Related papers: CapRL: Stimulating Dense Image Caption Capabilitie…

Reinforcement Learning with Verifiable Rewards(RLVR) has demonstrated great potential in enhancing the reasoning capabilities of large language models (LLMs). However, its success has thus far been largely confined to the mathematical and…

Reinforcement Learning (RL) is crucial for empowering VideoLLMs with complex spatiotemporal reasoning. However, current RL paradigms predominantly rely on random data shuffling or naive curriculum strategies based on scalar difficulty…

This work presents an end-to-end trainable deep bidirectional LSTM (Long-Short Term Memory) model for image captioning. Our model builds on a deep convolutional neural network (CNN) and two separate LSTM networks. It is capable of learning…

Recent breakthroughs in reasoning models have markedly advanced the reasoning capabilities of large language models, particularly via training on tasks with verifiable rewards. Yet, a significant gap persists in their adaptation to real…

Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating long-form and context-rich descriptions. State-of-the-art evaluation metrics involve…

Research on generative models to produce human-aligned / human-preferred outputs has seen significant recent contributions. Between text and image-generative models, we narrowed our focus to text-based generative models, particularly to…

Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diversity due to the over-incentivization of positive rewards. Although methods like Negative…

Reinforcement Learning (RL) is an important machine learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in this field due to the rapid development of deep neural networks.…

Recent advancements in reinforcement learning with verifiable rewards (RLVR) have significantly improved the complex reasoning ability of vision-language models (VLMs). However, its outcome-level supervision is too coarse to diagnose and…

In-Context Reinforcement Learning (ICRL) enables Large Language Models (LLMs) to learn online from external rewards directly within the context window. However, a central challenge in ICRL is reward estimation, as models typically lack…

Reinforcement learning (RL) has emerged as a promising paradigm for enhancing image editing and text-to-image (T2I) generation. However, current reward models, which act as critics during RL, often suffer from hallucinations and assign…

The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…

Automatically generating textual descriptions for massive unlabeled images on the web can greatly benefit realistic web applications, e.g. multimodal retrieval and recommendation. However, existing models suffer from the problem of…

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

While advanced image captioning systems are increasingly describing images coherently and exactly, recent progress in continual learning allows deep learning models to avoid catastrophic forgetting. However, the domain where image…

Reinforcement Learning from Verifiable Rewards (RLVR) suffers from exploration inefficiency, where models struggle to generate successful rollouts, resulting in minimal learning signal. This challenge is particularly severe for tasks that…

Multimodal large language models have various practical applications that demand strong reasoning abilities. Despite recent advancements, these models still struggle to solve complex geometric problems. A key challenge stems from the lack…

Language-image pre-training largely relies on how precisely and thoroughly a text describes its paired image. In practice, however, the contents of an image can be so rich that well describing them requires lengthy captions (e.g., with 10…

Vision language (VL) models like CLIP are robust to natural distribution shifts, in part because CLIP learns on unstructured data using a technique called caption supervision; the model inteprets image-linked texts as ground-truth labels.…

Multilingual vision-language models have made significant strides in image captioning, yet they still lag behind their English counterparts due to limited multilingual training data and costly large-scale model parameterization.…