The upper-tail accumulation scale derived from the gap-counting function N_n sets the critical inverse temperature for softmax attention concentration, unifying prior conflicting laws as special cases of different N_n.
super hub Mixed citations
RoFormer: Enhanced Transformer with Rotary Position Embedding
Mixed citation behavior. Most common role is background (46%).
182
Pith papers citing it
Background
46% of classified citations
abstract
Position encoding recently has shown effective in the transformer architecture. It enables valuable supervision for dependency modeling between elements at different positions of the sequence. In this paper, we first investigate various methods to integrate positional information into the learning process of transformer-based language models. Then, we propose a novel method named Rotary Position Embedding(RoPE) to effectively leverage the positional information. Specifically, the proposed RoPE encodes the absolute position with a rotation matrix and meanwhile incorporates the explicit relative position dependency in self-attention formulation. Notably, RoPE enables valuable properties, including the flexibility of sequence length, decaying inter-token dependency with increasing relative distances, and the capability of equipping the linear self-attention with relative position encoding. Finally, we evaluate the enhanced transformer with rotary position embedding, also called RoFormer, on various long text classification benchmark datasets. Our experiments show that it consistently overcomes its alternatives. Furthermore, we provide a theoretical analysis to explain some experimental results. RoFormer is already integrated into Huggingface: \url{https://huggingface.co/docs/transformers/model_doc/roformer}.
hub tools
citation-role summary
background 18
method 8
baseline 1
dataset 1
citation-polarity summary
claims ledger
- abstract Position encoding recently has shown effective in the transformer architecture. It enables valuable supervision for dependency modeling between elements at different positions of the sequence. In this paper, we first investigate various methods to integrate positional information into the learning process of transformer-based language models. Then, we propose a novel method named Rotary Position Embedding(RoPE) to effectively leverage the positional information. Specifically, the proposed RoPE encodes the absolute position with a rotation matrix and meanwhile incorporates the explicit relative
authors
co-cited works
representative citing papers
RULER shows most long-context LMs drop sharply in performance on complex tasks as length and difficulty increase, with only half maintaining results at 32K tokens.
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.
Score entropy loss enables discrete diffusion models (SEDD) that cut perplexity 25-75% versus prior diffusion methods and outperform GPT-2 on language modeling while supporting infilling and compute-quality tradeoffs.
Pythia releases 16 identically trained LLMs with full checkpoints and data tools to study training dynamics, scaling, memorization, and bias in language models.
HCMS partitions multi-head attention into chunks and pipelines them across dual CUDA streams to overlap communication and computation, delivering 10-17.5% speedup over Ulysses for 31K-56K token sequences.
Set diffusion factorizes likelihood over arbitrary token sets and uses a set-causal diffusion architecture to support KV caching and any-order decoding, yielding improved speed-quality tradeoffs versus prior diffusion LMs.
RayPE extends video DiT attention with Plucker coordinates and a gated reciprocal-product term to improve 3D consistency and camera controllability.
QCFuse achieves full-prefill quality in RAG with 1.7x average prefill speedup over full prefill and 1.5x over ProphetKV via compressed query-aware cache fusion.
MimeLens uses position-agnostic BERT encoders pretrained on random-offset binary windows to output one of 125 libmagic MIME labels, beating Magika on full files and enabling accurate classification on mid-file fragments.
Orli is an autoregressive image-to-sequence model that jointly detects text lines and determines their reading order on historical documents via chord-frame baselines, trained on 196k pages across ten scripts.
MoPE replaces fixed sinusoidal or rotary positional encodings with per-dimension learned Morlet wavelets that recover prior methods as limits and add a Gaussian locality kernel, yielding a 0.119 gain on TinyShakespeare when paired with energy-gated attention.
Introduces the first large-scale GRW dataset for semantic co-speech gesture classification, word recognition, and temporal localization in unconstrained videos, along with benchmarks for the three tasks.
Autoregressive transformers exhibit measurable cognitive fatigue during extended generation, quantified by the Fatigue Index that predicts degradation (AUROC 0.95) and repetition (rho 0.94).
LaneRoPE adds an inter-sequence attention mask and extended RoPE to enable collaborative parallel sequence generation in LLMs, yielding accuracy gains on math reasoning under length limits.
Transformers trained from different random seeds exhibit residual-stream polymorphism that is exactly a uniform random rotation, which a Procrustes alignment removes to transfer SAEs and steering vectors.
Tensor Cache augments sliding-window attention with an eviction-fed outer-product associative memory and a training correction to improve long-context performance under bounded memory.
POST uses prior-observation adversarial learning on adjacency matrices to reduce spatial over-generalization in graph-based multivariate time series anomaly detection and achieves new SOTA results on detection and channel-wise localization.
MemLens benchmark shows long-context LVLMs lose accuracy with length while memory agents lose visual fidelity, with multi-session reasoning below 30% for most systems and neither approach solving the task alone.
CRePE supplies depth-aware positional distributions along curved rays for stable unified-camera control in frozen video DiT models.
Embedding Temporal Logic (ETL) performs runtime monitoring directly in learned embedding spaces using distance-based predicates composed with temporal operators, supported by conformal calibration for reliable predicate evaluation.
Chirality emerges in SMILES translation models through an abrupt encoder-centered reorganization of representations after a long plateau, identified via checkpoint analysis and ablation.
CGAD is a staleness-aware Adam variant for DiLoCo that gates gradients with cosine and exponential decay, proves a convergence bound independent of maximum delay, and demonstrates stable pretraining of 25M to 7B parameter Llama-style models across controlled delays.
Jordan-RoPE realizes a distance-modulated phase basis via non-semisimple Jordan blocks, generating features such as d e^{iωd} for relative positional encoding.
citing papers explorer
-
RULER: What's the Real Context Size of Your Long-Context Language Models?
RULER shows most long-context LMs drop sharply in performance on complex tasks as length and difficulty increase, with only half maintaining results at 32K tokens.
-
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
Pythia releases 16 identically trained LLMs with full checkpoints and data tools to study training dynamics, scaling, memorization, and bias in language models.
-
Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement
Autoregressive transformers exhibit measurable cognitive fatigue during extended generation, quantified by the Fatigue Index that predicts degradation (AUROC 0.95) and repetition (rho 0.94).
-
Detection Without Correction: A Robust Asymmetry in Activation-Based Hallucination Probing
Activation probes detect hallucinations pre-generation in large LLMs but cannot correct them via steering, with output confidence outperforming on accuracy.
-
Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs
Cascaded systems remain the most reliable for speech translation overall, but recent SpeechLLMs match or outperform them in many conditions while standalone speech models lag.
-
When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs
Thought templates derived from training traces and refined via natural-language feedback improve multi-hop reasoning performance in long-context LMs across benchmarks and can be distilled into smaller models.
-
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
DuoAttention identifies retrieval heads requiring full KV cache and streaming heads using constant-length cache to reduce memory and latency in long-context LLM inference.
-
Massive Activations in Large Language Models
Massive activations are constant large values in LLMs that function as indispensable bias terms and concentrate attention probabilities on specific tokens.
-
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
LongRoPE extends LLM context windows to 2048k tokens via search for non-uniform positional interpolation, progressive fine-tuning from 256k, and short-context readjustment.
-
PORTER: Language-Grounded Event Representations for Portable Structured EHR Foundation Models
PORTER is a language-grounded EHR foundation model that uses text descriptions for events and a numeric pathway, matching fixed-vocabulary performance on 74 tasks while recovering 97.1% AUROC on unseen vocabularies and outperforming on MIMIC.
-
Inside the LLM Word Factory
Activation patching localizes English detokenization in Llama2-7B to a two-stage attention-then-MLP process at layer 1 that generalizes to 12 models from 8 families, with depth varying by positional encoding, plus an early-layer probe achieving 0.94-0.97 AUROC.
-
AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task
AlignAtt4LLM adapts AlignAtt to decoder-only LLMs via prompt layout, head selection, and attention replay, outperforming IWSLT 2026 baselines for En-De and En-It at ~2s and <4s latency.
-
SimSD: Simple Speculative Decoding in Diffusion Language Models
SimSD adds a masking strategy to enable speculative decoding in diffusion LLMs, delivering up to 7.46x throughput gains on SDAR models while preserving generation quality.
-
Give it Space! Explicit Disentangling of Positional and Semantic Representations in Encoders
Explicitly disentangling semantic and positional streams in a Transformer encoder reveals that absolute positional representations collapse to a 2D document-structure manifold, attention heads specialize by role, and the approach improves linguistic probing performance on 49 of 65 phenomena.
-
Positional Encoding via Token-Aware Phase Attention
TAPA adds a learnable phase function to attention to preserve long-range token interactions, enabling direct continual pretraining, length extrapolation, lower perplexity, and stronger retrieval than RoPE-style methods.
-
Chameleon: Mixed-Modal Early-Fusion Foundation Models
Chameleon is an early-fusion token model that handles mixed image-text sequences for understanding and generation, achieving competitive or superior performance to larger models like Llama-2, Mixtral, and Gemini-Pro on captioning, VQA, text, and image tasks.
-
The Falcon Series of Open Language Models
Falcon-180B is a 180B-parameter open decoder-only model trained on 3.5 trillion tokens that approaches PaLM-2-Large performance at lower cost and is released with dataset extracts.
-
Llemma: An Open Language Model For Mathematics
Continued pretraining of Code Llama on Proof-Pile-2 yields Llemma, an open math-specialized LLM that beats known open base models on MATH and supports tool use plus formal proving out of the box.
-
Efficient Streaming Language Models with Attention Sinks
StreamingLLM lets finite-window LLMs generalize to infinite-length sequences by retaining initial-token KV states as attention sinks, enabling stable streaming inference up to 4M tokens.
-
YaRN: Efficient Context Window Extension of Large Language Models
YaRN extends the context window of RoPE-based LLMs like LLaMA more efficiently than prior methods, using 10x fewer tokens and 2.5x fewer steps while surpassing state-of-the-art performance and enabling extrapolation beyond fine-tuning lengths.
-
Retentive Network: A Successor to Transformer for Large Language Models
RetNet is a new sequence modeling architecture that delivers parallel training, constant-time inference, and competitive language modeling performance as a potential replacement for Transformers.
-
Textbooks Are All You Need
A 1.3B-parameter code model trained on 7B tokens of curated textbook and synthetic data achieves 50.6% on HumanEval, indicating data quality can enable strong performance at small scale.
-
GPT-NeoX-20B: An Open-Source Autoregressive Language Model
GPT-NeoX-20B is a publicly released 20B parameter autoregressive language model trained on the Pile that shows strong gains in five-shot reasoning over similarly sized prior models.
-
PaLM: Scaling Language Modeling with Pathways
PaLM 540B demonstrates continued scaling benefits by setting new few-shot SOTA results on hundreds of benchmarks and outperforming humans on BIG-bench.
-
Depth-Staggered Fibonacci Spacing for Sparse Attention: Static Schedules Beat Learned Dilation and Extrapolate Where Dense Attention Fails
Static depth-staggered Fibonacci sparse attention improves perplexity over fixed/learned variants and extrapolates to 4x context while dense attention fails.
-
MeMo: Memory as a Model
MeMo encodes new knowledge into a separate memory model that integrates with frozen LLMs, showing strong performance on QA benchmarks while avoiding catastrophic forgetting and working without access to model weights.
-
Mela: Test-Time Memory Consolidation based on Transformation Hypothesis
Mela is a Transformer variant with a dual-frequency Hierarchical Memory Module and MemStack that performs test-time memory consolidation, outperforming baselines on long contexts.
-
Working Memory Constraints Scaffold Learning in Transformers under Data Scarcity
Fixed-width and decay-based attention mechanisms inspired by working memory improve Transformer grammatical accuracy and human alignment under limited training data.
-
NVIDIA Nemotron 3: Efficient and Open Intelligence
NVIDIA releases the Nemotron 3 model family with hybrid Mamba-Transformer architecture, LatentMoE, NVFP4 training, MTP layers, and multi-environment RL post-training for reasoning and agentic tasks.
-
Lightweight Domain Adaptation of a Large Language Model for Legal Assistance in the Indian Context
An 8B Llama model with RAG and prompt engineering scores 60.08% on the All-India Bar Examination, slightly above GPT-3.5 Turbo while claiming 22 times greater parameter efficiency via a new PEI metric.
-
Continuous diffusion for categorical data
The paper proposes CDCD, a continuous-time and continuous-space diffusion framework for categorical data, and reports results on language modeling tasks.
-
Ministral 3
Ministral 3 releases 3B/8B/14B parameter-efficient language models with base, instruction, and reasoning variants derived via iterative pruning and distillation, including image understanding capabilities.
-
Multi-Model Synthetic Training for Mission-Critical Small Language Models
Fine-tunes Qwen2.5-7B on 21,543 synthetic maritime Q&A pairs generated from 3.2B AIS records by GPT-4o and o3-mini, reaching 75% accuracy at 261x lower inference cost than larger models.
-
Gemma: Open Models Based on Gemini Research and Technology
Gemma introduces open 2B and 7B LLMs derived from Gemini technology that beat comparable open models on 11 of 18 text tasks and come with safety assessments.
-
Yi: Open Foundation Models by 01.AI
Yi models are 6B and 34B open foundation models pretrained on 3.1T curated tokens that achieve strong benchmark results through data quality and targeted extensions like long context and vision alignment.
-
TinyLlama: An Open-Source Small Language Model
TinyLlama is a 1.1B-parameter open-source language model pretrained on 1 trillion tokens that outperforms other open-source models of similar size on downstream tasks.
-
Baichuan 2: Open Large-scale Language Models
Baichuan 2 presents 7B and 13B LLMs trained on 2.6T tokens that match or exceed similar open models on MMLU, CMMLU, GSM8K, HumanEval and excel in medicine and law.
-
Gemma 2: Improving Open Language Models at a Practical Size
Gemma 2 models achieve leading performance at their sizes by combining established Transformer modifications with knowledge distillation for the 2B and 9B variants.
-
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
GLM-4 models rival or exceed GPT-4 on MMLU, GSM8K, MATH, BBH, GPQA, HumanEval, IFEval, long-context tasks, and Chinese alignment while adding autonomous tool use for web, code, and image generation.
-
Large Language Models: A Survey
The paper surveys key large language models, their training methods, datasets, evaluation benchmarks, and future research directions in the field.
-
A Survey of Large Language Models
This survey reviews the background, key techniques, and evaluation methods for large language models, emphasizing emergent abilities that appear at large scales.
-
EXAONE 4.5 Technical Report
EXAONE 4.5 is a new open-weight multimodal model that matches general benchmarks and outperforms similar-scale models on document understanding and Korean contextual reasoning.
-
A Comprehensive Overview of Large Language Models
A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.
- MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation
- Selective Rotary Position Embedding
- Lessons from the Trenches on Reproducible Evaluation of Language Models