Related papers: MusicRL: Aligning Music Generation to Human Prefer…

Video generation has achieved significant advances through rectified flow techniques, but issues like unsmooth motion and misalignment between videos and prompts persist. In this work, we develop a systematic pipeline that harnesses human…

Language models (LMs) are pretrained to imitate internet text, including content that would violate human preferences if generated by an LM: falsehoods, offensive comments, personally identifiable information, low-quality or buggy code, and…

Reinforcement Learning from Human Feedback (RLHF) has emerged as a important paradigm for aligning large language models (LLMs) with human preferences during post-training. This framework typically involves two stages: first, training a…

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptimization, in which policy models overfit to the reward model,…

Text-to-music generation models are now capable of generating high-quality music audio in broad styles. However, text control is primarily suitable for the manipulation of global musical attributes like genre, mood, and tempo, and is less…

A conversational music retrieval system can help users discover music that matches their preferences through dialogue. To achieve this, a conversational music retrieval system should seamlessly engage in multi-turn conversation by 1)…

Large Multimodal Models (LMMs) excel at comprehending human instructions and demonstrate remarkable results across a broad spectrum of tasks. Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF) further refine LLMs by…

Reinforcement learning from human feedback (RLHF), which aligns a diffusion model with input prompt, has become a crucial step in building reliable generative AI models. Most works in this area use a discrete-time formulation, which is…

This paper explores multiple optimization methods to improve the performance of rating-based reinforcement learning (RbRL). RbRL, a method based on the idea of human ratings, has been developed to infer reward functions in reward-free…

AI-based peer review systems tend to produce shallow and overpraising suggestions compared to human feedback. Here, we evaluate how well a reasoning LLM trained with multi-objective reinforcement learning (REMOR) can overcome these…

Diffusion and flow-matching models have revolutionized automatic text-to-audio generation in recent times. These models are increasingly capable of generating high quality and faithful audio outputs capturing to speech and acoustic events.…

This work investigates how listeners perceive and evaluate AI-generated as compared to human-composed music in the context of emotional resonance and regulation. Across a mixed-methods design, participants were exposed to both AI and human…

When operating in service of people, robots need to optimize rewards aligned with end-user preferences. Since robots will rely on raw perceptual inputs like RGB images, their rewards will inevitably use visual representations. Recently…

This paper presents a deep reinforcement learning algorithm for online accompaniment generation, with potential for real-time interactive human-machine duet improvisation. Different from offline music generation and harmonization, online…

Recent advancements in code generation have shown remarkable success across software domains, yet hardware description languages (HDLs) such as Verilog remain underexplored due to their concurrency semantics, syntactic rigidity, and…

Reinforcement Learning from Human Feedback (RLHF) remains indispensable for aligning large language models (LLMs) in subjective domains. To enhance robustness, recent work shifts toward Generative Reward Models (GenRMs) that generate…

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) easier to use and more effective. A core piece of the RLHF process is the training and utilization of a model of…

Reward models (RMs) are crucial for aligning large language models (LLMs) with human preferences. They are trained using preference datasets where each example consists of one input prompt, two responses, and a preference label. As curating…

Traditional RLHF optimizes language models with coarse, scalar rewards that mask the fine-grained reasons behind success or failure, leading to slow and opaque learning. Recent work augments RL with textual critiques through prompting or…

Reinforcement learning from human feedback (RLHF) has been widely adopted to align language models (LMs) with human preference. Prior RLHF works typically take a bandit formulation, which, though intuitive, ignores the sequential nature of…