repeat_kv
Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.
repeat_kv appears in the code Syntology harvested for 244 papers, as 33 distinct code bodies found in 267 places (a place is one code body under one paper). Of the 244 papers, 242 with a sample that ran: 7 with a run with no instrument failure, 235 where every run was a failure of Syntology's instrument. 25 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 repeat_kv 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; get_code(code_sha256="…") returns this sample's fingerprint on the shared battery, with the battery's shuffled null and lift; not shown on this site (how to connect). "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.
Samples Syntology
The 33 distinct code bodies named repeat_kv: 31 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 24 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. One tile per status, in the site's fixed vocabulary, each code body counted once:
Licence is a property of each copy, so it is counted per place: 129 of the 267 places are pointer only (Syntology does not serve that copy's text); at 11 of those this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text (4 of those are in the table below, where the licence cell's tooltip gives why; the JSON twin's withheld_clause gives why for each). 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 “the contract check could not run” (RAISES, DEP_MISSING or TIMEOUT; hover a row's label for which) 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; “with no instrument failure” is honoured, violated and ran with no contract checked. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Papers
100 papers shown of 244 (newest first; the JSON twin carries all 267 places); 110 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 35 papers added by Syntology; 14 papers have no page here and are shown by their id only (arXiv: for an arXiv id; an id from another venue, such as ACL Anthology or AAAI, is named as that venue's id, never as an arXiv id). 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. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
| Paper | Date | File | Status Syntology | Licence |
|---|---|---|---|---|
| ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation added by Syntology | 2026-09 (from id) | speridlabs/eneas/eneas/vendor/SeC/inference/modeling_internlm2.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| Focus When Necessary: Adaptive Routing and Collaborative Grounding for Training-Free Visual Grounding added by Syntology | 2026-06 (from id) | TencentBAC/LazyMCoT/Qwen2.5/modeling_qwen2_5_vl_re_infer.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Models added by Syntology | 2026-06 (from id) | KQL11/Deep-VRM/Models/DeepVRM/modeling_qwen2_5_vl.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| IR3DE: A Linear Router for Large Language Models added by Syntology | 2026-06 (from id) | gensyn-ai/IR3DE/models/modeling_llama.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| 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 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 f6e0c0fc3868b787 |
ran; the contract check could not run (RAISES) fingerprinted | 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 07d6ef500d143328 |
ran; the contract check could not run (RAISES) fingerprinted | Apache-2.0 (permissive) |
| ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning added by Syntology | 2026-05 (from id) | misonsky/chunk/models/modeling_llama.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention added by Syntology | 2026-05 (from id) | fasa-org/dash-attention/dash_attn/prefill/stage2_block_selection.py 4e762613ee907cdb |
ran; the contract check could not run (RAISES) fingerprinted | BSD-3-Clause (permissive) here; the stored copy is pointer only |
| MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization added by Syntology | 2026-05 (from id) | YupengSu/MuonQ/src/models.py 7140f5aa8cd118f3 |
ran; the contract check could not run (RAISES) fingerprinted | 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/modeling_mela.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention added by Syntology | 2026-05 (from id) | flas-ai/FLAS/src/flas/model.py 0f07b44f9c18969e |
ran; the contract check could not run (RAISES) 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference added by Syntology | 2026-04 (from id) | qqtang-code/FluxAttention/fluxattn/training/eval/modeling_flash_llama.py 56fbb035393380b6 |
ran; the contract check could not run (RAISES) | MIT (permissive) |
| 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents added by Syntology | 2026-03 (from id) | 94wen94/ST-Lite/eval/attention_helpers.py 404c0af567476d50 |
ran; the contract check could not run (RAISES) fingerprinted | no licence file found · pointer only |
| MoE-Spec: Expert Budgeting for Efficient Speculative Decoding added by Syntology | 2026-02 (from id) | SafeAILab/EAGLE/eagle/modeling_eagle.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| MoE-Spec: Expert Budgeting for Efficient Speculative Decoding added by Syntology | 2026-02 (from id) | SafeAILab/EAGLE/eagle/model/cnets.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs added by Syntology | 2026-02 (from id) | hrlics/CoPE/modeling_cope.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs added by Syntology | 2026-02 (from id) | hrlics/CoPE/train/training/modeling_flash_llama_cope.py 69874376c94f0785 |
ran; the contract check could not run (RAISES) | 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/llama3_dart.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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_qwen3.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| Latent Speech-Text Transformer added by Syntology | 2025-10 (from id) | facebookresearch/lst/lst/base_transformer.py 705c70c44ddc8080 |
ran fingerprinted | licence not identified · pointer only |
| ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding added by Syntology | 2025-09 (from id) | KangJialiang/ViSpec/vispec/model/cnets.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 f6e0c0fc3868b787 |
ran; the contract check could not run (RAISES) fingerprinted | Apache-2.0 (permissive) here; the stored copy is pointer only |
| 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| arXiv:2507.23284 | 2025-07 (from id) | mlvlab/BLiM/videochat_flash/modeling_qwen2_flash.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| arXiv:2507.22424 | 2025-07 (from id) | PineTreeWss/SpecVLA/openvla/specdecoding/model/cnets.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding | 15 Jul 2025 | ShiLuohe/KV-Latent/modelcodes/modeling_llama3.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| arXiv:2507.10419 | 2025-07 (from id) | Victorletzelter/LoRA-MCL/ALMA/modeling_xalma.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning | 23 Jun 2025 | thudm/longwriter/train/patch/modeling_llama.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| video-SALMONN 2: Captioning-Enhanced Audio-Visual Large Language Models | 18 Jun 2025 | bytedance/video-salmonn-2/video_SALMONN2_pro/qwenvl/model/modeling_qwen3_vl.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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_llama.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| arXiv:2506.09351 | 2025-06 (from id) | yuchenblah/DIVE/models/llama/modeling_llama.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| Draft-based Approximate Inference for LLMs | 10 Jun 2025 | identical code first harvested elsewhere 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs | 4 Jun 2025 | the-scale-lab/AsymKV/asymkv/method/asymkv.py 56a1aae391d1d899 |
unverified | Apache-2.0 (permissive) |
| Mamba Knockout for Unraveling Factual Information Flow | 30 May 2025 | nirendy/mamba-knockout/src/experiments/knockout/llama/sdpa_attention.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction | 29 May 2025 | identical code first harvested elsewhere 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation | 28 May 2025 | arthursbianchessi/bam/models/bam.py 6d2a08dcf3466514 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| Pretraining Language Models to Ponder in Continuous Space | 27 May 2025 | identical code first harvested elsewhere 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens | 20 May 2025 | arctanxarc/unictokens/models/phi.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning | 20 May 2025 | jiwonsong-dev/reasoningpathcompression/rpc/rpc_utils.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| Multi-Token Prediction Needs Registers | 15 May 2025 | nasosger/mutor/language_modeling/src/models/llama_mutor.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| Multi-Token Prediction Needs Registers | 15 May 2025 | nasosger/mutor/language_modeling/src/models/gemma_mutor.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| Parallel Scaling Law for Language Models | 15 May 2025 | identical code first harvested elsewhere 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale | 5 May 2025 | recursal/radlads-paper/rwkv6attn.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| arXiv:2504.21403 | 2025-04 (from id) | ANDgate99/Explore-Then-Select/model/modeling_qwen2.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| ReasonIR: Training Retrievers for Reasoning Tasks | 29 Apr 2025 | identical code first harvested elsewhere 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| Efficient Reinforcement Finetuning via Adaptive Curriculum Learning | 7 Apr 2025 | uscnlp-lime/verl/verl/models/transformers/monkey_patch.py 00f0f9848c8cd16c |
ran fingerprinted | Apache-2.0 (permissive) |
| Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence | 26 Mar 2025 | identical code first harvested elsewhere 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| Mixture of Lookup Experts | 20 Mar 2025 | jieshibo/mole/modeling_mole.py ab40781baaa35b67 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling | 17 Mar 2025 | hustvl/MaTVLM/mamba2/hybrid_mamba_layer.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding | 16 Mar 2025 | sczwangxiao/video-flexreduc/retake/longvideo_cache.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression | 16 Mar 2025 | aiot-mlsys-lab/svd-llm/SVDLLM.py 25ef0712acc702e7 |
ran; the contract check could not run (RAISES) fingerprinted | Apache-2.0 (permissive) |
| FastVID: Dynamic Density Pruning for Fast Video Large Language Models | 14 Mar 2025 | identical code first harvested elsewhere 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | 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 f6e0c0fc3868b787 |
ran; the contract check could not run (RAISES) fingerprinted | Apache-2.0 (permissive) here; the stored copy is pointer only |
| Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More | 17 Feb 2025 | zichenwen1/dart/Qwen2_5-VL/Qwen2_5VL_DART/modeling_qwen2_5_vl_self.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| Implicit Language Models are RNNs: Balancing Parallelization and Expressivity | 10 Feb 2025 | microsoft/implicit_languagemodels/implicit_llm/modules/attention.py 541ba8da0f7b6512 |
ran fingerprinted | MIT (permissive) |
| LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models | 10 Feb 2025 | identical code first harvested elsewhere 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| VideoRoPE: What Makes for Good Video Rotary Position Embedding? | 7 Feb 2025 | wiselnn570/videorope/videorope_plus/v_ruler/easy_context/modeling_qwen2.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| M+: Extending MemoryLLM with Scalable Long-Term Memory | 1 Feb 2025 | identical code first harvested elsewhere 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting | 23 Jan 2025 | brotherhappy/ostquant/models/modeling_llama.py ab40781baaa35b67 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing | 23 Jan 2025 | mbzuai-oryx/geopixel/model/IXC/modeling_internlm2.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping | 11 Jan 2025 | mayank31398/ladder-residual-inference/hf_modeling_utils/modeling_llama_ladder.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | BSD-3-Clause (permissive) |
| FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models | 30 Dec 2024 | thu-nics/framefusion/framefusion/models/internvl/modeling_internlm2.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding | 29 Dec 2024 | sczwangxiao/video-retake/retake/longvideo_cache.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| 3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding | 24 Dec 2024 | cognitiveaisystems/3dgraphllm/models/modeling_llama.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| Experience of Training a 1.7B-Parameter LLaMa Model From Scratch | 17 Dec 2024 | identical code first harvested elsewhere 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| Byte Latent Transformer: Patches Scale Better Than Tokens | 13 Dec 2024 | facebookresearch/blt/bytelatent/base_transformer.py 705c70c44ddc8080 |
ran fingerprinted | no licence file found · pointer only |
| Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences | 10 Dec 2024 | alannawzadamin/clonebo/clonebo/modeling_llama.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| Cross-Self KV Cache Pruning for Efficient Vision-Language Inference | 5 Dec 2024 | identical code first harvested elsewhere 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences | 2 Dec 2024 | Hoyyyaard/LSceneLLM/models/modeling_llama.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| Scaling Particle Collision Data Analysis | 28 Nov 2024 | supersymmetry-technologies/bbt-neutron/model/modeling_binbbt.py ab40781baaa35b67 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models | 7 Nov 2024 | allenzren/open-pi-zero/src/model/utils.py 4e762613ee907cdb |
ran; the contract check could not run (RAISES) fingerprinted | MIT (permissive) here; the stored copy is pointer only |
| The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units | 4 Nov 2024 | bkhmsi/llm-localization/models/modeling_gemma.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning | 25 Oct 2024 | fyyfu/headkv/headkv/snapkv_utils.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing | 24 Oct 2024 | yangyifei729/kvsharer/internlm2_real_share/modeling_internlm2_kvsharer.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| Value Residual Learning For Alleviating Attention Concentration In Transformers | 23 Oct 2024 | Zcchill/Value-Residual-Learning/src/modeling/modeling_llama_NeuTRENO_lambda04.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| Scaling Diffusion Language Models via Adaptation from Autoregressive Models | 23 Oct 2024 | HKUNLP/DiffuLLaMA/DiffuLLaMA-training/model_llama.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction | 22 Oct 2024 | identical code first harvested elsewhere 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| MagicPIG: LSH Sampling for Efficient LLM Generation | 21 Oct 2024 | infini-ai-lab/magicpig/models/utils.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | Apache-2.0 (permissive) |
| Provable Benefits of Complex Parameterizations for Structured State Space Models | 17 Oct 2024 | alxndrTL/mamba.py/mambapy/jamba.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | MIT (permissive) |
| On the Role of Attention Heads in Large Language Model Safety | 17 Oct 2024 | ydyjya/SafetyHeadAttribution/lib/utils/custommodel.py 3c76e52815c5401d |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors | 16 Oct 2024 | weixuan-wang123/SADI/modeling_llama.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | no licence file found · pointer only |
| DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models | 15 Oct 2024 | identical code first harvested elsewhere 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| MoH: Multi-Head Attention as Mixture-of-Head Attention | 15 Oct 2024 | identical code first harvested elsewhere 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | licence of this copy not recorded |
| Subspace Optimization for Large Language Models with Convergence Guarantees | 15 Oct 2024 | pkumelon/Golore/zo-bench/modeling_llama.py 30d7eec482ebf6b1 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | GPL-3.0 (copyleft) · pointer only |
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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text. 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