The rapidly increasing capabilities of large language models (LLMs) raise an urgent need to align AI systems with diverse human preferences to simultaneously enhance their usefulness and safety, despite the often conflicting nature of these goals. To address this important problem, a promising approach is to enforce a safety constraint at the fine-tuning stage through a constrained Reinforcement Learning from Human Feedback (RLHF) framework. This approach, however, is computationally expensive and often unstable. In this work, we introduce Constrained DPO (C-DPO), a novel extension of the recently proposed Direct Preference Optimization (DPO) approach for fine-tuning LLMs that is both efficient and lightweight. By integrating dual gradient descent and DPO, our method identifies a nearly optimal trade-off between helpfulness and harmlessness without using reinforcement learning. Empirically, our approach provides a safety guarantee to LLMs that is missing in DPO while achieving significantly higher rewards under the same safety constraint compared to a recently proposed safe RLHF approach. Warning: This paper contains example data that may be offensive or harmful.
As a fundamental task in computational chemistry, retrosynthesis prediction aims to identify a set of reactants to synthesize a target molecule. Existing template-free approaches only consider the graph structures of the target molecule, which often cannot generalize well to rare reaction types and large molecules. Here, we propose T-Rex, a text-assisted retrosynthesis prediction approach that exploits pre-trained text language models, such as ChatGPT, to assist the generation of reactants. T-Rex first exploits ChatGPT to generate a description for the target molecule and rank candidate reaction centers based both the description and the molecular graph. It then re-ranks these candidates by querying the descriptions for each reactants and examines which group of reactants can best synthesize the target molecule. We observed that T-Rex substantially outperformed graph-based state-of-the-art approaches on two datasets, indicating the effectiveness of considering text information. We further found that T-Rex outperformed the variant that only use ChatGPT-based description without the re-ranking step, demonstrate how our framework outperformed a straightforward integration of ChatGPT and graph information. Collectively, we show that text generated by pre-trained language models can substantially improve retrosynthesis prediction, opening up new avenues for exploiting ChatGPT to advance computational chemistry. And the codes can be found at https://github.com/lauyikfung/T-Rex.
This paper proposes a method for analyzing a series of potential motions in a coupling-tiltable aerial-aquatic quadrotor based on its nonlinear dynamics. Some characteristics and constraints derived by this method are specified as Singular Thrust Tilt Angles (STTAs), utilizing to generate motions including planar motions. A switch-based control scheme addresses issues of control direction uncertainty inherent to the mechanical structure by incorporating a saturated Nussbaum function. A high-fidelity simulation environment incorporating a comprehensive hydrodynamic model is built based on a Hardware-In-The-Loop (HITL) setup with Gazebo and a flight control board. The experiments validate the effectiveness of the absolute and quasi planar motions, which cannot be achieved by conventional quadrotors, and demonstrate stable performance when the pitch or roll angle is activated in the auxiliary control channel.
Deep neural networks enable real-time monitoring of in-vehicle driver, facilitating the timely prediction of distractions, fatigue, and potential hazards. This technology is now integral to intelligent transportation systems. Recent research has exposed unreliable cross-dataset end-to-end driver behavior recognition due to overfitting, often referred to as ``shortcut learning", resulting from limited data samples. In this paper, we introduce the Score-Softmax classifier, which addresses this issue by enhancing inter-class independence and Intra-class uncertainty. Motivated by human rating patterns, we designed a two-dimensional supervisory matrix based on marginal Gaussian distributions to train the classifier. Gaussian distributions help amplify intra-class uncertainty while ensuring the Score-Softmax classifier learns accurate knowledge. Furthermore, leveraging the summation of independent Gaussian distributed random variables, we introduced a multi-channel information fusion method. This strategy effectively resolves the multi-information fusion challenge for the Score-Softmax classifier. Concurrently, we substantiate the necessity of transfer learning and multi-dataset combination. We conducted cross-dataset experiments using the SFD, AUCDD-V1, and 100-Driver datasets, demonstrating that Score-Softmax improves cross-dataset performance without modifying the model architecture. This provides a new approach for enhancing neural network generalization. Additionally, our information fusion approach outperforms traditional methods.
Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL). Although methods like resetting and regularization can potentially mitigate plasticity loss, the influences of various components within the VRL framework on the agent's plasticity are still poorly understood. In this work, we conduct a systematic empirical exploration focusing on three primary underexplored facets and derive the following insightful conclusions: (1) data augmentation is essential in maintaining plasticity; (2) the critic's plasticity loss serves as the principal bottleneck impeding efficient training; and (3) without timely intervention to recover critic's plasticity in the early stages, its loss becomes catastrophic. These insights suggest a novel strategy to address the high replay ratio (RR) dilemma, where exacerbated plasticity loss hinders the potential improvements of sample efficiency brought by increased reuse frequency. Rather than setting a static RR for the entire training process, we propose Adaptive RR, which dynamically adjusts the RR based on the critic's plasticity level. Extensive evaluations indicate that Adaptive RR not only avoids catastrophic plasticity loss in the early stages but also benefits from more frequent reuse in later phases, resulting in superior sample efficiency.
Developing text mining approaches to mine aspects from customer reviews has been well-studied due to its importance in understanding customer needs and product attributes. In contrast, it remains unclear how to predict the future emerging aspects of a new product that currently has little review information. This task, which we named product aspect forecasting, is critical for recommending new products, but also challenging because of the missing reviews. Here, we propose ForeSeer, a novel textual mining and product embedding approach progressively trained on temporal product graphs for this novel product aspect forecasting task. ForeSeer transfers reviews from similar products on a large product graph and exploits these reviews to predict aspects that might emerge in future reviews. A key novelty of our method is to jointly provide review, product, and aspect embeddings that are both time-sensitive and less affected by extremely imbalanced aspect frequencies. We evaluated ForeSeer on a real-world product review system containing 11,536,382 reviews and 11,000 products over 3 years. We observe that ForeSeer substantially outperformed existing approaches with at least 49.1\% AUPRC improvement under the real setting where aspect associations are not given. ForeSeer further improves future link prediction on the product graph and the review aspect association prediction. Collectively, Foreseer offers a novel framework for review forecasting by effectively integrating review text, product network, and temporal information, opening up new avenues for online shopping recommendation and e-commerce applications.
Since the resurgence of deep learning, vision-language models (VLMs) enhanced by large language models (LLMs) have grown exponentially in popularity. However, while LLMs can utilize extensive background knowledge and task information with in-context learning, most VLMs still struggle with understanding complex multi-modal prompts with multiple images, making VLMs less effective in downstream vision-language tasks. In this paper, we address the limitation above by 1) introducing MMICL, a new approach to allow the VLM to deal with multi-modal inputs efficiently; 2) proposing a novel context scheme to augment the in-context learning ability of the VLM; 3) constructing the Multi-modal In-Context Learning (MIC) dataset, designed to enhance the VLM's ability to understand complex multi-modal prompts. Our experiments confirm that MMICL achieves new state-of-the-art zero-shot performance on a wide range of general vision-language tasks, especially for complex benchmarks, including MME and MMBench. Our analysis demonstrates that MMICL effectively tackles the challenge of complex multi-modal prompt understanding and emerges the impressive ICL ability. Furthermore, we observe that MMICL successfully alleviates language bias in VLMs, a common issue for VLMs that often leads to hallucination when faced with extensive textual context.
Differentiable optimization has received a significant amount of attention due to its foundational role in the domain of machine learning based on neural networks. The existing methods leverages the optimality conditions and implicit function theorem to obtain the Jacobian matrix of the output, which increases the computational cost and limits the application of differentiable optimization. In addition, some non-differentiable constraints lead to more challenges when using prior differentiable optimization layers. This paper proposes a differentiable layer, named Differentiable Frank-Wolfe Layer (DFWLayer), by rolling out the Frank-Wolfe method, a well-known optimization algorithm which can solve constrained optimization problems without projections and Hessian matrix computations, thus leading to a efficient way of dealing with large-scale problems. Theoretically, we establish a bound on the suboptimality gap of the DFWLayer in the context of l1-norm constraints. Experimental assessments demonstrate that the DFWLayer not only attains competitive accuracy in solutions and gradients but also consistently adheres to constraints. Moreover, it surpasses the baselines in both forward and backward computational speeds.