SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.04431 · 2024

Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

arXiv · PDF · Open in the Atlas

Code that ran

14 of 19 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; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 13 failures of our instrument; 5 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/2412.04431.json · badge: /api/ran/2412.04431.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
FoundationVision/VAR canonical (classifier label)
classifier basis not recorded on the link
7 ran · 5 no recorded run
FoundationVision/Infinity canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
4 ran · 0 no recorded run
FunctionStatusWhere it lives
Normalize Ran
ran; our contract draft was wrong, not the code
FoundationVision/VAR/models/basic_vae.py
code served (permissive licence) · get_code("9fcdaa6e423e8aa7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned GroupNorm. 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

torch.manual_seed(0)

# The Normalize function takes in_channels and num_groups (with default 32)
# It returns a GroupNorm layer

# in_channels: number of channels for the GroupNorm layer
# num_groups: number of groups to separate the channels into (default 32)

# We need to provide valid arguments where num_groups divides in_channels evenly
# Let's use in_channels=64 so it's divisible by the default num_groups=32

ARGS = {
    'in_channels': 64,
    'num_groups': 32
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GroupNorm — a GroupNorm output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GroupNorm 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
allgather Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
FoundationVision/VAR/dist.py
code served (permissive licence) · get_code("e847ee15f089dee6")
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 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.distributed as tdist

torch.manual_seed(0)

# Create a small tensor for testing
# The function checks t.is_cuda and uses it in all_gather and torch.cat
# Shape: (2, 4) - small batch with 4 dimensions
tensor_arg = torch.randn(2, 4)

# Define ARGS dict with all parameters
ARGS = {
    "t": tensor_arg,
    "cat": True
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
aug_with_positive_prompt Ran
ran, violated the contract we drafted
FoundationVision/Infinity/tools/run_infinity.py
code served (permissive licence) · get_code("9e7e8cb16293d38e")
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 str. 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

torch.manual_seed(0)

# The function takes a single parameter 'prompt' which is a string
# It checks if certain keywords are in the prompt and augments it if found
# No complex objects needed - just a string

ARGS = {
    'prompt': 'a man standing in the park'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
drop_path Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
FoundationVision/VAR/models/helpers.py
code served (permissive licence) · get_code("971ae8d2d8313e30")
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 Tensor, ndim 4, dtype family float, shape (2, 4, 3, 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

torch.manual_seed(0)

# Create a small tensor for testing
# Shape: (batch_size=2, channels=4, height=3, width=3) - 4D tensor
x = torch.randn(2, 4, 3, 3)

ARGS = {
    "x": x,
    "drop_prob": 0.5,
    "training": True,
    "scale_by_keep": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
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, 3, 3) — shape (2, 4, 3, 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
encode_prompt Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
FoundationVision/Infinity/tools/run_infinity.py
code served (permissive licence) · get_code("c490ce79bba70918")
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 tuple. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Stand-in tokenizer class
class MockTokenizer:
    def __call__(self, text, max_length, padding, truncation, return_tensors):
        batch_size = len(text)
        seq_len = 10
        input_ids = torch.randint(0, 1000, (batch_size, seq_len))
        attention_mask = torch.ones(batch_size, seq_len, dtype=torch.long)
        attention_mask[0, 7:] = 0  # Make first sample shorter
        
        class TokenizerOutput:
            def __init__(self, input_ids, attention_mask):
                self.input_ids = input_ids
                self.attention_mask = attention_mask
        
        return TokenizerOutput(input_ids, attention_mask)

# Stand-in text encoder class
class MockTextEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(1000, 4)
    
    def forward(self, input_ids, attention_mask):
        batch_size = input_ids.shape[0]
        seq_len = input_ids.shape[1]
        hidden_dim = 4
        last_hidden_state = torch.randn(batch_size, seq_len, hidden_dim)
        
        class EncoderOutput:
            def __init__(self, last_hidden_state):
                self.last_hidden_state = last_hidden_state
            
            def __getitem__(self, key):
                if key == 'last_hidden_state':
                    return self.last_hidden_state
                raise KeyError(key)
        
        return EncoderOutput(last_hidden_state)

text_tokenizer = MockTokenizer()
text_encoder = MockTextEncoder()
prompt = "a man wearing a hat"
enable_positive_prompt = True

ARGS = {
    'text_tokenizer': text_tokenizer,
    'text_encoder': text_encoder,
    'prompt': prompt,
    'enable_positive_prompt': enable_positive_prompt
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
extract_key_val Ran
ran; our contract draft was wrong, not the code
FoundationVision/Infinity/tools/run_infinity.py
code served (permissive licence) · get_code("8535a42ccd56fce0")
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 dict. 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 re

def extract_key_val(text):
    pattern = '<(.+?):(.+?)>'
    matches = re.findall(pattern, text)
    key_val = {}
    for match in matches:
        key_val[match[0]] = match[1].lstrip()
    return key_val

# The function takes a single parameter: text (a string)
# It uses regex to find patterns like <key:value> and returns a dict
# We need to provide a string with some key-value pairs in the specified format

ARGS = {
    "text": "<name: Alice><age: 30><city: New York>"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
get_params_num Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from FoundationVision/Infinity
pointer only · get_code("6a19741de3a68058")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

gumbel_softmax_with_rng Ran
ran; our contract draft was wrong, not the code
FoundationVision/VAR/models/helpers.py
code served (permissive licence) · get_code("e543491ea064c733")
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 2, dtype family float, shape (2, 4) 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 torch.nn.functional as F

torch.manual_seed(0)

# Create a small logits tensor (batch_size=2, num_classes=4)
logits = torch.randn(2, 4)

# Create an RNG generator
rng = torch.Generator()
rng.manual_seed(42)

ARGS = {
    "logits": logits,
    "tau": 1.0,
    "hard": False,
    "eps": 1e-10,
    "dim": -1,
    "rng": rng
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
nonlinearity Ran
ran; our contract draft was wrong, not the code
FoundationVision/VAR/models/basic_vae.py
code served (permissive licence) · get_code("3137073275f8c21a")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

# The function takes a single parameter 'x' which is used with:
# - multiplication operator (*)
# - torch.sigmoid() function
# This means x should be a tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
normalize_01_into_pm1 Ran
ran; our contract draft was wrong, not the code
FoundationVision/VAR/utils/data.py
code served (permissive licence) · get_code("eabecb1bb23906fe")
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 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

# The function normalize_01_into_pm1 takes a single parameter 'x'
# and performs: x.add(x).add_(-1)
# This means x must be a tensor with .add() method
# The function doubles x and subtracts 1, converting [0,1] range to [-1,1]

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
sample_with_top_k_top_p_ Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
FoundationVision/VAR/models/helpers.py
code served (permissive licence) · get_code("80371584448f2f6e")
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 3, dtype family int, shape (2, 3, 1) 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

torch.manual_seed(0)

# Create logits tensor with shape (B, l, V) = (batch_size, sequence_length, vocab_size)
# Using distinct dimensions: B=2, l=3, V=4
logits_BlV = torch.randn(2, 3, 4)

# top_k parameter: filter to keep only top k logits
top_k = 2

# top_p parameter: nucleus sampling threshold
top_p = 0.9

# rng parameter: random number generator (None or torch.Generator)
rng = None

# num_samples parameter: number of samples to draw per position
num_samples = 1

ARGS = {
    "logits_BlV": logits_BlV,
    "top_k": top_k,
    "top_p": top_p,
    "rng": rng,
    "num_samples": num_samples,
}
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 Tensor, ndim 3, dtype family int, shape (2, 3, 1) — shape (2, 3, 1) 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
sample_with_top_k_top_p_also_inplace_modifying_logits_ Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from FoundationVision/Infinity
pointer only · get_code("9526ce09c7148703")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

sampling_with_top_k_top_p_also_inplace_modifying_probs_ Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from FoundationVision/Infinity
pointer only · get_code("5451c3f14c7e520c")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

timed Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from ByteDance-Seed/Bagel
pointer only · get_code("844a4aecea80d106")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

allreduce Not yet run
unverified (harvested, no recorded run)
FoundationVision/VAR/dist.py
code served (permissive licence) · get_code("ff4c548fd07140d0")
How it ran

no invocation recorded.

build_dataset Not yet run
unverified (harvested, no recorded run)
FoundationVision/VAR/utils/data.py
code served (permissive licence) · get_code("8ff7703f731423de")
How it ran

no invocation recorded.

make_attn Not yet run
unverified (harvested, no recorded run)
FoundationVision/VAR/models/basic_vae.py
code served (permissive licence) · get_code("793c7e2489dd8dfc")
How it ran

no invocation recorded.

new_group Not yet run
unverified (harvested, no recorded run)
FoundationVision/VAR/dist.py
code served (permissive licence) · get_code("826ea3fc406a6a09")
How it ran

no invocation recorded.

pil_loader Not yet run
unverified (harvested, no recorded run)
FoundationVision/VAR/utils/data.py
code served (permissive licence) · get_code("b1714d4e3b7ac3b9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 18 are also present in other papers whose code we hold (16 with at least one paper dated earlier, 2 the same month, 18 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
nonlinearity 156 other papers
115 dated earlier, 2 the same month, 35 later, 4 same year, order not determinable · 25 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 153 more not named here
drop_path 66 other papers
44 dated earlier, 1 the same month, 18 later, 1 same year, order not determinable, 2 undated · 15 only as an assembly brick
1906.01502 (2019-06)
How multilingual is Multilingual BERT?
2011.10566 (2020-11)
Exploring Simple Siamese Representation Learning
2103.03230 (2021-03)
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
and 63 more not named here
Normalize 54 other papers
41 dated earlier, 12 later, 1 same year, order not determinable · 3 only as an assembly brick
2204.06125 (2022-04)
Hierarchical Text-Conditional Image Generation with CLIP Latents
2208.13753 (2022-08)
Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis
2211.13221 (2022-11)
Latent Video Diffusion Models for High-Fidelity Long Video Generation
and 51 more not named here
allgather 8 other papers
4 dated earlier, 4 later
2404.02905 (2024-04)
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
2406.09750 (2024-06)
ControlVAR: Exploring Controllable Visual Autoregressive Modeling
2408.01181 (2024-08)
VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling
and 5 more not named here
allreduce 8 other papers
4 dated earlier, 4 later
2404.02905 (2024-04)
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
2406.09750 (2024-06)
ControlVAR: Exploring Controllable Visual Autoregressive Modeling
2408.01181 (2024-08)
VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling
and 5 more not named here
gumbel_softmax_with_rng 8 other papers
3 dated earlier, 5 later
2408.01181 (2024-08)
VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling
2410.10812 (2024-10)
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
2411.10433 (2024-11)
M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation
and 5 more not named here
make_attn 8 other papers
4 dated earlier, 4 later
2404.02905 (2024-04)
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
2408.01181 (2024-08)
VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling
2410.10812 (2024-10)
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
and 5 more not named here
new_group 8 other papers
4 dated earlier, 4 later
2404.02905 (2024-04)
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
2406.09750 (2024-06)
ControlVAR: Exploring Controllable Visual Autoregressive Modeling
2408.01181 (2024-08)
VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling
and 5 more not named here
sample_with_top_k_top_p_ 8 other papers
3 dated earlier, 5 later
2408.01181 (2024-08)
VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling
2410.10812 (2024-10)
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
2411.10433 (2024-11)
M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation
and 5 more not named here
sample_with_top_k_top_p_also_inplace_modifying_logits_ 5 other papers
1 dated earlier, 4 later
2404.02905 (2024-04)
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
2507.18537 (2025-07)
TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation
and 2 more not named here
get_params_num 4 other papers
1 dated earlier, 3 later
2404.02905 (2024-04)
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
2508.15772 (2025-08)
Visual Autoregressive Modeling for Instruction-Guided Image Editing
and 1 more not named here
normalize_01_into_pm1 4 other papers
1 dated earlier, 3 later
2411.10433 (2024-11)
M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation
2507.11441 (2025-07)
Implementing Adaptations for Vision AutoRegressive Model
2508.15772 (2025-08)
Visual Autoregressive Modeling for Instruction-Guided Image Editing
and 1 more not named here
sampling_with_top_k_top_p_also_inplace_modifying_probs_ 4 other papers
1 dated earlier, 3 later
2404.02905 (2024-04)
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
2508.15772 (2025-08)
Visual Autoregressive Modeling for Instruction-Guided Image Editing
and 1 more not named here
timed 4 other papers
1 dated earlier, 3 later
2310.11513 (2023-10)
GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment
2505.14683 (2025-05)
Emerging Properties in Unified Multimodal Pretraining
2505.23380 (2025-05)
UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
and 1 more not named here
build_dataset 2 other papers
1 dated earlier, 1 later
2411.10433 (2024-11)
M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation
2601.07293 (2026-01)
Inference-Time Scaling for Visual AutoRegressive modeling by Searching Representative Samples
pil_loader 2 other papers
1 dated earlier, 1 later
2411.10433 (2024-11)
M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation
2601.07293 (2026-01)
Inference-Time Scaling for Visual AutoRegressive modeling by Searching Representative Samples
aug_with_positive_prompt 1 other paper
1 later
2507.18537 (2025-07)
TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation
extract_key_val 1 other paper
1 later
2507.18537 (2025-07)
TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation

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

We present Infinity, a Bitwise Visual AutoRegressive Modeling capable of generating high-resolution, photorealistic images following language instruction. Infinity redefines visual autoregressive model under a bitwise token prediction framework with an infinite-vocabulary tokenizer &amp; classifier and bitwise self-correction mechanism, remarkably improving the generation capacity and details. By theoretically scaling the tokenizer vocabulary size to infinity and concurrently scaling the transformer size, our method significantly unleashes powerful scaling capabilities compared to vanilla VAR. Infinity sets a new record for autoregressive text-to-image models, outperforming top-tier diffusion models like SD3-Medium and SDXL. Notably, Infinity surpasses SD3-Medium by improving the GenEval benchmark score from 0.62 to 0.73 and the ImageReward benchmark score from 0.87 to 0.96, achieving a win rate of 66%. Without extra optimization, Infinity generates a high-quality 1024x1024 image in 0.8 seconds, making it 2.6x faster than SD3-Medium and establishing it as the fastest text-to-image model. Models and codes will be released to promote further exploration of Infinity for visual generation and unified tokenizer modeling.

For agents

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

get_harvested_code_for_paper("2412.04431")
get_code_for_paper("2412.04431")
have("2412.04431")

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

curl https://syntology.ai/api/ran/2412.04431.json

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

[![Syntology run record](https://syntology.ai/api/ran/2412.04431.svg)](https://syntology.ai/paper/2412.04431)

Connect an agent — have() is free.