BehaviorVLM: Unified Finetuning-Free Behavioral Understanding with Vision-Language Reasoning

Understanding freely moving animal behavior is central to neuroscience, where pose estimation and behavioral understanding form the foundation for linking neural activity to natural actions. Yet both tasks still depend heavily on human annotation or unstable unsupervised pipelines, limiting scalability and reproducibility. We present BehaviorVLM, a unified vision-language framework for pose estimation and behavioral understanding that requires no task-specific finetuning and minimal human labeling by guiding pretrained Vision-Language Models (VLMs) through detailed, explicit, and verifiable reasoning steps. For pose estimation, we leverage quantum-dot-grounded behavioral data and propose a multi-stage pipeline that integrates temporal, spatial, and cross-view reasoning. This design greatly reduces human annotation effort, exposes low-confidence labels through geometric checks such as reprojection error, and produces labels that can later be filtered, corrected, or used to fine-tune downstream pose models. For behavioral understanding, we propose a pipeline that integrates deep embedded clustering for over-segmented behavior discovery, VLM-based per-clip video captioning, and LLM-based reasoning to merge and semantically label behavioral segments. The behavioral pipeline can operate directly from visual information and does not require keypoints to segment behavior. Together, these components enable scalable, interpretable, and label-light analysis of multi-animal behavior.

Learning Task-Agnostic Skill Bases to Uncover Motor Primitives in Animal Behaviors

Animals flexibly recombine a finite set of core motor primitives to meet diverse task demands, but existing behavior-segmentation methods oversimplify this process by imposing discrete syllables under restrictive generative assumptions. To reflect the animal behavior generation procedure, we introduce skill-based imitation learning (SKIL) for behavior understanding, a reinforcement learning-based imitation framework that (1) infers interpretable skill sets, i.e., latent basis functions of behavior, by leveraging representation learning on transition probabilities, and (2) parameterizes policies as dynamic mixtures of these skills. We validate our approach on a simple grid world, a discrete labyrinth, and unconstrained videos of freely moving animals. Across tasks, it identifies reusable skill components, learns continuously evolving compositional policies, and generates realistic trajectories beyond the capabilities of traditional discrete models. By exploiting generative behavior modeling with compositional representations, our method offers a concise, principled account of how complex animal behaviors emerge from dynamic combinations of fundamental motor primitives.

Inverse Reinforcement Learning with the Average Reward Criterion

We study the problem of Inverse Reinforcement Learning (IRL) with an average-reward criterion. The goal is to recover an unknown policy and a reward function when the agent only has samples of states and actions from an experienced agent. Previous IRL methods assume that the expert is trained in a discounted environment, and the discount factor is known. This work alleviates this assumption by proposing an average-reward framework with efficient learning algorithms. We develop novel stochastic first-order methods to solve the IRL problem under the average-reward setting, which requires solving an Average-reward Markov Decision Process (AMDP) as a subproblem. To solve the subproblem, we develop a Stochastic Policy Mirror Descent (SPMD) method under general state and action spaces that needs $\mathcal{{O}}(1/\varepsilon)$ steps of gradient computation. Equipped with SPMD, we propose the Inverse Policy Mirror Descent (IPMD) method for solving the IRL problem with a $\mathcal{O}(1/\varepsilon^2)$ complexity. To the best of our knowledge, the aforementioned complexity results are new in IRL. Finally, we corroborate our analysis with numerical experiments using the MuJoCo benchmark and additional control tasks.