT encoder emits a causal 1D sequence of continuous tokens that conditions a DiT diffusion decoder. During training, every token after a uniformly sampled index is replaced by a learned null token (“nested CFG”), so earlier tokens carry more. The result is coarse-to-fine and PCA-like, and any prefix decodes. ImageNet-256 rFID 0.78 with 256×16 floats against ImageFolder’s 0.80 at 286×32. An autoregressive model trained on only the first 32 tokens reaches gFID 2.57. The diffusion decoder is argued to keep image spectrum out of the tokens, but that is shown against other tokenizers, not ablated. | Active |
| LIT-755 | Wonderland: Navigating 3D Scenes from a Single Image | Liang et al. (2024), ARXIV-2412.12091 — Wonderland (CVPR 2025). Fine-tune CogVideoX-5B-I2V for camera control with a ControlNet branch plus LoRA, then train a reconstructor (LaLRM) that regresses 3D Gaussians directly from the video latents rather than decoded frames. Reading latents beat reading RGB at matched cost (RealEstate10K PSNR 27.10 against 25.06). The reconstructor is trained on captured RealEstate10K, ACID and DL3DV first, then fine-tuned on those plus 20K videos the video model generated, supervised by its own decoded frames; that addition moved benchmark PSNR by at most 0.09. | Active |
| LIT-770 v2 | DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation | Yu et al., Texas A&M and ByteDance (2026), ARXIV-2610.02188. DMAD replaces DMD’s fake-score critic with a discriminator and trains the student on a linear loss on its logit. At the unrestricted discriminator optimum that gradient equals DMD’s idealized one (App. A, checked); nothing bounds it off the optimum, where training runs with one discriminator step per student step. One-step ImageNet-64 FID is 1.24 against DMD2’s 1.28, at 570K iterations, and 1.04 with an ImageNet-pretrained discriminator scored only by FID. Four-step SDXL reaches 14.47 FID at lower CLIP. Wan2.1 VBench margins are 0.1–0.3 points. No diversity metric and no seeds are reported. | Active |
| LIT-775 | Inductive Moment Matching | Zhou, Ermon and Song, Luma AI and Stanford (2025), ARXIV-2503.07565. A one-network, from-scratch few-step model that maps the interpolant’s marginal at t to the one at s < t. It is trained by matching, with MMD over groups of samples, the distributions reached from t and from a nearby r. Consistency models are its one-sample, first-moment case, and that case collapses on ImageNet. ImageNet-256 FID is 8.05 at one step and 1.99 at eight, with guidance at sampling time, so 16 evaluations. Training is 1.2M steps at batch 4,096. CIFAR-10 2-step 1.98. One run per row. | Active |
| LIT-783 | Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency | Zheng et al., Tsinghua and NVIDIA (2025), ARXIV-2510.08431. sCM made to run on 14B text-to-image and text-to-video models, with a FlashAttention-2 JVP kernel under FSDP and context parallelism. Pure sCM loses fine detail and temporal coherence there. Adding a DMD loss at weight 0.01 (rCM) fixes it. Four-step Wan2.1 VBench is 84.43 at 1.3B against a re-implemented DMD2’s 84.56, and 84.92 at 14B; GenEval tracks the teacher at 1–4 steps. The diversity advantage over DMD2 is shown in samples only. One run per row. | Active |
| LIT-784 | Mean Flows for One-step Generative Modeling | Geng, Deng, Bai, Kolter and He, CMU and MIT (2025), ARXIV-2505.13447. Train a network for the average velocity u(z, r, t) over an interval, using the identity u = v − (t − r)·du/dt with du/dt from a Jacobian-vector product and the target under stop-gradient. With r = t it is flow matching. From scratch on ImageNet-256 with DiT-XL/2 and guidance folded into the target, one-step FID is 3.43 at 240 epochs and two-step 2.20 at 1,000. The best one-step baselines it beats, Shortcut 10.60 and IMM 7.77, are copied rows at other budgets. Behind iCT on CIFAR-10. One run per row. | Active |
| LIT-787 | One Step Diffusion via Shortcut Models | Frans, Hafner, Levine and Abbeel, UC Berkeley (2024), ARXIV-2410.12557. A flow-matching network also conditioned on step size d, trained in one run: the flow-matching loss at d = 0, and a target for step 2d built from two of its own d-steps. On DiT-B at matched compute, one model gives 6.9 / 13.8 / 20.5 FID at 128 / 4 / 1 steps on CelebA-HQ-256 and 15.5 / 28.3 / 40.3 on ImageNet-256. Progressive distillation is better at one step (14.8 and 35.6) and cannot sample at many. The re-run consistency baselines are far below their published numbers. DiT-XL reaches 10.6 in one step. One run per cell. | Active |
| LIT-796 | InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation | Liu, Zhang, Ma, Peng and Liu, UT Austin and Helixon (2023), ARXIV-2309.06380. Reflow Stable Diffusion once, then distil the reflowed model to one step with an LPIPS regression. Against distilling SD 1.4 directly, at the same 100K steps and 3.2M generated pairs, reflow first gives one-step FID 31.0 against 40.9 on COCO-2017-5k and 20.0 against 34.6 on COCO-2014-30k. The scaled model, InstaFlow-0.9B, scores 23.4 and 13.10. The teacher is a diffusion model, not a rectified flow, and the distiller is a regression, not distribution matching. One run per row. | Active |