DataComp-VLM benchmark shows instruction-heavy data mixing outperforms filtering for VLM training, with DCVLM-Baseline achieving 63.6% on 33 tasks for 8B models (+5.4pp over FineVision).
mega hub Mixed citations
Decoupled Weight Decay Regularization
Mixed citation behavior. Most common role is method (58%).
1169
Pith papers citing it
Method
58% of classified citations
abstract
L$_2$ regularization and weight decay regularization are equivalent for standard stochastic gradient descent (when rescaled by the learning rate), but as we demonstrate this is \emph{not} the case for adaptive gradient algorithms, such as Adam. While common implementations of these algorithms employ L$_2$ regularization (often calling it "weight decay" in what may be misleading due to the inequivalence we expose), we propose a simple modification to recover the original formulation of weight decay regularization by \emph{decoupling} the weight decay from the optimization steps taken w.r.t. the loss function. We provide empirical evidence that our proposed modification (i) decouples the optimal choice of weight decay factor from the setting of the learning rate for both standard SGD and Adam and (ii) substantially improves Adam's generalization performance, allowing it to compete with SGD with momentum on image classification datasets (on which it was previously typically outperformed by the latter). Our proposed decoupled weight decay has already been adopted by many researchers, and the community has implemented it in TensorFlow and PyTorch; the complete source code for our experiments is available at https://github.com/loshchil/AdamW-and-SGDW
hub tools
citation-role summary
method 103
background 64
dataset 5
baseline 3
other 3
citation-polarity summary
claims ledger
- abstract L$_2$ regularization and weight decay regularization are equivalent for standard stochastic gradient descent (when rescaled by the learning rate), but as we demonstrate this is \emph{not} the case for adaptive gradient algorithms, such as Adam. While common implementations of these algorithms employ L$_2$ regularization (often calling it "weight decay" in what may be misleading due to the inequivalence we expose), we propose a simple modification to recover the original formulation of weight decay regularization by \emph{decoupling} the weight decay from the optimization steps taken w.r.t. the
authors
mega hub controls
export citing contexts JSON
export graph JSON
export full bundle JSON
open full Pith review
annotated reader queued
Recognition alignment
counterfactual ablation
co-cited works
representative citing papers
Lip Forcing distills a 14B bidirectional video diffusion teacher into autoregressive students that achieve real-time lip synchronization at 31 FPS using two denoising steps without CFG.
Every9D-21M supplies 21.8M real-world 9D pose annotations for 700 everyday categories by propagating manual canonical poses through cross-instance alignment in object-centric videos and verifying them multiview.
AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
Rigel3D jointly generates rigged 3D meshes with geometry, skeleton topology, joint positions, and skinning weights using coupled surface and skeleton latent representations for image-conditioned animation-ready asset synthesis.
TrackCraft3R is the first method to repurpose a video diffusion transformer as a feed-forward dense 3D tracker via dual-latent representations and temporal RoPE alignment, achieving SOTA performance with lower compute.
A Particle Transformer jet tagger contains a sparse six-head circuit whose source-relay-readout structure recovers most performance and whose residual stream preferentially encodes 2-prong energy correlators.
IRIS-14B is the first LLM trained explicitly for GIMPLE-to-LLVM IR translation and outperforms much larger models by up to 44 percentage points on real-world C code.
Momentum-based async SGD achieves optimal convergence rates for data-dependent delays without biasing updates toward simpler samples.
CADFS supplies a large real-world CAD dataset and FeatureScript representation that, after VLM fine-tuning, produces more accurate and feature-rich designs than prior generative CAD systems.
Looped transformers with recall and outer normalization produce reachable, input-dependent fixed points with stable gradients, enabling generalization, while those without recall cannot; a new internal recall variant performs competitively or better.
CLAD is the first deep learning framework for log anomaly detection that operates directly on compressed byte streams using a dilated convolutional encoder, hybrid Transformer-mLSTM, and two-stage training, achieving 0.9909 average F1-score across five datasets.
EQ-VMamba adds rotation-equivariant cross-scan and group Mamba blocks to enforce end-to-end rotation equivariance, yielding better rotation robustness, competitive accuracy, and roughly 50% fewer parameters than non-equivariant baselines across classification, segmentation, and super-resolution.
Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
VMamba introduces a state-space vision backbone using 2D selective scanning across four routes to achieve linear complexity and strong performance on image tasks.
Grokking arises from gradual amplification of a Fourier-based circuit in the weights followed by removal of memorizing components.
An unsupervised technique extracts latent yes-no knowledge from language model activations by locating a direction that satisfies logical consistency properties, outperforming zero-shot accuracy by 4% on average across models and datasets.
Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
Decision Transformer casts RL as autoregressive sequence modeling conditioned on desired returns, past states and actions, matching or exceeding offline RL baselines on Atari, Gym and Key-to-Door tasks.
RoFormer introduces rotary position embeddings that encode absolute positions via rotation matrices and relative dependencies in attention, outperforming prior position methods on long text classification tasks.
GPT-3 shows that scaling an autoregressive language model to 175 billion parameters enables strong few-shot performance across diverse NLP tasks via in-context prompting without fine-tuning.
Introduces APRS task and PanoSeeker agent using VLM plus EgoSphere memory for active 360° search and segmentation, outperforming baselines on a new benchmark.
citing papers explorer
-
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
TrackCraft3R is the first method to repurpose a video diffusion transformer as a feed-forward dense 3D tracker via dual-latent representations and temporal RoPE alignment, achieving SOTA performance with lower compute.
-
AuraMask: An Extensible Pipeline for Developing Aesthetic Anti-Facial Recognition Image Filters
AuraMask produces 40 aesthetic anti-facial recognition filters that match or exceed prior adversarial effectiveness and achieve significantly higher user acceptance in a 630-person study.
-
PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
PointForward uses sparse world-space 3D queries and scene graphs to deliver consistent single-pass reconstruction of dynamic driving scenes via point-aligned representations.
-
Unified Modeling of Lane and Lane Topology for Driving Scene Reasoning
UniTopo unifies lane detection and topology reasoning into a single perception model, outperforming prior methods on OpenLane-V2 benchmarks with TOP_ll scores of 30.1% and 31.8%.
-
From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation
A kinematic-to-visual lifting paradigm combined with hierarchically routed control generates action-conditioned surgical videos with better faithfulness, fidelity, and efficiency.
-
SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild
SAM 3D Animal is the first promptable framework for multi-animal 3D reconstruction from single images, built on SMAL+ and trained on the new Herd3D dataset, achieving SOTA results on Animal3D, APTv2, and Animal Kingdom benchmarks.
-
SignMAE: Segmentation-Driven Self-Supervised Learning for Sign Language Recognition
SignMAE uses segmentation-driven masking in a mask-and-reconstruct self-supervised task to learn fine-grained sign representations, achieving state-of-the-art accuracy on WLASL, NMFs-CSL, and Slovo with fewer frames and modalities.
-
LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
LeapAlign fine-tunes flow matching models by constructing two consecutive leaps that skip multiple ODE steps with randomized timesteps and consistency weighting, enabling stable updates at any generation step.
-
TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
TokenGS uses learnable Gaussian tokens in an encoder-decoder architecture to regress 3D means directly, achieving SOTA feed-forward reconstruction on static and dynamic scenes with better robustness.
-
Geometrically Consistent Multi-View Scene Generation from Freehand Sketches
A framework generates consistent multi-view scenes from one freehand sketch via a ~9k-sample dataset, Parallel Camera-Aware Attention Adapters, and Sparse Correspondence Supervision Loss, outperforming baselines in realism and consistency.
-
Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding
Bridge-STG decouples spatio-temporal alignment via semantic bridging and query-guided localization modules to achieve state-of-the-art m_vIoU of 34.3 on VidSTG among MLLM methods.
-
MoRight: Motion Control Done Right
MoRight disentangles object and camera motion via canonical-view specification and temporal cross-view attention, while decomposing motion into active user-driven and passive consequence components to learn and apply causality in video generation.
-
Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training
Mem3R achieves better long-sequence 3D reconstruction by decoupling tracking and mapping with a hybrid memory of TTT-updated MLP and explicit tokens, reducing model size and trajectory errors.
-
Your Pre-trained Diffusion Model Secretly Knows Restoration
Pre-trained diffusion models inherently support image restoration that can be unlocked by optimizing prompt embeddings at the text encoder output using a diffusion bridge formulation, achieving competitive results on models like WAN and FLUX without fine-tuning.
-
InCaRPose: In-Cabin Relative Camera Pose Estimation Model and Dataset
InCaRPose is a Transformer-based model trained on synthetic data that predicts absolute metric-scale relative poses between distorted in-cabin camera views and generalizes to real images while releasing a new test dataset.
-
Deformation-based In-Context Learning for Point Cloud Understanding
DeformPIC deforms query point clouds under prompt guidance for in-context learning, outperforming prior methods with lower Chamfer Distance on reconstruction, denoising, and registration tasks.
-
Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
Pretraining on 1M wild videos followed by post-training on curated data yields high-fidelity feedforward 3D avatars that generalize across identities, clothing, and lighting with emergent relightability and loose-garment support.
-
UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes
UniGeoSeg releases the first million-scale dataset for instruction-driven remote sensing segmentation and a unified model that achieves state-of-the-art results with strong zero-shot generalization.
-
Structured 3D Latents for Scalable and Versatile 3D Generation
SLAT provides a unified 3D latent representation enabling versatile high-quality generation across multiple output formats from text or image inputs.
-
ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
ELLA introduces a timestep-aware semantic connector to link LLMs with diffusion models for improved dense prompt following, validated on a new 1K-prompt benchmark.
-
Scalable Diffusion Models with Transformers
DiTs achieve SOTA FID of 2.27 on ImageNet 256x256 by scaling transformer-based latent diffusion models, with performance improving consistently as Gflops increase.
-
Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction
CineNeuron improves fMRI-to-video reconstruction by combining bottom-up semantic enrichment with top-down Mixture-of-Memories integration and outperforms prior methods on benchmarks.
-
The Missing GAP: From Solving Square Jigsaw Puzzles to Handling Real World Archaeological Fragments
Introduces GAP datasets of synthetic heavily eroded irregular puzzle pieces modeled on archaeological fragments and PuzzleFlow, a ViT and flow-matching framework that outperforms prior jigsaw solvers on these datasets.
-
DuetFair: Coupling Inter- and Intra-Subgroup Robustness for Fair Medical Image Segmentation
DuetFair couples inter-subgroup adaptation with intra-subgroup robustness via FairDRO (dMoE plus subgroup-conditioned DRO) to boost worst-case and equity-scaled performance on medical segmentation benchmarks.
-
Noise-Started One-Step Real-World Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement
SMFSR achieves state-of-the-art perceptual quality among one-step diffusion-based real-world super-resolution methods by preserving noise-started generation via LR-conditioned SplitMeanFlow and GAN refinement.
-
Curvature-Aware Captioning:Leveraging Geodesic Attention for 3D Scene Understanding
A new framework combines self-attention on the Oblique manifold with bidirectional geodesic cross-attention on the Lorentz hyperboloid to improve both localization accuracy and descriptive coherence in 3D dense captioning.
-
L2A: Learning to Accumulate Pose History for Accurate 3D Human Pose Estimation
A new method accumulates historical pose features across layers in a Transformer network to reach state-of-the-art 3D human pose estimation accuracy.
-
Gate-and-Merge: Zero-shot Compositional Personalization of Vision Language Models
Gate-and-Merge enables zero-shot compositional personalization of VLMs by independently learning concept-specific LoRA adapters and merging them in weight space with cue-based gating to suppress interference.
-
DVD: Discrete Voxel Diffusion for 3D Generation and Editing
DVD applies discrete diffusion directly to voxel occupancy for 3D generation, uncertainty estimation via entropy, and single-round editing via block perturbation fine-tuning.
-
ICDAR 2026 Competition on Writer Identification and Pen Classification from Hand-Drawn Circles
CircleID introduces a controlled dataset of 46,155 circles from 66 writers and 8 pens, with competition results showing top accuracies of 64.8% for open-set writer identification and 92.7% for pen classification.
-
Lightweight Unpaired Smartphone ISP Transfer with Semantic Pseudo-Pairing
Semantic pseudo-pairing via DINOv2 embeddings and fused Gromov-Wasserstein optimal transport enables training a 7K-parameter CNN for unpaired smartphone ISP, achieving 22.569 PSNR on the NTIRE 2026 challenge test set.
-
DIMoE-Adapters: Dynamic Expert Evolution for Continual Learning in Vision-Language Models
DIMoE-Adapters uses self-calibrated expert evolution and prototype-guided selection to dynamically grow and allocate experts, outperforming prior continual learning methods on vision-language models.
-
Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency
Introduces Eulerian motion guidance with bidirectional geometric consistency to improve training speed and temporal quality in diffusion-based image animation.
-
Height-Guided Projection Reparameterization for Camera-LiDAR Occupancy
HiPR improves 3D occupancy prediction by reparameterizing image-to-voxel projections using LiDAR-derived height priors to adapt sampling ranges to scene sparsity and height variations.
-
Lyra 2.0: Explorable Generative 3D Worlds
Lyra 2.0 produces persistent 3D-consistent video sequences for large explorable worlds by using per-frame geometry for information routing and self-augmented training to correct temporal drift.
-
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.
-
Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models
Rein3D generates photorealistic, globally consistent 3D indoor scenes by using a restore-and-refine process where radial panoramic videos are restored via diffusion models and then used to update a 3D Gaussian field.
-
Latent-Compressed Variational Autoencoder for Video Diffusion Models
A frequency-based latent compression method for video VAEs yields higher reconstruction quality than channel-reduction baselines at fixed compression ratios.
-
SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
SpatialEdit provides a benchmark, large synthetic dataset, and baseline model for precise object and camera spatial manipulations in images, with the model beating priors on spatial editing.
-
R\'enyi Attention Entropy for Patch Pruning
Rényi entropy of attention maps serves as a tunable criterion for pruning redundant patches in vision transformers, reducing compute with preserved accuracy on image recognition.
-
An Explainable Vision-Language Model Framework with Adaptive PID-Tversky Loss for Lumbar Spinal Stenosis Diagnosis
A VLM framework with spatial patch cross-attention and adaptive PID-Tversky loss reports 90.69% classification accuracy, 0.9512 Dice score, and 92.80 CIDEr for LSS diagnosis plus automated report generation.
-
Street-Legal Physical-World Adversarial Rim for License Plates
SPAR is a street-legal physical rim that cuts modern ALPR accuracy by 60% and reaches 18% targeted impersonation while costing under $100 and requiring no plate modification.
-
PET-DINO: Unifying Visual Cues into Grounding DINO with Prompt-Enriched Training
PET-DINO unifies visual and text prompts in Grounding DINO via an alignment-friendly generation module and prompt-enriched training strategies to improve zero-shot open-set object detection.
-
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
-
Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
Stable Video Diffusion scales latent video diffusion models via text-to-image pretraining, video pretraining on curated data, and high-quality finetuning to produce competitive text-to-video and image-to-video results while enabling motion LoRA and multi-view 3D applications.
-
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
IP-Adapter adds effective image prompting to text-to-image diffusion models using a lightweight decoupled cross-attention adapter that works alongside text prompts and other controls.
-
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
HPD v2 is the largest human preference dataset for text-to-image images with 798k choices, and HPS v2 is the resulting CLIP-based scorer that better predicts human judgments and responds to model improvements.
-
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
DINO reaches 51.3 AP on COCO val2017 with a ResNet-50 backbone after 24 epochs, a +2.7 AP gain over the prior best DETR variant.
-
Frequency Adapter with SAM for Generalized Medical Image Segmentation
FSAM integrates a frequency adapter into SAM with LoRA to extract domain-invariant high-frequency features and outperforms prior domain generalization methods on fundus and prostate datasets.
-
Video Generation with Predictive Latents
PV-VAE improves video latent spaces for generation by unifying reconstruction with future-frame prediction, reporting 52% faster convergence and 34.42 FVD gain over Wan2.2 VAE on UCF101.