Search Results for author:
Found 16 papers, 9 papers with code
R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
Our reward model, R1-Reward, trained using the StableReinforce algorithm on this dataset, significantly improves performance on multimodal reward modeling benchmarks.
SeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding
With the rapid development of Multi-modal Large Language Models (MLLMs), an increasing number of benchmarks have been established to evaluate the video understanding capabilities of these models.
VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform
Offline experiments and large-scale online A/B test demonstrates the superiority of KuaiMod: KuaiMod achieves the best moderation performance on our benchmark.
InstructEngine: Instruction-driven Text-to-Image Alignment
Reinforcement Learning from Human/AI Feedback (RLHF/RLAIF) has been extensively utilized for preference alignment of text-to-image models.
TIME: Temporal-sensitive Multi-dimensional Instruction Tuning and Benchmarking for Video-LLMs
Video large language models have achieved remarkable performance in tasks such as video question answering, however, their temporal understanding remains suboptimal.
Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding
To address these challenges, we propose learning the mapping between exocentric and egocentric domains, leveraging the extensive exocentric knowledge within existing MLLMs to enhance egocentric video understanding.
iMOVE: Instance-Motion-Aware Video Understanding
Enhancing the fine-grained instance spatiotemporal motion perception capabilities of Video Large Language Models is crucial for improving their temporal and general video understanding.
Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization
Accordingly, we propose the Latent Reward Model (LRM), which repurposes components of diffusion models to predict preferences of latent images at various timesteps.
Kwai-STaR: Transform LLMs into State-Transition Reasoners
In this work, we define mathematical problem-solving as a process of transiting from an initial unsolved state to the final resolved state, and propose Kwai-STaR framework, which transforms LLMs into State-Transition Reasoners to improve their intuitive reasoning capabilities.
CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation
To address this gap, we introduce CoMM, a high-quality Coherent interleaved image-text MultiModal dataset designed to enhance the coherence, consistency, and alignment of generated multimodal content.
Learning Multi-dimensional Human Preference for Text-to-Image Generation
Current metrics for text-to-image models typically rely on statistical metrics which inadequately represent the real preference of humans.
MicroDreamer: Efficient 3D Generation in $\sim$20 Seconds by Score-based Iterative Reconstruction
Optimization-based approaches, such as score distillation sampling (SDS), show promise in zero-shot 3D generation but suffer from low efficiency, primarily due to the high number of function evaluations (NFEs) required for each sample and the limitation of optimization confined to latent space.
DragAnything: Motion Control for Anything using Entity Representation
We introduce DragAnything, which utilizes a entity representation to achieve motion control for any object in controllable video generation.
Paragraph-to-Image Generation with Information-Enriched Diffusion Model
In this paper, we introduce an information-enriched diffusion model for paragraph-to-image generation task, termed ParaDiffusion, which delves into the transference of the extensive semantic comprehension capabilities of large language models to the task of image generation.
Decouple Content and Motion for Conditional Image-to-Video Generation
The goal of conditional image-to-video (cI2V) generation is to create a believable new video by beginning with the condition, i. e., one image and text. The previous cI2V generation methods conventionally perform in RGB pixel space, with limitations in modeling motion consistency and visual continuity.
Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing
A novel Shuffled Style Assembly Network (SSAN) is proposed to extract and reassemble different content and style features for a stylized feature space.
