SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.01432 · ICLR · 2025

Adaptive teachers for amortized samplers

Yoshua Bengio, Emmanuel Bengio, Sungsoo Ahn, Minsu Kim, Nikolay Malkin, Sanghyeok Choi, Kaist Taeyoung, Yun Kaist, Kaist Jinkyoo, Park Kaist

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2410.01432.json · badge: /api/ran/2410.01432.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
alstn12088/adaptive-teacher canonical (classifier label)
classifier basis: classifier_2025
5 ran · 0 no recorded run
FunctionStatusWhere it lives
TeacherGFlowNet Ran
ran on a synthesized input · constructed an object; no result was computed
alstn12088/adaptive-teacher/discovery/gflownet/GFNs/teacher.py
pointer only (licence: NONE) · get_code("ad1d91a903c30ac7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alstn12088/adaptive-teacher when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

accumulate_by_traj Ran
ran; our contract draft was wrong, not the code
alstn12088/adaptive-teacher/discovery/gflownet/GFNs/teacher.py
pointer only (licence: NONE) · get_code("830498975b1eccbb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alstn12088/adaptive-teacher when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

batch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
alstn12088/adaptive-teacher/discovery/gflownet/GFNs/teacher.py
pointer only (licence: NONE) · get_code("1a1ebe33ee0285e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alstn12088/adaptive-teacher when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

tensor_to_np Ran
ran, honoured the contract we drafted
alstn12088/adaptive-teacher/discovery/gflownet/GFNs/teacher.py
pointer only (licence: NONE) · get_code("973c7b0697f6a623")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alstn12088/adaptive-teacher when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

unroll_trajs Ran
ran; our contract draft was wrong, not the code
alstn12088/adaptive-teacher/discovery/gflownet/GFNs/teacher.py
pointer only (licence: NONE) · get_code("9d260f82cae9af81")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alstn12088/adaptive-teacher when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 0 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
batch
brick of this paper's assembly: helper
3 other papers
3 dated earlier · 1 only as an assembly brick
2310.00386 (2023-10)
Order-Preserving GFlowNets
2310.02710 (2023-10)
Local Search GFlowNets
2310.02823 (2023-10)
Learning to Scale Logits for Temperature-Conditional GFlowNets
accumulate_by_traj
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 2 only as an assembly brick
2310.02710 (2023-10)
Local Search GFlowNets
2310.02823 (2023-10)
Learning to Scale Logits for Temperature-Conditional GFlowNets
tensor_to_np
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2310.00386 (2023-10)
Order-Preserving GFlowNets
2310.02710 (2023-10)
Local Search GFlowNets
unroll_trajs
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 2 only as an assembly brick
2310.02710 (2023-10)
Local Search GFlowNets
2310.02823 (2023-10)
Learning to Scale Logits for Temperature-Conditional GFlowNets

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnormalized density where exact sampling is intractable. When sampling is implemented as a sequential decision-making process, reinforcement learning (RL) methods, such as generative flow networks, can be used to train the sampling policy. Off-policy RL training facilitates the discovery of diverse, high-reward candidates, but existing methods still face challenges in efficient exploration. We propose to use an adaptive training distribution (the Teacher) to guide the training of the primary amortized sampler (the Student). The Teacher, an auxiliary behavior model, is trained to sample high-loss regions of the Student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum. We validate the effectiveness of this approach in a synthetic environment designed to present an exploration challenge, two diffusion-based sampling tasks, and four biochemical discovery tasks demonstrating its ability to improve sample efficiency and mode coverage. Source code is available at https://github.com/alstn12088/adaptive-teacher.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.01432")
get_code_for_paper("2410.01432")
have("2410.01432")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2410.01432.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2410.01432.svg)](https://syntology.ai/paper/2410.01432)

Connect an agent — have() is free.