FSN achieves lower validation loss (1.5953) than a RoPE-SwiGLU transformer (1.611) on character-level tasks at 1M parameters by implementing next-token prediction as synchronization frustrated by data transitions.
super hub Mixed citations
GLU Variants Improve Transformer
Mixed citation behavior. Most common role is background (47%).
307
Pith papers citing it
20
external citations · Pith
Background
47% of classified citations
abstract
Gated Linear Units (arXiv:1612.08083) consist of the component-wise product of two linear projections, one of which is first passed through a sigmoid function. Variations on GLU are possible, using different nonlinear (or even linear) functions in place of sigmoid. We test these variants in the feed-forward sublayers of the Transformer (arXiv:1706.03762) sequence-to-sequence model, and find that some of them yield quality improvements over the typically-used ReLU or GELU activations.
hub tools
citation-role summary
background 30
method 24
dataset 2
extension 1
citation-polarity summary
claims ledger
- abstract Gated Linear Units (arXiv:1612.08083) consist of the component-wise product of two linear projections, one of which is first passed through a sigmoid function. Variations on GLU are possible, using different nonlinear (or even linear) functions in place of sigmoid. We test these variants in the feed-forward sublayers of the Transformer (arXiv:1706.03762) sequence-to-sequence model, and find that some of them yield quality improvements over the typically-used ReLU or GELU activations.
authors
co-cited works
representative citing papers
Hard-attention Transformers with W parameters and depth L have VC dimension Θ(WL log(TW)); teacher forcing is sample-optimal for chain-of-thought learning.
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.
Test-time training with KV binding reduces to learned linear attention.
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.
Mamba is a linear-time sequence model using input-dependent selective SSMs that achieves SOTA results across modalities and matches twice-larger Transformers on language modeling with 5x higher inference throughput.
Active lifting of data distributions via latent-sequence sampling and max-rate uncertainty reduction formally derives slow-thinking LLMs and places them on representation and sampler hierarchies that can be climbed.
A joint discrete–continuous flow-matching model designs open-vocabulary multilayer optical coatings from query-time n/k curves and spectra, validated on 224 tasks and four fabricated coolers.
A 5B-parameter latent diffusion model generates real-time four-player Rocket League matches conditioned on all players' actions, staying stable far beyond its training horizon.
A transformer-based diffusion model learns the joint distribution of convergence maps and cosmology from log-normal weak lensing simulations and generates calibrated posterior samples matching MCMC results.
DTM-Codec achieves better reconstruction quality and intelligibility than fixed-frame-rate neural speech codecs at matched total bitrate via dynamic token masking and Path Length Equalization for variable frame rates.
MLVC transmits entropy scale parameters via the hyperprior so that neural video decoding stays deterministic across different NPU vendors, achieving >70% BD-rate (MOS) gains over hardware HEVC in video-conferencing tests.
PRA approximates sequential rollout training in parallel for pixel-space AR models via intermediate states and a pixel decoder, achieving FID 2.58 (135M params) and 1.94 (511M params) on ImageNet-1K 256x256, new SOTA among pixel-space AR models.
MEET is a new equivariant transformer backbone that achieves linear memory scaling for full-atom peptide generation and improves quality over prior methods.
Tapered Language Models monotonically decrease MLP width across depth with a cosine schedule, yielding better perplexity and downstream performance than uniform-width baselines across multiple architectures and scales at no extra cost.
MADField is a multi-fidelity amortized model for predicting density fields to improve accuracy and speed of adsorption calculations in nanoporous materials for high-throughput screening.
A 1.3B-parameter rectified flow transformer is the first generative foundation model for chest radiograph synthesis at billion-parameter scale, producing images indistinguishable from real ones to experts.
FoundCause is a transformer-based amortized model for causal graph discovery that explicitly models latent confounders via learnable tokens and reports better performance than prior methods on 15 real-world datasets.
AttentionCap, a customized Transformer, predicts capacitance matrices across multiple process nodes with 0.67% self-capacitance and 3.99% coupling error on unseen designs, outperforming CNN baselines in accuracy and speed.
Stateful visual encoders condition each visual representation on prior features, yielding consistent gains on multi-image tasks under supervised finetuning across model sizes and domains.
A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.
SubFit enables better LLM compression by fitting residual bypasses to non-contiguously selected submodules, outperforming layer-granularity baselines in accuracy-perplexity trade-offs at 12.5-37.5% sparsity.
mRNAutilus generates full-length therapeutic mRNAs via diffusion models and multi-objective guidance, achieving over 400-fold expression gains for luciferase and outperforming baselines for Spike and other targets in zero-shot tests.
Introduces Chess-World-Model benchmark from 10M chess games showing recurrent models (SLiCE, Mamba-3, Gated DeltaNet) outperform Transformers on exact state tracking, with random-play split remaining hard at larger scales.
citing papers explorer
-
Attention as Frustrated Synchronization
FSN achieves lower validation loss (1.5953) than a RoPE-SwiGLU transformer (1.611) on character-level tasks at 1M parameters by implementing next-token prediction as synchronization frustrated by data transitions.
-
Tight Sample Complexity of Transformers
Hard-attention Transformers with W parameters and depth L have VC dimension Θ(WL log(TW)); teacher forcing is sample-optimal for chain-of-thought learning.
-
CLAD: Efficient Log Anomaly Detection Directly on Compressed Representations
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.
-
Test-Time Training with KV Binding Is Secretly Linear Attention
Test-time training with KV binding reduces to learned linear attention.
-
Large Language Diffusion Models
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.
-
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Mamba is a linear-time sequence model using input-dependent selective SSMs that achieves SOTA results across modalities and matches twice-larger Transformers on language modeling with 5x higher inference throughput.
-
A First-Principles Theory of Slow Thinking and Active Perception
Active lifting of data distributions via latent-sequence sampling and max-rate uncertainty reduction formally derives slow-thinking LLMs and places them on representation and sampler hierarchies that can be climbed.
-
Joint Discrete-Continuous Flow Matching for Open-Vocabulary Inverse Design of Multilayer Optical Coatings
A joint discrete–continuous flow-matching model designs open-vocabulary multilayer optical coatings from query-time n/k curves and spectra, validated on 224 tasks and four fabricated coolers.
-
Multiplayer Interactive World Models with Representation Autoencoders
A 5B-parameter latent diffusion model generates real-time four-player Rocket League matches conditioned on all players' actions, staying stable far beyond its training horizon.
-
Joint inference of weak lensing convergence map and cosmology with diffusion models
A transformer-based diffusion model learns the joint distribution of convergence maps and cosmology from log-normal weak lensing simulations and generates calibrated posterior samples matching MCMC results.
-
DTM-Codec: Dynamic Token Masking for VFR Speech Coding with Efficient Boundary Selection
DTM-Codec achieves better reconstruction quality and intelligibility than fixed-frame-rate neural speech codecs at matched total bitrate via dynamic token masking and Path Length Equalization for variable frame rates.
-
MLVC: Multi-platform Learned Video Codec for Real-World Deployment
MLVC transmits entropy scale parameters via the hyperprior so that neural video decoding stays deterministic across different NPU vendors, achieving >70% BD-rate (MOS) gains over hardware HEVC in video-conferencing tests.
-
Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
PRA approximates sequential rollout training in parallel for pixel-space AR models via intermediate states and a pixel decoder, achieving FID 2.58 (135M params) and 1.94 (511M params) on ImageNet-1K 256x256, new SOTA among pixel-space AR models.
-
Scalable Peptide Design via Memory-Efficient Equivariant Transformer
MEET is a new equivariant transformer backbone that achieves linear memory scaling for full-atom peptide generation and improves quality over prior methods.
-
Tapered Language Models
Tapered Language Models monotonically decrease MLP width across depth with a cosine schedule, yielding better perplexity and downstream performance than uniform-width baselines across multiple architectures and scales at no extra cost.
-
MADField: Multi-fidelity Amortized Density Field for Adsorption in Nanoporous Materials
MADField is a multi-fidelity amortized model for predicting density fields to improve accuracy and speed of adsorption calculations in nanoporous materials for high-throughput screening.
-
Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformers
A 1.3B-parameter rectified flow transformer is the first generative foundation model for chest radiograph synthesis at billion-parameter scale, producing images indistinguishable from real ones to experts.
-
FoundCause: Causal Discovery with Latent Confounders from Observational Data
FoundCause is a transformer-based amortized model for causal graph discovery that explicitly models latent confounders via learnable tokens and reports better performance than prior methods on 15 real-world datasets.
-
AttentionCap: Transformer Based Capacitance Matrix Learning Toward Full-Chip Extraction
AttentionCap, a customized Transformer, predicts capacitance matrices across multiple process nodes with 0.67% self-capacitance and 3.99% coupling error on unseen designs, outperforming CNN baselines in accuracy and speed.
-
Stateful Visual Encoders for Vision-Language Models
Stateful visual encoders condition each visual representation on prior features, yielding consistent gains on multi-image tasks under supervised finetuning across model sizes and domains.
-
Diffusing in the Right Space: A Systematic Study of Latent Diffusability
A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.
-
From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression
SubFit enables better LLM compression by fitting residual bypasses to non-contiguously selected submodules, outperforming layer-granularity baselines in accuracy-perplexity trade-offs at 12.5-37.5% sparsity.
-
mRNAutilus: Multi-Objective-Guided Discrete Generation of mRNA with Optimized Therapeutic Properties
mRNAutilus generates full-length therapeutic mRNAs via diffusion models and multi-objective guidance, achieving over 400-fold expression gains for luciferase and outperforming baselines for Spike and other targets in zero-shot tests.
-
Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences
Introduces Chess-World-Model benchmark from 10M chess games showing recurrent models (SLiCE, Mamba-3, Gated DeltaNet) outperform Transformers on exact state tracking, with random-play split remaining hard at larger scales.
-
An In-Vitro Study on Cross-Lingual Generalization in Language Models
An in-vitro study with synthetic languages finds cross-lingual transfer depends more on tokenization preserving reusable substructure than on lexical similarity or balance, with transfer emerging in stages.
-
Forgotten Words: Benchmarking NeoBERT for Dementia Detection in Low-Resource Conversational Filipino and English Speech
Bilingual fine-tuning on a new parallel Filipino-English dementia dataset yields Macro-F1 scores of 0.969-0.973 and eliminates cross-lingual degradation for all tested transformers.
-
MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning
MuCRASP prunes VLMs in a CoT-aware manner, outperforming baselines by preserving reasoning quality at 30-50% compression rates on models like Qwen2.5-VL-7B.
-
Disentangling Generation and Regression in Stochastic Interpolants for Controllable Image Restoration
DiSI disentangles stochastic interpolants into separate generation and regression paths, allowing controllable transitions between regression and generative image restoration with a unified few-step sampler.
-
StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video
StableHand introduces a quality-aware flow matching framework conditioned on predicted four-channel per-frame hand observation quality to estimate dual-hand world-space motion from egocentric video, achieving SOTA results with 20-25% W-MPJPE reduction on HOT3D and ARCTIC benchmarks.
-
$\phi$-Balancing for Mixture-of-Experts Training
φ-balancing is a convex optimization method for population-level expert balance in MoE training that derives an online EMA adjustment and outperforms heuristic baselines.
-
VMU-Diff: A Coarse-to-fine Multi-source Data Fusion Framework for Precipitation Nowcasting
VMU-Diff improves precipitation nowcasting via coarse multi-source Vision Mamba fusion followed by residual conditional diffusion refinement.
-
Parallel Scan Recurrent Neural Quantum States for Scalable Variational Monte Carlo
PSR-NQS makes recurrent neural quantum states scalable for variational Monte Carlo by using parallel scan recurrence, reaching accurate results on 52x52 two-dimensional lattices.
-
Neural Statistical Functions
Neural statistical functions use prefix statistics to unify and directly predict statistical quantities over continuous ranges from pre-trained single-sample models without repeated sampling.
-
Locking Pretrained Weights via Deep Low-Rank Residual Distillation
DLR-Lock locks open-weight LLMs against unauthorized fine-tuning by swapping MLPs for deep low-rank residual networks that inflate backprop memory and complicate optimization, yet preserve original capabilities via module-wise distillation.
-
Learning Less Is More: Premature Upper-Layer Attention Specialization Hurts Language Model Pretraining
Temporarily reducing the learning rate on upper-layer query and key projections during early GPT pretraining prevents premature attention specialization and improves model performance.
-
From Syntax to Semantics: Unveiling the Emergence of Chirality in SMILES Translation Models
Chirality emerges in SMILES translation models through an abrupt encoder-centered reorganization of representations after a long plateau, identified via checkpoint analysis and ablation.
-
Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech
GibbsTTS combines a training-free kinetic-optimal scheduler with finite-step moment correction in MI-DFM to deliver top naturalness and strong speaker similarity in zero-shot TTS.
-
Fast Byte Latent Transformer
BLT-D, BLT-S, and BLT-DV use block-wise diffusion training and speculative verification to enable parallel byte generation in byte-level LMs, cutting memory-bandwidth cost by over 50%.
-
Every Feedforward Neural Network Definable in an o-Minimal Structure Has Finite Sample Complexity
Every fixed finite feedforward neural network definable in an o-minimal structure has finite sample complexity in the agnostic PAC setting.
-
Degradation-Aware Adaptive Context Gating for Unified Image Restoration
DACG-IR adds a lightweight degradation-aware module that generates prompts to adaptively gate attention temperature, output features, and spatial-channel fusion in an encoder-decoder network for unified image restoration.
-
Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting
LeGS turns density control in 3D Gaussian Splatting into a learnable RL policy whose reward is derived from a closed-form sensitivity analysis that measures each Gaussian's marginal contribution to reconstruction quality.
-
Homogeneous Stellar Parameters from Heterogeneous Spectra with Deep Learning
A single end-to-end Transformer model unifies stellar labels from heterogeneous spectroscopic surveys into a self-consistent scale without post-hoc recalibration.
-
Can an MLP Absorb Its Own Skip Connection?
Skip-connected MLPs and residual-free MLPs of equal width represent generically disjoint function classes for common activations, with explicit impossibility proofs and a non-generic absorption condition for ReLU and GELU.
-
WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images
WildSplatter jointly learns 3D Gaussians and appearance embeddings from unconstrained photo collections to enable fast feed-forward reconstruction and flexible lighting control in 3D Gaussian Splatting.
-
Grokking of Diffusion Models: Case Study on Modular Addition
Diffusion models show grokking on modular addition by composing periodic operand representations in simple data regimes or by separating arithmetic computation from visual denoising across timesteps in varied regimes.
-
Scalable Model-Based Clustering with Sequential Monte Carlo
A memory-efficient SMC clustering method decomposes problems into approximately independent subproblems to handle large-scale online clustering with complex distributions.
-
Mamba Sequence Modeling meets Model Predictive Control
Mamba-MPC stabilizes and tracks references on SISO and MIMO systems in simulation and hardware while outperforming LSTM-MPC with faster computation.
-
MIXAR: Scaling Autoregressive Pixel-based Language Models to Multiple Languages and Scripts
MIXAR is the first autoregressive pixel-based language model for eight languages and scripts, with empirical gains on multilingual tasks, robustness to unseen languages, and further improvements when scaled to 0.5B parameters.
-
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
The first survey on Attention Sink in Transformers structures the literature around fundamental utilization, mechanistic interpretation, and strategic mitigation.
-
Envisioning the Future, One Step at a Time
An autoregressive diffusion model on sparse point trajectories predicts multi-modal future scene dynamics from single images with orders-of-magnitude faster sampling than dense video simulators while matching accuracy.