Rethinking Test-Time Training: Tilting The Latent Distribution For Few-Shot Source-Free Adaptation
Often, constraints arise in deployment settings where even lightweight parameter updates e.g. parameter-efficient fine-tuning could induce model shift or tuning instability. We study test-time adaptation of foundation models for few-shot classification under a completely frozen-model regime, where additionally, no upstream data are accessible. We propose arguably the first training-free inference method that adapts predictions to the new task by performing a change of measure over the latent embedding distribution induced by the encoder. Using task-similarity scores derived from a small labeled support set, exponential tilting reweights latent distributions in a KL-optimal manner without modifying model parameters. Empirically, the method consistently competes with parameter-update-based methods across multiple benchmarks and shot regimes, while operating under strictly and universally stronger constraints. These results demonstrate the viability of inference-level distributional correction for test-time adaptation even with a fully-frozen model pipeline.
Code (0)
등록된 구현이 없습니다.
Tasks
parameter-efficient fine-tuningTest-time AdaptationSimilar Papers 제목 키워드 기반
Inference-Time Rethinking with Latent Thought Vectors for Math Reasoning
Standard chain-of-thought reasoning generates a solution in a single forward pass, committing irrevocably to each token and lacking a mechanism to recover from early errors. We introduce Inference-Time Rethinking, a gene…
Mathematical ReasoningReward Weighted Classifier-Free Guidance as Policy Improvement in Autoregressive Models
Consider an auto-regressive model that produces outputs x (e.g., answers to questions, molecules) each of which can be summarized by an attribute vector y (e.g., helpfulness vs. harmlessness, or bio-availability vs. lipo…
Reinforcement LearningExponential Tilting of Generative Models: Improving Sample Quality by Training and Sampling from Latent Energy
In this paper, we present a general method that can improve the sample quality of pre-trained likelihood based generative models. Our method constructs an energy function on the latent variable space that yields an energ…
Low-level Pose Control of Tilting Multirotor for Wall Perching Tasks Using Reinforcement Learning
Recently, needs for unmanned aerial vehicles (UAVs) that are attachable to the wall have been highlighted. As one of the ways to address the need, researches on various tilting multirotors that can increase maneuverabili…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Conformal Bayes for Two-Sided Censored Gaussian Regression under Label Shift
Prediction under label shift becomes nonstandard when responses are censored. In a two-sided censored Gaussian model, latent values below $L$ and above $U$ are recorded at the boundary values, so the observed predictive …