Home › Code › collate_fn

collate_fn

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

collate_fn appears in the code Syntology harvested for 500 papers, as 384 distinct code bodies found in 551 places (a place is one code body under one paper). At least one of them ran in 285 of the papers; 11 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 collate_fn 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 172 of the 384 distinct code bodies named collate_fn; 212 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

6ran · honoured contract
1ran · violated contract
42ran · our draft was wrong
1ran · fixture could not drive it
122ran
212unverified
11fingerprinted

Licence is a property of each copy, so it is counted per place: 181 of the 551 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 500 (newest first; the JSON twin carries all 551 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 42 papers added by Syntology; 44 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
Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM added by Syntology 2026-09 (from id) zxp555/ACFT_MM26/ACFT/llava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong no licence file found · pointer only
SemPOI-RL: Aligning LLM Semantic Reasoning for Interpretable Out-of-Town POI Sequential Generation added by Syntology 2026-08 (from id) Wind-Flipped/SemPOI-RL/code/utils.py 57a8d6752075da4a unverified no licence file found · pointer only
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers added by Syntology 2026-08 (from id) chidaksh/spurious_mitigator/src/civil_comments/causal_verify_api.py cf80248c006d1518 ran no licence file found · pointer only
DIVE: Dynamic Iterative Visual Evidence Construction for Efficient Vision-Language Models added by Syntology 2026-08 (from id) Zhong-Chenchen/DIVE/llava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong Apache-2.0 (permissive)
MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation added by Syntology 2026-07 (from id) opendatalab/MLLM-DataEngine/LLaVA/llava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong Apache-2.0 (permissive)
Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study added by Syntology 2026-07 (from id) otanl/microground/src/micro_ground/data.py 0c88aff7f7d23d35 ran MIT (permissive)
CBD: API-Only LLM Black-Box Unlearning through Controlled Behavioral Divergence added by Syntology 2026-06 (from id) DGL-codes/CBD/uld/tofuutil/data_module.py cdd171f20cd6f53d ran MIT (permissive)
Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets? added by Syntology 2026-06 (from id) lin-zhao-resoLve/D3HR/generation/dit_inversion_save_statistic.py 6fc038f89ff59f28 ran · our draft was wrong no licence file found · pointer only
CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning added by Syntology 2026-05 (from id) zhyzmath/CurveRL/recipe/sppo/sppo_ray_trainer.py a67c1dea604c8a67 unverified Apache-2.0 (permissive)
DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models added by Syntology 2026-05 (from id) CityU-MLO/DualOptimPlus/dataset/data_module.py cdd171f20cd6f53d ran no licence file found · pointer only
DeCoR: Design and Control Co-Optimization for Urban Streets Using Reinforcement Learning added by Syntology 2026-05 (from id) poudel-bibek/DeCoR/ppo/ppo_utils.py b42728badf61b2c7 ran MIT (permissive)
Full-Spectrum Graph Neural Networks: Expressive and Scalable added by Syntology 2026-05 (from id) xwangxshi/FSpecGNN/Hom-Cycle-count/main.count.py 7a01234c5af0c132 unverified no licence file found · pointer only
PRIME: Protein Representation via Physics-Informed Multiscale Equivariant Hierarchies added by Syntology 2026-05 (from id) HySonLab/PRIME/plm_baseline.py 890ccf93ef063709 ran MIT (permissive)
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL added by Syntology 2026-04 (from id) XIAO4579/PRISM/moe/dense_model/train_dense_vl_warmup.py d36fc4b002a2590e ran MIT (permissive)
OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Manner added by Syntology 2026-04 (from id) atrijhy/OFA-Diffusion_Compression/sd/train_ofa.py ffb5e3f9fdba1308 unverified no licence file found · pointer only
Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions added by Syntology 2026-04 (from id) zhangwenhao6/PERA/dataset/dataset_hg.py 66cc6da5838e8cf0 unverified licence not identified · pointer only
Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions added by Syntology 2026-04 (from id) zhangwenhao6/PERA/dataset/dataset_hg_combined.py 44b91c3044f0042b unverified licence not identified · pointer only
Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation added by Syntology 2026-04 (from id) qingyue2014/Rsum/dataloader.py afea9beadf818cbd unverified no licence file found · pointer only
Reproduction Beyond Benchmarks: ConstBERT and ColBERT-v2 Across Backends and Query Distributions added by Syntology 2026-04 (from id) utshabkg/multi-vector-reproducibility/experiments/10_finetune_constbert_tot.py 5e70a0d689a286bb unverified no licence file found · pointer only
ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery added by Syntology 2026-03 (from id) gaow0007/ATSPrivacy/benchmark/cifar100_attack.py 50b843f4577cb9e7 unverified MIT (permissive)
Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping added by Syntology 2026-03 (from id) LzyFischer/REdit/src/get_dataset_math.py 30bcd3b2a291a41d unverified no licence file found · pointer only
CRISP: Compressed Reasoning via Iterative Self-Policy Distillation added by Syntology 2026-03 (from id) HJSang/OPSD_Reasoning_Compression/workspace/src/self_distill_hybrid/sd_dataset.py e100d95c89946352 unverified no licence file found · pointer only
SaFeR-ToolKit: Structured Reasoning via Virtual Tool Calling for Multimodal Safety added by Syntology 2026-03 (from id) hiyouga/EasyR1/verl/utils/dataset.py 6dabc7804e03b1d0 unverified Apache-2.0 (permissive)
LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards added by Syntology 2026-03 (from id) real-absolute-AI/LongRLVR/recipe/dapo/longrl_reward_manager.py 78baa936d52b4277 unverified no licence file found · pointer only
HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit added by Syntology 2026-02 (from id) EIT-NLP/HiDrop/llava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong Apache-2.0 (permissive)
RegionRoute: Regional Style Transfer with Diffusion Model added by Syntology 2026-02 (from id) bwchen05/RegionRoute/training/lora.py dcbeeb19dbf60ca2 unverified no licence file found · pointer only
Agent-Omit: Adaptive Context Omission for Efficient LLM Agents added by Syntology 2026-02 (from id) usail-hkust/Agent-Omit/AgentOmit-RL/verl/utils/agent_dataset/rl_dataset.py ecd75498a47b0cf1 unverified no licence file found · pointer only
TTCS: Test-Time Curriculum Synthesis for Self-Evolving added by Syntology 2026-01 (from id) XMUDeepLIT/TTCS/src/Challenger_dataset.py b8d8d572aa0f7ad9 unverified no licence file found · pointer only
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning added by Syntology 2026-01 (from id) meituan/MemOCR/recurrent/generation_manager.py f2a7d1d12a2a2a8d unverified Apache-2.0 (permissive)
Mind the Shift: Using Delta SSL Embeddings to Enhance Child ASR added by Syntology 2026-01 (from id) Zilai-WANG/Delta-Embedding-Fusion/embed_fusion/data.py fbe00a78b6430e96 unverified no licence file found · pointer only
Contrastive Language-Image Mamba Pretraining added by Syntology 2026-01 (from id) NimrodShabtay/CLIMP/eval_nocaps.py f52bda65e1c22ab1 unverified no licence file found · pointer only
A General Neural Backbone for Mixed-Integer Linear Optimization via Dual Attention added by Syntology 2026-01 (from id) hpx2024/Dual-Attention/02.Element-Level/2_train.py f55c31d782e48ffb ran · honoured contract fingerprinted no licence file found · pointer only
CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval added by Syntology 2026-01 (from id) qzp2018/CSMCIR/src/data_utils_csmcir.py b6c1f837e6faaeba ran · honoured contract fingerprinted no licence file found · pointer only
Evaluating the Diagnostic Classification Ability of Multimodal Large Language Models: Insights from the Osteoarthritis Initiative added by Syntology 2026-01 (from id) wanglihx/LLaVA-OA/cliptrain_focal.py 0362ac3c9b5bde11 unverified no licence file found · pointer only
WhAM: Towards A Translative Model of Sperm Whale Vocalization added by Syntology 2025-12 (from id) Project-CETI/wham/wham/embedding/train_downstream.py e082a4e27242a338 unverified MIT (permissive)
Masked Symbol Modeling for Demodulation of Oversampled Baseband Communication Signals in Impulsive Noise-Dominated Channels added by Syntology 2025-12 (from id) OguzBedir/Masked_Symbol_Modeling/core/train_utils.py f847af280cc41e11 unverified no licence file found · pointer only
Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling added by Syntology 2025-11 (from id) GenuineWWD/SCS/evaluation/eval_qwen_m3cot.py 66307ccd5a78a143 unverified Apache-2.0 (permissive)
Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling added by Syntology 2025-11 (from id) GenuineWWD/SCS/evaluation/eval_qwen_mathverse.py 1dcd2f9d386042a6 unverified Apache-2.0 (permissive)
Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling added by Syntology 2025-11 (from id) GenuineWWD/SCS/evaluation/eval_qwen_mmmu.py 2987642d3528ecb0 unverified Apache-2.0 (permissive)
Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling added by Syntology 2025-11 (from id) GenuineWWD/SCS/evaluation/eval_qwen_wemath.py 2a6087e29d42d61d unverified Apache-2.0 (permissive)
Learning to Flow from Generative Pretext Tasks for Neural Architecture Encoding added by Syntology 2025-10 (from id) y0ngjaenius/CVPR2024_FLOWERFormer/utils.py 1466d657fc2b6567 unverified no licence file found · pointer only
ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control added by Syntology 2025-10 (from id) tanyuqian/synthetic-private-data/finetune.py 52b43047818c6eae unverified no licence file found · pointer only
QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models added by Syntology 2025-10 (from id) SAI-Lab-NYU/QSVD/fake_quant/eval_utilsdistvizwiz.py 20e4f665698a3d18 ran · our draft was wrong Apache-2.0 (permissive)
QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models added by Syntology 2025-10 (from id) SAI-Lab-NYU/QSVD/fake_quant/eval_smolvlm_vizwiz.py 07ead1dab90ee7a6 unverified Apache-2.0 (permissive)
SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition added by Syntology 2025-09 (from id) chenshunpeng/SAGE/datasets_ws.py 937b98b0302097b0 unverified MIT (permissive)
Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards added by Syntology 2025-09 (from id) baaivision/CoS/eval/mathvista/evaluate_mathvista.py 9483aaa3e36c23a0 unverified Apache-2.0 (permissive)
Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards added by Syntology 2025-09 (from id) baaivision/CoS/eval/mathvista/evaluate_mathvista_mine.py 53ae416061b7cd9e unverified Apache-2.0 (permissive)
CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning added by Syntology 2025-08 (from id) WNQzhu/CARFT/code/mwp_ReFT/sampling.py 2bb5bd3526f55ecb unverified no licence file found · pointer only
arXiv:2507.19993 2025-07 (from id) Howardkhh/FROSS/EGTR/pretrain_detr.py cdb6e23f77eb4b45 unverified Apache-2.0 (permissive)
arXiv:2507.17342 2025-07 (from id) fudan-zvg/DeMo/src/datamodule/av2_dataset.py cb3df1ace0ca2089 unverified no licence file found · pointer only
CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions 8 Jul 2025 lukahhcm/cultureclip/model_finetune/data.py 041e7ddf4cb7d30f unverified no licence file found · pointer only
LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs 1 Jul 2025 CnFaker/LLaVA-SP/llava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong Apache-2.0 (permissive)
NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments 30 Jun 2025 Feliciaxyao/NavMorph/vlnce_baselines/dagger_trainer.py f474c29ed36d8065 unverified no licence file found · pointer only
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs 21 Jun 2025 aoshuang92/splora/llama2_alpaca_pd_lora.py 3053998047069bec unverified no licence file found · pointer only
UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation 20 Jun 2025 tliby/unifork/unifork/eval/model_vqa_loader.py 9738a62bfa4c292d unverified no licence file found · pointer only
arXiv:2506.17124 2025-06 (from id) prediction-action-lab/thinking-as-control/data_utils.py 29defc8158c0ead0 unverified no licence file found · pointer only
Watermarking Autoregressive Image Generation 19 Jun 2025 GAIR-NLP/anole/facilitating_image_generation/train_image_head.py abbbb29b34ebbb42 unverified no licence file found · pointer only
Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs 12 Jun 2025 theia-4869/cdpruner/llava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong Apache-2.0 (permissive)
Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay 5 Jun 2025 astral-group/data-efficient-llm-rl/rl_training/verl/verl/trainer/ppo/ray_trainer_teacher_replay.py d11b448b5d76e167 unverified no licence file found · pointer only
Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos 5 Jun 2025 AFeng-x/Draw-and-Understand/accessory/eval/infer_and_save.py f5b33c6a8295f129 unverified Apache-2.0 (permissive)
Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency 2 Jun 2025 appletea233/temporal-r1/verl/utils/dataset.py 69132eba50f047ff unverified Apache-2.0 (permissive)
Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models 27 May 2025 jefferyzhan/griffon/griffon/eval/model_vqa_loader_batch.py 5ef2d21cca6281db unverified Apache-2.0 (permissive)
OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation 26 May 2025 PKU-YuanGroup/OpenS2V-Nexus/data_process/step3-1_get_caption.py ea468804bf7f0516 unverified Apache-2.0 (permissive)
OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation 26 May 2025 PKU-YuanGroup/OpenS2V-Nexus/data_process/step4-1_get_tag_local.py 68791d7cdd051179 unverified Apache-2.0 (permissive)
Taming Diffusion for Dataset Distillation with High Representativeness 23 May 2025 lin-zhao-resolve/d3hr/generation/dit_inversion_save_statistic.py 6fc038f89ff59f28 ran · our draft was wrong no licence file found · pointer only
arXiv:2505.17447 2025-05 (from id) Cheungki/LeTS/src/verl/workers/reward_manager/lets.py c9608313dd7b30d5 unverified MIT (permissive)
ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay 22 May 2025 dvlab-research/arpo/verl/utils/dataset.py 69132eba50f047ff unverified Apache-2.0 (permissive)
Training-Free Watermarking for Autoregressive Image Generation 20 May 2025 maifoundations/indexmark/Index_encoder/ft2_2loss.py 9780feca2753ce85 unverified MIT (permissive)
s3: You Don't Need That Much Data to Train a Search Agent via RL 20 May 2025 pat-jj/s3/s3/llm_agent/generation_s3.py 90f6865eb340d338 unverified Apache-2.0 (permissive)
MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision 19 May 2025 modalminds/mm-prm/eval/prm/evaluate_k12_prm.py 3426ef0ff637108e ran · our draft was wrong MIT (permissive)
Visual Planning: Let's Think Only with Images 16 May 2025 yix8/VisualPlanning/train_rl_frozen.py f55c31d782e48ffb ran · honoured contract fingerprinted MIT (permissive)
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models 14 Apr 2025 opengvlab/internvl/internvl_chat/eval/mmmu/evaluate_mmmu.py 74fcec52489e905d ran · our draft was wrong MIT (permissive)
arXiv:2504.00502 2025-04 (from id) icip-cas/ShortV/llava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong Apache-2.0 (permissive)
Sonata: Self-Supervised Learning of Reliable Point Representations 20 Mar 2025 facebookresearch/sonata/sonata/data.py 19a350b1109880a0 unverified Apache-2.0 (permissive)
MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling 17 Mar 2025 hustvl/MaTVLM/tinyllava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong Apache-2.0 (permissive)
TimeZero: Temporal Video Grounding with Reasoning-Guided LVLM 17 Mar 2025 www-ye/timezero/src/open_r1/sft.py 0ba9682f0587f9f4 unverified Apache-2.0 (permissive)
Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-tuning 14 Mar 2025 OPTML-Group/VLM-Safety-Unlearn/llava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong MIT (permissive)
TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models 13 Mar 2025 shawntan86/tokencarve/TokenCarve/TokenCarve_model_vqa_loader.py 4aa3263a9ac1bd63 unverified Apache-2.0 (permissive)
AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption 13 Mar 2025 joonsungjeon/advpaint/AdvPaint.py 90fadec0aec03c1b ran · honoured contract MIT (permissive)
ELECTRA: A Cartesian Network for 3D Charge Density Prediction with Floating Orbitals 11 Mar 2025 Jotels/ELECTRA_2025/models/electra_hotpp/ELECTRA.py f55c31d782e48ffb ran · honoured contract fingerprinted MIT (permissive)
SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation 26 Feb 2025 3dagentworld/sca3d/SCA3D/dataloaders/data.py eb503fa05caab93e unverified MIT (permissive)
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment 24 Feb 2025 facico/goat-peft/goat/train_vit.py 9a79ef50064b77e4 ran · our draft was wrong MIT (permissive)
SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition 23 Feb 2025 Lu-Feng/SelaVPR/datasets_ws.py 937b98b0302097b0 unverified MIT (permissive)
Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More 17 Feb 2025 zichenwen1/dart/llava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong Apache-2.0 (permissive)
HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation 14 Feb 2025 dcdmllm/healthgpt/HealthGPT/llava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong Apache-2.0 (permissive)
Training Sparse Mixture Of Experts Text Embedding Models 11 Feb 2025 nomic-ai/contrastors/src/contrastors/dataset/text_text_loader.py 801ebbc0eea48637 unverified Apache-2.0 (permissive)
TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting 10 Feb 2025 huangst21/timekan/data_provider/uea.py bbdc0c4ddfbaa19b ran Apache-2.0 (permissive)
UASTHN: Uncertainty-Aware Deep Homography Estimation for UAV Satellite-Thermal Geo-localization 3 Feb 2025 arplaboratory/UASTHN/global_pipeline/datasets_ws.py 247429ce34fc3671 ran MIT (permissive)
Regularized Langevin Dynamics for Combinatorial Optimization 1 Feb 2025 identical code first harvested elsewhere f55c31d782e48ffb ran · honoured contract fingerprinted licence of this copy not recorded
Sebra: Debiasing Through Self-Guided Bias Ranking 30 Jan 2025 kadarsh22/Sebra/bar_trainers/sebra.py fbdf12a7504f8ac4 ran · our draft was wrong no licence file found · pointer only
Multi-concept Model Immunization through Differentiable Model Merging 19 Dec 2024 amberyzheng/MIMA/adaptation/train_custom_diffusion.py 6d82c6864fe791d6 ran · our draft was wrong Apache-2.0 (permissive)
G-VEval: A Versatile Metric for Evaluating Image and Video Captions Using GPT-4o 18 Dec 2024 ztangaj/gveval/correlation.py a428a145149517f7 unverified no licence file found · pointer only
ArchesWeather & ArchesWeatherGen: a deterministic and generative model for efficient ML weather forecasting 17 Dec 2024 inria/geoarches/geoarches/main_hydra.py aff28d380df91506 unverified BSD-3-Clause (permissive)
Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models 17 Dec 2024 Savannah120/alignment-handbook-PoFT/generate_preference_scores.py 23bd8e38a433b4b5 ran · our draft was wrong Apache-2.0 (permissive)
Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning 17 Dec 2024 ShipingGe/ILCACM/src/util/dataloader.py d3a2efceb5304d00 unverified MIT (permissive)
LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering 16 Dec 2024 bibisbar/LLaVA-Steering/tinyllava/eval/model_vqa_loader.py 68ad5f668d4f2976 unverified Apache-2.0 (permissive)
Causal Graphical Models for Vision-Language Compositional Understanding 12 Dec 2024 aimagelab/COGT/dataset.py bc629eb0de6e6850 unverified no licence file found · pointer only
Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark 12 Dec 2024 yongliang-wu/repurpose/dataset/RepurposeClip.py f1d6f311ec1139dc unverified MIT (permissive)
TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft 6 Dec 2024 teamcraft-bench/teamcraft/llava_teamcraft/llava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong MIT (permissive)
p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay 5 Dec 2024 mcg-nju/p-mod/llava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong Apache-2.0 (permissive)
PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation 4 Dec 2024 hqhqaq/patchdpo/inference_dreambooth.py ccf8fb11b2e5dd2c unverified no licence file found · pointer only
A Graph Neural Network Simulation of Dispersed Systems 2024-12 (from id) rfjd/GNS-DispersedSystems/gns/data_loader.py 10d4ddc0d667a1f3 unverified no licence file found · pointer only
Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs 2 Dec 2024 theia-4869/fastervlm/llava/eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong Apache-2.0 (permissive)
Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification 1 Dec 2024 Osilly/dynamic_llava/llava/dynamic_eval/model_vqa_loader.py 20e4f665698a3d18 ran · our draft was wrong Apache-2.0 (permissive)
EDTformer: An Efficient Decoder Transformer for Visual Place Recognition 1 Dec 2024 tong-jin01/edtformer/datasets_ws.py c160834241fc1797 unverified MIT (permissive)
LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos 29 Nov 2024 ttgeng233/LongVALE/preprocess/beats_feature_extract.py ac11ca70992e72fb unverified MIT (permissive)
LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos 29 Nov 2024 ttgeng233/LongVALE/preprocess/clip_feature_extract.py 4d8e90858b179363 unverified MIT (permissive)
LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos 29 Nov 2024 ttgeng233/LongVALE/preprocess/whisper_feature_extract.py 98415dceedab1609 unverified MIT (permissive)
GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks 28 Nov 2024 the-ai-alliance/geo-bench-vlm/eval_geobenchvlm/llava1pt5_cls_single.py ed69126ee53f8ce6 unverified Apache-2.0 (permissive)
GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks 28 Nov 2024 the-ai-alliance/geo-bench-vlm/eval_geobenchvlm/qwen_cls_single.py ca49a9290f4e93c3 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