Home › Code › apply_rotary_pos_emb

apply_rotary_pos_emb

Syntologyentry name in harvested coderead from the graph 2026-09-24

apply_rotary_pos_emb appears in the code Syntology harvested for 393 papers, as 119 distinct code bodies found in 458 places (a place is one code body under one paper). At least one of them ran in 327 of the papers; 20 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named apply_rotary_pos_emb do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 71 of the 119 distinct code bodies named apply_rotary_pos_emb; 48 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

1ran · honoured contract
2ran · violated contract
21ran · our draft was wrong
23ran · fixture could not drive it
24ran
48unverified
20fingerprinted

Licence is a property of each copy, so it is counted per place: 179 of the 458 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

100 papers shown of 393 (newest first; the JSON twin carries all 458 places); 122 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 61 papers added by Syntology; 23 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation added by Syntology 2026-09 (from id) speridlabs/eneas/eneas/vendor/SeC/inference/modeling_phi3.py bac65c3dafaec040 ran · our draft was wrong Apache-2.0 (permissive)
ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation added by Syntology 2026-09 (from id) speridlabs/eneas/eneas/vendor/SeC/inference/modeling_internlm2.py 051ebcfa8673a02e unverified Apache-2.0 (permissive)
Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding added by Syntology 2026-09 (from id) qluoluo/faster-flash-decoding/ffd_core/modeling/llama.py de11bf4368235366 unverified Apache-2.0 (permissive)
FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation added by Syntology 2026-08 (from id) FireRedTeam/FireRedAudio/fireredaudio/flow/x_transformers.py 587e69a3ace67351 ran Apache-2.0 (permissive)
Decoupled Vision-Language System for Multimodal Understanding and Generation added by Syntology 2026-08 (from id) YifanXu74/Libra/libra/models/libra/modeling_libra.py 45b8a2c070efc3ed ran Apache-2.0 (permissive)
RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation added by Syntology 2026-08 (from id) RoyChao19477/RT-SEMamba/models/transformer_block.py 3a782e0711823a97 unverified licence not identified · pointer only
Cross-Subject Modeling for Widefield Calcium Imaging via Atlas-Aligned Spatiotemporal Tokenization added by Syntology 2026-07 (from id) ShanechiLab/WiCAT/wicat/models/transformer.py 4fd6fbd2e5d5a63e ran fingerprinted licence not identified · pointer only
Omni-Sleep: A Sleep Foundation Model via Hierarchical Contrastive Learning of CNS-ANS Dynamics added by Syntology 2026-07 (from id) AutoBrain-sleep/OmniSleep/src/omnisleep/models.py 0f92704bc4a6e1f6 ran · our draft was wrong fingerprinted MIT (permissive)
The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders added by Syntology 2026-06 (from id) Tiny-Snow/GenRec/src/genrec/models/model_seqrec/sasrec_sprint.py b715a071c5e5950e ran · our draft was wrong GPL-3.0 (copyleft) · pointer only
Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation added by Syntology 2026-06 (from id) PunchlineAAAA/DICE/dream/modeling_dream.py bac65c3dafaec040 ran · our draft was wrong MIT (permissive)
Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment added by Syntology 2026-06 (from id) facebookresearch/esm/esm/rotary_embedding.py 2a127d3ae372d7bd ran fingerprinted MIT (permissive)
JETSPEC: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting added by Syntology 2026-06 (from id) hao-ai-lab/JetSpec/jetspec/models/draft_head.py 517fb615df4dde0c unverified MIT (permissive)
REPAIR: Predictive Self-Supervised Representation Learning in Chess added by Syntology 2026-06 (from id) Artificial-Chrisi/RePAIR/networks.py 64e4135bdebae85b ran · fixture could not drive it fingerprinted no licence file found · pointer only
Analyzing the Correlation Between Hallucinations and Knowledge Conflicts in Large Language Models added by Syntology 2026-06 (from id) llaraspata/HallucinationDetection/src/model/LlaMa.py bac65c3dafaec040 ran · our draft was wrong no licence file found · pointer only
Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings added by Syntology 2026-06 (from id) CentreChen/EmbFilter/models/modeling_llama_lr.py bac65c3dafaec040 ran · our draft was wrong MIT (permissive)
Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings added by Syntology 2026-06 (from id) CentreChen/EmbFilter/models/modeling_mistral_lr.py 583539efd6fd01fb ran · our draft was wrong MIT (permissive)
IR3DE: A Linear Router for Large Language Models added by Syntology 2026-06 (from id) gensyn-ai/IR3DE/models/modeling_llama.py 583539efd6fd01fb ran · our draft was wrong MIT (permissive)
TreeFlash: Parallel AR-Approximation for Faster Speculative Decoding added by Syntology 2026-06 (from id) ETH-DISCO/TreeFlash/tree_flash.py cce1f5188f2264e4 unverified no licence file found · pointer only
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation added by Syntology 2026-06 (from id) SAI-Lab-NYU/DREAM-S/dream_s/model/cnets.py 9a65a30d006fc96e ran · fixture could not drive it no licence file found · pointer only
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation added by Syntology 2026-06 (from id) SAI-Lab-NYU/DREAM-S/dream_s/model/modeling_llama_kv.py bad260f6d71db00c unverified no licence file found · pointer only
Eigenvectors of Experts are Training-free Non-collapsing Routers added by Syntology 2026-05 (from id) giangdip2410/SSMoE/SSMoE/Language/SSMoE-Embedding/models/modeling_deepseek.py d61c483a3c2b3156 ran · fixture could not drive it no licence file found · pointer only
Eigenvectors of Experts are Training-free Non-collapsing Routers added by Syntology 2026-05 (from id) giangdip2410/SSMoE/SSMoE/Language/SSMoE-Embedding/models/modeling_olmoe.py bac65c3dafaec040 ran · our draft was wrong no licence file found · pointer only
Periodic RoPE for Infinite Context LLMs added by Syntology 2026-05 (from id) Cominder/miniwin/model/model_miniwin.py 41e3bef5aa57fbfa unverified Apache-2.0 (permissive)
One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs added by Syntology 2026-05 (from id) hed-ucas/Layer-wise-Learning-Rate/galore_utils/modeling_llama.py f725bc2d76076485 ran · fixture could not drive it no licence file found · pointer only
ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning added by Syntology 2026-05 (from id) misonsky/chunk/models/modeling_llama.py 0fe82a947dc39b42 ran · fixture could not drive it no licence file found · pointer only
Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era added by Syntology 2026-05 (from id) lluosi/RDB-CL/ETrain/Models/Qwen/modeling_qwen.py fbda921818ec02df unverified no licence file found · pointer only
One Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer added by Syntology 2026-05 (from id) juchengshen/air/models/air/air_1net_L2x_H2x_input_token_prepend.py 99138bc8ae291d5f unverified Apache-2.0 (permissive)
Mela: Test-Time Memory Consolidation based on Transformation Hypothesis added by Syntology 2026-05 (from id) Musubi-ai/Mela/mela/model/commons.py 583539efd6fd01fb ran · our draft was wrong Apache-2.0 (permissive)
SynerMedGen: Synergizing Medical Multimodal Understanding with Generation via Task Alignment added by Syntology 2026-05 (from id) piooip/SynerMedGen/modeling/bagel/siglip_navit.py 4102c144078044c7 ran Apache-2.0 (permissive)
TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis added by Syntology 2026-04 (from id) xiaomi-research/tts-prism/models/mimo_audio_tokenizer/modeling_rope_utils.py 80d3a54eab8134eb unverified Apache-2.0 (permissive)
GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion added by Syntology 2026-04 (from id) mikumifa/GS-Quant/codebook/rqvae.py b0bb9cd4b9fd6357 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
R 2 -dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction added by Syntology 2026-04 (from id) GATECH-EIC/R2-dLLM/dream/model/modeling_dream.py ac6507e437413e71 unverified no licence file found · pointer only
DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference added by Syntology 2026-04 (from id) X-Xia0828/DepCap/dream/model/modeling_dream.py ac6507e437413e71 unverified no licence file found · pointer only
Gumbel Distillation for Parallel Text Generation added by Syntology 2026-03 (from id) hxixixh/gumbel-distill/models/dit_gumbel.py 2700f6838f384546 unverified no licence file found · pointer only
Learning Transferable Sensor Models via Language-Informed Pretraining added by Syntology 2026-03 (from id) yuc0805/SLIP/modeling_slip.py 6ab251ef16ca3891 unverified no licence file found · pointer only
SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization SERQ: SALIENCY-AWARE LOW-RANK ERROR RECONSTRUCTION FOR LLM QUANTIZATION added by Syntology 2026-03 (from id) acalabys/SERQ/modeling/modeling_llama.py bac65c3dafaec040 ran · our draft was wrong no licence file found · pointer only
SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization SERQ: SALIENCY-AWARE LOW-RANK ERROR RECONSTRUCTION FOR LLM QUANTIZATION added by Syntology 2026-03 (from id) acalabys/SERQ/modeling/modeling_gemma3.py 583539efd6fd01fb ran · our draft was wrong no licence file found · pointer only
SR-TTT Does Not Learn Retrieval: A Correction and Mechanistic Post-Mortem of Surprisal-Aware Residual Test-Time Training added by Syntology 2026-03 (from id) swamynathanvp/Surprisal-Aware-Residual-Test-Time-Training/sr_ttt_fixed.py e96c58f6ba701d7c unverified MIT (permissive)
SR-TTT Does Not Learn Retrieval: A Correction and Mechanistic Post-Mortem of Surprisal-Aware Residual Test-Time Training added by Syntology 2026-03 (from id) swamynathanvp/Surprisal-Aware-Residual-Test-Time-Training/sr_ttt_kaggle.py db4420e92850c6d0 unverified MIT (permissive)
SR-TTT Does Not Learn Retrieval: A Correction and Mechanistic Post-Mortem of Surprisal-Aware Residual Test-Time Training added by Syntology 2026-03 (from id) swamynathanvp/Surprisal-Aware-Residual-Test-Time-Training/sr_ttt_v2.py 42256aaa3ae587e2 unverified MIT (permissive)
Stacked from One: Multi-Scale Self-Injection for Context Window Extension added by Syntology 2026-03 (from id) Clement25/SharedLLM/modeling/modeling_llama_sharedllm_flash.py f725bc2d76076485 ran · fixture could not drive it no licence file found · pointer only
Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement added by Syntology 26 Feb 2026 SHUCHENZHU/LITE/peft_pretraining/modeling_llama.py f725bc2d76076485 ran · fixture could not drive it no licence file found · pointer only
Large Causal Models for Temporal Causal Discovery added by Syntology 2026-02 (from id) kougioulis/LCM/lcm_pytorch/models/misc/RotaryEmbedding.py 045feff71ed98d11 unverified Apache-2.0 (permissive)
MoE-Spec: Expert Budgeting for Efficient Speculative Decoding added by Syntology 2026-02 (from id) SafeAILab/EAGLE/eagle/modeling_eagle.py f725bc2d76076485 ran · fixture could not drive it no licence file found · pointer only
Doc-to-LoRA: Learning to Instantly Internalize Contexts added by Syntology 2026-02 (from id) SakanaAI/doc-to-lora/src/ctx_to_lora/modeling/text_to_lora.py 22f75dc2bea7b46e ran · our draft was wrong fingerprinted MIT (permissive)
DAWN: Dependency-Aware Fast Inference for Diffusion LLMs added by Syntology 2026-02 (from id) lizhuo-luo/DAWN/dream/model/modeling_dream.py ac6507e437413e71 unverified MIT (permissive)
CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs added by Syntology 2026-02 (from id) hrlics/CoPE/modeling_cope.py bac65c3dafaec040 ran · our draft was wrong no licence file found · pointer only
Audio ControlNet for Fine-Grained Audio Generation and Editing added by Syntology 2026-02 (from id) haidog-yaqub/EzAudio/src/models/controlnet.py 206c90f5d5d477d1 ran · fixture could not drive it fingerprinted MIT (permissive)
LLM4Fluid: Large Language Models as Generalizable Neural Solvers for Fluid Dynamics added by Syntology 29 Jan 2026 BaratiLab/FactFormer/libs/factorization_module.py c3acddf93e491a49 ran · our draft was wrong MIT (permissive)
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention added by Syntology 2026-01 (from id) thunlp/APB/experiments_apb/APB/modeling_llama_locret.py e12c6e1855e9fbe0 ran · our draft was wrong fingerprinted no licence file found · pointer only
DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference added by Syntology 2026-01 (from id) fvliang/DART/dart/model/modeling_mixtral_kv.py d61c483a3c2b3156 ran · fixture could not drive it Apache-2.0 (permissive)
DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference added by Syntology 2026-01 (from id) fvliang/DART/dart/model/modeling_qwen3_kv.py 583539efd6fd01fb ran · our draft was wrong Apache-2.0 (permissive)
DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference added by Syntology 2026-01 (from id) fvliang/DART/dart/model/llama3_dart.py a93e62ca7757414c unverified Apache-2.0 (permissive)
DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference added by Syntology 2026-01 (from id) fvliang/DART/dart/model/modeling_llama_kv.py eee34413e2bccab6 unverified Apache-2.0 (permissive)
VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding added by Syntology 2026-01 (from id) ziHoHe/VidLaDA/train/llada_v_prepare/files/modeling_llada.py bac65c3dafaec040 ran · our draft was wrong Apache-2.0 (permissive)
Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers added by Syntology 2026-01 (from id) LCM-Lab/Elastic-Attention/elasticattn/src/model_utils.py 583539efd6fd01fb ran · our draft was wrong Apache-2.0 (permissive)
MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification added by Syntology 2026-01 (from id) 5SSjw/MARS/mars/model/cnets1.py f725bc2d76076485 ran · fixture could not drive it MIT (permissive)
MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification added by Syntology 2026-01 (from id) 5SSjw/MARS/mars/model/cnets.py 9a65a30d006fc96e ran · fixture could not drive it MIT (permissive)
MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification added by Syntology 2026-01 (from id) 5SSjw/MARS/mars/model/modeling_llama_kv.py eee34413e2bccab6 unverified MIT (permissive)
UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation added by Syntology 2026-01 (from id) ZrH42/UniX/modeling/unix/siglip_navit.py 4102c144078044c7 ran MIT (permissive)
STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning added by Syntology 2026-01 (from id) LingFengGold/STReasoner/base_model/Config-Qwen2.5-14B-Instruct/modeling_qwen2.py d61c483a3c2b3156 ran · fixture could not drive it MIT (permissive)
FOAM: Blocked State Folding for Memory-Efficient LLM Training added by Syntology 2025-12 (from id) zqOuO/FOAM/peft_pretraining/modeling_llama.py f725bc2d76076485 ran · fixture could not drive it no licence file found · pointer only
Few-shot Protein Fitness Prediction via In-context Learning and Test-time Training added by Syntology 2025-12 (from id) fteufel/PRIMO/primo/zero_shot_utils/modeling_progen.py 2f6618868885e7ca ran · fixture could not drive it no licence file found · pointer only
LiveStar: Live Streaming Assistant for Real-World Online Video Understanding added by Syntology 2025-11 (from id) yzy-bupt/LiveStar/inference/modeling_livestar_llm.py 051ebcfa8673a02e unverified no licence file found · pointer only
IG-Pruning: Input-Guided Block Pruning for Large Language Models added by Syntology 2025-11 (from id) ictnlp/IG-Pruning/src/models/dsr_modeling_llama.py bac65c3dafaec040 ran · our draft was wrong no licence file found · pointer only
Information-Theoretic Discrete Diffusion added by Syntology 2025-10 (from id) Dongjae0324/infodis/model/rotary.py b3c9c4aebf03fa97 unverified no licence file found · pointer only
Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs added by Syntology 2025-10 (from id) LiuJinzhe-Keepgoing/NMKE/modeling_llama.py bac65c3dafaec040 ran · our draft was wrong no licence file found · pointer only
Sparser Block-Sparse Attention via Token Permutation added by Syntology 2025-10 (from id) xinghaow99/pbs-attn/pbs_attn/patch/huggingface.py de11bf4368235366 unverified no licence file found · pointer only
MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization added by Syntology 2025-10 (from id) pkumelon/MeCeFO/peft_pretraining/modeling_llama.py 9a65a30d006fc96e ran · fixture could not drive it Apache-2.0 (permissive)
Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model added by Syntology 2025-10 (from id) RuipingL/Situat3DChange/SCReasoner/model/transformers.py 9a65a30d006fc96e ran · fixture could not drive it CC-BY-4.0 · pointer only
Towards Generalizable PDE Dynamics Forecasting via Physics-Guided Invariant Learning added by Syntology 2025-09 (from id) LSY-Cython/iMOOE/models/framework.py f1c3b8a106802591 ran · our draft was wrong no licence file found · pointer only
ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding added by Syntology 2025-09 (from id) KangJialiang/ViSpec/vispec/model/modeling_mixtral_kv.py d61c483a3c2b3156 ran · fixture could not drive it Apache-2.0 (permissive)
ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding added by Syntology 2025-09 (from id) KangJialiang/ViSpec/vispec/model/cnets.py 9a65a30d006fc96e ran · fixture could not drive it Apache-2.0 (permissive)
ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding added by Syntology 2025-09 (from id) KangJialiang/ViSpec/vispec/model/modeling_llama_kv.py bad260f6d71db00c unverified Apache-2.0 (permissive)
Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision added by Syntology 2025-08 (from id) Fr0zenCrane/UniCoT/modeling/qwen2/modeling_qwen2.py bac65c3dafaec040 ran · our draft was wrong Apache-2.0 (permissive)
Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision added by Syntology 2025-08 (from id) Fr0zenCrane/UniCoT/modeling/bagel/siglip_navit.py 4102c144078044c7 ran Apache-2.0 (permissive)
arXiv:2507.23284 2025-07 (from id) mlvlab/BLiM/videochat_flash/modeling_qwen2_flash.py d61c483a3c2b3156 ran · fixture could not drive it MIT (permissive)
arXiv:2507.22424 2025-07 (from id) PineTreeWss/SpecVLA/openvla/specdecoding/model/modeling_mixtral_kv.py d61c483a3c2b3156 ran · fixture could not drive it MIT (permissive)
arXiv:2507.22424 2025-07 (from id) PineTreeWss/SpecVLA/openvla/specdecoding/model/cnets.py f725bc2d76076485 ran · fixture could not drive it MIT (permissive)
arXiv:2507.22424 2025-07 (from id) PineTreeWss/SpecVLA/openvla/specdecoding/model/modeling_llama_kv.py eee34413e2bccab6 unverified MIT (permissive)
arXiv:2507.17539 2025-07 (from id) MeteorElf/FundusExpert/src/internvl_chat/internvl/patch/llama2_flash_attn_monkey_patch.py 3408dd47e939d760 unverified Apache-2.0 (permissive)
arXiv:2507.10419 2025-07 (from id) Victorletzelter/LoRA-MCL/ALMA/modeling_xalma.py bac65c3dafaec040 ran · our draft was wrong Apache-2.0 (permissive)
arXiv:2507.01299 2025-07 (from id) alibaba/EfficientAI/larosa/inference/modeling_llama_larosa.py bac65c3dafaec040 ran · our draft was wrong Apache-2.0 (permissive)
Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models 25 Jun 2025 thecommonirin/qresafe/quant-with-ft/models/modeling_llama_quant.py f725bc2d76076485 ran · fixture could not drive it no licence file found · pointer only
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning 23 Jun 2025 thudm/longwriter/train/patch/modeling_llama.py bac65c3dafaec040 ran · our draft was wrong Apache-2.0 (permissive)
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning 23 Jun 2025 thudm/longwriter/train/patch/modeling_chatglm.py 5cfeaee89a75c5ff ran · fixture could not drive it Apache-2.0 (permissive)
Show-o2: Improved Native Unified Multimodal Models 18 Jun 2025 showlab/Show-o/show-o2/models/modules.py bac65c3dafaec040 ran · our draft was wrong Apache-2.0 (permissive)
Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking 11 Jun 2025 princeton-pli/QRHead/src/qrretriever/custom_modeling_qwen2.py d61c483a3c2b3156 ran · fixture could not drive it MIT (permissive)
Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking 11 Jun 2025 princeton-pli/QRHead/src/qrretriever/custom_modeling_llama.py bac65c3dafaec040 ran · our draft was wrong MIT (permissive)
arXiv:2506.09351 2025-06 (from id) yuchenblah/DIVE/models/llama/modeling_llama.py bac65c3dafaec040 ran · our draft was wrong Apache-2.0 (permissive)
dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching 17 May 2025 maomaocun/dLLM-cache/dllm_cache/hooks/cache_hook_LLaDA_V.py ebbbedae1f60f76d unverified Apache-2.0 (permissive)
Pretraining Language Models to Ponder in Continuous Space 27 May 2025 identical code first harvested elsewhere bac65c3dafaec040 ran · our draft was wrong licence of this copy not recorded
Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation 24 May 2025 ashaba1in/smoothie/model/score_estimator.py a4f77e43ad34dc66 unverified no licence file found · pointer only
Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation 22 May 2025 ruizheliUOA/ARC_JSD/llm_models/modeling_gemma2.py bac65c3dafaec040 ran · our draft was wrong MIT (permissive)
Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning 22 May 2025 jiaruzouu/transformercopilot/src/Decoder_Only/copilot/modeling_flax_llama.py a1b46b3f84e76f6a ran · honoured contract fingerprinted MIT (permissive)
Emerging Properties in Unified Multimodal Pretraining 20 May 2025 neverbiasu/ComfyUI-BAGEL/modeling/bagel/siglip_navit.py 4102c144078044c7 ran Apache-2.0 (permissive)
UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens 20 May 2025 arctanxarc/unictokens/models/phi.py d61c483a3c2b3156 ran · fixture could not drive it Apache-2.0 (permissive)
VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation 20 May 2025 opengvlab/videochat-flash/llava-train_videochat/llava/model/language_model/modeling_qwen2_flash.py d61c483a3c2b3156 ran · fixture could not drive it MIT (permissive)
Multi-Token Prediction Needs Registers 15 May 2025 nasosger/mutor/language_modeling/src/models/llama_mutor.py bac65c3dafaec040 ran · our draft was wrong MIT (permissive)
Multi-Token Prediction Needs Registers 15 May 2025 nasosger/mutor/language_modeling/src/models/gemma_mutor.py 583539efd6fd01fb ran · our draft was wrong MIT (permissive)
Parallel Scaling Law for Language Models 15 May 2025 identical code first harvested elsewhere 583539efd6fd01fb ran · our draft was wrong licence of this copy not recorded
Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free 10 May 2025 qiuzh20/gated_attention/modeling_qwen3.py bac65c3dafaec040 ran · our draft was wrong MIT (permissive)
RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale 5 May 2025 recursal/radlads-paper/rwkv6qwen2/modeling_rwkv6qwen2.py bac65c3dafaec040 ran · our draft was wrong Apache-2.0 (permissive)
RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale 5 May 2025 recursal/radlads-paper/models/qwen2.py 67e215883a9a54b6 unverified Apache-2.0 (permissive)
arXiv:2504.21403 2025-04 (from id) ANDgate99/Explore-Then-Select/model/modeling_qwen2.py d61c483a3c2b3156 ran · fixture could not drive it MIT (permissive)
ReasonIR: Training Retrievers for Reasoning Tasks 29 Apr 2025 identical code first harvested elsewhere bac65c3dafaec040 ran · our draft was wrong licence of this copy not recorded
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos 24 Apr 2025 renshuhuai-andy/timechat/timechat/models/modeling_llama.py d61c483a3c2b3156 ran · fixture could not drive it BSD-3-Clause (permissive)
Why do LLMs attend to the first token? 3 Apr 2025 zzmtsvv/ad-gta/src/nn/memeff_rope_fn.py e8f6d785640a6346 unverified Apache-2.0 (permissive)
Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence 26 Mar 2025 identical code first harvested elsewhere 0fe82a947dc39b42 ran · fixture could not drive it licence of this copy not recorded
Scaling Vision Pre-Training to 4K Resolution 25 Mar 2025 efficient-large-model/vila/llava/eval/vision_niah_vila/zigzag_ring_attn/modeling_qwen2.py 5d81bffdb6022427 unverified Apache-2.0 (permissive)
Mixture of Lookup Experts 20 Mar 2025 jieshibo/mole/modeling_mole.py fc2a2c4d5dc6bf94 unverified MIT (permissive)
MP-GUI: Modality Perception with MLLMs for GUI Understanding 18 Mar 2025 BigTaige/MP-GUI/model/internvl/patch/llama2_flash_attn_monkey_patch.py 3408dd47e939d760 unverified MIT (permissive)
SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression 16 Mar 2025 aiot-mlsys-lab/svd-llm/SVDLLM.py af9e30f5a1fe133e ran · fixture could not drive it Apache-2.0 (permissive)
FastVID: Dynamic Density Pruning for Fast Video Large Language Models 14 Mar 2025 identical code first harvested elsewhere bac65c3dafaec040 ran · our draft was wrong licence of this copy not recorded
TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models 13 Mar 2025 shawntan86/tokencarve/TokenCarve/modeling_llama.py d61c483a3c2b3156 ran · fixture could not drive it Apache-2.0 (permissive)
Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding 13 Mar 2025 AMD-AIG-AIMA/Gumiho/gumiho/model/cnets.py 9a65a30d006fc96e ran · fixture could not drive it Apache-2.0 (permissive)
Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding 13 Mar 2025 AMD-AIG-AIMA/Gumiho/gumiho/model/modeling_llama_kv.py bad260f6d71db00c unverified Apache-2.0 (permissive)
Language-Enhanced Representation Learning for Single-Cell Transcriptomics 12 Mar 2025 identical code first harvested elsewhere 9b4dff79d5e6102c ran · fixture could not drive it licence of this copy not recorded
Implicit Reasoning in Transformers is Reasoning through Shortcuts 10 Mar 2025 TianheL/LM-Implicit-Reasoning/src/model/modeling_gpt2_rope.py be41b9c696d434d2 unverified MIT (permissive)
ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration 10 Mar 2025 idea-isail-lab-uiuc/resmoe/mixtral/resmoe_mixtral/modeling_mixtral.py d61c483a3c2b3156 ran · fixture could not drive it MIT (permissive)
Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas 3 Mar 2025 shiqichen17/AdaptVis/model_zoo/llama/modeling_llama.py 373a7df152e5a1a5 ran · our draft was wrong fingerprinted no licence file found · pointer only
FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference 28 Feb 2025 bytedance/FlexPrefill/flex_prefill/modules/glm/glm_self_attention_foward.py 059a805ecbeca6af unverified Apache-2.0 (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections