相关论文: POCA: Pareto-Optimal Curriculum Alignment for Visu…

Language models must be adapted to understand and follow user instructions. Reinforcement learning is widely used to facilitate this -- typically using fixed criteria such as "helpfulness" and "harmfulness". In our work, we instead propose…

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…

Recent advances in audio-based generative language models have accelerated AI-driven lyric-to-song generation. However, these models frequently suffer from content hallucination, producing outputs misaligned with the input lyrics and…

Robotic real-world reinforcement learning (RL) with vision-language-action (VLA) models is bottlenecked by sparse, handcrafted rewards and inefficient exploration. We introduce VLAC, a general process reward model built upon InternVL and…

In recent years, reinforcement learning (RL)-based methods for learning driving policies have gained increasing attention in the autonomous driving community and have achieved remarkable progress in various driving scenarios. However,…

Reinforcement learning (RL) can refine Vision-Language-Action (VLA) policies beyond behavior cloning, but real-world RL remains expensive due to extensive rollouts, resets, supervision, and safety risks. Action-conditioned video world…

We introduce Prompt Curriculum Learning (PCL), a lightweight reinforcement learning (RL) algorithm that selects intermediate-difficulty prompts using a learned value model to post-train language models. Since post-training LLMs via RL…

In this paper, we focus on the task of conditional image generation, where an image is synthesized according to user instructions. The critical challenge underpinning this task is ensuring both the fidelity of the generated images and their…

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…

Current Text-to-SQL methods are evaluated and only focused on executable queries, overlooking the semantic alignment challenge -- both in terms of the semantic meaning of the query and the correctness of the execution results. Even…

In reinforcement learning, the classic objectives of maximizing discounted and finite-horizon cumulative rewards are PAC-learnable: There are algorithms that learn a near-optimal policy with high probability using a finite amount of samples…

Aligning image and text encoders from scratch using contrastive learning requires large amounts of paired image-text data. We alleviate this need by aligning individually pre-trained language and vision representation models using a much…

Faithful text rendering remains a persistent weakness of large text-to-image generative models, as it requires both semantic instruction following and fine-grained glyph-level structure. Prior methods often improve this ability through…

Multi-task trade-offs in machine learning can be addressed via Pareto Front Learning (PFL) methods that parameterize the Pareto Front (PF) with a single model. PFL permits to select the desired operational point during inference, contrary…

Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to learn complex reasoning from long-horizon human interactions. While Multi-modal Large Language Models (MLLMs) have driven recent progress, current training…

Aligning large language models with human preferences is crucial for their safe deployment. While Direct Preference Optimization (DPO) offers an efficient alternative to reinforcement learning from human feedback, traditional DPO methods…

Current parameter-efficient fine-tuning (PEFT) methods build adapters widely agnostic of the context of downstream task to learn, or the context of important knowledge to maintain. As a result, there is often a performance gap compared to…

Autonomous agents must often deal with conflicting requirements, such as completing tasks using the least amount of time/energy, learning multiple tasks, or dealing with multiple opponents. In the context of reinforcement learning~(RL),…

Curriculum Data Augmentation (CDA) improves neural models by presenting synthetic data with increasing difficulties from easy to hard. However, traditional CDA simply treats the ratio of word perturbation as the difficulty measure and goes…

Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference Optimization (TPO), a framework that aligns…