What happens to diffusion model likelihood when your model is conditional?
Diffusion Models (DMs) iteratively denoise random samples to produce high-quality data. The iterative sampling process is derived from Stochastic Differential Equations (SDEs), allowing a speed-quality trade-off chosen at inference. Another advantage of sampling with differential equations is exact likelihood computation. These likelihoods have been used to rank unconditional DMs and for out-of-domain classification. Despite the many existing and possible uses of DM likelihoods, the distinct properties captured are unknown, especially in conditional contexts such as Text-To-Image (TTI) or Text-To-Speech synthesis (TTS). Surprisingly, we find that TTS DM likelihoods are agnostic to the text input. TTI likelihood is more expressive but cannot discern confounding prompts. Our results show that applying DMs to conditional tasks reveals inconsistencies and strengthens claims that the properties of DM likelihood are unknown. This impact sheds light on the previously unknown nature of DM likelihoods. Although conditional DMs maximise likelihood, the likelihood in question is not as sensitive to the conditioning input as one expects. This investigation provides a new point-of-view on diffusion likelihoods.
Code (0)
등록된 구현이 없습니다.
Tasks
domain classificationmodelSpeech Synthesistext-to-speechText to SpeechText-To-Speech SynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
How do you revise your belief set with %$;@*?
In the classic AGM belief revision theory, beliefs are static and do not change their own shape. For instance, if p is accepted by a rational agent, it will remain p to the agent. But such rarely happens to us. Often, wh…
PushupBench: Your VLM is not good at counting pushups
Large vision-language models (VLMs) can recognize \textit{what} happens in video but fail to count \textit{how many} times. We introduce \textbf{PushupBench}, 446 long-form clips (avg. 36.7s) for evaluating repetition co…
When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
Past analyses of reinforcement learning from human feedback (RLHF) assume that the human evaluators fully observe the environment. What happens when human feedback is based only on partial observations? We formally defin…
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
Discrete diffusion models with absorbing processes have shown promise in language modeling. The key quantities to be estimated are the ratios between the marginal probabilities of two transitive states at all timesteps, …
DenoisingLanguage ModelingLanguage ModellingHow I Met Your Bias: Investigating Bias Amplification in Diffusion Models
Diffusion-based generative models demonstrate state-of-the-art performance across various image synthesis tasks, yet their tendency to replicate and amplify dataset biases remains poorly understood. Although previous res…