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.
super hub Mixed citations
GLU Variants Improve Transformer
Mixed citation behavior. Most common role is background (47%).
209
Pith papers citing it
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
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.
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.
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 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.
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 improves precipitation nowcasting via coarse multi-source Vision Mamba fusion followed by residual conditional diffusion refinement.
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.
GeoFlowVLM learns joint distributions of l2-normalized VLM embeddings on the product hypersphere via Riemannian flow matching to expose both aleatoric and epistemic uncertainty through derived entropy and typicality scores.
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.
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.
Temporarily reducing the learning rate on upper-layer query and key projections during early GPT pretraining prevents premature attention specialization and improves model performance.
Chirality emerges in SMILES translation models through an abrupt encoder-centered reorganization of representations after a long plateau, identified via checkpoint analysis and ablation.
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.
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 fixed finite feedforward neural network definable in an o-minimal structure has finite sample complexity in the agnostic PAC setting.
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.
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.
A single end-to-end Transformer model unifies stellar labels from heterogeneous spectroscopic surveys into a self-consistent scale without post-hoc recalibration.
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 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.
citing papers explorer
-
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.
-
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.
-
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.
-
$\phi$-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.
-
GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding
GeoFlowVLM learns joint distributions of l2-normalized VLM embeddings on the product hypersphere via Riemannian flow matching to expose both aleatoric and epistemic uncertainty through derived entropy and typicality scores.
-
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.
-
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.
-
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.
-
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.
-
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.
-
Screening Is Enough
Multiscreen replaces softmax attention with screening to provide absolute query-key relevance, resulting in models with 30% fewer parameters that maintain stable performance at long contexts.
-
NEST: Nested Event Stream Transformer for Sequences of Multisets
NEST is a nested transformer for sequences of multisets that uses masked set modeling to learn improved set-level representations from hierarchical event streams like EHRs.
-
Deep Delta Learning
Deep Delta Learning replaces additive residual updates with a gated delta-rule that selectively overwrites residual content along learned directions, improving language modeling quality over standard ResNet-style accumulation.
-
Less is More: Recursive Reasoning with Tiny Networks
TRM with 7M parameters achieves 45% accuracy on ARC-AGI-1 and 8% on ARC-AGI-2, surpassing most LLMs with under 0.01% of their parameters.
-
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
A recurrent-depth architecture enables language models to improve reasoning performance by iterating computation in latent space, achieving gains equivalent to much larger models on benchmarks.
-
Improving Dictionary Learning with Gated Sparse Autoencoders
Gated SAEs decouple which features to use from how large their activations should be, applying the L1 penalty only to selection and thereby eliminating shrinkage while halving the number of firing features needed for good fidelity.
-
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
GaLore performs full-parameter LLM training with up to 65.5% less optimizer memory by projecting gradients onto a low-rank subspace at each step, matching full-rank performance on LLaMA pre-training and RoBERTa fine-tuning.
-
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Griffin hybrid model matches Llama-2 performance while trained on over 6 times fewer tokens and offers lower inference latency with higher throughput.
-
Contribution Weights: A Geometrical Analysis of Self-Attention Transformers
Contribution Weights combine attention, value magnitude, and directional alignment to measure token influence more faithfully than attention alone, and show attention sinks actively suppress information via a convex sink-rate to output-norm relationship.
-
STAP: A Shuffle-Tokenized App Predictor with Ultra Long Context for Vocabulary-Free Mobile App Prediction
A Transformer model with app-identity shuffling and ultra-long context achieves vocabulary-free next-app prediction with cross-dataset zero-shot capability and competitive cold-start performance.
-
Complete-muE: Optimal Hyperparameter Transfer and Scaling for MoE Models
Complete-muE combines active-width μP and activated-expert scaling to transfer hyperparameters across dense FFN, dense MoE, and sparse MoE while covering changes in experts, capacity, width, depth, batch size, and duration.
-
Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation
RankElastor mitigates embedding collapse via spectrum-robust token mixing and GLU-based P-FFNs, yielding better performance and scaling on industrial recommendation datasets.
-
Most Transformer Modifications Still Do Not Transfer at 1-3B: A 2020-2026 Update to Narang et al. (2021) with Downstream Evaluation and a Noise Floor
Empirical update to prior work shows most of 20 recent Transformer modifications do not transfer at 1-3B scales when measured with downstream CLIMB-12 tasks, multi-seed noise floor, and cross-scale stability.
-
Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility
SP-KV trains a utility predictor jointly with the LLM to dynamically prune low-utility KV cache entries, achieving 3-10x memory reduction during generation with negligible performance loss.
-
BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization
BROS achieves memory-efficient single-loop stochastic bilevel optimization with O(ε^{-2}) sample complexity by performing updates in randomized subspaces and using Rademacher bi-probe correction for unbiased estimation.
-
Sparse Layers are Critical to Scaling Looped Language Models
Looped MoE models scale better than standard transformers because different experts activate on each loop pass, recovering expressivity without extra parameters, and support superior early exits.
-
Revisiting Transformer Layer Parameterization Through Causal Energy Minimization
CEM recasts Transformer layers as energy minimization steps, enabling constrained parameterizations like weight sharing and low-rank interactions that match standard baselines in 100M-scale language modeling.
-
Echo: KV-Cache-Free Associative Recall with Spectral Koopman Operators
Spectral Koopman operators let SSMs achieve 100% accuracy on long-gap multi-query associative recall with fixed memory, where pure Mamba fails.
-
Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting
Tyche achieves competitive probabilistic weather forecasting skill and calibration using a single-step flow model with JVP-regularized training and rollout finetuning.
-
UniPool: A Globally Shared Expert Pool for Mixture-of-Experts
A shared global expert pool in MoE improves validation loss over per-layer experts and allows sublinear expert-parameter growth with depth.
-
Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less
Full finetuning with the pretraining optimizer reduces forgetting compared to other optimizers or LoRA while achieving comparable new-task performance.
-
The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity
Attention sinks arise from variance discrepancy in self-attention value aggregation, amplified by super neurons and first-token dimension disparity, and can be mitigated by head-wise RMSNorm to accelerate pre-training convergence.
-
Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant
Cumulative-goodness Forward-Forward networks exhibit layer free-riding where discrimination gradients decay exponentially with prior positive margins; per-block, hardness-gated, and depth-scaled remedies yield 4-45x better layer separation but <1% accuracy change on CIFAR and Tiny ImageNet.
-
Adaptive Inverted-Index Routing for Granular Mixtures-of-Experts
AIR-MoE introduces a two-stage inverted-index routing method based on vector quantization that approximates optimal expert selection for granular MoE models at lower cost and with empirical performance gains.
-
Geometric Monomial (GEM): a family of rational 2N-differentiable activation functions
GEM is a new family of C^{2N}-smooth rational activation functions with variants that achieve performance on par with or exceeding GELU on ResNet, GPT-2, and BERT benchmarks.
-
C-voting: Confidence-Based Test-Time Voting without Explicit Energy Functions
C-voting improves recurrent reasoning models by selecting among multiple latent trajectories the one with highest average top-1 probability, achieving 4.9% better Sudoku-hard accuracy than energy-based voting and outperforming HRM on Sudoku-extreme and Maze when paired with the new ItrSA++ model.
-
ARCS: Autoregressive Circuit Synthesis with Topology-Aware Graph Attention and Spec Conditioning
ARCS generates valid SPICE-simulatable analog circuits in milliseconds via graph VAE, flow-matching, and GRPO reinforcement learning, reaching 99.9% validity with 8 evaluations across 32 topologies.
-
Rethinking Language Model Scaling under Transferable Hypersphere Optimization
HyperP transfers optimal learning rates across model width, depth, tokens, and MoE granularity under Frobenius-sphere constraints, delivering stable scaling and 1.58x efficiency gains.
-
FluidFlow: a flow-matching generative model for fluid dynamics surrogates on unstructured meshes
FluidFlow uses conditional flow-matching with U-Net and DiT architectures to predict pressure and friction coefficients on airfoils and 3D aircraft meshes, outperforming MLP baselines with better generalization.
-
Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers
Attention sinks induce gradient sinks under causal masking, with massive activations serving as adaptive RMSNorm regulators that attenuate localized gradient pressure in Transformer training.
-
M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling
M²RNN achieves perfect state tracking at unseen lengths and outperforms Gated DeltaNet hybrids by 0.4-0.5 perplexity on 7B models with 3x smaller recurrent states.
-
SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm
SiameseNorm is a two-stream architecture that reconciles Pre-Norm and Post-Norm in Transformers by coupling streams via shared residual blocks, yielding performance gains with maintained stability on language, vision, and diffusion models.
-
Vision-LLMs for Spatiotemporal Traffic Forecasting
ST-Vision-LLM reframes spatiotemporal traffic forecasting as vision-language fusion, using visual encoders on traffic grids and efficient numerical tokenization to achieve 15.6% better long-term accuracy and 30% gains in few-shot cross-domain settings.
-
From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill
Layered prefill replaces token-chunked prefill with layer-group interleaving in MoE models, cutting TTFT by up to 70%, end-to-end latency by 41%, and per-token energy by 22% while preserving stall-free TBT.
-
mGRADE: Minimal Recurrent Gating Meets Delay Convolutions for Lightweight Sequence Modeling
mGRADE uses learnable-spaced convolutions shown to be equivalent to delay embeddings plus a lightweight gated recurrent component to achieve low-memory multi-timescale sequence modeling.
-
LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
LLaDA-V is a diffusion-based multimodal large language model that reaches competitive or state-of-the-art results on visual instruction tasks while using a non-autoregressive architecture.
-
FlashNorm: Fast Normalization for Transformers
FlashNorm is an exact algebraic reformulation of RMSNorm plus linear projection that folds weights and defers normalization to allow parallel execution, plus scale-invariance simplifications that remove redundant norms in certain architectures.
-
DataComp-LM: In search of the next generation of training sets for language models
DCLM-Baseline dataset lets a 7B model reach 64% 5-shot MMLU accuracy after 2.6T tokens, beating prior open-data models by 6.6 points on MMLU with 40% less compute.