Papers › Value Residual Learning For Alleviating Attention Concentration In Transformers

Value Residual Learning For Alleviating Attention Concentration In Transformers

23 Oct 2024arXiv:2410.17897archive 2025-07-28

Zhanchao Zhou, Tianyi Wu, Zhiyun Jiang, Zhenzhong Lan

Transformers can capture long-range dependencies using self-attention, allowing tokens to attend to all others directly. However, stacking multiple attention layers leads to attention concentration. One natural way to address this issue is to use cross-layer attention, allowing information from earlier layers to be directly accessible to later layers. However, this approach is computationally expensive. To address this problem, we propose Transformer with residual value (ResFormer) which approximates cross-layer attention through adding a residual connection from the values of the the first layer to all subsequent layers. Based on this method, one variant is the Transformer with single layer value (SVFormer), where all layers share the same value embedding from first layer. Comprehensive empirical evidence demonstrates ResFormer achieves equivalent validation loss with 10.4% fewer model parameters and 13.6% less training data compared to Transformer, while maintaining similar memory usage and computational cost. Besides, SVFormer reduces KV cache size by nearly half with only a small performance penalty and can be integrated with other KV-efficient methods, yielding further reductions in KV cache, with performance influenced by sequence length and cumulative learning rate. Further visualization results suggest that Resformer and SVFormer alleviate attention concentration in deeper layers through avoiding value-state drains and enhance representation across most layers.

PaperPDFCodeCode Syntology ran

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):

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 9 ran (4 with no instrument failure; 5 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 on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 9 samples that ran have no recorded date.

Zcchill/Value-Residual-Learning officialmentioned in papermentioned on GitHubpytorchMITSyntology: 12 samples, 9 ran (5 instrument-failed) · 3 unverified report

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

12 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 3 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.

4ran · our draft was wrong
1ran; the contract check could not run
4ran
3unverified

Licence: 1 of the 12 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Zcchill/Value-Residual-Learning. “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”. “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.

Zcchill/Value-Residual-Learning official repository 12 samples, 9 ran (5 instrument-failed) · 3 unverified
repeat_kv in 244 papers
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
src/modeling/modeling_llama_NeuTRENO_lambda04.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 30d7eec482ebf6b1 · report fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded, date not recorded
apply_rotary_pos_emb in 393 papers
census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket
src/modeling/modeling_llama_NeuTRENO_lambda04.py ran · our draft was wrong MIT (permissive) · 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
calculate_entropy in 22 papers analyze/get_entropy.py ran · our draft was wrong MIT (permissive) · ed28cdaf289e0435 · report fixture: signature attention_weights:Tensor/3/float · returned float64 · level recorded 2026-09-26
calculate_similarity in 15 papers analyze/get_similarity.py ran MIT (permissive) · b486d0595afc6517 · report fixture: signature data:Tensor/3/float, head_operation:str/0/str · returned float · level recorded 2026-09-26
data_generator_interleave src/dataloaders.py ran MIT (permissive) · 394fe2301da65126 · report fixture: signature datasets:dict/0/?, probabilities:ndarray/1/float, seed:int/0/int · returned IterableDataset · level recorded 2026-09-26
domain_data_gen src/dataloaders.py ran MIT (permissive) · f63c6075be4f4b9e · report fixture: signature shards:list/1/str, domain_name:str/0/str, max_samples_domain:int/0/int, loop:bool/0/bool, seed:int/0/int, shuffle:bool/0/bool, keep_in_memory:bool/0/bool · returned generator · level recorded 2026-09-26
extract_loss analyze/plot_relative_loss.py ran MIT (permissive) · 7beae4353ada6744 · report fixture: signature log_file_path:str/0/str, section:list/1/int · returned tuple · level recorded 2026-09-26
moving_average in 46 papers
census: 9 implementations from 11 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
analyze/plot_relative_loss.py ran · our draft was wrong fingerprinted MIT (permissive) · 01bbee0c31a1d848 · report fixture: signature data:ndarray/1/float, window_size:int/0/int · returned ndarray · level recorded 2026-09-26
rotate_half in 424 papers
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
src/modeling/modeling_llama_NeuTRENO_lambda04.py ran · our draft was wrong fingerprinted MIT (permissive) · b99eea6376d1e212 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
get_perdomain_datasets src/dataloaders.py unverified MIT (permissive) · 5cf3265bba37e71f · report
get_scheduler_extended src/trainer.py unverified MIT (permissive) · 3c38d2d597def42a · report
load_tf_weights_in_gpt2 in 68 papers src/modeling/modeling_gpt2_baseline.py unverified MIT (permissive) here; the stored copy is pointer only · eae14ebac1cd9c52 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionAttention SinksBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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