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

Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an…

Reinforcement learning (RL) has demonstrated remarkable potential in robotic manipulation but faces challenges in sample inefficiency and lack of interpretability, limiting its applicability in real world scenarios. Enabling the agent to…

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have empowered large language models (LLMs) to tackle challenging reasoning tasks such as mathematics and programming. Despite its promise, the RLVR paradigm poses…

Multimodal Large Language Models (MLLMs) excel in vision-language reasoning but often struggle with structured perception tasks requiring precise localization and robustness. We propose a reinforcement learning framework that augments Group…

Video generation models produce visually coherent content but struggle with tasks requiring spatial reasoning and multi-step planning. Reinforcement learning (RL) offers a path to improve generalization, but its effectiveness in video…

This paper investigates the so-called reward-balancing methods, a novel class of algorithms for solving discounted-return reinforcement learning (RL) problems. These methods consist of iteratively adjusting the reward function to transform…

Fine-tuning large language models (LLMs) to align with human preferences has driven the success of systems such as Gemini and ChatGPT. However, approaches like Reinforcement Learning from Human Feedback (RLHF) remain computationally…

Learning from human feedback has been shown to improve text-to-image models. These techniques first learn a reward function that captures what humans care about in the task and then improve the models based on the learned reward function.…

Training large language models with reinforcement learning (RL) against verifiable rewards significantly enhances their reasoning abilities, yet remains computationally expensive due to inefficient uniform prompt sampling. We introduce…

Reinforcement learning (RL) -- algorithms that teach artificial agents to interact with environments by maximising reward signals -- has achieved significant success in recent years. These successes have been facilitated by advances in…

In the realm of multi-objective alignment for large language models, balancing disparate human preferences often manifests as a zero-sum conflict. Specifically, the intrinsic tension between competing goals dictates that aggressively…

Recent proprietary models such as Sora2 demonstrate promising progress in generating multi-shot videos conditioned on multiple reference characters. However, academic research on this problem remains limited. We study this task and identify…

Constrained Reinforcement Learning (RL) aims to maximize the return while adhering to predefined constraint limits, which represent domain-specific safety requirements. In continuous control settings, where learning agents govern system…

Reinforcement learning (RL) has become a standard approach for post-training large language models and, more recently, for improving image generation models, which uses reward functions to enhance generation quality and human preference…

Text-to-Image (T2I) generation has long been an open problem, with compositional synthesis remaining particularly challenging. This task requires accurate rendering of complex scenes containing multiple objects that exhibit diverse…

Video-to-Audio (V2A) generation requires balancing four critical perceptual dimensions: semantic consistency, audio-visual temporal synchrony, aesthetic quality, and spatial accuracy; yet existing methods suffer from objective entanglement…

Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that…

Low-Rank Adaptation (LoRA) enables efficient Continual Learning but often suffers from catastrophic forgetting due to destructive interference between tasks. Our analysis reveals that this degradation is primarily driven by antagonistic…

As generative agents become increasingly capable, alignment of their behavior with complex human values remains a fundamental challenge. Existing approaches often simplify human intent through reduction to a scalar reward, overlooking the…

Reward modeling in large language models is susceptible to reward hacking, causing models to latch onto superficial features such as the tendency to generate lists or unnecessarily long responses. In reinforcement learning from human…