TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models

• URL: http://arxiv.org/abs/2604.00666v1
• Date: Wed, 01 Apr 2026 09:13:31 GMT
• Title: TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models
• Abstract summary: Diffusion language models (DLMs) offer a promising path toward low-latency generation through parallel decoding.<n>We propose Trajectory-Ranked Instruction Masked Supervision (TRIMS), a simple trajectory-guided supervised fine-tuning framework.
• Score: 46.490931189790956
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion language models (DLMs) offer a promising path toward low-latency generation through parallel decoding, but their practical efficiency depends heavily on the decoding trajectory. In practice, this advantage often fails to fully materialize because standard training does not provide explicit supervision over token reveal order, creating a train-inference mismatch that leads to suboptimal decoding behavior. We propose Trajectory-Ranked Instruction Masked Supervision (TRIMS), a simple trajectory-guided supervised fine-tuning framework that injects trajectory supervision into standard Masked Diffusion Language Model (MDLM) training with minimal overhead. Instead of relying on costly DLM-based distillation, TRIMS uses lightweight signals from an autoregressive teacher to guide a trajectory-aware masking strategy, encouraging the model to learn more effective decoding orders. Experiments on LLaDA and Dream across math and coding benchmarks show that TRIMS significantly improves the accuracy-parallelism trade-off over both standard MDLM training and train-free acceleration baselines, while achieving competitive performance with prior distillation-based approaches at substantially lower training cost. Further analysis shows that TRIMS leads to better decoding trajectories, validating the effectiveness of trajectory-guided supervision for DLMs.

Related papers

• Revisiting Complete Reasoning Traces for Post-Training [61.76889440384448]
  Large language models (LLMs) are often post-trained on pre-collected reasoning trajectories to improve their reasoning capability.<n>We show that full trajectories provide only limited benefit, while partial trajectories are effective even under heavy truncation.
  arXiv  Detail & Related papers  (2026-09-07T06:46:17Z)
• Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models [65.89572755202245]
  Diffusion Language Models (DLMs) offer stronger global awareness and highly parallel generation.<n>Post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient.<n>We propose a self-distilled trajectory-based post-training framework that aligns training with the easy-to-hard structure of inference.
  arXiv  Detail & Related papers  (2026-05-12T09:39:06Z)
• Open-Ended Instruction Realization with LLM-Enabled Multi-Planner Scheduling in Autonomous Vehicles [40.195332742819865]
  This study proposes an instruction-realization framework that leverages a large language model (LLM) to interpret instructions.<n>It generates executable scripts that schedule multiple model predictive control (MPC)-based motion planners based on real-time feedback, and converts planned trajectories into control signals.
  arXiv  Detail & Related papers  (2026-04-09T09:32:21Z)
• T3D: Few-Step Diffusion Language Models via Trajectory Self-Distillation with Direct Discriminative Optimization [45.026481622387244]
  Diffusion large language models (DLLMs) have the potential to enable fast text generation by decoding multiple tokens in parallel.<n>We propose a trajectory self-distillation framework that improves few-step decoding by distilling the model's own generative trajectories.<n>Our approach consistently outperforms strong few-step baselines and standard training under tight step budgets.
  arXiv  Detail & Related papers  (2026-02-12T18:52:35Z)
• TIDE: Temporal Incremental Draft Engine for Self-Improving LLM Inference [1.0091292967761423]
  TIDE is a serving-engine-native framework that integrates online draft adaptation directly into high-performance LLM inference systems.<n>TIDE reuses target model hidden states generated during inference as training signals, enabling zero-overhead draft adaptation without reloading the target model.<n>Across diverse real-world workloads, TIDE achieves up to 1.15x throughput improvement over static speculative decoding.
  arXiv  Detail & Related papers  (2026-02-05T00:06:12Z)
• Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step [28.12392773921128]
  Masked diffusion language models offer properties such as parallel decoding, flexible generation orders, and the potential for fewer inference steps.<n>A naive approach is to directly transfer techniques well-established for autoregressive (AR) language models to MDLMs.<n>We propose EOS Early Rejection (EOSER) and Ascending Step-Size (ASS) decoding schedulers, which unlock the potential of MDLMs to perform full diffusion-style decoding.
  arXiv  Detail & Related papers  (2025-09-28T15:01:15Z)
• Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking [61.61356842567952]
  We propose STeP, a novel method for improving LLM-based agent training.<n>We synthesize self-reflected trajectories that include reflections and corrections of error steps.<n>Experiments demonstrate that our method improves agent performance across three representative tasks.
  arXiv  Detail & Related papers  (2025-05-26T14:11:12Z)
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models [69.798277882245]
  We introduce Unsupervised Prefix Fine-Tuning (UPFT) to enhance large language models' reasoning efficiency.<n>UPFT removes the need for labeled data or exhaustive sampling.<n> Experiments show that UPFT matches the performance of supervised methods.
  arXiv  Detail & Related papers  (2025-03-04T18:56:03Z)
• Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
  We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs)<n>RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness.<n>RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
  arXiv  Detail & Related papers  (2025-01-31T17:19:57Z)
• Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves [123.07450481623124]
  We propose Skip Tuning as a novel paradigm for adapting vision-language models to downstream tasks.<n>Unlike existing PT or adapter-based methods, Skip Tuning applies Layer-wise Skipping (LSkip) and Class-wise Skipping (CSkip) upon the FT baseline without introducing extra context vectors or adapter modules.
  arXiv  Detail & Related papers  (2024-12-16T07:33:23Z)
• GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs [11.572835837392867]
  This study introduces GPTA, a Large Language Model assistance training framework, that enhances the training of downstream task models via prefix prompt. By minimizing data exposure to LLM, the framework addresses the security and legal challenges of applying LLM in downstream task model training.
  arXiv  Detail & Related papers  (2024-03-29T23:04:04Z)
• Semi-Supervised Learning of Optical Flow by Flow Supervisor [16.406213579356795]
  We propose a practical fine tuning method to adapt a pretrained model to a target dataset without ground truth flows. This design is aimed at stable convergence and better accuracy over conventional self-supervision methods. We achieve meaningful improvements over state-of-the-art optical flow models on Sintel and KITTI benchmarks.
  arXiv  Detail & Related papers  (2022-07-21T06:11:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.