Declarative logic programs offer a powerful and interpretable abstraction for encoding relational structure and neurosymbolic reasoning, by expressing dependencies as weighted compositional rules. However, inducing them from data remains fundamentally hard, bottlenecked by the combinatorial explosion of symbolic search...
A typed decision model reads a piece of text and returns a probability over caller-defined options, each with a short written definition, generating no text. Recent work places these models in agent systems as guardrails: the component that reads a proposed tool call or incoming message and decides whether to allow it....
Seyedarmin Azizi, Erfan Baghaei Potraghloo, M. Pedram· 1 citation
Bayesian neural network predictions are commonly approximated using a fixed number of Monte Carlo samples per input, without controlling the resulting error that comes from this finite sample. We propose the use of confidence sequences to dynamically determine how many samples are needed while maintaining statistical g...
Recursive self-improvement (RSI) of a model on non-verifiable tasks, such as open-ended research, faces a supervision bottleneck when its outputs exceed what even human experts can reliably assess, leaving the model itself (optimizee) as the best available optimizer and evaluator. However, a single model instance strug...
Hyunin Lee, Jinglue Xu, Jeffrey Seely et al.· 3 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
We introduce a self-improvement loop for reasoning models based on the following observation: Even when the difficulty of a problem exceeds the model's current solving abilities, an additionally supplied solution might enable the model to extract useful solution ideas in hindsight. We operationalize this by jointly tra...
Lars Simon, Holger Eble, Manuel Radons· 0 citations
Electromagnetic spectrum monitoring increasingly requires flexible analysis beyond task-specific recognition and detection. Multimodal large language models offer a unified interface, but extending vision-language models (VLMs) to raw I/Q signals requires tokenization that balances fidelity against a strict budget. For...
Lei Zhai, Zhihao Chang, Shuyuan Yang et al.· 0 citations
Q-Shaped Options (QSO) is introduced, which builds on an architecture with distinct state-value functions, Q functions and policies at each level of the hierarchy, and characterise three desiderata for an action abstraction.
C. Wibault, Antoine Gorceix, Antonio León Villares et al.· 0 citations
Knee osteoarthritis (KOA) progression prediction can support patient monitoring, requiring the integration of multimodal data and multidomain expertise. Moreover, isolated risk estimates provide limited insight underlying a prediction. To automate the progression assessment workflow and reduce manual effort while provi...
Si-Xu Chen, Ming-Rui Yang, Qiang Guan et al.· 0 citations
A large body of research measures model coherence based on output variance without adequately considering competing causes. We identify two such causes, ambiguity and indifference, and we introduce a set of 175 questions where contradicting answers cannot easily be explained by either. We then measure incoherence in te...
Robert Graham, Yariv Barsheshat, Phil Blandfort et al.· 0 citations
The evolution of Large Language Model agents from single-task execution to long-term autonomous operation highlights the critical challenge of transforming continuous experiences into reusable knowledge. To address this, we propose Hippocam, a hierarchical memory and continual learning architecture. Hippocam draws insp...
Xiangyi Zeng, Baihang Liu, Xutong Wang et al.· 0 citations
Knowledge distillation (KD) transfers knowledge from stronger Teacher models to weaker Student models, but most methods require training the Student parameters, thereby binding the distilled knowledge to a specific architecture and checkpoint. This implicit representation is difficult to interpret or reuse across model...
Latent reasoning enables vision-language-action (VLA) models to transform multimodal observations into task-relevant internal states before generating continuous robot actions. While existing methods learn to generate or refine such states for each policy query, they discard successful reasoning after execution and the...
Hong-Yu Shi, Sen Zhao, Zuyu Zhang et al.· 0 citations
