SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.04312 · NeurIPS · 2024

ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization

Karsten Roth, Alexey Dosovitskiy, Zeynep Akata, Shyamgopal Karthik, Luca Eyring

arXiv · PDF · Open in the Atlas

Code that ran

13 of 22 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 11 failures of our instrument; 9 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2406.04312.json · badge: /api/ran/2406.04312.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
salesforce/DOODL canonical (classifier label)
classifier basis: census
10 ran · 9 no recorded run
ExplainableML/ReNO canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
attention_drop Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
salesforce/DOODL/fgvc_ws_dan_helpers/attention.py
code served (permissive licence) · get_code("4b9a1f20af5b88a2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 5, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
import random

torch.manual_seed(0)
np.random.seed(0)
random.seed(0)

# attention_maps: shape (batch_size, num_parts, height, width)
# input_image: shape (B, N, W, H)
# The function expects these to be tensors

batch_size = 2
num_parts = 4
height = 3
width = 5

# Create attention_maps tensor with shape (batch_size, num_parts, height, width)
attention_maps = torch.rand(batch_size, num_parts, height, width)

# Create input_image tensor with shape (B, N, W, H)
# B=batch_size, N=num_parts, W=width, H=height
input_image = torch.rand(batch_size, num_parts, width, height)

ARGS = {
    "attention_maps": attention_maps,
    "input_image": input_image,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 4, 5, 3) — shape (2, 4, 5, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
batch_norm Ran
ran; our contract draft was wrong, not the code
salesforce/DOODL/memcnn/models/resnet.py
code served (permissive licence) · get_code("06864fef7f15d70b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned BatchNorm2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function batch_norm(x) expects x to be an integer (number of features/channels)
# It calls nn.BatchNorm2d(x, ...) which expects an integer as the first argument

ARGS = {
    "x": 4
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type BatchNorm2d — a BatchNorm2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a BatchNorm2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
calculate_shift Ran
ran, violated the contract we drafted
ExplainableML/ReNO/models/RewardFlux.py
code served (permissive licence) · get_code("4e3ad3679e5c37b2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - image_seq_len: a numeric value (int or float) representing sequence length
# - base_seq_len: int, default 256
# - max_seq_len: int, default 4096
# - base_shift: float, default 0.5
# - max_shift: float, default 1.16
# The function performs linear interpolation calculations on these numeric values

ARGS = {
    "image_seq_len": 512,
    "base_seq_len": 256,
    "max_seq_len": 4096,
    "base_shift": 0.5,
    "max_shift": 1.16
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
check_imports Ran
ran; our contract draft was wrong, not the code
salesforce/DOODL/my_half_diffusers/dynamic_modules_utils.py
code served (permissive licence) · get_code("301682fc3342590a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os

# Create a temporary Python file with various import statements
temp_file = tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False, encoding='utf-8')
temp_file.write("""
import os
import sys
from pathlib import Path
from . import utils
from .submodule import helper
import torch
import numpy
""")
temp_file.close()

ARGS = {
    "filename": temp_file.name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv3x3 Ran
ran; our contract draft was wrong, not the code
salesforce/DOODL/memcnn/models/resnet.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, and GitHub detected no licence in that repository 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.

get_alpha_and_beta Ran
ran, honoured the contract we drafted
salesforce/DOODL/helper_functions.py
code served (permissive licence) · get_code("1e2c27972c98db0d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

class MockScheduler:
    def __init__(self):
        # Create alphas_cumprod tensor with enough entries for indexing
        # Use 100 steps to be safe for various time indices
        self.alphas_cumprod = torch.linspace(0.9999, 0.1, 100)
        self.final_alpha_cumprod = torch.tensor(0.0001)

scheduler = MockScheduler()

# Test case 1: integer time step
t_int = torch.tensor(5, dtype=torch.long)

ARGS = {
    "t": t_int,
    "scheduler": scheduler
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_parameter_device Ran
ran; our contract draft was wrong, not the code
salesforce/DOODL/my_half_diffusers/modeling_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from mayuelala/followyourcanvas, is pointer only (licence: NONE) · get_code("eafa252fd6f86857")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from mayuelala/followyourcanvas, and GitHub detected no licence in that repository 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.

get_parameter_dtype Ran
ran; our contract draft was wrong, not the code
salesforce/DOODL/my_half_diffusers/modeling_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from mayuelala/followyourcanvas, is pointer only (licence: NONE) · get_code("dc2045840ce679cb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from mayuelala/followyourcanvas, and GitHub detected no licence in that repository 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.

get_relative_import_files Ran
ran; our contract draft was wrong, not the code
salesforce/DOODL/my_half_diffusers/dynamic_modules_utils.py
code served (permissive licence) · get_code("00cc853a73f3aeb6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import re
from pathlib import Path
import tempfile
import os

# Create a temporary directory and files for testing
temp_dir = tempfile.mkdtemp()

# Create a simple module file with relative imports
module_file = os.path.join(temp_dir, "main_module.py")
with open(module_file, 'w') as f:
    f.write("""
from .helper import some_function
import .utils
from .submodule import ClassA
""")

# Create helper module
helper_file = os.path.join(temp_dir, "helper.py")
with open(helper_file, 'w') as f:
    f.write("""
def some_function():
    pass
""")

# Create utils module
utils_file = os.path.join(temp_dir, "utils.py")
with open(utils_file, 'w') as f:
    f.write("""
# utility functions
""")

# Create submodule
submodule_file = os.path.join(temp_dir, "submodule.py")
with open(submodule_file, 'w') as f:
    f.write("""
class ClassA:
    pass
""")

ARGS = {
    "module_file": module_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_relative_imports Ran
ran; our contract draft was wrong, not the code
salesforce/DOODL/my_half_diffusers/dynamic_modules_utils.py
code served (permissive licence) · get_code("450aeffe7f80f917")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os

# Create a temporary Python file with relative imports
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_module.py")

content = """
import .submodule
import .utils
from .helpers import some_function
from .core import another_function
import os
from typing import List
"""

with open(temp_file, 'w', encoding='utf-8') as f:
    f.write(content)

ARGS = {
    'module_file': temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
retrieve_timesteps Ran
ran; our contract draft was wrong, not the code
ExplainableML/ReNO/models/RewardFlux.py
pointer only (licence: MIT); the stored copy get_code serves, from krafton-ai/Rare-to-Frequent, is pointer only (licence: NONE) · get_code("0b56680ee1708fee")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from krafton-ai/Rare-to-Frequent, and GitHub detected no licence in that repository 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.

retrieve_timesteps Ran
ran; our contract draft was wrong, not the code
ExplainableML/ReNO/models/RewardStableDiffusion.py
code served (permissive licence) · get_code("6c337532224391b0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import inspect
from typing import List, Optional, Union

torch.manual_seed(0)

class MockScheduler:
    """Mock scheduler that implements set_timesteps and has a timesteps attribute."""
    
    def __init__(self):
        self.timesteps = torch.tensor([999, 750, 500, 250, 0])
    
    def set_timesteps(self, num_inference_steps: Optional[int] = None, device: Optional[Union[str, torch.device]] = None, timesteps: Optional[List[int]] = None, **kwargs):
        """Mock set_timesteps method that accepts both num_inference_steps and timesteps."""
        if timesteps is not None:
            self.timesteps = torch.tensor(timesteps, device=device)
        elif num_inference_steps is not None:
            # Generate dummy timesteps based on num_inference_steps
            self.timesteps = torch.linspace(999, 0, num_inference_steps, dtype=torch.long, device=device)
        else:
            # Default behavior
            self.timesteps = torch.tensor([999, 750, 500, 250, 0], device=device)


scheduler = MockScheduler()

ARGS = {
    "scheduler": scheduler,
    "num_inference_steps": 5,
    "device": None,
    "timesteps": None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
symmetry_loss_fn Ran
ran; our contract draft was wrong, not the code
salesforce/DOODL/doodl.py
code served (permissive licence) · get_code("6fa6035b98a8620c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# The function symmetry_loss_fn takes:
# 1. symmetry_type: a string specifying the type of symmetry
# 2. grad_scale: a numeric value for scaling gradients

# Looking at the function body:
# - It returns a loss_fn that takes im_pix (an image tensor)
# - The loss_fn flips the tensor along the last dimension (-1)
# - It computes MSE loss between original and flipped
# - It multiplies by grad_scale

# Create a small image tensor for testing
# Shape: (batch=2, channels=3, height=4, width=5)
im_pix = torch.randn(2, 3, 4, 5)

ARGS = {
    'symmetry_type': 'horizontal',
    'grad_scale': 1.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
attention_crop Not yet run
unverified (harvested, no recorded run)
salesforce/DOODL/fgvc_ws_dan_helpers/attention.py
code served (permissive licence) · get_code("f4b39efe5d9d4cd6")
How it ran

no invocation recorded.

attention_crop_drop Not yet run
unverified (harvested, no recorded run)
salesforce/DOODL/fgvc_ws_dan_helpers/attention.py
code served (permissive licence) · get_code("90d39f0e29e120ed")
How it ran

no invocation recorded.

clip_loss_fn Not yet run
unverified (harvested, no recorded run)
salesforce/DOODL/doodl.py
code served (permissive licence) · get_code("98d441978db01287")
How it ran

no invocation recorded.

forward_step Not yet run
unverified (harvested, no recorded run)
salesforce/DOODL/helper_functions.py
code served (permissive licence) · get_code("2b1d2002a86e6988")
How it ran

no invocation recorded.

inception_v3 Not yet run
unverified (harvested, no recorded run)
salesforce/DOODL/fgvc_ws_dan_helpers/inception_bap.py
code served (permissive licence) · get_code("281fab24f1d00b4d")
How it ran

no invocation recorded.

inception_v3_bap Not yet run
unverified (harvested, no recorded run)
salesforce/DOODL/fgvc_ws_dan_helpers/inception_bap.py
code served (permissive licence) · get_code("0be62823f1d5be59")
How it ran

no invocation recorded.

load_state_dict Not yet run
unverified (harvested, no recorded run)
salesforce/DOODL/my_half_diffusers/modeling_utils.py
code served (permissive licence) · get_code("77bd5e6e8ca8c91d")
How it ran

no invocation recorded.

reverse_step Not yet run
unverified (harvested, no recorded run)
salesforce/DOODL/helper_functions.py
code served (permissive licence) · get_code("6dfd0473df9ccaa5")
How it ran

no invocation recorded.

spherical_dist_loss Not yet run
unverified (harvested, no recorded run)
salesforce/DOODL/doodl.py
code served (permissive licence) · get_code("216e276b9fb00d10")
How it ran

no invocation recorded.

Also present in other papers' code

Of 22 samples lifted from this paper's linked repositories, 22 carry a function identity and 0 do not. Of the 22 distinct functions with an identity, 11 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 8 the same month, 10 later) and 11 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
conv3x3 686 other papers
596 dated earlier, 6 the same month, 67 later, 17 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
retrieve_timesteps 46 other papers
3 dated earlier, 41 later, 2 undated
2312.04461 (2023-12)
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
2402.10491 (2024-02)
Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation
2405.18991 (2024-05)
EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation
and 43 more not named here
retrieve_timesteps 21 other papers
4 dated earlier, 2 the same month, 15 later
2310.06313 (2023-10)
Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
2401.11708 (2024-01)
Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs
2403.06976 (2024-03)
BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion
and 18 more not named here
get_relative_import_files 18 other papers
13 dated earlier, 2 the same month, 3 later
2211.11694 (2022-11)
Exploring Discrete Diffusion Models for Image Captioning
2304.05568 (2023-04)
Improving Diffusion Models for Scene Text Editing with Dual Encoders
2305.15756 (2023-05)
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
and 15 more not named here
get_relative_imports 18 other papers
13 dated earlier, 2 the same month, 3 later
2211.11694 (2022-11)
Exploring Discrete Diffusion Models for Image Captioning
2304.05568 (2023-04)
Improving Diffusion Models for Scene Text Editing with Dual Encoders
2305.15756 (2023-05)
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
and 15 more not named here
calculate_shift 15 other papers
15 later
2410.22376 (2024-10)
Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance
2411.06558 (2024-11)
Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement
2411.16318 (2024-11)
One Diffusion to Generate Them All
and 12 more not named here
check_imports 10 other papers
7 dated earlier, 1 the same month, 2 later
2211.11694 (2022-11)
Exploring Discrete Diffusion Models for Image Captioning
2304.05568 (2023-04)
Improving Diffusion Models for Scene Text Editing with Dual Encoders
2305.15756 (2023-05)
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
and 7 more not named here
get_parameter_device 10 other papers
4 dated earlier, 2 the same month, 4 later
2304.05568 (2023-04)
Improving Diffusion Models for Scene Text Editing with Dual Encoders
2306.05720 (2023-06)
Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model
2307.10829 (2023-07)
Exact Diffusion Inversion via Bi-directional Integration Approximation
and 7 more not named here
get_parameter_dtype 10 other papers
4 dated earlier, 2 the same month, 4 later
2304.05568 (2023-04)
Improving Diffusion Models for Scene Text Editing with Dual Encoders
2306.05720 (2023-06)
Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model
2307.10829 (2023-07)
Exact Diffusion Inversion via Bi-directional Integration Approximation
and 7 more not named here
load_state_dict 5 other papers
3 dated earlier, 1 the same month, 1 later
2304.05568 (2023-04)
Improving Diffusion Models for Scene Text Editing with Dual Encoders
2306.05720 (2023-06)
Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model
2307.10829 (2023-07)
Exact Diffusion Inversion via Bi-directional Integration Approximation
and 2 more not named here
batch_norm 1 other paper
1 dated earlier
2005.05220 (2020-05)
iUNets: Fully invertible U-Nets with Learnable Up- and Downsampling

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

Text-to-Image (T2I) models have made significant advancements in recent years, but they still struggle to accurately capture intricate details specified in complex compositional prompts. While fine-tuning T2I models with reward objectives has shown promise, it suffers from "reward hacking" and may not generalize well to unseen prompt distributions. In this work, we propose Reward-based Noise Optimization (ReNO), a novel approach that enhances T2I models at inference by optimizing the initial noise based on the signal from one or multiple human preference reward models. Remarkably, solving this optimization problem with gradient ascent for 50 iterations yields impressive results on four different onestep models across two competitive benchmarks, T2I-CompBench and GenEval. Within a computational budget of 20-50 seconds, ReNO-enhanced one-step models consistently surpass the performance of all current open-source Text-to-Image models. Extensive user studies demonstrate that our model is preferred nearly twice as often compared to the popular SDXL model and is on par with the proprietary Stable Diffusion 3 with 8B parameters. Moreover, given the same computational resources, a ReNO-optimized one-step model outperforms widelyused open-source models such as SDXL and PixArt-α, highlighting the efficiency and effectiveness of ReNO in enhancing T2I model performance at inference time. Code is available at https://github.com/ExplainableML/ReNO. * equal contribution 38th Conference on Neural Information Processing Systems (NeurIPS 2024).

For agents

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

get_harvested_code_for_paper("2406.04312")
get_code_for_paper("2406.04312")
have("2406.04312")

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

curl https://syntology.ai/api/ran/2406.04312.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.04312.svg)](https://syntology.ai/paper/2406.04312)

Connect an agent — have() is free.