- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies cross-model KV cache reuse to avoid redundant prefilling during model switching. The authors propose CacheLink, which introduces a coupled K/V residual correction module on top of a frozen Ridge mapping, optimized through receiver-side CE and KL supervision. Experiments across four model pairs and seven benchmarks show improvements over Ridge while preserving zero-prefill efficiency.
Critical strengths
Cross-model KV cache reuse is relevant to multi-model collaboration, model routing, and long-context inference. This paper addresses the quality degradation associated with cache transfer and attempts to optimize the transferred cache based on the receiver's actual predictive behavior rather than solely minimizing numerical KV reconstruction errors. The reported improvements across multiple model pairs suggest potential practical value.
Critical weaknesses
W1. Limited methodological novelty and insufficient validation of the proposed architecture.
Cross-model KV transfer, nonlinear correction, and receiver-side functional supervision have already been explored in prior work. For instance, Heo et al. studied the mismatch between reconstruction fidelity and downstream performance, while Dery et al. employed receiver-side continuation losses.
The main novelty appears to be the coupled K/V late-fusion residual architecture. However, the paper lacks comparisons with simpler alternatives, such as independent K/V residuals or a joint MLP under identical supervision. Consequently, it remains unclear whether the improvements stem from the proposed architecture or from combining existing techniques.
W2. Insufficient baseline comparisons and concerns about experimental reliability.
Although Ridge, CacheBridge, and LatentAlign are included, important comparisons are missing, particularly the nonlinear MLP mapping from Heo et al. and simple functionally supervised residual baselines. Other closely related learning-based approaches are also insufficiently discussed.
Moreover, LatentAlign scores zero across all long-context evaluations, while CacheBridge performs unexpectedly poorly on several tasks. Without sufficient validation of baseline implementations, training convergence, and hyperparameter selection, the fairness and reliability of these comparisons remain uncertain. Some training configurations are also insufficiently documented.
Questions for authors
Q1. Core technical novelty
Given that cross-model KV transfer, nonlinear correction, and receiver-side functional supervision have already been explored in prior work, could the authors clarify the core technical contribution that distinguishes CacheLink from existing approaches? In particular, what new capabilities or substantive advantages does the proposed coupled K/V late-fusion residual architecture provide compared with existing residual correction methods?
Q2. Necessity of the proposed architecture
Under the same Ridge initialization, training data, approximately matched parameter budget, and CE+KL supervision, does the proposed coupled K/V residual architecture consistently and significantly outperform simpler alternatives, such as independent K/V residual modules or a straightforward joint MLP? How do the current experiments demonstrate that the improvements arise specifically from the proposed architecture rather than additional model capacity or functional supervision?
Q3. Baseline selection and fairness
Why does the paper not include the nonlinear MLP mapping explored by Heo et al., or a simple Ridge-plus-residual mapper trained with the same functional objective, as direct baselines?
In addition, related approaches such as Dense Latent Communication, LatentPort, and SCD have explored cross-model state transfer, learned correction mechanisms, or functional optimization. Although these methods differ in architecture, available input states, and deployment constraints, could the authors further clarify the substantive differences between CacheLink and these approaches? How does the current baseline selection sufficiently support the claimed performance advantages? For methods that permit comparable experimental settings, could more direct comparisons be provided?
Q4. Unexpected baseline results
Why does LatentAlign obtain zero scores across all long-context evaluations? What explains the substantially degraded performance of CacheBridge on certain tasks? Have the authors verified the correctness of the baseline implementations, training convergence, and appropriate hyperparameter configurations? Could representative failure cases or reproduction results under the original experimental settings be provided to substantiate the validity of the comparisons?
Q5. Anonymous code accessibility and reproducibility
The anonymous code link provided in the paper could not be accessed from my environment. Could the authors verify the validity and access permissions of the link and provide an accessible anonymous repository with the necessary reproduction instructions, so that reviewers can inspect the implementation and verify the main experimental results?
4 comments
Response to Reviewer tcoy (2/2)
W2&Q3: Baseline selection and fairness
Thank you for the suggestion. We provide additional comparisons with MLP (Heo) [1], Ridge+independent K/V residuals with functional supervision, and Dense Latent Communication [2]. LatentPort [3] targets hybrid architectures with GDN and requires transferring recurrent and convolutional states, while SCD [4] requires sender hidden-state encodings in addition to KV. These requirements go beyond our current handoff setting, which uses only the existing KV cache, so we have not performed direct comparisons. The results by dataset for Qwen3-8B→14B are as follows:
| Method | SciQ | MMLU-Pro | MMLU-Pro+ | OBQA | Oolong | LB-v2 | BABILong | Mean |
|---|---|---|---|---|---|---|---|---|
| Ridge | 43.00 | 20.00 | 12.50 | 36.50 | 32.78 | 32.00 | 10.00 | 26.68 |
| MLP (Heo), 20 epochs | 51.00 | 12.50 | 8.00 | 37.00 | 32.21 | 31.00 | 6.00 | 25.39 |
| MLP (Heo), 40 epochs | 49.00 | 21.50 | 20.00 | 37.00 | 31.40 | 30.00 | 11.00 | 28.56 |
| Independent K/V residual, CE+KL | 76.17 | 44.33 | 27.67 | 39.00 | 35.02 | 34.00 | 25.67 | 40.27 |
| Dense Latent Communication | 40.00 | 16.00 | 7.00 | 28.00 | 0.00 | 15.00 | 0.00 | 15.14 |
| CacheLink | 81.90 | 44.28 | 30.00 | 39.80 | 43.02 | 37.93 | 35.40 | 44.62 |
MLP (Heo) obtains mean scores of 25.39 and 28.56 after 20 and 40 epochs, respectively, while Dense Latent Communication collapses on the three long-context datasets. Under the same Ridge, CE+KL, data, and approximately matched parameter budget, the independent K/V residual scores 40.27, while CacheLink scores 44.62.
We will also expand the related-work discussion: LatentPort additionally transfers the recurrent and convolutional states of hybrid models, while the full SCD method also uses Patch information generated from sender hidden states. Our method uses only the sender's KV cache and does not depend on other inputs.
Q4: Unexpected baseline results
We reproduced CacheBridge using the official code and conducted an experiment on HellaSwag for Qwen3-14B→32B to verify the correctness of the CacheBridge reproduction:
| Setting | Native 32B | CacheBridge | Retention relative to Native |
|---|---|---|---|
| Original paper v1 | 80.2 | 77.4 | 96.51% |
| Our reproduction | 82.4 | 79.6 | 96.60% |
However, on the long-context datasets we use, such as BABILong, we observe that the receiver under CacheBridge often claims that it cannot find the information and therefore fails to provide the correct answer.
LatentAlign does not provide official code, and its authors used their own pretrained Gemma-2 architecture models of approximately 100M–400M parameters to study a shared latent space. We therefore reproduced LatentAlign according to the original paper's description, implementing LatentAlign for our current model pairs, and have added relevant reproduction details to the paper.
Q5: Anonymous code accessibility and reproducibility
Thank you for pointing out that the anonymous code link could not be accessed. We have corrected the anonymous repository. The repository provides CacheLink's core implementation, Ridge fitting, training and evaluation scripts, as well as dependency and usage instructions.
Thank you again for your valuable feedback.
[1] Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse, arXiv:2608.03893.
[2] See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents, arXiv:2606.13594.
[3] LatentPort: Beyond KV Cache—Cross-Model Transfer of Recurrent Memory in Hybrid Language Models, arXiv:2609.25053.
[4] Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching, ICML 2026.
thanks for your clarification.
Dear Reviewer tcoy
Thank you for your reconsideration and for raising the score. We sincerely appreciate your thoughtful evaluation and are glad that our clarifications helped address your concerns. Your recognition and support are truly encouraging to us.
Best regards,
Authors
Response to Reviewer tcoy (1/2)
We sincerely thank you for your evaluation of our work and constructive comments. Below we provide detailed clarifications regarding the raised concerns.
Thank you for summarizing the related work and for your suggestions on the method design. Heo et al. studied Ridge and nonlinear MLP mappings based on KV reconstruction loss; Dery et al. translate KV caches through a shared latent space and train the translators using cross-entropy on the true suffix predicted by the receiver model. Through experimental analysis, CacheLink finds that:
These findings guide the subsequent design of CacheLink: we choose to learn a coupled K/V residual on top of a frozen Ridge mapping and train it using task CE together with forward KL to the native receiver's token output distribution.
To examine the effect of the coupled K/V late-fusion residual relative to simpler alternatives (MLP and independent K/V), we additionally evaluate independent K/V residual and joint MLP controls on Qwen3-8B→14B. Please refer to our responses to Q2 and Q3 for the detailed results.
Thank you for the suggestion. To distinguish the effects of the training objective and residual architecture, we conducted additional ablation experiments on Qwen3-8B→14B:
Functional supervision outperforms MSE: For independent K/V, CE+KL improves the mean score by 14.03 percentage points over MSE. The matched retrained Coupled K/V version scores 44.62, which is 17.44 percentage points higher than the MSE score of 27.18. Thus, functional supervision is a more reasonable optimization objective than MSE.
Coupled K/V late fusion outperforms the other architectures: Under the same CE+KL objective, CacheLink has a mean score of 44.62, independent K/V scores 40.27, and the joint MLP scores 40.24. CacheLink is higher by 4.35 and 4.38 points, respectively, with the three architectures having very similar parameter budgets. The coupled K/V approach used by CacheLink performs best.