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.
super hub
Attention Is All You Need
156 Pith papers cite this work. Polarity classification is still indexing.
156
Pith papers citing it
abstract
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.
hub tools
citation-role summary
background 2
citation-polarity summary
claims ledger
- abstract The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the W
co-cited works
fields
cs.LG 31 cs.CL 23 cs.CV 20 cs.AI 9 cs.SE 9 cs.DC 8 cs.CR 5 astro-ph.GA 4 astro-ph.IM 3 cs.RO 3roles
background 2polarities
background 2representative citing papers
Tessera performs kernel-granularity disaggregation on heterogeneous GPUs, achieving up to 2.3x throughput and 1.6x cost efficiency gains for large model inference while generalizing beyond prior methods.
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.
Neural networks exhibit grokking on small algorithmic datasets, achieving perfect generalization well after overfitting.
Reformer matches standard Transformer accuracy on long sequences while using far less memory and running faster via LSH attention and reversible residual layers.
The BiLT autoencoder recovers absorption and scattering spectra from integrating sphere data with high accuracy while remaining robust to wavelength shifts up to 10 bands and generalizing to different instrument line shapes without retraining.
A liveness-based Bellman operator enables conservative offline policy evaluation for manipulation tasks by encoding task progression and reducing truncation bias from finite horizons.
Dingo-Pop uses a transformer to perform amortized, end-to-end population inference from GW strain data in seconds, bypassing per-event Monte Carlo sampling.
A new annotated dataset of zebrafish embryo image sequences enables a spatiotemporal transformer to classify fertility at 98% accuracy and detect compound-induced malformations at 92% accuracy.
PCT replaces softmax token competition with a smooth phase-preserving gate on normalized complex similarities, yielding stronger generalization on long-range and phase-sensitive benchmarks than both real and complex Transformers.
Chirality emerges in SMILES translation models through an abrupt encoder-centered reorganization of representations after a long plateau, identified via checkpoint analysis and ablation.
Merlin generates CodeQL queries from natural language questions via RAG-based iteration and a self-test technique using assistive queries, achieving 3.8x higher task accuracy and 31% less completion time in user studies while finding additional software issues.
Dooly reduces LLM inference profiling costs by 56.4% via configuration-agnostic taint-based labeling and selective database reuse, delivering simulation accuracy within 5% MAPE for TTFT and 8% for TPOT across 12 models.
A new neural quantum state ansatz for bosons in the grand canonical ensemble achieves competitive variational energies in 1D and 2D systems and provides access to one-body reduced density matrices.
A Dutch BERT model encodes gender linearly by epoch 20 but does not dynamically update its representations when explicit female cues contradict learned stereotypical associations in short sentence templates.
TSCG compiles JSON tool schemas into token-efficient structured text, raising tool-use accuracy for small LLMs from 0% to 84.4% on benchmarks while cutting tokens by 52-57%.
The paper introduces the VODA setting for domain adaptation from scratch using vision-language models and presents TS-DRD, which achieves competitive performance on standard benchmarks without source models.
EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.
Transformers reconstruct the constituent RCFTs in tensor-product theories from low-energy spectra, reaching 98% accuracy on WZW models and generalizing to larger central charges with few out-of-domain examples.
A single end-to-end Transformer model unifies stellar labels from heterogeneous spectroscopic surveys into a self-consistent scale without post-hoc recalibration.
Influpaint uses generative diffusion models on image-encoded influenza data to produce realistic and diverse epidemic trajectories that match leading ensemble methods in accuracy.
Physics-informed transformer with sin^2(theta) encoding, physics-aware positional encoding, multi-task decoder, and three-stage curriculum classifies powder diffraction into 99 extinction groups, with structured errors on symmetry subgroup hierarchy.
Oracle Noise optimizes diffusion model noise on a Riemannian hypersphere guided by key prompt words to preserve the Gaussian prior, eliminate norm inflation, and achieve faster semantic alignment than Euclidean methods.
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
citing papers explorer
-
Dissecting Jet-Tagger Through Mechanistic Interpretability
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.
-
Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation
Tessera performs kernel-granularity disaggregation on heterogeneous GPUs, achieving up to 2.3x throughput and 1.6x cost efficiency gains for large model inference while generalizing beyond prior methods.
-
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.
-
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
Neural networks exhibit grokking on small algorithmic datasets, achieving perfect generalization well after overfitting.
-
Reformer: The Efficient Transformer
Reformer matches standard Transformer accuracy on long sequences while using far less memory and running faster via LSH attention and reversible residual layers.
-
Bin Latent Transformer (BiLT): A shift-invariant autoencoder for calibration-free spectral unmixing of turbid media
The BiLT autoencoder recovers absorption and scattering spectra from integrating sphere data with high accuracy while remaining robust to wavelength shifts up to 10 bands and generalizing to different instrument line shapes without retraining.
-
Offline Policy Evaluation for Manipulation Policies via Discounted Liveness Formulation
A liveness-based Bellman operator enables conservative offline policy evaluation for manipulation tasks by encoding task progression and reducing truncation bias from finite horizons.
-
End-to-End Population Inference from Gravitational-Wave Strain using Transformers
Dingo-Pop uses a transformer to perform amortized, end-to-end population inference from GW strain data in seconds, bypassing per-event Monte Carlo sampling.
-
Automated Detection of Abnormalities in Zebrafish Development
A new annotated dataset of zebrafish embryo image sequences enables a spatiotemporal transformer to classify fertility at 98% accuracy and detect compound-induced malformations at 92% accuracy.
-
Complex-Valued Phase-Coherent Transformer
PCT replaces softmax token competition with a smooth phase-preserving gate on normalized complex similarities, yielding stronger generalization on long-range and phase-sensitive benchmarks than both real and complex Transformers.
-
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.
-
Generating Complex Code Analyzers from Natural Language Questions
Merlin generates CodeQL queries from natural language questions via RAG-based iteration and a self-test technique using assistive queries, achieving 3.8x higher task accuracy and 31% less completion time in user studies while finding additional software issues.
-
Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation
Dooly reduces LLM inference profiling costs by 56.4% via configuration-agnostic taint-based labeling and selective database reuse, delivering simulation accuracy within 5% MAPE for TTFT and 8% for TPOT across 12 models.
-
Neural network quantum states in the grand canonical ensemble
A new neural quantum state ansatz for bosons in the grand canonical ensemble achieves competitive variational energies in 1D and 2D systems and provides access to one-body reduced density matrices.
-
Is She Even Relevant? When BERT Ignores Explicit Gender Cues
A Dutch BERT model encodes gender linearly by epoch 20 but does not dynamically update its representations when explicit female cues contradict learned stereotypical associations in short sentence templates.
-
TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments
TSCG compiles JSON tool schemas into token-efficient structured text, raising tool-use accuracy for small LLMs from 0% to 84.4% on benchmarks while cutting tokens by 52-57%.
-
Rethinking the Need for Source Models: Source-Free Domain Adaptation from Scratch Guided by a Vision-Language Model
The paper introduces the VODA setting for domain adaptation from scratch using vision-language models and presents TS-DRD, which achieves competitive performance on standard benchmarks without source models.
-
Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks
EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.
-
Reconstructing conformal field theoretical compositions with Transformers
Transformers reconstruct the constituent RCFTs in tensor-product theories from low-energy spectra, reaching 98% accuracy on WZW models and generalizing to larger central charges with few out-of-domain examples.
-
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.
-
Generative diffusion models for spatiotemporal influenza forecasting
Influpaint uses generative diffusion models on image-encoded influenza data to produce realistic and diverse epidemic trajectories that match leading ensemble methods in accuracy.
-
Attention Is Not All You Need for Diffraction
Physics-informed transformer with sin^2(theta) encoding, physics-aware positional encoding, multi-task decoder, and three-stage curriculum classifies powder diffraction into 99 extinction groups, with structured errors on symmetry subgroup hierarchy.
-
Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization
Oracle Noise optimizes diffusion model noise on a Riemannian hypersphere guided by key prompt words to preserve the Gaussian prior, eliminate norm inflation, and achieve faster semantic alignment than Euclidean methods.
-
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
-
EgoMAGIC- An Egocentric Video Field Medicine Dataset for Training Perception Algorithms
EgoMAGIC is a new public egocentric video dataset of medical tasks with object labels for 124 items and action detection baselines reaching 0.526 mAP on eight tasks.
-
Masked-Token Prediction for Anomaly Detection at the Large Hadron Collider
The work demonstrates masked-token prediction with transformers for model-independent anomaly detection in LHC data, achieving strong results on top-rich BSM signatures like four-top production using VQ-VAE tokenization.
-
Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining
Multilingual pretraining develops translation in two phases: early copying driven by surface similarities, followed by generalizing mechanisms while copying is refined.
-
Working Memory in a Recurrent Spiking Neural Networks With Heterogeneous Synaptic Delays
A recurrent SNN with heterogeneous synaptic delays (D=41) achieves perfect F1=1.0 recall of 16 arbitrary spike patterns on a synthetic benchmark by representing them as chains of overlapping spiking motifs.
-
Dual Triangle Attention: Effective Bidirectional Attention Without Positional Embeddings
Dual Triangle Attention achieves effective bidirectional attention with built-in positional inductive bias via dual triangular masks, outperforming standard bidirectional attention on position-sensitive tasks and showing strong masked language modeling results with or without positional embeddings.
-
The UNDO Flip-Flop: A Controlled Probe for Reversible Semantic State Management in State Space Model
Mamba-2 models fail to learn reversible state retrieval in the UNDO Flip-Flop task, defaulting to a toggle heuristic and achieving only 41% accuracy under adversarial conditions.
-
Joint Fullband-Subband Modeling for High-Resolution SingFake Detection
A joint fullband-subband model using high-resolution 44.1 kHz audio outperforms standard 16 kHz detectors for singing voice deepfake detection by exploiting spectrum-specific synthesis artifacts.
-
Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents
PTR framework profiles a workflow upfront then executes it deterministically with bounded verification and repair, limiting LM calls to 2-3 while outperforming ReAct in 16 of 24 tested configurations.
-
Fusion and Alignment Enhancement with Large Language Models for Tail-item Sequential Recommendation
FAERec fuses collaborative ID embeddings with LLM semantic embeddings using adaptive gating and dual-level alignment to enhance tail-item sequential recommendations.
-
Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy
LLMs display clear performance stratification on formal language tasks aligned with Chomsky hierarchy complexity levels, limited by severe efficiency barriers rather than absolute capability.
-
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.
-
Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
Low-cost imprecise robots achieve 80-90% success on six fine bimanual manipulation tasks using imitation learning with a new Action Chunking with Transformers algorithm trained on only 10 minutes of demonstrations.
-
LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
LLM.int8() performs 8-bit inference for transformers up to 175B parameters with no accuracy loss by combining vector-wise quantization for most features with 16-bit mixed-precision handling of systematic outlier dimensions.
-
Hierarchical Text-Conditional Image Generation with CLIP Latents
A hierarchical prior-decoder model using CLIP latents generates more diverse text-conditional images than direct methods while preserving photorealism and caption fidelity.
-
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
A 3.5-billion-parameter diffusion model with classifier-free guidance generates images preferred over DALL-E by human raters and can be fine-tuned for text-guided inpainting.
-
Diffusion Models Beat GANs on Image Synthesis
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.
-
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
Intra-layer model parallelism in PyTorch enables training of 8.3B-parameter transformers, achieving SOTA perplexity of 10.8 on WikiText103 and 66.5% accuracy on LAMBADA.
-
SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing
SentencePiece trains subword models directly from raw text to enable language-independent neural text processing.
-
Graph Attention Networks
Graph Attention Networks compute learnable attention coefficients over node neighborhoods to produce weighted feature aggregations, achieving state-of-the-art results on citation networks and inductive protein-protein interaction graphs.
-
Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models
TABOM models inference unmasking preferences as a Boltzmann distribution over predictive entropies and derives a ranking loss to align DLM training with observed trajectories, yielding gains in new domains and reduced catastrophic forgetting versus standard SFT.
-
ShardTensor: Domain Parallelism for Scientific Machine Learning
ShardTensor is a domain-parallelism system for SciML that enables flexible scaling of extreme-resolution spatial datasets by removing the constraint of batch size one per device.
-
MambaNetBurst: Direct Byte-level Network Traffic Classification without Tokenization or Pretraining
A compact Mamba-2 model performs end-to-end byte-level network traffic classification without tokenization or pre-training and remains competitive with substantially larger pre-trained systems.
-
Quantum Injection Pathways for Implicit Graph Neural Networks
Independent quantum signal injection into graph DEQs yields higher test accuracy and fewer solver iterations than state-dependent or backbone-dependent injection and classical equilibrium models on NCI1, PROTEINS, and MUTAG benchmarks.
-
Investigating Anisotropy in Visual Grounding under Controlled Counterfactual Perturbations
Controlled counterfactual perturbations reveal no correlation between embedding cosine similarity and approximation behavior in two visual grounding models.
-
Structured Recurrent Mixers for Massively Parallelized Sequence Generation
Structured Recurrent Mixers enable algebraic switching between parallel training and recurrent inference representations, delivering higher efficiency, information capacity, and throughput than other linear-complexity models.
-
GRASP -- Graph-Based Anomaly Detection Through Self-Supervised Classification
GRASP detects anomalies in system provenance graphs via self-supervised executable prediction from two-hop neighborhoods, outperforming prior PIDS on DARPA datasets by identifying all documented attacks where behaviors are learnable plus additional unlabeled suspicious activity.