Related papers: Information Must Flow: Recursive Bootstrapping for…
Concept bottleneck models perform classification by first predicting which of a list of human provided concepts are true about a datapoint. Then a downstream model uses these predicted concept labels to predict the target label. The…
Concept Bottleneck Models (CBMs) first map raw input(s) to a vector of human-defined concepts, before using this vector to predict a final classification. We might therefore expect CBMs capable of predicting concepts based on distinct…
Many consumer decisions are repeated choices under uncertainty. Standard models capture these decisions using Bayesian learning and dynamic programming: consumers update beliefs from feedback and use those beliefs to guide future choices.…
This paradigm encapsulates knowledge from various models into a solitary prompt without altering the original models or requiring access to the training data, which enables us to achieve efficient and convenient knowledge transfer in more…
The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions using concepts understandable by humans, addressing the black-box…
Recent years have witnessed significant progress in Unified Multimodal Models, yet a fundamental question remains: Does understanding truly inform generation? To investigate this, we introduce UniSandbox, a decoupled evaluation framework…
AI applications increasingly depend on long-context inference, where LLMs consume substantial context to support stronger reasoning. Common examples include retrieval-augmented generation, agent memory layers, and multi-agent orchestration.…
Machine learning models must continuously self-adjust themselves for novel data distribution in the open world. As the predominant principle, entropy minimization (EM) has been proven to be a simple yet effective cornerstone in existing…
Model Predictive Control (MPC) is a vital technique for autonomous systems, like Unmanned Aerial Vehicles (UAVs), enabling optimized motion planning. However, traditional MPC struggles to adapt to real-time changes such as dynamic obstacles…
This paper exploits the fact that the variability in the inter-spike intervals, in the spike train issuing from a neuron, carries substantial information regarding the input to the neuron. A framework for neuronal information processing is…
Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. However, the reasoning chains of demonstrations generated by…
Understanding how information about external stimuli is transformed into behavior is one of the central goals of neuroscience. Here we characterize the information flow through a complete sensorimotor circuit: from stimulus, to sensory…
Information theory is a powerful tool to express principles to drive autonomous systems because it is domain invariant and allows for an intuitive interpretation. This paper studies the use of the predictive information (PI), also called…
In this paper, we introduce the application of Information Bottleneck as a method to investigate properties of questionnaires developed for the study of motivational profiles based on self-determination theory. Founded on information…
Concept Bottleneck Models (CBMs) aim for ante-hoc interpretability by learning a bottleneck layer that predicts interpretable concepts before the decision. State-of-the-art approaches typically select which concepts to learn via human…
Multimodal sentiment analysis has received significant attention across diverse research domains. Despite advancements in algorithm design, existing approaches suffer from two critical limitations: insufficient learning of…
MB-DPOP is an important complete algorithm for solving Distributed Constraint Optimization Problems (DCOPs) by exploiting a cycle-cut idea to implement memory-bounded inference. However, each cluster root in the algorithm is responsible for…
Bayesian integral functional measure of entropy-uncertainty (EF) on trajectories of Markov multi-dimensional diffusion process is cutting off by interactive impulses (controls). Each cutoff minimax of EF superimposes and entangles…
Generating intermediate steps, or Chain of Thought (CoT), is an effective way to significantly improve language models' (LM) multi-step reasoning capability. However, the CoT lengths can grow rapidly with the problem complexity, easily…
This paper investigates a novel lossy compression framework operating under logarithmic loss, designed to handle situations where the reconstruction distribution diverges from the source distribution. This framework is especially relevant…