- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Latent Flow Reasoning Models, which utilize representations from multiple layers of a strong autoregressive teacher. To improve efficiency, the authors also introduce a prompt encoder to replace the teacher Transformer for inference. The authors also adopt asynchronous denoising for different representation components and DiffusionNFT to improve the reasoning ability of the trained models.
Critical strengths
- The topic of the paper is interesting. By introducing different layer representations, the authors propose a relatively effective way to utilize continuous latent diffusion for reasoning tasks. The authors also combine different techniques like the asynchronous denoising to improve the performance.
- The analyses of different latent representations and prompt encoder training are interesting and provide useful insights.
Critical weaknesses
- The generalization of LFRM may be limited. The authors train different models for different tasks instead of a unified model. And there is no generalization evaluation on other types of tasks. Moreover, the fixed 1024-token length limits the maximum sequence length.
- The experiments are not comprehensive. Many results are missing in Tables 2 and 3, and different methods are not evaluated under the same settings. Moreover, the method relies on representations from a Qwen3-4B-Instruct teacher, but the authors do not show how using a weaker or stronger teacher model influences performance. Replacing the teacher's prompt representations with the learned encoder also leads to substantial performance degradation on some benchmarks.
Questions for authors
- Please see the weaknesses.
- Could the authors provide end-to-end inference latency comparisons with existing methods? And what is the cost of building up the training dataset?
9 comments
Response to Reviewer MS2M (2/6)
2. Transfer and shared-task modeling
The authors train different models for different tasks instead of a unified model. And there is no generalization evaluation on other types of tasks.
With 64-step DMD2 sampling, the MATH-trained model achieves 36.22% on GSM8K without adaptation and 49.66% after short mixed-task adaptation, keeping MATH500 accuracy near its starting value (28.65% → 28.70%). Before adaptation, our MATH model uses only the math/augmented_math populations of OpenMathInstruct-2, and our GSM8K models use only its gsm8k/augmented_gsm8k populations, alongside Orca-Math and GSM-typed MetaMathQA. Thus the MATH model has not trained on the GSM8K portion of OpenMathInstruct-2, or vice versa.
We present evaluation accuracies using both the standard ODE sampler and a stronger stochastic sampler based on DMD2 (Yin et al., 2024), which interleaves clean-latent prediction and Gaussian noise injection; the precise update rule is specified in Appendix K.1, Eq. (31). Both full benchmarks use four seeds and 64 denoising steps. The headline accuracies above use DMD2.
Before adaptation. The MATH-trained model already transfers substantially to GSM8K, whereas reverse transfer is much weaker, consistent with MATH's greater difficulty. DMD2 evaluations of the supervised epoch-21 LFRM-L models give:
| Training task | Backbone/prompt EMA | GSM8K evaluation | MATH500 evaluation |
|---|---|---|---|
| MATH | .9999 / .9999 | 36.22 (0.94) | 28.65 (1.26) |
| GSM8K | .999 / .999 | 64.95 (1.04) | 4.20 (1.07) |
After short mixed-task adaptation. Starting from supervised MATH epoch 21, we jointly fine-tune the backbone and learned prompt encoder for three epochs on 200k GSM8K and 200k MATH training examples, keeping the representation unchanged. Training takes 9.29 H200-hours, approximately 1.6% of the original MATH model's recorded training GPU-hours. For this short adaptation run, we use EMA .999 for both the backbone and prompt encoder: its shorter averaging window tracks recent training updates more quickly than .9999. The GSM8K reverse-transfer reference above uses the same .999/.999 selector; epoch zero retains the actual MATH initialization at .9999/.9999. Each checkpoint is evaluated on both benchmarks:
| Mixed-training epoch | GSM8K, ODE | GSM8K, DMD2 | MATH500, ODE | MATH500, DMD2 |
|---|---|---|---|---|
| 0: before adaptation | 22.86 (0.69) | 36.22 (0.94) | 21.45 (0.89) | 28.65 (1.26) |
| 1 | 26.84 (0.66) | 43.20 (1.10) | 21.00 (2.38) | 29.40 (1.47) |
| 2 | 30.23 (0.90) | 46.21 (0.38) | 19.85 (0.57) | 29.25 (0.30) |
| 3 | 33.49 (0.46) | 49.66 (0.62) | 19.25 (0.85) | 28.70 (1.19) |
GSM8K accuracy improves at every epoch with both samplers. DMD2 gains 13.44 percentage points, while MATH500 remains near its starting accuracy (28.65% → 28.70%). ODE gains 10.63 points on GSM8K with a 2.20-point MATH500 decrease. The paired DMD2 endpoint differences are +13.44 pp [11.68, 15.22] on GSM8K and +0.05 pp [−2.00, 2.10] on MATH500 (95% problem-bootstrap intervals).
Our coding model already serves both HumanEval and MBPP with one checkpoint, trained on OpenCodeInstruct. Together, these experiments demonstrate shared-checkpoint performance within both mathematical reasoning and coding; unified math-and-code training is a natural next step.
Task-focused training is common among comparable-scale baselines. ELF-REG and S-FLM also train task-specific models, with training budgets comparable to ours (Appendix N.3, Tables 41–42). MLFM covers broader, general-domain tasks, but uses a larger model and a substantially longer reported training budget. FMLM+ and PlaidQ lack sufficient information to report GPU-hours.
Moreover, the fixed 1024-token length limits the maximum sequence length.
The fixed 1,024-token canvas limits the combined prompt-and-answer length. We obtain strong results on the reported benchmarks with a 1,024-token prompt-and-answer canvas; longer canvases or blockwise generation are promising extensions.
Revised manuscript: Appendix L.3 (Table 34, Figure 11) reports mixed-task adaptation, EMA settings, the GSM8K reverse-transfer reference, and additional 32-step results; Section 6.2 uses one coding checkpoint for HumanEval and MBPP. Appendix A.2 documents training populations, and Appendix N.3 (Tables 41–42) gives training scopes and budgets. Appendix K.1, Eq. (31), defines DMD2 sampling.
(cont below)
Response to Reviewer MS2M (3/6)
3. Completing and clarifying baseline comparisons
Many results are missing in Tables 2 and 3, and different methods are not evaluated under the same settings.
We have evaluated additional public checkpoints and address comparability along four axes: prompt encoder and training compute, inference cost, scoring, and prompting. The ELF-REG comparisons below use two seeds and supervised LFRM checkpoints, matching the baselines' absence of NFT training.
Additional previously missing entries. The original blanks combined missing evaluations with unavailable task/scale counterparts. In Table 2, S-FLM, FMLM+, ELF-REG-B, and LFRM-B have no MATH-trained checkpoint; our MATH experiments use LFRM-L. In Table 3, FMLM+ has no approximately 650M or MATH-trained counterpart. The revised Tables 2–3 now explain every remaining missing entry beneath the corresponding table, using N/T for absent task/scale counterparts and N/A where denoising NFE does not apply to autoregressive models. The broader appendix comparison separately labels unavailable full-benchmark results as N/R. We added the following evaluations and documented the remaining availability limits:
| Model | Benchmark / coverage | Result or availability |
|---|---|---|
| Qwen3-0.6B-Base | Full MATH500 | 22.40 (2.26)%, official four-shot math-CoT prompt |
| Qwen3-0.6B thinking | Full GSM8K | 79.23 (0.43)%, native thinking prompt |
| MLFM, released checkpoint | Stratified 200-problem MATH500 pilot | 6/200 correct (3.00%) |
| MLFM, released checkpoint | All 164 HumanEval problems | 0/164 on base/extended tests, with either naming rule |
| PlaidQ | Missing evaluations | Official inference code unavailable; author-reported results retained |
The MLFM pilot uses seed 42 and its official stochastic/token-promotion sampler; it shows limited transfer from this released checkpoint. Its MATH subset remains separate from full-benchmark comparisons. The Qwen evaluations retain their native AR prompting and generation budgets.
(cont below)
Response to Reviewer MS2M (1/6)
We thank the reviewer for their reading of our paper, and for their questions about generalization, baseline comparability, teacher dependence, and computational cost. We have completed mixed-task adaptation, a smaller-teacher control, additional baseline evaluations, and end-to-end timing measurements. Accuracies below are pass@1 percentages, with generation-seed SD in parentheses.
1. Scientific objective and the cost of teacher replacement
Our objective is competitive continuous-diffusion reasoning with its own compact learned prompt encoder. FMLM+, MLFM, and S-FLM process prompts within their generative systems. Teacher-conditioned ELF variants instead execute an external pretrained contextual encoder during inference, so their accuracy depends on both diffusion and the teacher's contextual computation. A single teacher forward pass may be inexpensive while still supplying powerful semantic features.
Removing that inference-time dependency is a necessary premise of our scientific objective. Training on teacher features is compatible with this goal; at test time, LFRM replaces the contextual Qwen Transformer with the learned prompt encoder, retaining only its frozen vocabulary lookup. This objective holds even when replacement reduces accuracy or the teacher contributes little latency: replacing the teacher is not an attempt to improve the teacher-conditioned system's speed or accuracy.
The performance cost depends strongly on the task. After equal 18-epoch backbone training, GSM8K-B reaches 39.35 (0.59)% with the learned prompt encoder versus 41.05 (0.53)% with the frozen Qwen prompt encoder, using four-seed ODE64 evaluation. Coding shows a larger gap. Holding the epoch-12 denoiser fixed, replacing the frozen Qwen prompt encoder with the MSE-trained prompt encoder reduces HumanEval+ from 30.87 (2.09)% to 25.30 (1.84)%, and MBPP+ from 33.99 (1.62)% to 16.96 (1.11)%. Subsequent joint training and NFT reach 30.18 (1.79)% and 19.61 (1.36)%, respectively, in the existing eight-seed ODE128 evaluation. These later stages adapt both networks.
These experiments quantify the external encoder's contribution: the learned prompt encoder retains most GSM8K accuracy, while MBPP exposes a substantial conditioning bottleneck. Coding's longer, more complex prompts are a plausible explanation (mean training-prefix lengths: 233 tokens versus 84/89 for GSM8K/MATH).
Revised manuscript: Sections 1 and 4.2 explain teacher replacement; Appendix L.2 (Table 33) gives the equal-duration comparison, and Appendix H (Table 24) gives the quoted 128-step coding substitution results; the same appendix also provides prompt-length context.
(cont below)