· ai
[Paper] FALCON: Few-step Accurate Likelihoods for Continuous Flows
Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann Generators tackle this problem...
-
- · ai
[Paper] Supervised learning pays attention
In-context learning with attention enables large neural networks to make context-specific predictions by selectively focusing on relevant examples. Here, we ada...
- · ai
[Paper] Efficient Continual Learning in Neural Machine Translation: A Low-Rank Adaptation Approach
Continual learning in Neural Machine Translation (NMT) faces the dual challenges of catastrophic forgetting and the high computational cost of retraining. This ...
- · ai
[Paper] STACHE: Local Black-Box Explanations for Reinforcement Learning Policies
Reinforcement learning agents often behave unexpectedly in sparse-reward or safety-critical environments, creating a strong need for reliable debugging and veri...
- · ai
[Paper] Bayesian Networks, Markov Networks, Moralisation, Triangulation: a Categorical Perspective
Moralisation and Triangulation are transformations allowing to switch between different ways of factoring a probability distribution into a graphical model. Mor...
- · ai
[Paper] Visual Heading Prediction for Autonomous Aerial Vehicles
The integration of Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) is increasingly central to the development of intelligent autonomous syst...
- · ai
[Paper] SCOPE: Language Models as One-Time Teacher for Hierarchical Planning in Text Environments
Long-term planning in complex, text-based environments presents significant challenges due to open-ended action spaces, ambiguous observations, and sparse feedb...
- · ai
[Paper] Human-in-the-Loop and AI: Crowdsourcing Metadata Vocabulary for Materials Science
Metadata vocabularies are essential for advancing FAIR and FARR data principles, but their development constrained by limited human resources and inconsistent s...
- · ai
[Paper] Exploring Protein Language Model Architecture-Induced Biases for Antibody Comprehension
Recent advances in protein language models (PLMs) have demonstrated remarkable capabilities in understanding protein sequences. However, the extent to which dif...
- · ai
[Paper] Provably Learning from Modern Language Models via Low Logit Rank
While modern language models and their inner workings are incredibly complex, recent work (Golowich, Liu & Shetty; 2025) has proposed a simple and potential...
- · ai
[Paper] Analysis of Dirichlet Energies as Over-smoothing Measures
We analyze the distinctions between two functionals often used as over-smoothing measures: the Dirichlet energies induced by the unnormalized graph Laplacian an...
- · ai
[Paper] HPM-KD: Hierarchical Progressive Multi-Teacher Framework for Knowledge Distillation and Efficient Model Compression
Knowledge Distillation (KD) has emerged as a promising technique for model compression but faces critical limitations: (1) sensitivity to hyperparameters requir...