Papers › TroL: Traversal of Layers for Large Language and Vision Models
TroL: Traversal of Layers for Large Language and Vision Models
Byung-Kwan Lee, Sangyun Chung, Chae Won Kim, Beomchan Park, Yong Man Ro
Large language and vision models (LLVMs) have been driven by the generalization power of large language models (LLMs) and the advent of visual instruction tuning. Along with scaling them up directly, these models enable LLVMs to showcase powerful vision language (VL) performances by covering diverse tasks via natural language instructions. However, existing open-source LLVMs that perform comparably to closed-source LLVMs such as GPT-4V are often considered too large (e.g., 26B, 34B, and 110B parameters), having a larger number of layers. These large models demand costly, high-end resources for both training and inference. To address this issue, we present a new efficient LLVM family with 1.8B, 3.8B, and 7B LLM model sizes, Traversal of Layers (TroL), which enables the reuse of layers in a token-wise manner. This layer traversing technique simulates the effect of looking back and retracing the answering stream while increasing the number of forward propagation layers without physically adding more layers. We demonstrate that TroL employs a simple layer traversing approach yet efficiently outperforms the open-source LLVMs with larger model sizes and rivals the performances of the closed-source LLVMs with substantial sizes.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2406.12246")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2406.12246", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2406.12246")
Code
Syntology 30 code samples harvested from 1 repository linked to this paper: 23 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 11 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 30 samples from 1 repository, 23 ran (12 with no instrument failure; 11 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 23 samples that ran have no recorded date.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
30 samples harvested: 23 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 11 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 30 of the 30 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from byungkwanlee/trol. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
census: 15 implementations from 60 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 trol/arch_phi3/modeling_phi3.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only ·
30d7eec482ebf6b1 · report
fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded, date not recorded 857584bac85d8412 · report
fixture: returned IdentityMap · level recorded 2026-09-22 9822da74ee01d405 · report
fixture: returned InternLM2Config · level recorded 2026-09-22 4361bf5382e3c53c · report
fixture: returned InternLM2DecoderLayer · level recorded 2026-09-22 47e0c2b232b80540 · report
fixture: returned InternLM2DynamicNTKScalingRotaryEmbedding · level recorded 2026-09-22 d0ec931771ba164d · report
fixture: returned InternLM2FlashAttention2 · level recorded 2026-09-22 f4d34988b284f4c3 · report
fixture: returned InternLM2MLP · level recorded 2026-09-22 e7b40b692059c263 · report
fixture: returned InternLM2PreTrainedModel · level recorded 2026-09-22 817ef1d945956306 · report
fixture: returned InternLM2RMSNorm · level recorded 2026-09-22 611ae4bdd7a59aa3 · report
fixture: returned InternLM2RotaryEmbedding · level recorded 2026-09-22 cce1025c634158b5 · report
fixture: returned LoRA · level recorded 2026-09-22 7df2e495a39e79bb · report
fixture: returned TroLCausalLMOutputWithPast · level recorded 2026-09-22 census: 13 implementations from 13 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 trol/arch_internlm2/modeling_trol.py ran · our draft was wrong no licence file found · pointer only ·
3794e953547aa39d · report
fixture: signature mask:Tensor/2/float, dtype:dtype/0/?, tgt_len:int/0/int · returned Tensor · level recorded 2026-09-22 1df4c4c3e8d2767d · report
fixture: signature attention_mask:Tensor/2/int · returned tuple · level recorded 2026-09-22 3a68636f8c901f91 · report
fixture: signature input_ids_shape:Size/1/int, dtype:dtype/0/?, device:device/0/?, past_key_values_length:int/0/int · returned Tensor · level recorded 2026-09-22 census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket trol/arch_phi3/modeling_phi3.py ran · our draft was wrong no licence file found · pointer only ·
bac65c3dafaec040 · report
fixture: signature q:Tensor/4/float, k:Tensor/4/float, cos:Tensor/3/float, sin:Tensor/3/float, position_ids:NoneType/0/?, unsqueeze_dim:int/0/int · returned tuple · level recorded, date not recorded census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket trol/arch_internlm2/modeling_internlm2.py ran; the contract check could not run (RAISES) no licence file found · pointer only ·
051ebcfa8673a02e · report
fixture: signature q:Tensor/3/float, k:Tensor/3/float, cos:Tensor/2/float, sin:Tensor/2/float, position_ids:Tensor/2/int, unsqueeze_dim:int/0/int · returned tuple · level recorded 2026-09-26 4836c910f4ac2e06 · report
fixture: signature hidden_size:int/0/int · returned Sequential · level recorded 2026-09-22 ec01154f26b3b92e · report
fixture: signature hidden_size:int/0/int · returned Sequential · level recorded 2026-09-24 53e08d7b0496620d · report
fixture: returned CLIPVisionTower · level recorded 2026-09-22 census: 15 implementations from 60 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 trol/arch_internlm2/modeling_trol.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only ·
6045450d1a869974 · report
fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded 2026-09-22 census: 15 implementations from 60 papers, 2 distinct outputs on one shared input trol/arch_internlm2/modeling_internlm2.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only ·
c0aae1f053da2578 · report
fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded 2026-09-24 census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 trol/arch_internlm2/modeling_internlm2.py ran · our draft was wrong fingerprinted no licence file found · pointer only ·
b99eea6376d1e212 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded 10e2214bdfa59401 · report
b56683a8ab013eed · report
47c71786c33638b3 · report
f16a36d9f1f29fad · report
b163c3fb95a74dcc · report
census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket trol/arch_internlm2/modeling_trol.py unverified no licence file found · pointer only ·
c028aebfc37921e4 · report
6b626dcd8d06f0af · report
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.
1 assembly on this paper: 1 harvested, 0 generated.
harvested Assembly for TroL (graph method: TroL). 24 bricks; individually on a fixture: 18 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.
- TroLForCausalLM entry · level 0 · unverified ·
f16a36d9f1f29fad - InternLM2Model model · level 0 · unverified ·
47c71786c33638b3 - InternLM2PreTrainedModel helper · level 1 · ran ·
e7b40b692059c263 - TroLCausalLMOutputWithPast model · level 1 · ran ·
7df2e495a39e79bb - build_vision_projector helper · level 1 · ran · our draft was wrong ·
4836c910f4ac2e06 - build_vision_tower helper · level 1 · ran ·
53e08d7b0496620d - InternLM2Config helper · level 1 · ran ·
9822da74ee01d405 - InternLM2DecoderLayer model · level 1 · ran ·
4361bf5382e3c53c - InternLM2RMSNorm helper · level 1 · ran ·
817ef1d945956306 - _expand_mask helper · level 1 · ran · our draft was wrong ·
3794e953547aa39d - _import_flash_attn helper · level 0 · unverified ·
b163c3fb95a74dcc - _make_causal_mask helper · level 1 · ran; the contract check could not run (RAISES) ·
3a68636f8c901f91 - IdentityMap helper · level 1 · ran ·
857584bac85d8412 - CLIPVisionTower helper · level 0 · unverified ·
10e2214bdfa59401 - InternLM2Attention model · level 0 · unverified ·
b56683a8ab013eed - InternLM2FlashAttention2 helper · level 1 · ran ·
d0ec931771ba164d - InternLM2MLP helper · level 1 · ran ·
f4d34988b284f4c3 - InternLM2DynamicNTKScalingRotaryEmbedding helper · level 1 · ran ·
47e0c2b232b80540 - InternLM2RotaryEmbedding helper · level 1 · ran ·
611ae4bdd7a59aa3 - LoRA helper · level 1 · ran ·
cce1025c634158b5 - apply_rotary_pos_emb helper · level 0 · unverified ·
c028aebfc37921e4 - repeat_kv helper · level 1 · ran; the contract check could not run (RAISES) ·
6045450d1a869974 - _get_unpad_data helper · level 1 · ran · our draft was wrong ·
1df4c4c3e8d2767d - rotate_half helper · level 1 · ran · our draft was wrong ·
e03d53ba9d4f9ae5
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2406.12246") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Visual Question Answering | MM-Vet | TroL-7B | GPT-4 score | 54.7 | #49 of 231 | Archive leaderboard | report |
| Visual Question Answering | MM-Vet | TroL-7B | Params | 7B | #49 of 231 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections