Related papers: A Variational Perspective on Generative Protein Fi…
Vision-and-Language Navigation (VLN) requires agents to navigate photo-realistic environments following natural language instructions. Current methods predominantly rely on imitation learning, which suffers from limited generalization and…
Designing protein sequences with optimal energetic stability is a key challenge in protein inverse folding, as current deep learning methods are primarily trained by maximizing sequence recovery rates, often neglecting the energy of the…
We propose a new way of looking at global optimization of off-lattice protein models. We present a dual optimization concept of predicting optimal sequences as well as optimal folds. We validate the utility of the recently introduced…
In this article we provide a comprehensive review of the different evolutionary algorithm techniques used to address multimodal optimization problems, classifying them according to the nature of their approach. On the one hand there are…
Deep generative models have emerged as a popular machine learning-based approach for inverse design problems in the life sciences. However, these problems often require sampling new designs that satisfy multiple properties of interest in…
By leveraging differentiable dynamics, Reparameterization Policy Gradient (RPG) achieves high sample efficiency. However, current approaches are hindered by two critical limitations: the under-utilization of computationally expensive…
Vision generation remains a challenging frontier in artificial intelligence, requiring seamless integration of visual understanding and generative capabilities. In this paper, we propose a novel framework, Vision-Driven Prompt Optimization…
Multimodal protein features play a crucial role in protein function prediction. However, these features encompass a wide range of information, ranging from structural data and sequence features to protein attributes and interaction…
Variational quantum algorithms have emerged as a leading paradigm that extracts practical computation from near-term intermediate-scale quantum devices, enabling advances in quantum chemistry simulations, combinatorial optimization, and…
Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific f-divergence between the model and data distribution. In light of recent successes in training Generative Adversarial Networks,…
Accurately predicting protein fitness with minimal experimental data is a persistent challenge in protein engineering. We introduce PRIMO (PRotein In-context Mutation Oracle), a transformer-based framework that leverages in-context learning…
We devise an approach for targeted molecular design, a problem of interest in computational drug discovery: given a target protein site, we wish to generate a chemical with both high binding affinity to the target and satisfactory…
This paper concerns applications of genetic algorithms and genetic programming to tasks for which it is difficult to find a representation that does not map to a highly complex and discontinuous fitness landscape. In such cases the standard…
To reduce experimental effort associated with directed protein evolution and to explore the sequence space encoded by mutating multiple positions simultaneously, we incorporate machine learning in the directed evolution workflow.…
Current critic-less RLHF methods aggregate multi-objective rewards via an arithmetic mean, leaving them vulnerable to constraint neglect: high-magnitude success in one objective can numerically offset critical failures in others (e.g.,…
Using effective generalization capabilities of vision language models (VLMs) in context-specific dynamic tasks for embodied artificial intelligence remains a significant challenge. Although supervised fine-tuned models can better align with…
Group Relative Policy Optimisation (GRPO) enhances large language models by estimating advantages across a group of sampled trajectories. However, mapping these trajectory-level advantages to policy updates requires aggregating token-level…
We revisit Group Relative Policy Optimization (GRPO) in both on-policy and off-policy optimization regimes. Our motivation comes from recent work on off-policy Proximal Policy Optimization (PPO), which improves training stability, sampling…
Large reasoning models (LRMs) generate intermediate reasoning traces before producing final answers, yielding strong gains on multi-step and mathematical tasks. Yet aligning LRMs with human preferences, a crucial prerequisite for model…
Biomolecular generators are often adapted with reward feedback to improve task-specific utility, but pushing utility alone can concentrate generation on a narrow family of candidates. Maintaining diversity is difficult because sample…