Related papers: GrndCtrl: Grounding World Models via Self-Supervis…

Video Temporal Grounding (VTG) aims to localize relevant temporal segments in videos given natural language queries. Despite recent progress with large vision-language models (LVLMs) and instruction-tuning, existing approaches often suffer…

Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. Such biases can produce suboptimal samples, skewed outcomes, and unfairness, with potentially serious consequences.…

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.…

Denoising-based generative models, particularly diffusion and flow matching algorithms, have achieved remarkable success. However, aligning their output distributions with complex downstream objectives, such as human preferences,…

Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs), especially when structured reference answers are…

Recent advances in reinforcement learning (RL) have delivered strong reasoning capabilities in natural image domains, yet their potential for Earth Observation (EO) remains largely unexplored. EO tasks introduce unique challenges, spanning…

Recent advances in reinforcement learning (RL) have significantly improved the complex reasoning capabilities of large language models (LLMs). Despite these successes, existing methods mainly focus on single-domain RL (e.g., mathematics)…

The alignment of Large Language Models (LLMs) is critically dependent on reward models trained on costly human preference data. While recent work explores bypassing this cost with AI feedback, these methods often lack a rigorous theoretical…

Recent advances have shown that video generation models can enhance robot learning by deriving effective robot actions through inverse dynamics. However, these methods heavily depend on the quality of generated data and struggle with…

Reinforcement learning (RL) has been widely adopted in post-training for large language models (LLMs) at scale. Recently, the incentivization of reasoning capabilities in LLMs from RL indicates that $\textit{proper learning methods could…

Graphical user interface visual grounding (GUI-VG), a core capability for GUI agents, has primarily relied on supervised fine-tuning (SFT) of multimodal large language models (MLLMs), which demands extensive data curation and significant…

Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting the generator with additional modules or applying…

Reinforcement learning (RL) has recently emerged as a promising approach for aligning text-to-image generative models with human preferences. A key challenge, however, lies in designing effective and interpretable rewards. Existing methods…

Self-supervision has the potential to transform reinforcement learning (RL), paralleling the breakthroughs it has enabled in other areas of machine learning. While self-supervised learning in other domains aims to find patterns in a fixed…

Models capable of "thinking with images" by dynamically grounding their reasoning in visual evidence represent a major leap in multimodal AI. However, replicating and advancing this ability is non-trivial, with current methods often trapped…

Medical visual grounding serves as a crucial foundation for fine-grained multimodal reasoning and interpretable clinical decision support. Despite recent advances in reinforcement learning (RL) for grounding tasks, existing approaches such…

Vision-language models (VLMs) have shown remarkable abilities by integrating large language models with visual inputs. However, they often fail to utilize visual evidence adequately, either depending on linguistic priors in vision-centric…

Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Models (LMs). A common problem is reward hacking, where the policy may exploit inaccuracies of the…

Reinforcement Learning with Verifiable Rewards (RLVR) has markedly enhanced the reasoning abilities of large language models (LLMs). Its success, however, largely depends on strong base models with rich world knowledge, yielding only modest…

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…