SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.23925 · NeurIPS · 2025

Latent Chain-of-Thought for Visual Reasoning

Zhiqiang Tao, Jian Wang, Jiebo Luo, Hang Hua, Guohao Sun, Sohail Dianat, Majid Rabbani, Raghuveer Rao

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 2 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/2510.23925.json · badge: /api/ran/2510.23925.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
heliossun/LaCoT canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
get_model_name_from_path Ran
ran; our contract draft was wrong, not the code
heliossun/LaCoT/src/utils.py
pointer only (licence: NONE) · get_code("fa6d2859d3461c9e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heliossun/LaCoT 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.

pad_sequence Ran
ran, honoured the contract we drafted
heliossun/LaCoT/src/training/data.py
pointer only (licence: NONE); the stored copy get_code serves, from ZL-KA/MICL, is pointer only (licence: NONE) · get_code("2109d5ac2845731d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heliossun/LaCoT 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.

truncate_sequence Ran
ran; our contract draft was wrong, not the code
heliossun/LaCoT/src/training/data.py
pointer only (licence: NONE) · get_code("533c2d12f5c89416")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heliossun/LaCoT 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.

load_pretrained_model Not yet run
unverified (harvested, no recorded run)
heliossun/LaCoT/src/utils.py
pointer only (licence: NONE) · get_code("e14d8abe35b899e2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heliossun/LaCoT 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. No invocation recorded.

qwen_2_mixed_modality_forward Not yet run
unverified (harvested, no recorded run)
heliossun/LaCoT/src/training/monkey_patch_forward.py
pointer only (licence: NONE) · get_code("36c0dbaa97aa4bdf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heliossun/LaCoT 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. No invocation 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, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 3 later) and 2 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
get_model_name_from_path 5 other papers
3 dated earlier, 2 later
2024.findings-emnlp.619 (2024 (year only))
MEDCARE: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation
2402.16050 (2024-02)
Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge
2404.09027 (2024-04)
MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts
and 2 more not named here
truncate_sequence 2 other papers
2 later
2607.04364 (2026-07)
RL Forgets! Towards Continual Policy Optimization
2608.18096 (2026-08)
MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluators
pad_sequence 1 other paper
1 later
2601.05707 (2026-01)
Multimodal In-context Learning for ASR of Low-resource Languages

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

Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs). However, existing training algorithms such as SFT, PPO, and GRPO may not generalize well across unseen reasoning tasks and heavily rely on a biased reward model. To address this challenge, we reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference. By leveraging diversity-seeking reinforcement learning algorithms, we introduce a novel sparse reward function for token-level learning signals that encourage diverse, high-likelihood latent CoT, overcoming deterministic sampling limitations and avoiding reward hacking. Additionally, we implement a Bayesian inference-scaling strategy that replaces costly Best-of-N and Beam Search with a marginal likelihood to efficiently rank optimal rationales and answers. We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks, in terms of effectiveness, generalization, and interpretability. The code is available at https://github.com/heliossun/LaCoT.

For agents

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

get_harvested_code_for_paper("2510.23925")
get_code_for_paper("2510.23925")
have("2510.23925")

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

curl https://syntology.ai/api/ran/2510.23925.json

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

[![Syntology run record](https://syntology.ai/api/ran/2510.23925.svg)](https://syntology.ai/paper/2510.23925)

Connect an agent — have() is free.