Cover Image

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Kecheng, Liu, Ziru, Tao, Xijia, Liu, Hui, Liu, Yibing, Fu, Xinyu, Wu, Shi, Zhang, Suiyun, Tu, Dandan, Kong, Lingpeng, Liu, Rui, Li, Haoliang
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models
by: Chen, Kecheng, et al.
Published: (2025)

Disentangling Instruction Influence in Diffusion Transformers for Parallel Multi-Instruction-Guided Image Editing
by: Liu, Hui, et al.
Published: (2025)

MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agents
by: Tao, Xijia, et al.
Published: (2025)

GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning
by: Liu, Ziru, et al.
Published: (2025)

CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification
by: Chen, Jinpeng, et al.
Published: (2026)

ImgTrojan: Jailbreaking Vision-Language Models with ONE Image
by: Tao, Xijia, et al.
Published: (2024)

Efficient Reasoning via Reward Model
by: Wang, Yuhao, et al.
Published: (2025)

Intention-Aware Diffusion Model for Pedestrian Trajectory Prediction
by: Liu, Yu, et al.
Published: (2025)

Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance
by: Liu, Hui, et al.
Published: (2025)

Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need
by: Chen, Kecheng, et al.
Published: (2024)

Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios
by: Liu, Hui, et al.
Published: (2026)

Rethinking Individual Risk and Aggregation in Survival Analysis: A Latent Mechanism Framework
by: Liu, Xijia
Published: (2026)

Proxy Compression for Language Modeling
by: Zheng, Lin, et al.
Published: (2026)

Intention Enhanced Diffusion Model for Multimodal Pedestrian Trajectory Prediction
by: Liu, Yu, et al.
Published: (2025)

Test-time Adaptation for Foundation Medical Segmentation Model without Parametric Updates
by: Chen, Kecheng, et al.
Published: (2025)

Pusa V1.0: Unlocking Temporal Control in Pretrained Video Diffusion Models via Vectorized Timestep Adaptation
by: Liu, Yaofang, et al.
Published: (2025)

Occlusion-Aware Diffusion Model for Pedestrian Intention Prediction
by: Liu, Yu, et al.
Published: (2025)

Model Will Tell: Training Membership Inference for Diffusion Models
by: Fu, Xiaomeng, et al.
Published: (2024)

Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition
by: Liu, Hui, et al.
Published: (2026)

KINDLE: Knowledge-Guided Distillation for Prior-Free Gene Regulatory Network Inference
by: Peng, Rui, et al.
Published: (2025)

Learnable Sampler Distillation for Discrete Diffusion Models
by: Fu, Feiyang, et al.
Published: (2025)

Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpainting
by: Liu, Haipeng, et al.
Published: (2024)

AEGIS: Exploring the Limit of World Knowledge Capabilities for Unified Mulitmodal Models
by: Lin, Jintao, et al.
Published: (2026)

Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
by: Zhai, Shengfang, et al.
Published: (2024)

Gradient-Congruity Guided Federated Sparse Training
by: Tian, Chris Xing, et al.
Published: (2024)

M3FAS: An Accurate and Robust MultiModal Mobile Face Anti-Spoofing System
by: Kong, Chenqi, et al.
Published: (2023)

Reflective VLM Planning for Dual-Arm Desktop Cleaning: Bridging Open-Vocabulary Perception and Precise Manipulation
by: Liu, Yufan, et al.
Published: (2025)

Variance-Reduction Guidance: Sampling Trajectory Optimization for Diffusion Models
by: Xu, Shifeng, et al.
Published: (2025)

Dataset Distillation by Automatic Training Trajectories
by: Liu, Dai, et al.
Published: (2024)

A Reparameterized Discrete Diffusion Model for Text Generation
by: Zheng, Lin, et al.
Published: (2023)

Efficient Test-Time Adaptation through Latent Subspace Coefficients Search
by: Luo, Xinyu, et al.
Published: (2025)

Training a Student Expert via Semi-Supervised Foundation Model Distillation
by: Taghavi, Pardis, et al.
Published: (2026)

DiffServe: Efficiently Serving Text-to-Image Diffusion Models with Query-Aware Model Scaling
by: Ahmad, Sohaib, et al.
Published: (2024)

TrajDiffuse: A Conditional Diffusion Model for Environment-Aware Trajectory Prediction
by: Qingze, et al.
Published: (2024)

CoDA: From Text-to-Image Diffusion Models to Training-Free Dataset Distillation
by: Zhou, Letian, et al.
Published: (2025)

Bridge the Gap between Past and Future: Siamese Model Optimization for Context-Aware Document Ranking
by: Wu, Songhao, et al.
Published: (2025)

Intention-aware Denoising Diffusion Model for Trajectory Prediction
by: Liu, Chen, et al.
Published: (2024)

Semi-supervised Image Dehazing via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models
by: Liu, Bing, et al.
Published: (2025)

TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM
by: Zhou, Haoyang, et al.
Published: (2026)

BridgeScope: A Universal Toolkit for Bridging Large Language Models and Databases
by: Weng, Lianggui, et al.
Published: (2025)