MARS: Enabling Autoregressive Models Multi-Token Generation episode artwork

EPISODE · Apr 10, 2026 · 23 MIN

MARS: Enabling Autoregressive Models Multi-Token Generation

from Daily Paper Cast · host Jingwen Liang, Gengyu Wang

🤗 Upvotes: 25 | cs.CL Authors: Ziqi Jin, Lei Wang, Ziwei Luo, Aixin Sun Title: MARS: Enabling Autoregressive Models Multi-Token Generation Arxiv: http://arxiv.org/abs/2604.07023v1 Abstract: Autoregressive (AR) language models generate text one token at a time, even when consecutive tokens are highly predictable given earlier context. We introduce MARS (Mask AutoRegreSsion), a lightweight fine-tuning method that teaches an instruction-tuned AR model to predict multiple tokens per forward pass. MARS adds no architectural modifications, no extra parameters, and produces a single model that can still be called exactly like the original AR model with no performance degradation. Unlike speculative decoding, which maintains a separate draft model alongside the target, or multi-head approaches such as Medusa, which attach additional prediction heads, MARS requires only continued training on existing instruction data. When generating one token per forward pass, MARS matches or exceeds the AR baseline on six standard benchmarks. When allowed to accept multiple tokens per step, it maintains baseline-level accuracy while achieving 1.5-1.7x throughput. We further develop a block-level KV caching strategy for batch inference, achieving up to 1.71x wall-clock speedup over AR with KV cache on Qwen2.5-7B. Finally, MARS supports real-time speed adjustment via confidence thresholding: under high request load, the serving system can increase throughput on the fly without swapping models or restarting, providing a practical latency-quality knob for deployment.

Episode metadata supplied by the publisher feed · Published Apr 10, 2026

🤗 Upvotes: 25 | cs.CL Authors: Ziqi Jin, Lei Wang, Ziwei Luo, Aixin Sun Title: MARS: Enabling Autoregressive Models Multi-Token Generation Arxiv: http://arxiv.org/abs/2604.07023v1 Abstract: Autoregressive (AR) language models generate text one token at a time, even when consecutive tokens are highly predictable given earlier context. We introduce MARS (Mask AutoRegreSsion), a lightweight fine-tuning method that teaches an instruction-tuned AR model to predict multiple tokens per forward pass. MARS adds no architectural modifications, no extra parameters, and produces a single model that can still be called exactly like the original AR model with no performance degradation. Unlike speculative decoding, which maintains a separate draft model alongside the target, or multi-head approaches such as Medusa, which attach additional prediction heads, MARS requires only continued training on existing instruction data. When generating one token per forward pass, MARS matches or exceeds the AR baseline on six standard benchmarks. When allowed to accept multiple tokens per step, it maintains baseline-level accuracy while achieving 1.5-1.7x throughput. We further develop a block-level KV caching strategy for batch inference, achieving up to 1.71x wall-clock speedup over AR with KV cache on Qwen2.5-7B. Finally, MARS supports real-time speed adjustment via confidence thresholding: under high request load, the serving system can increase throughput on the fly without swapping models or restarting, providing a practical latency-quality knob for deployment.

PodParley-generated summary based on available episode metadata and transcript content.

NOW PLAYING

MARS: Enabling Autoregressive Models Multi-Token Generation

0:00 23:23

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of Daily Paper Cast?

This episode is 23 minutes long.

When was this Daily Paper Cast episode published?

This episode was published on April 10, 2026.

What is this episode about?

🤗 Upvotes: 25 | cs.CL Authors: Ziqi Jin, Lei Wang, Ziwei Luo, Aixin Sun Title: MARS: Enabling Autoregressive Models Multi-Token Generation Arxiv: ...

Can I download this Daily Paper Cast episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!