Home › Code › union_tensor_dict

union_tensor_dict

Syntologyentry name in harvested code

Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

union_tensor_dict appears in the code Syntology harvested for 69 papers, as 2 distinct code bodies found in 69 places (a place is one code body under one paper). Of the 69 papers, 69 with a sample that ran: 0 with a run with no instrument failure, 69 where every run was a failure of Syntology's instrument. 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 union_tensor_dict 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 2 distinct code bodies named union_tensor_dict: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 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:

0ran · honoured contract
0ran · violated contract
2ran · our draft was wrong
0ran; the contract check could not run
0ran
0unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 16 of the 69 places are pointer only (Syntology does not serve that copy's text); at 6 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 (hover the licence cell for why). 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

69 papers shown of 69, newest first; 69 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 31 papers added by Syntology; 5 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.

PaperDateFileStatus SyntologyLicence
Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs added by Syntology 2026-09 (from id) hexixiang/MT-SDPO/training/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents added by Syntology 2026-09 (from id) AlibabaResearch/SignalCoverageRL/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Best Practice Critic Optimization BEST PRACTICE CRITIC OPTIMIZATION added by Syntology 2026-08 (from id) QPHutu/golden_critic/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
DENSER ̸ = BETTER: LIMITS OF ON-POLICY SELF-DISTILLATION FOR CONTINUAL POST-TRAINING added by Syntology 2026-07 (from id) Moenupa/SDPO-CL/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models added by Syntology 2026-06 (from id) Zhaolutuan/SAW/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Self-Distilled Policy Gradient added by Syntology 2026-06 (from id) lauyikfung/SDPG/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains added by Syntology 2026-05 (from id) ZiqiZhao1/ROSD/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards added by Syntology 2026-05 (from id) Lumina04/CARE/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Ranking-Aware Calibration for Reliable Multimodal Reinforcement Learning added by Syntology 2026-05 (from id) Stellaris167/RAC/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective added by Syntology 2026-05 (from id) horizon-llm/CTPO/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
When Less is Enough: Efficient Inference via Collaborative Reasoning added by Syntology 2026-05 (from id) fairytale9/llm_bottleneck/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning added by Syntology 2026-04 (from id) yuyongcan/DDRL/verl/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong MIT (permissive)
Bounded Ratio Reinforcement Learning added by Syntology 2026-04 (from id) bounded-ratio-rl/bounded_ratio_rl/src/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong no licence file found · pointer only
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? added by Syntology 2026-03 (from id) lasgroup/SDPO/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs added by Syntology 2026-03 (from id) ucsd-wang-lab-lm/tips/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong no licence file found · pointer only
Online Causal Kalman Filtering for Stable and Effective Policy Optimization added by Syntology 2026-02 (from id) shuohe1995/verl-kpo/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Uncovering Cross-Objective Interference in Multi-Objective Alignment added by Syntology 2026-02 (from id) yining610/ctwa/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models added by Syntology 2026-02 (from id) Easy195/FaithRL/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong no licence file found · pointer only
Rethinking the Trust Region in LLM Reinforcement Learning added by Syntology 2026-02 (from id) sail-sg/Stable-RL/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning added by Syntology 2026-02 (from id) wenquanlu/PrAg-PO/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong no licence file found · pointer only
CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs added by Syntology 2026-02 (from id) Within-yao/CoBA-RL/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong no licence file found · pointer only
Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation added by Syntology 2026-01 (from id) Cherry-qwq/LcRL-Open/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
RelayLLM: Efficient Reasoning via Collaborative Decoding added by Syntology 2026-01 (from id) Chengsong-Huang/RelayLLM/RL_stage/verl/protocol.py ad658a1d6fe829ba ran · our draft was wrong no licence file found · pointer only
AT 2 PO: Agentic Turn-based Policy Optimization via Tree Search added by Syntology 2026-01 (from id) zzfoutofspace/ATPO/ATPO/verl_atpo/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong no licence file found · pointer only
Prioritized Replay for RL Post-training added by Syntology 2026-01 (from id) fatemi/verl/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Meta-RL Induces Exploration in Language Agents added by Syntology 2025-12 (from id) mlbio-epfl/LaMer/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong no licence file found · pointer only
Ophiuchus: Incentivizing Tool-augmented "Think with Images" for Joint Medical Segmentation, Understanding and Reasoning added by Syntology 2025-12 (from id) SII-zyj/Ophiuchus/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning added by Syntology 2025-11 (from id) aiming-lab/Agent0/Agent0-VL/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents added by Syntology 2025-10 (from id) GuoqingWang1/IGPO/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Multi-Agent Tool-Integrated Policy Optimization added by Syntology 2025-10 (from id) mzf666/MATPO/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking added by Syntology 2025-09 (from id) bytedance/EvoQuality/verl/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Scaling RL to Long Videos 10 Jul 2025 NVlabs/Long-RL/verl/protocol.py ad658a1d6fe829ba ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only
Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training 7 Jul 2025 zhhvvv/rft_vs_sft/EasyR1/verl/protocol.py ad658a1d6fe829ba ran · our draft was wrong no licence file found · pointer only
SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models 15 Jun 2025 xid32/SoundMind/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong MIT (permissive)
RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling 10 Jun 2025 bigai-nlco/rulereasoner/verl/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong MIT (permissive)
Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency 2 Jun 2025 appletea233/temporal-r1/verl/protocol.py ad658a1d6fe829ba ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only
ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL 30 May 2025 Franklin-Zhang0/ReasonGen-R1/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind 29 May 2025 ulab-uiuc/ToMAP/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
REARANK: Reasoning Re-ranking Agent via Reinforcement Learning 26 May 2025 lezhang7/rearank/verl/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Behavior Injection: Preparing Language Models for Reinforcement Learning 25 May 2025 czp16/bridge-llm-reasoning/simple_verl/sverl/protocol.py 21331a58f93375e4 ran · our draft was wrong MIT (permissive)
AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting 24 May 2025 joeying1019/adactrl/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Synthetic Data RL: Task Definition Is All You Need 18 May 2025 gydpku/data_synthesis_rl/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
UFT: Unifying Supervised and Reinforcement Fine-Tuning 22 May 2025 liumy2010/uft/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay 22 May 2025 dvlab-research/arpo/verl/protocol.py ad658a1d6fe829ba ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only
DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning 20 May 2025 visual-agent/deepeyes/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (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 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Thinkless: LLM Learns When to Think 19 May 2025 vainf/thinkless/verl/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs 19 May 2025 zhyang2226/ar-lopti/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning 16 May 2025 yueliu1999/guardreasoner-vl/train/EasyR1/verl/protocol.py ad658a1d6fe829ba ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only
Scalable Chain of Thoughts via Elastic Reasoning 8 May 2025 salesforceairesearch/elastic-reasoning/verl/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only
ZeroSearch: Incentivize the Search Capability of LLMs without Searching 7 May 2025 alibaba-nlp/zerosearch/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Reinforcement Learning for Reasoning in Large Language Models with One Training Example 29 Apr 2025 ypwang61/one-shot-rlvr/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning 2025-04 (from id) IDEA-FinAI/SQL-R1/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Efficient Reinforcement Finetuning via Adaptive Curriculum Learning 7 Apr 2025 uscnlp-lime/verl/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models? 2 Apr 2025 bigai-ai/ToM-RL/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong MIT (permissive)
ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning 2 Apr 2025 UCSB-NLP-Chang/ThinkPrune/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models 28 Mar 2025 lzhxmu/cppo/cppo_verl/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement 21 Mar 2025 yihedeng9/openvlthinker/EasyR1/verl/protocol.py ad658a1d6fe829ba ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only
Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond 13 Mar 2025 Qihoo360/Light-R1/deepscaler-release/verl/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Agent models: Internalizing Chain-of-Action Generation into Reasoning models 9 Mar 2025 adam-bjtu/autocoa/RL_training/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong MIT (permissive)
Self-rewarding correction for mathematical reasoning 26 Feb 2025 agentica-project/verl-pipeline/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning 20 Feb 2025 Unakar/Logic-RL/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models 28 Oct 2024 yaof20/real/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
HybridFlow: A Flexible and Efficient RLHF Framework 28 Sep 2024 du-nlp-lab/lengthreward/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
OpenReview id openreview_dzcDbh8ewp Xiao-Youth/LECTOR/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
OpenReview id openreview_Y1rHxA58If qiancheng0/ToolRL/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
OpenReview id openreview_Y1PXB8HBV7 youwyouw/mirl-main/verl/protocol.py ad658a1d6fe829ba ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only
OpenReview id openreview_VZDlkXuIQc ShadeCloak/IP-GRM/verl/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong Apache-2.0 (permissive)
ACL Anthology id 2025.findings-emnlp.1015 fzp0424/MT-R1-Zero/verl/protocol.py 21331a58f93375e4 ran · our draft was wrong 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 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