Related papers: Reward Guided Latent Consistency Distillation

We introduce Latent Space Distribution Matching (LSDM), a novel framework for semi-supervised generative modeling of conditional distributions. LSDM operates in two stages: (i) learning a low-dimensional latent space from both paired and…

Autoregressive large language models achieve strong results on many benchmarks, but decoding remains fundamentally latency-limited by sequential dependence on previously generated tokens. Diffusion language models (DLMs) promise parallel…

In the field of large language models (LLMs), Knowledge Distillation (KD) is a critical technique for transferring capabilities from teacher models to student models. However, existing KD methods face limitations and challenges in…

Reward models (RMs) are crucial for aligning large language models (LLMs) with human preferences. They are trained using preference datasets where each example consists of one input prompt, two responses, and a preference label. As curating…

Text-to-image models have shown remarkable progress in generating high-quality images from user-provided prompts. Despite this, the quality of these images varies due to the models' sensitivity to human language nuances. With advancements…

Sequential recommender systems have achieved significant success in modeling temporal user behavior but remain limited in capturing rich user semantics beyond interaction patterns. Large Language Models (LLMs) present opportunities to…

As large language models (LLMs) tackle increasingly complex tasks and longer documents, their computational and memory costs during inference become a major bottleneck. To address this, we propose PromptDistill, a novel, training-free…

By embedding discrete representations into a continuous latent space, we can leverage continuous-space latent diffusion models to handle generative modeling of discrete data. However, despite their initial success, most latent diffusion…

In image super-resolution, both pixel-wise accuracy and perceptual fidelity are desirable. However, most deep learning methods only achieve high performance in one aspect due to the perception-distortion trade-off, and works that…

Efficient streaming video generation is critical for simulating interactive and dynamic worlds. Existing methods distill few-step video diffusion models with sliding window attention, using initial frames as sink tokens to maintain…

Masked Generative Models (MGM)s demonstrate strong capabilities in generating high-fidelity images. However, they need many sampling steps to create high-quality generations, resulting in slow inference speed. In this work, we propose…

Video diffusion models have shown great potential in generating high-quality videos, making them an increasingly popular focus. However, their inherent iterative nature leads to substantial computational and time costs. While efforts have…

Current approaches for restoration of degraded images face a trade-off: high-performance models are slow for practical use, while fast models produce poor results. Knowledge distillation transfers teacher knowledge to students, but existing…

Latent diffusion models have made great strides in generating expressive portrait videos with accurate lip-sync and natural motion from a single reference image and audio input. However, these models are far from real-time, often requiring…

Generative reward models (GRMs) have emerged as a promising approach for aligning Large Language Models (LLMs) with human preferences by offering greater representational capacity and flexibility than traditional scalar reward models.…

Traditional black-box distillation for Large Vision-Language Models (LVLMs) typically relies on a single teacher response per input, which often yields high-variance responses and format inconsistencies in multimodal or temporal scenarios.…

Although diffusion models have achieved strong results in decision-making tasks, their slow inference speed remains a key limitation. While consistency models offer a potential solution, existing applications to decision-making either…

Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities. However, when adapting these priors to complex visual modalities, often represented…

Recent advancements in large language models (LLMs) have raised concerns about inference costs, increasing the need for research into model compression. While knowledge distillation (KD) is a prominent method for this, research on KD for…

This research paper proposes a Latent Diffusion Model for 3D (LDM3D) that generates both image and depth map data from a given text prompt, allowing users to generate RGBD images from text prompts. The LDM3D model is fine-tuned on a dataset…