paper-with-me

홈 › Papers

Beyond Token-Level Cross-Entropy: Fréchet Distributional Post-Training for Autoregressive Image Generation

2026-08-01 · Jinhua Zhang, Yisong Lin, Wei Long, Shuhang Gu arxiv

Autoregressive image generators are commonly pretrained with token-level cross-entropy under teacher forcing, yet evaluated by the distributional quality of decoded images. This creates an objective mismatch, because categorical errors have unequal image-level consequences, and a context mismatch, because inference conditions on model-generated histories. We introduce FD-loss post-training, which adapts a pretrained discrete generator using representation-space Fréchet distance as the sole objective. A dual-pass scheme first constructs detached rollout contexts through gradient-free generation under the model's native inference configuration, then performs differentiable replay with a probability-level straight-through estimator (STE) that preserves hard argmax decoding in the forward pass while propagating image-level gradients through temperature-scaled probabilities. Only the generator is updated, while the tokenizer and feature extractors remain frozen. Across eight completed configurations from four generator families on class-conditional ImageNet at $256\times256$, FD-loss post-training reduces FID and $\mathrm{FD}_{r6}$ by 41.4% and 52.0% on average. The strongest FID result improves from 2.42 to 1.43 without adding parameters or inference steps.

📄 PDF Abstract BibTeX arXiv:2608.00562

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning

2026-06-18 · Xuanzhi Feng, Zhengyang Li, Zeyu Liu, Haoxi Li 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced Large Language Model (LLM) reasoning; however, it faces a fundamental optimization instability: uniform token updates precipitate entropy c…

Reinforcement Learning

SAF-OPD: Stable Advantage Fusion for On-Policy Distillation

2026-07-31 · Yifan Ding, Xincheng Wei, Yoshua Y. Li, Ziheng Li 외 hf

Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) scores each token against a stronger teacher for a dense advantage but ca…

Mathematical ReasoningReinforcement LearningCode Generation

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

2025-06-02 · Shenzhi Wang, Le Yu, Chang Gao, Chujie Zheng 외

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs), while its mechanisms are not yet well understood. In this …

ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs

2026-06-30 · Yuhao Wang, Mu Qiao, Haiwen Diao, Yunzhi Zhuge 외 arxiv

Multimodal Large Language Models (MLLMs) incur prohibitive inference costs due to long visual token sequences. Training-free visual token reduction provides an efficient solution. However, existing methods distort attent…

Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens

2026-04-29 · Zhenyu Zhao, Sander Land, Daniel M. Bikel, Waseem Alshikh arxiv

Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains underexplored. We observe that reasoning tokens split into two functiona…

Mathematical Reasoning