Related papers: SpatialReward: Bridging the Perception Gap in Onli…

Instruction-based image editing has made a great process in using natural human language to manipulate the visual content of images. However, existing models are limited by the quality of the dataset and cannot accurately localize editing…

Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…

Reinforcement learning (RL) with rule-based reward functions has recently shown great promise in enhancing the reasoning depth and generalization ability of vision-language models (VLMs), while maintaining computational efficiency. In spite…

Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed significant breakthroughs in complex LLM reasoning within verifiable domains, such as mathematics and programming. Recent efforts have sought to extend this paradigm to…

Medical Image Grounding (MIG), which involves localizing specific regions in medical images based on textual descriptions, requires models to not only perceive regions but also deduce spatial relationships of these regions. Existing…

Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning…

We present MetaSpatial, the first reinforcement learning (RL)-based framework designed to enhance 3D spatial reasoning in vision-language models (VLMs), enabling real-time 3D scene generation without the need for hard-coded optimizations.…

MLLMs have demonstrated significant visual understanding capabilities, yet their fine-grained visual perception in complex real-world scenarios, such as densely crowded public areas, remains limited. Inspired by the recent success of RL in…

With enhanced capabilities and widespread applications, Multimodal Large Language Models (MLLMs) are increasingly required to process and reason over multiple images simultaneously. However, existing MLLM benchmarks focus either on…

Recent advances in multimodal large language models (MLLMs) have shown great potential for extending vision-language reasoning to professional tool-based image editing, enabling intuitive and creative editing. A promising direction is to…

Spatial reasoning, the ability to understand spatial relations, causality, and dynamic evolution, is central to human intelligence and essential for real-world applications such as autonomous driving and robotics. Existing studies, however,…

Image captioning is a fundamental task that bridges the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Current state-of-the-art captioning models are typically trained with…

Reinforcement Learning with Verifiable Rewards (RLVR) has proven to be a highly effective strategy for endowing Large Language Models (LLMs) with robust multi-step reasoning abilities. However, its design and optimizations remain tailored…

Reinforcement learning (RL) has become a promising paradigm for optimizing Retrieval-Augmented Generation (RAG) in complex reasoning tasks. However, traditional outcome-based RL approaches often suffer from reward sparsity and inefficient…

Leveraging the priors of 2D diffusion models for 3D editing has emerged as a promising paradigm. However, maintaining multi-view consistency in edited results remains challenging, and the extreme scarcity of 3D-consistent editing paired…

Adversarial learning has shown its advances in generating natural and diverse descriptions in image captioning. However, the learned reward of existing adversarial methods is vague and ill-defined due to the reward ambiguity problem. In…

Training image captioning models using teacher forcing results in very generic samples, whereas more distinctive captions can be very useful in retrieval applications or to produce alternative texts describing images for accessibility.…

As the field of deep learning steadily transitions from the realm of academic research to practical application, the significance of self-supervised pretraining methods has become increasingly prominent. These methods, particularly in the…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Reward models have been increasingly critical for improving the reasoning capability of LLMs. Existing research has shown that a well-trained reward model can substantially improve model performances at inference time via search. However,…