SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.09576 · 2020

LSQ+: Improving low-bit quantization through learnable offsets and better initialization

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 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; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 5 no recorded run), measured 2026-11-21; 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/2004.09576.json · badge: /api/ran/2004.09576.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
yashbhalgat/QualcommAI-MicroNet-submission-MixNet community (classifier label)
classifier basis not recorded on the link
3 ran · 5 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
FunctionStatusWhere it lives
flops_to_string Ran
ran; our contract draft was wrong, not the code
yashbhalgat/QualcommAI-MicroNet-submission-MixNet/lsq_quantizer/flops_counter.py
pointer only (licence: MIT); the stored copy get_code serves, from rui-qian/SoTA-3D-Object-Detection, is pointer only (licence: NONE) · get_code("ad708b63b59159a6")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yashbhalgat/QualcommAI-MicroNet-submission-MixNet, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

grad_scale Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from jiyoonkm/columnquant
pointer only; the stored copy get_code serves, from jiyoonkm/columnquant, is pointer only (licence: NONE) · get_code("a488bae52f1bfd5d")
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.

params_to_string Ran
ran; our contract draft was wrong, not the code
yashbhalgat/QualcommAI-MicroNet-submission-MixNet/lsq_quantizer/flops_counter.py
pointer only (licence: MIT) · get_code("4c52df27c25660c5")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yashbhalgat/QualcommAI-MicroNet-submission-MixNet, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

resume_checkpoint Ran
ran on a synthesized input
yashbhalgat/QualcommAI-MicroNet-submission-MixNet/lsq_quantizer/helpers.py
pointer only (licence: MIT) · get_code("e52c4d73ce21cdfa")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yashbhalgat/QualcommAI-MicroNet-submission-MixNet, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

round_pass Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from jiyoonkm/columnquant
pointer only; the stored copy get_code serves, from jiyoonkm/columnquant, is pointer only (licence: NONE) · get_code("ed1a69e092272dba")
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.

Conv1x1Bn Not yet run
unverified (harvested, no recorded run)
yashbhalgat/QualcommAI-MicroNet-submission-MixNet/lsq_quantizer/utils/mixnet.py
pointer only (licence: MIT) · get_code("40695dc7514bcb11")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yashbhalgat/QualcommAI-MicroNet-submission-MixNet, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

Conv3x3Bn Not yet run
unverified (harvested, no recorded run)
yashbhalgat/QualcommAI-MicroNet-submission-MixNet/lsq_quantizer/utils/mixnet.py
pointer only (licence: MIT) · get_code("86d29f3a94353011")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yashbhalgat/QualcommAI-MicroNet-submission-MixNet, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

add_lsqmodule Not yet run
unverified (harvested, no recorded run)
yashbhalgat/QualcommAI-MicroNet-submission-MixNet/lsq_quantizer/utils/add_lsqmodule.py
pointer only (licence: MIT) · get_code("572064beb59d24e5")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yashbhalgat/QualcommAI-MicroNet-submission-MixNet, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

efficientnet_b0 Not yet run
unverified (harvested, no recorded run)
yashbhalgat/QualcommAI-MicroNet-submission-MixNet/lsq_quantizer/utils/effnet.py
pointer only (licence: MIT) · get_code("50cb4735b09169be")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yashbhalgat/QualcommAI-MicroNet-submission-MixNet, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

mixnet_s Not yet run
unverified (harvested, no recorded run)
yashbhalgat/QualcommAI-MicroNet-submission-MixNet/lsq_quantizer/utils/mixnet.py
pointer only (licence: MIT) · get_code("e8fc1d1906b17dfb")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yashbhalgat/QualcommAI-MicroNet-submission-MixNet, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 4 later) and 6 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
flops_to_string 5 other papers
5 later
2104.05707 (2021-04)
LocalViT: Analyzing Locality in Vision Transformers
2106.10823 (2021-06)
3D Object Detection for Autonomous Driving: A Survey
2112.13635 (2021-12)
AdaptivePose: Human Parts as Adaptive Points
and 2 more not named here
grad_scale 4 other papers
1 dated earlier, 3 later
1902.08153 (2019-02)
Learned Step Size Quantization
2203.08368 (2022-03)
Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance
2302.02210 (2023-02)
Oscillation-free Quantization for Low-bit Vision Transformers
and 1 more not named here
round_pass 4 other papers
1 dated earlier, 3 later
1902.08153 (2019-02)
Learned Step Size Quantization
2203.08368 (2022-03)
Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance
2302.02210 (2023-02)
Oscillation-free Quantization for Low-bit Vision Transformers
and 1 more not named here
params_to_string 1 other paper
1 later
2106.10823 (2021-06)
3D Object Detection for Autonomous Driving: A Survey

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Unlike ReLU, newer activation functions (like Swish, H-swish, Mish) that are frequently employed in popular efficient architectures can also result in negative activation values, with skewed positive and negative ranges. Typical learnable quantization schemes [PACT, LSQ] assume unsigned quantization for activations and quantize all negative activations to zero which leads to significant loss in performance. Naively using signed quantization to accommodate these negative values requires an extra sign bit which is expensive for low-bit (2-, 3-, 4-bit) quantization. To solve this problem, we propose LSQ+, a natural extension of LSQ, wherein we introduce a general asymmetric quantization scheme with trainable scale and offset parameters that can learn to accommodate the negative activations. Gradient-based learnable quantization schemes also commonly suffer from high instability or variance in the final training performance, hence requiring a great deal of hyper-parameter tuning to reach a satisfactory performance. LSQ+ alleviates this problem by using an MSE-based initialization scheme for the quantization parameters. We show that this initialization leads to significantly lower variance in final performance across multiple training runs. Overall, LSQ+ shows state-of-the-art results for EfficientNet and MixNet and also significantly outperforms LSQ for low-bit quantization of neural nets with Swish activations (e.g.: 1.8% gain with W4A4 quantization and upto 5.6% gain with W2A2 quantization of EfficientNet-B0 on ImageNet dataset). To the best of our knowledge, ours is the first work to quantize such architectures to extremely low bit-widths.

For agents

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

get_harvested_code_for_paper("2004.09576")
get_code_for_paper("2004.09576")
have("2004.09576")

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

curl https://syntology.ai/api/ran/2004.09576.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.09576.svg)](https://syntology.ai/paper/2004.09576)

Connect an agent — have() is free.