Large language models (LLMs) have achieved remarkable performance across many tasks, yet aligning them with desired behaviors remains challenging. Activation intervention has emerged as an effective and economical method to modify the behavior of LLMs. Despite considerable interest in this area, current intervention methods exclusively employ a fixed steering vector to modify model activations, lacking adaptability to diverse input semantics. To address this limitation, we propose Semantics-Adaptive Dynamic Intervention (SADI), a novel method that constructs a dynamic steering vector to intervene model activations at inference time. More specifically, SADI utilizes activation differences in contrastive pairs to precisely identify critical elements of an LLM (i.e., attention heads, hidden states, and neurons) for targeted intervention. During inference, SADI dynamically steers model behavior by scaling element-wise activations based on the directions of input semantics. Experimental results show that SADI outperforms established baselines by substantial margins, improving task performance without training. SADI's cost-effectiveness and generalizability across various LLM backbones and tasks highlight its potential as a versatile alignment technique. In addition, we release the code to foster research along this line:https://github.com/weixuan-wang123/SADI.

In this paper, we present EH-MAM (Easy-to-Hard adaptive Masked Acoustic Modeling), a novel self-supervised learning approach for speech representation learning. In contrast to the prior methods that use random masking schemes for Masked Acoustic Modeling (MAM), we introduce a novel selective and adaptive masking strategy. Specifically, during SSL training, we progressively introduce harder regions to the model for reconstruction. Our approach automatically selects hard regions and is built on the observation that the reconstruction loss of individual frames in MAM can provide natural signals to judge the difficulty of solving the MAM pre-text task for that frame. To identify these hard regions, we employ a teacher model that first predicts the frame-wise losses and then decides which frames to mask. By learning to create challenging problems, such as identifying harder frames and solving them simultaneously, the model is able to learn more effective representations and thereby acquire a more comprehensive understanding of the speech. Quantitatively, EH-MAM outperforms several state-of-the-art baselines across various low-resource speech recognition and SUPERB benchmarks by 5%-10%. Additionally, we conduct a thorough analysis to show that the regions masked by EH-MAM effectively capture useful context across speech frames.

Messenger RNA (mRNA) plays a crucial role in protein synthesis, with its codon structure directly impacting biological properties. While Language Models (LMs) have shown promise in analyzing biological sequences, existing approaches fail to account for the hierarchical nature of mRNA's codon structure. We introduce Hierarchical Encoding for mRNA Language Modeling (HELM), a novel pre-training strategy that incorporates codon-level hierarchical structure into language model training. HELM modulates the loss function based on codon synonymity, aligning the model's learning process with the biological reality of mRNA sequences. We evaluate HELM on diverse mRNA datasets and tasks, demonstrating that HELM outperforms standard language model pre-training as well as existing foundation model baselines on six diverse downstream property prediction tasks and an antibody region annotation tasks on average by around 8%. Additionally, HELM enhances the generative capabilities of language model, producing diverse mRNA sequences that better align with the underlying true data distribution compared to non-hierarchical baselines. RNA analysis is becoming increasingly important in molecular biology (Liu et al., 2023; Fu, 2014). Messenger RNA (mRNA) is of particular interest due to its unique role in protein synthesis (Sahin et al., 2014). Language Models (LMs) have emerged as powerful tools for analyzing biological sequences, with notable successes in protein (Elnaggar et al., 2021; Ferruz et al., 2022; Lin et al., 2023; Hie et al., 2024) and DNA (Nguyen et al., 2024a; Zhou et al., 2023) research. Despite the importance of mRNA, the field still lacks specialized LMs tailored for its analysis. Existing RNA LMs (Li et al., 2023; Chen et al., 2023) focus on non-coding sequences and do not account properly for codon hierarchy (Figure 1 right) which, as we demonstrate, falls short when dealing with mRNA tasks. In this work, we aim to address this gap in mRNA language modeling by focusing specifically on the unique challenges presented by mRNA sequences. To address the limitations of existing bio-language modeling methods, we introduce Hierarchical Encoding for mRNA Language Modeling (HELM), a novel pre-training strategy for mRNA sequences. The tree diagram illustrates the codon hierarchy used in the HELM approach, categorizing codons into Start, Coding (grouped by amino acids), and Stop. This hierarchy informs the loss calculation.

When combined with In-Context Learning, a technique that enables models to adapt to new tasks by incorporating task-specific examples or demonstrations directly within the input prompt, autoregressive language models have achieved good performance in a wide range of tasks and applications. However, this combination has not been properly explored in the context of named entity recognition, where the structure of this task poses unique challenges. We propose RENER (Retrieval-Enhanced Named Entity Recognition), a technique for named entity recognition using autoregressive language models based on In-Context Learning and information retrieval techniques. When presented with an input text, RENER fetches similar examples from a dataset of training examples that are used to enhance a language model to recognize named entities from this input text. RENER is modular and independent of the underlying language model and information retrieval algorithms. Experimental results show that in the CrossNER collection we achieve state-of-the-art performance with the proposed technique and that information retrieval can increase the F-score by up to 11 percentage points.

Real-time aerial image segmentation plays an important role in the environmental perception of Uncrewed Aerial Vehicles (UAVs). We introduce BlabberSeg, an optimized Vision-Language Model built on CLIPSeg for on-board, real-time processing of aerial images by UAVs. BlabberSeg improves the efficiency of CLIPSeg by reusing prompt and model features, reducing computational overhead while achieving real-time open-vocabulary aerial segmentation. We validated BlabberSeg in a safe landing scenario using the Dynamic Open-Vocabulary Enhanced SafE-Landing with Intelligence (DOVESEI) framework, which uses visual servoing and open-vocabulary segmentation. BlabberSeg reduces computational costs significantly, with a speed increase of 927.41% (16.78 Hz) on a NVIDIA Jetson Orin AGX (64GB) compared with the original CLIPSeg (1.81Hz), achieving real-time aerial segmentation with negligible loss in accuracy (2.1% as the ratio of the correctly segmented area with respect to CLIPSeg). BlabberSeg's source code is open and available online.

Extensive knowledge graphs (KGs) have been constructed to facilitate knowledge-driven tasks across various scenarios. However, existing work usually develops separate reasoning models for different KGs, lacking the ability to generalize and transfer knowledge across diverse KGs and reasoning settings. In this paper, we propose a prompt-based KG foundation model via in-context learning, namely KG-ICL, to achieve a universal reasoning ability. Specifically, we introduce a prompt graph centered with a query-related example fact as context to understand the query relation. To encode prompt graphs with the generalization ability to unseen entities and relations in queries, we first propose a unified tokenizer that maps entities and relations in prompt graphs to predefined tokens. Then, we propose two message passing neural networks to perform prompt encoding and KG reasoning, respectively. We conduct evaluation on 43 different KGs in both transductive and inductive settings. Results indicate that the proposed KG-ICL outperforms baselines on most datasets, showcasing its outstanding generalization and universal reasoning capabilities. The source code is accessible on GitHub: https://github.com/nju-websoft/KG-ICL.

As Large Language Model (LLM)-based agents become increasingly autonomous and will more freely interact with each other, studying interactions between them becomes crucial to anticipate emergent phenomena and potential risks. Drawing inspiration from the widely popular Stanford Prison Experiment, we contribute to this line of research by studying interaction patterns of LLM agents in a context characterized by strict social hierarchy. We do so by specifically studying two types of phenomena: persuasion and anti-social behavior in simulated scenarios involving a guard and a prisoner agent who seeks to achieve a specific goal (i.e., obtaining additional yard time or escape from prison). Leveraging 200 experimental scenarios for a total of 2,000 machine-machine conversations across five different popular LLMs, we provide a set of noteworthy findings. We first document how some models consistently fail in carrying out a conversation in our multi-agent setup where power dynamics are at play. Then, for the models that were able to engage in successful interactions, we empirically show how the goal that an agent is set to achieve impacts primarily its persuasiveness, while having a negligible effect with respect to the agent's anti-social behavior. Third, we highlight how agents' personas, and particularly the guard's personality, drive both the likelihood of successful persuasion from the prisoner and the emergence of anti-social behaviors. Fourth, we show that even without explicitly prompting for specific personalities, anti-social behavior emerges by simply assigning agents' roles. These results bear implications for the development of interactive LLM agents as well as the debate on their societal impact.

The computational cost for inference and prediction of statistical models based on Gaussian processes with Mat\'ern covariance functions scales cubicly with the number of observations, limiting their applicability to large data sets. The cost can be reduced in certain special cases, but there are currently no generally applicable exact methods with linear cost. Several approximate methods have been introduced to reduce the cost, but most of these lack theoretical guarantees for the accuracy. We consider Gaussian processes on bounded intervals with Mat\'ern covariance functions and for the first time develop a generally applicable method with linear cost and with a covariance error that decreases exponentially fast in the order $m$ of the proposed approximation. The method is based on an optimal rational approximation of the spectral density and results in an approximation that can be represented as a sum of $m$ independent Gaussian Markov processes, which facilitates easy usage in general software for statistical inference, enabling its efficient implementation in general statistical inference software packages. Besides the theoretical justifications, we demonstrate the accuracy empirically through carefully designed simulation studies which show that the method outperforms all state-of-the-art alternatives in terms of accuracy for a fixed computational cost in statistical tasks such as Gaussian process regression.

Recent normalization-based methods have shown great success in tackling the distribution shift issue, facilitating non-stationary time series forecasting. Since these methods operate in the time domain, they may fail to fully capture the dynamic patterns that are more apparent in the frequency domain, leading to suboptimal results. This paper first theoretically analyzes how normalization methods affect frequency components. We prove that the current normalization methods that operate in the time domain uniformly scale non-zero frequencies, and thus, they struggle to determine components that contribute to more robust forecasting. Therefore, we propose FredNormer, which observes datasets from a frequency perspective and adaptively up-weights the key frequency components. To this end, FredNormer consists of two components: a statistical metric that normalizes the input samples based on their frequency stability and a learnable weighting layer that adjusts stability and introduces sample-specific variations. Notably, FredNormer is a plug-and-play module, which does not compromise the efficiency compared to existing normalization methods. Extensive experiments show that FredNormer improves the averaged MSE of backbone forecasting models by 33.3% and 55.3% on the ETTm2 dataset. Compared to the baseline normalization methods, FredNormer achieves 18 top-1 results and 6 top-2 results out of 28 settings.

Twenty-four years ago, the surgeon Santiago Horgan performed the first robotically assisted gastric-bypass surgery in the world, a major medical breakthrough. Now Horgan is working with a new tool that he argues could be even more transformative in operating rooms: the Apple Vision Pro. Over the last month, Horgan and other surgeons at the University of California, San Diego have performed more than 20 minimally invasive operations while wearing Apple's mixed-reality headsets. Apple released the headsets to the public in February, and they've largely been a commercial flop. But practitioners in some industries, including architecture and medicine, have been testing how they might serve particular needs.