Related papers: Entropy Aware Reward Guidance for Diffusion Langua…
Diffusion models have become emerging generative models. Their sampling process involves multiple steps, and in each step the models predict the noise from a noisy sample. When the models make prediction, the output deviates from the ground…
The recent success of denoising diffusion models has significantly advanced text-to-image generation. While these large-scale pretrained models show excellent performance in general image synthesis, downstream objectives often require…
To fully leverage the capabilities of diffusion models, we are often interested in optimizing downstream reward functions during inference. While numerous algorithms for reward-guided generation have been recently proposed due to their…
With recent breakthroughs in large language models (LLMs) for reasoning, planning, and complex task generation, artificial intelligence systems are transitioning from isolated single-agent architectures to multi-agent systems with…
Reasoning models often outperform smaller models but at 3--5$\times$ higher cost and added latency. We present entropy-guided refinement: a lightweight, test-time loop that uses token-level uncertainty to trigger a single, targeted…
Diffusion language models are a promising alternative to autoregressive models, yet post-training methods for them largely adapt reward-maximizing objectives. We identify a central failure mode in this setting we call trajectory locking:…
Feature attribution methods highlight the important input tokens as explanations to model predictions, which have been widely applied to deep neural networks towards trustworthy AI. However, recent works show that explanations provided by…
Recent studies have demonstrated the strong empirical performance of diffusion models on discrete sequences across domains from natural language to biological sequence generation. For example, in the protein inverse folding task,…
Large Reasoning Models (LRMs) have demonstrated impressive capabilities but suffer from cognitive inefficiencies like "overthinking" simple problems and "underthinking" complex ones. While existing methods that use supervised fine-tuning…
The modern autoregressive Large Language Models (LLMs) have achieved outstanding performance on NLP benchmarks, and they are deployed in the real world. However, they still suffer from limitations of the autoregressive training paradigm.…
Recent reinforcement learning has enhanced the flow matching models on human preference alignment. While stochastic sampling enables the exploration of denoising directions, existing methods which optimize over multiple denoising steps…
Chain-of-thought (CoT) reasoning improves large language model performance on complex tasks, but often produces excessively long and inefficient reasoning traces. Existing methods shorten CoTs using length penalties or global entropy…
Network optimization remains fundamental in wireless communications, with Artificial Intelligence (AI)-based solutions gaining widespread adoption. As Sixth-Generation (6G) communication networks pursue full-scenario coverage, optimization…
Diffusion models recently emerged as a powerful paradigm for recommender systems, offering state-of-the-art performance by modeling the generative process of user-item interactions. However, training such models from scratch is both…
Reinforcement learning (RL) shows promise for enhancing LLM agentic reasoning, yet sparse terminal rewards hinder fine-grained optimization. Process reward modeling offers an alternative but incurs high computational costs, reward hacking…
Reward models are central to both reinforcement learning (RL) with language models and inference-time verification. However, existing reward models often lack temporal consistency, leading to ineffective policy updates and unstable RL…
We introduce Entropy-Guided Sequence Weighting (EGSW), a novel approach that enhances the exploration-exploitation tradeoff by dynamically assigning weights to generated outputs based on their advantage and entropy for Reinforcement…
Standard Bradley--Terry (BT) reward models are limited when human preferences are pluralistic. Although soft preference labels preserve disagreement information, BT can only express it by shrinking reward margins. Gaussian reward models…
Latent Consistency Distillation (LCD) has emerged as a promising paradigm for efficient text-to-image synthesis. By distilling a latent consistency model (LCM) from a pre-trained teacher latent diffusion model (LDM), LCD facilitates the…
Recent advances in diffusion models have led to impressive image generation capabilities, but aligning these models with human preferences remains challenging. Reward-based fine-tuning using models trained on human feedback improves…