Home › Code › default_init

default_init

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

default_init appears in the code Syntology harvested for 38 papers, as 21 distinct code bodies found in 40 places (a place is one code body under one paper). At least one of them ran in 24 of the papers; 0 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 default_init 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 13 of the 21 distinct code bodies named default_init; 8 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
5ran · our draft was wrong
0ran · fixture could not drive it
8ran
8unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 10 of the 40 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

38 papers shown of 38, newest first; 40 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 6 papers added by Syntology; 1 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
Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport added by Syntology 2026-09 (from id) Yonsei-DILLab/OptiFlow/optiflow/networks.py 2aaa6f4e0d62bf22 ran · our draft was wrong no licence file found · pointer only
ReBRAC-v2: The Return of the King added by Syntology 2026-08 (from id) JongseongChae/FAC/agents/rebrac.py 2aaa6f4e0d62bf22 ran · our draft was wrong no licence file found · pointer only
Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning added by Syntology 2026-06 (from id) zhouzypaul/qgf/utils/networks.py 2aaa6f4e0d62bf22 ran · our draft was wrong MIT (permissive)
Language Modeling with Hyperspherical Flows added by Syntology 2026-05 (from id) s-sahoo/duo/models/unet.py fdd6aad96accd488 ran Apache-2.0 (permissive)
Reward-Conditioned Reinforcement Learning added by Syntology 2026-03 (from id) naumix/BiggerRegularizedCategorical/jaxrl/agent/brc_learner.py 7e1b1dbdf882411b ran · our draft was wrong MIT (permissive)
Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism added by Syntology 2025-12 (from id) proroklab/memoroids/modules.py e31de52332dff52c ran · our draft was wrong no licence file found · pointer only
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning 23 Jun 2025 thudm/longwriter/train/patch/modeling_chatglm.py 237019e36b9481d9 unverified Apache-2.0 (permissive)
Simple Guidance Mechanisms for Discrete Diffusion Models 13 Dec 2024 kuleshov-group/discrete-diffusion-guidance/models/unet.py fdd6aad96accd488 ran Apache-2.0 (permissive)
Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching 11 Nov 2024 arnavkj1995/sfm/agents/sfm_sac.py c5e2d65ae4ba9bc6 ran · our draft was wrong MIT (permissive)
Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration 23 Oct 2024 rail-berkeley/supe/supe/agents/model.py 58986e64f92121be unverified MIT (permissive)
Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models 4 Oct 2024 1zhou-Wang/MemVR/modeling/modeling_chatglm.py 237019e36b9481d9 unverified Apache-2.0 (permissive)
Generative AI for fast and accurate statistical computation of fluids 27 Sep 2024 camlab-ethz/gencfd/GenCFD/utils/model_utils.py ec800de8d7a491d0 ran Apache-2.0 (permissive)
SysBench: Can Large Language Models Follow System Messages? 20 Aug 2024 pku-baichuan-mlsystemlab/sysbench/attenscore/modeling_chatglm.py 237019e36b9481d9 unverified no licence file found · pointer only
Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning 6 May 2024 stonet2000/rfcl/rfcl/models/mlp.py d8302176def1e542 ran no licence file found · pointer only
Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning 6 May 2024 stonet2000/rfcl/rfcl/agents/sac/networks.py 32b82cb936cbd54d ran no licence file found · pointer only
Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding 19 Feb 2024 cteant/space/src/models/modeling_chatglm.py 237019e36b9481d9 unverified Apache-2.0 (permissive)
DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems 6 Feb 2024 google-research/swirl-dynamics/swirl_dynamics/lib/diffusion/unets.py 5aeb858a9d4f09ef ran licence not identified · pointer only
LongAlign: A Recipe for Long Context Alignment of Large Language Models 31 Jan 2024 thudm/longalign/modeling_chatglm.py 237019e36b9481d9 unverified Apache-2.0 (permissive)
Equivariant Graph Neural Operator for Modeling 3D Dynamics 19 Jan 2024 minkaixu/egno/model/layer_no.py 04548c6c9fff2b3f ran MIT (permissive)
Continuous Diffusion for Mixed-Type Tabular Data 16 Dec 2023 ChaejeongLee/CoDi/models/layers.py 66362066ac43ccc4 ran no licence file found · pointer only
VTimeLLM: Empower LLM to Grasp Video Moments 30 Nov 2023 huangb23/vtimellm/vtimellm/model/chatglm/modeling_chatglm.py 237019e36b9481d9 unverified no licence file found · pointer only
Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning 27 Oct 2023 leaplabthu/famo2o/jax_iql/family_learner.py 29e1a06c6560973e ran · our draft was wrong MIT (permissive)
Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning 27 Oct 2023 LeapLabTHU/FamO2O/jax_iql/common.py 718462716d78ea99 ran MIT (permissive)
Generative Marginalization Models 19 Oct 2023 PrincetonLIPS/MaM/mam/models/layers.py fdd6aad96accd488 ran no licence file found · pointer only
FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios 25 Jul 2023 freedomintelligence/sdak/code/workers/modeling_chatglm.py 237019e36b9481d9 unverified Apache-2.0 (permissive)
Video Diffusion Models with Local-Global Context Guidance 5 Jun 2023 exisas/LGC-VD/model/utils.py fdd6aad96accd488 ran MIT (permissive)
Spontaneous Symmetry Breaking in Generative Diffusion Models 31 May 2023 gabrielraya/symmetry_breaking_diffusion_models/models/layers.py 04548c6c9fff2b3f ran MIT (permissive)
Efficient Deep Reinforcement Learning Requires Regulating Overfitting 20 Apr 2023 evgenii-nikishin/rl_with_resets/continuous_control/networks/common.py 718462716d78ea99 ran MIT (permissive)
Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization 28 Mar 2023 ryanxhr/IVR/common.py 718462716d78ea99 ran MIT (permissive)
Preference Transformer: Modeling Human Preferences using Transformers for RL 2 Mar 2023 csmile-1006/preferencetransformer/common.py 718462716d78ea99 ran MIT (permissive)
Disentangling Learning Representations with Density Estimation 8 Feb 2023 ericyeats/gcae-disentanglement/src/architectures.py e1d504336b0f31fc unverified MIT (permissive)
Direct Preference-based Policy Optimization without Reward Modeling 30 Jan 2023 snu-mllab/DPPO/common.py 718462716d78ea99 ran MIT (permissive)
Fast Sampling of Diffusion Models via Operator Learning 24 Nov 2022 devzhk/dsno-pytorch/models/layers.py 04548c6c9fff2b3f ran MIT (permissive)
DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Change Detection 23 Jun 2022 wgcban/ddpm-cd/model/ddpm_modules/vanilla_unet.py 66362066ac43ccc4 ran MIT (permissive)
gDDIM: Generalized denoising diffusion implicit models 11 Jun 2022 qsh-zh/gDDIM/blur_jax/models/layers.py f537ef3271967db2 unverified Apache-2.0 (permissive)
When does return-conditioned supervised learning work for offline reinforcement learning? 2 Jun 2022 davidbrandfonbrener/rcsl-paper/jax_continuous_rl/jaxrl/networks/common.py facdc73f9b000275 unverified MIT (permissive)
MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation 19 May 2022 voletiv/mcvd-pytorch/models/unet.py 90b0411e98af1284 unverified MIT (permissive)
Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation 6 Jun 2021 evgenii-nikishin/omd/mujoco/jax_rl/networks/common.py 1bd2d556360ac9c9 unverified MIT (permissive)
Soft Actor-Critic Algorithms and Applications 13 Dec 2018 patrickhart/jaxdl/jaxdl/nn/dnn/conv.py 7e5ed014bde23917 unverified MIT (permissive)
arXiv:openreview_RdkOaK4q6p 2012060/DFQL/utils/networks.py 2aaa6f4e0d62bf22 ran · our draft was wrong MIT (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