Kanchana Ranasinghe, Michael Ryoo, Mu Cai, Yong Lee, Xiang Li, Jinghuan Shang, Kumara Kahatapitiya, Cristina Mata, Jongwoo Park, Yoo Jang, Ryan Burgert
13 of 15 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; 6 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 2 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/2406.20095.json · badge: /api/ran/2406.20095.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.
| Repository | Role | Ran |
|---|---|---|
| LostXine/LLaRA | canonical (classifier label) classifier basis: census |
13 ran · 0 no recorded run |
| lostxine/llara | community Papers with Code archive |
0 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| action_to_text | Ran ran; our contract draft was wrong, not the code |
LostXine/LLaRA/eval/eval-rt2.py code served (permissive licence) · get_code("ca12919c16b4a4f5") How it ranRan 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 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.
|
| all_gather | Ran ran, honoured the contract we drafted |
LostXine/LLaRA/maskrcnn/utils.py code served (permissive licence) · get_code("91dc40b44121e385") How it ranRan 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 3, 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.
|
| collate_fn | Ran ran; our contract draft was wrong, not the code |
LostXine/LLaRA/train-llava/llava/eval/model_vqa_loader.py code served (permissive licence) · get_code("20e4f665698a3d18") How it ranRan 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.
|
| collate_fn | Ran ran; our contract draft was wrong, not the code |
LostXine/LLaRA/maskrcnn/utils.py code served (permissive licence) · get_code("0ec4ff97dc3a732e") How it ranRan 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.
|
| get_bounding_box | Ran ran, honoured the contract we drafted |
LostXine/LLaRA/eval/vima_utils.py code served (permissive licence) · get_code("b77412266f910afa") How it ranRan 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 int; 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.
|
| get_chunk | Ran ran; our contract draft was wrong, not the code |
LostXine/LLaRA/train-llava/llava/eval/model_vqa.py code served (permissive licence) · get_code("42a46570620cd9fa") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, ndim 1, dtype family int; 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.
|
| load_image | Ran ran, honoured the contract we drafted |
LostXine/LLaRA/train-llava/predict.py code served (permissive licence) · get_code("9b3c1cb391672ccb") How it ranRan 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 Image. 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.
|
| pix2pos_front | Ran ran, honoured the contract we drafted |
LostXine/LLaRA/eval/vima_utils.py code served (permissive licence) · get_code("c072147381d37e39") How it ranRan 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.
|
| pos2pix_front | Ran ran, honoured the contract we drafted |
LostXine/LLaRA/eval/vima_utils.py code served (permissive licence) · get_code("67c19efa51776cee") How it ranRan 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 int; 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.
|
| quantize_float_to_text | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
LostXine/LLaRA/eval/eval-rt2.py code served (permissive licence) · get_code("7b583a6159d6539d") How it ranRan 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 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.
|
| reduce_dict | Ran ran; our contract draft was wrong, not the code |
LostXine/LLaRA/maskrcnn/utils.py code served (permissive licence) · get_code("d4ff7353113eadb2") How it ranRan 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 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.
|
| split_list | Ran ran; our contract draft was wrong, not the code |
LostXine/LLaRA/train-llava/llava/eval/model_vqa.py code served (permissive licence) · get_code("076c252c52cbb161") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list. 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.
|
| text_to_float | Ran ran, honoured the contract we drafted |
LostXine/LLaRA/eval/eval-rt2.py code served (permissive licence) · get_code("2c1424966e072851") How it ranRan 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.
|
| LlavaLlamaForCausalLM | Not yet run unverified (harvested, no recorded run) |
lostxine/llara/train-llava/llava/model/language_model/llava_llama.py code served (permissive licence) · get_code("e8b1d3f3b543afbc") How it ranno invocation recorded. |
| LlavaMetaForCausalLM | Not yet run unverified (harvested, no recorded run) |
lostxine/llara/train-llava/llava/model/language_model/llava_llama.py code served (permissive licence) · get_code("6106e117d2c9317b") How it ranno invocation recorded. |
Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 4 the same month, 5 later) and 9 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| split_list | 197 other papers 60 dated earlier, 22 the same month, 108 later, 6 same year, order not determinable, 1 undated |
2112.05682 (2021-12) Self-attention Does Not Need $O(n^2)$ Memory |
2306.17107 (2023-06) LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding 2307.10490 (2023-07) Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs and 194 more not named here |
| get_chunk | 189 other papers 58 dated earlier, 21 the same month, 104 later, 6 same year, order not determinable |
2112.05682 (2021-12) Self-attention Does Not Need $O(n^2)$ Memory |
2306.17107 (2023-06) LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding 2307.10490 (2023-07) Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs and 186 more not named here |
| load_image | 85 other papers 31 dated earlier, 4 the same month, 46 later, 4 same year, order not determinable |
2112.05682 (2021-12) Self-attention Does Not Need $O(n^2)$ Memory |
2305.10973 (2023-05) Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold 2307.10490 (2023-07) Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs and 82 more not named here |
| collate_fn | 54 other papers 11 dated earlier, 4 the same month, 39 later |
2308.13566 (2023-08) MLLM-DataEngine: An Iterative Refinement Approach for MLLM |
2310.08588 (2023-10) Octopus: Embodied Vision-Language Programmer from Environmental Feedback 2311.07362 (2023-11) Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision and 51 more not named here |
| collate_fn | 7 other papers 6 dated earlier, 1 later |
1405.0312 (2014-05) Microsoft COCO: Common Objects in Context |
1811.10200 (2018-11) IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments 1901.07973 (2019-01) DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images and 4 more not named here |
| all_gather | 3 other papers 3 dated earlier |
2204.06859 (2022-04) Semi-Supervised Training to Improve Player and Ball Detection in Soccer |
2303.05148 (2023-03) Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection 2311.15939 (2023-11) Unleashing the Power of Prompt-driven Nucleus Instance Segmentation |
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Vision Language Models (VLMs) have recently been leveraged to generate robotic actions, forming Vision-Language-Action (VLA) models. However, directly adapting a pretrained VLM for robotic control remains challenging, particularly when constrained by a limited number of robot demonstrations. In this work, we introduce LLaRA: Large Language and Robotics Assistant, a framework that formulates robot action policy as visuo-textual conversations and enables an efficient transfer of a pretrained VLM into a powerful VLA, motivated by the success of visual instruction tuning in Computer Vision. First, we present an automated pipeline to generate conversation-style instruction tuning data for robots from existing behavior cloning datasets, aligning robotic actions with image pixel coordinates. Further, we enhance this dataset in a self-supervised manner by defining six auxiliary tasks, without requiring any additional action annotations. We show that a VLM finetuned with a limited amount of such datasets can produce meaningful action decisions for robotic control. Through experiments across multiple simulated and real-world tasks, we demonstrate that LLaRA achieves stateof-the-art performance while preserving the generalization capabilities of large language models. The code, datasets, and pretrained models are available at https://github.com/LostXine/LLaRA.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.20095")
get_code_for_paper("2406.20095")
have("2406.20095")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.20095.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.20095)
Connect an agent — have() is free.