Eliya Nachmani
Author directory2026
TokenMapper: A Step Toward Interoperable Speech Token Translation
Tal Kozakov | Tal Rosenwein | Eliya Nachmani
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Tal Kozakov | Tal Rosenwein | Eliya Nachmani
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Neural audio codecs discretize speech into token sequences, but the resulting token spaces differ in vocabulary and codebook structure, preventing direct communication across models. This limitation affects applications such as conversational voice agents and speech to speech translation systems where multiple speech models must interact. As a result, transferring information between speech systems typically requires decoding to waveform audio and re-encoding with a second tokenizer, increasing latency and introducing potential information loss. To address these limitations, we present TokenMapper, a direction aware framework for direct token to token translation between heterogeneous speech tokenizers in the discrete domain. TokenMapper supports structurally mismatched token spaces, including mappings between single codebook and multi codebook representations, under a shared effective token rate. Experiments on GLM-4-Voice, MiMi and DualCodec show consistent cross model performance. Specifically, translation WER approaches native reconstructions within 2.5-6.8% absolute WER, human MOS for TokenMapper outputs ranges from 2.29 to 4.39, following the same direction level trends as UTMOS and end to end latency is reduced by 4.8-94.5% relative to waveform bridging, reaching up to 972 ms per utterance. These results provide a practical step toward cross model speech token interoperability without intermediate waveform reconstruction.
ILRR: Inference-Time Steering Method for Masked Diffusion Language Models
Eden Avrahami | Eliya Nachmani
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
Eden Avrahami | Eliya Nachmani
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
Discrete Diffusion Language Models (DLMs) offer a promising non-autoregressive alternative for text generation, yet effective mechanisms for inference-time control remain relatively underexplored. Existing approaches include sampling-level guidance or trajectory optimization mechanisms. In this work, we study the paradigm of reference-based latent steering for DLMs. We introduce Iterative Latent Representation Refinement (ILRR), an efficient framework for steering DLMs using a reference text as a high-level semantic blueprint. ILRR extracts and injects reference-derived semantic signals into the evolving activations of the generated sequence, enabling tunable transfer of coarse properties such as sentiment. We further introduce Spatially Modulated Steering, an extension that enables long-form generation to be guided by shorter references by regulating intensity across the sequence. Empirically, we demonstrate that ILRR achieves effective control on LLaDA and MDLM architectures with low computational overhead, requiring only one additional parallel forward pass per denoising step. Under comparable compute budgets, ILRR improves attribute accuracy over baselines by 10% to 60% points. Our results suggest that the iterative, global denoising process makes DLMs a natural substrate for effective sequence-wide activation-level control.
2025
Differential Mamba
Nadav Schneider | Itamar Zimerman | Eliya Nachmani
Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
Nadav Schneider | Itamar Zimerman | Eliya Nachmani
Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
Sequence models like Transformers and RNNs often overallocate attention to irrelevant context, leading to noisy intermediate representations. This degrades LLM capabilities by promoting hallucinations, weakening long-range and retrieval abilities, and reducing robustness. Recent work has shown that differential design can mitigate this issue in Transformers, improving their effectiveness across various applications. In this paper, we explore whether these techniques, originally developed for Transformers, can be applied to Mamba, a recent architecture based on selective state-space layers that achieves Transformer-level performance with greater efficiency. We show that a naive adaptation of differential design to Mamba is insufficient and requires careful architectural modifications. To address this, we introduce a novel differential mechanism for Mamba, empirically validated on language modeling benchmarks, demonstrating improved retrieval capabilities and superior performance over vanilla Mamba. Finally, we conduct extensive ablation studies and empirical analyses to justify our design choices and provide evidence that our approach effectively mitigates the overallocation problem in Mamba-based models.
Search