This paper presents BAMBI (BAby language Models Boostrapped for Italian), a series of Baby Language Models (BabyLMs) trained on data that mimic the linguistic input received by a five-year-old Italian-speaking child. The BAMBI models are tested using a benchmark specifically designed to evaluate language models, which takes into account the amount of training input the models received. The BAMBI models are compared against a large language model (LLM) and a multimodal language model (VLM) to study the contribution of extralinguistic information for language acquisition. The results of our evaluation align with the existing literature on English language models, confirming that while reduced training data support the development of relatively robust syntactic competence, they are insufficient for fostering semantic understanding. However, the gap between the training resources (data and computation) of the BAMBI models and the LLMs is not fully reflected in their performance: despite LLMs' massive training, their performance is not much better than that of BAMBI models. This suggests that strategies beyond scaling training resources, such as data curation, inclusion of multimodal input, and other training strategies such as curriculum learning, could play a crucial role in shaping model performance.
Cross-lingual transfer enables vision-language models (VLMs) to perform vision tasks in various languages with training data only in one language. Current approaches rely on large pre-trained multilingual language models. However, they face the curse of multilinguality, sacrificing downstream task performance for multilingual capabilities, struggling with lexical ambiguities, and falling behind recent advances. In this work, we study the scaling laws of systematic generalization with monolingual VLMs for multilingual tasks, focusing on the impact of model size and seen training samples. We propose Florenz, a monolingual encoder-decoder VLM with 0.4B to 11.2B parameters combining the pre-trained VLM Florence-2 and the large language model Gemma-2. Florenz is trained with varying compute budgets on a synthetic dataset that features intentionally incomplete language coverage for image captioning, thus, testing generalization from the fully covered translation task. We show that not only does indirectly learning unseen task-language pairs adhere to a scaling law, but also that with our data generation pipeline and the proposed Florenz model family, image captioning abilities can emerge in a specific language even when only data for the translation task is available. Fine-tuning on a mix of downstream datasets yields competitive performance and demonstrates promising scaling trends in multimodal machine translation (Multi30K, CoMMuTE), lexical disambiguation (CoMMuTE), and image captioning (Multi30K, XM3600, COCO Karpathy).
Large Language Models (LLMs) are often asked to explain their outputs to enhance accuracy and transparency. However, evidence suggests that these explanations can misrepresent the models' true reasoning processes. One effective way to identify inaccuracies or omissions in these explanations is through consistency checking, which typically involves asking follow-up questions. This paper introduces, cross-examiner, a new method for generating follow-up questions based on a model's explanation of an initial question. Our method combines symbolic information extraction with language model-driven question generation, resulting in better follow-up questions than those produced by LLMs alone. Additionally, this approach is more flexible than other methods and can generate a wider variety of follow-up questions.
Dynamically integrating new or rapidly evolving information after (Large) Language Model pre-training remains challenging, particularly in low-data scenarios or when dealing with private and specialized documents. In-context learning and retrieval-augmented generation (RAG) face limitations, including their high inference costs and their inability to capture global document information. In this paper, we propose a way of modularizing knowledge by training document-level Knowledge Modules (KMs). KMs are lightweight components implemented as parameter-efficient LoRA modules, which are trained to store information about new documents and can be easily plugged into models on demand. We show that next-token prediction performs poorly as the training objective for KMs. We instead propose Deep Context Distillation: we learn KMs parameters such as to simulate hidden states and logits of a teacher that takes the document in context. Our method outperforms standard next-token prediction and pre-instruction training techniques, across two datasets. Finally, we highlight synergies between KMs and retrieval-augmented generation.
In many-task optimization scenarios, surrogate models are valuable for mitigating the computational burden of repeated fitness evaluations across tasks. This study proposes a novel meta-surrogate framework to assist many-task optimization, by leveraging the knowledge transfer strengths and emergent capabilities of large language models (LLMs). We formulate a unified framework for many-task fitness prediction, by defining a universal model with metadata to fit a group of problems. Fitness prediction is performed on metadata and decision variables, enabling efficient knowledge sharing across tasks and adaptability to new tasks. The LLM-based meta-surrogate treats fitness prediction as conditional probability estimation, employing a unified token sequence representation for task metadata, inputs, and outputs. This approach facilitates efficient inter-task knowledge sharing through shared token embeddings and captures complex task dependencies via multi-task model training. Experimental results demonstrate the model's emergent generalization ability, including zero-shot performance on problems with unseen dimensions. When integrated into evolutionary transfer optimization (ETO), our framework supports dual-level knowledge transfer -- at both the surrogate and individual levels -- enhancing optimization efficiency and robustness. This work establishes a novel foundation for applying LLMs in surrogate modeling, offering a versatile solution for many-task optimization.
Classical asset price forecasting methods primarily rely on numerical data, such as price time series, trading volumes, limit order book data, and technical analysis indicators. However, the news flow plays a significant role in price formation, making the development of multimodal approaches that combine textual and numerical data for improved prediction accuracy highly relevant. This paper addresses the problem of forecasting financial asset prices using the multimodal approach that combines candlestick time series and textual news flow data. A unique dataset was collected for the study, which includes time series for 176 Russian stocks traded on the Moscow Exchange and 79,555 financial news articles in Russian. For processing textual data, pre-trained models RuBERT and Vikhr-Qwen2.5-0.5b-Instruct (a large language model) were used, while time series and vectorized text data were processed using an LSTM recurrent neural network. The experiments compared models based on a single modality (time series only) and two modalities, as well as various methods for aggregating text vector representations. Prediction quality was estimated using two key metrics: Accuracy (direction of price movement prediction: up or down) and Mean Absolute Percentage Error (MAPE), which measures the deviation of the predicted price from the true price. The experiments showed that incorporating textual modality reduced the MAPE value by 55%. The resulting multimodal dataset holds value for the further adaptation of language models in the financial sector. Future research directions include optimizing textual modality parameters, such as the time window, sentiment, and chronological order of news messages.
Code embeddings capture the semantic representations of code and are crucial for various code-related large language model (LLM) applications, such as code search. Previous training primarily relies on optimizing the InfoNCE loss by comparing positive natural language (NL)-code pairs with in-batch negatives. However, due to the sparse nature of code contexts, training solely by comparing the major differences between positive and negative pairs may fail to capture deeper semantic nuances. To address this issue, we propose a novel order-augmented strategy for improved code search (OASIS). It leverages order-based similarity labels to train models to capture subtle differences in similarity among negative pairs. Extensive benchmark evaluations demonstrate that our OASIS model significantly outperforms previous state-of-the-art models focusing solely on major positive-negative differences. It underscores the value of exploiting subtle differences among negative pairs with order labels for effective code embedding training.
Traditional single-modality sensing faces limitations in accuracy and capability, and its decoupled implementation with communication systems increases latency in bandwidth-constrained environments. Additionally, single-task-oriented sensing systems fail to address users' diverse demands. To overcome these challenges, we propose a semantic-driven integrated multimodal sensing and communication (SIMAC) framework. This framework leverages a joint source-channel coding architecture to achieve simultaneous sensing decoding and transmission of sensing results. Specifically, SIMAC first introduces a multimodal semantic fusion (MSF) network, which employs two extractors to extract semantic information from radar signals and images, respectively. MSF then applies cross-attention mechanisms to fuse these unimodal features and generate multimodal semantic representations. Secondly, we present a large language model (LLM)-based semantic encoder (LSE), where relevant communication parameters and multimodal semantics are mapped into a unified latent space and input to the LLM, enabling channel-adaptive semantic encoding. Thirdly, a task-oriented sensing semantic decoder (SSD) is proposed, in which different decoded heads are designed according to the specific needs of tasks. Simultaneously, a multi-task learning strategy is introduced to train the SIMAC framework, achieving diverse sensing services. Finally, experimental simulations demonstrate that the proposed framework achieves diverse sensing services and higher accuracy.
Developing versatile quadruped robots that can smoothly perform various actions and tasks in real-world environments remains a significant challenge. This paper introduces a novel vision-language-action (VLA) model, mixture of robotic experts (MoRE), for quadruped robots that aim to introduce reinforcement learning (RL) for fine-tuning large-scale VLA models with a large amount of mixed-quality data. MoRE integrates multiple low-rank adaptation modules as distinct experts within a dense multi-modal large language model (MLLM), forming a sparse-activated mixture-of-experts model. This design enables the model to effectively adapt to a wide array of downstream tasks. Moreover, we employ a reinforcement learning-based training objective to train our model as a Q-function after deeply exploring the structural properties of our tasks. Effective learning from automatically collected mixed-quality data enhances data efficiency and model performance. Extensive experiments demonstrate that MoRE outperforms all baselines across six different skills and exhibits superior generalization capabilities in out-of-distribution scenarios. We further validate our method in real-world scenarios, confirming the practicality of our approach and laying a solid foundation for future research on multi-task learning in quadruped robots.
In this study, we unveil a new AI model, termed PhyE2E, to discover physical formulas through symbolic regression. PhyE2E simplifies symbolic regression by decomposing it into sub-problems using the second-order derivatives of an oracle neural network, and employs a transformer model to translate data into symbolic formulas in an end-to-end manner. The resulting formulas are refined through Monte-Carlo Tree Search and Genetic Programming. We leverage a large language model to synthesize extensive symbolic expressions resembling real physics, and train the model to recover these formulas directly from data. A comprehensive evaluation reveals that PhyE2E outperforms existing state-of-the-art approaches, delivering superior symbolic accuracy, precision in data fitting, and consistency in physical units. We deployed PhyE2E to five applications in space physics, including the prediction of sunspot numbers, solar rotational angular velocity, emission line contribution functions, near-Earth plasma pressure, and lunar-tide plasma signals. The physical formulas generated by AI demonstrate a high degree of accuracy in fitting the experimental data from satellites and astronomical telescopes. We have successfully upgraded the formula proposed by NASA in 1993 regarding solar activity, and for the first time, provided the explanations for the long cycle of solar activity in an explicit form. We also found that the decay of near-Earth plasma pressure is proportional to r^2 to Earth, where subsequent mathematical derivations are consistent with satellite data from another independent study. Moreover, we found physical formulas that can describe the relationships between emission lines in the extreme ultraviolet spectrum of the Sun, temperatures, electron densities, and magnetic fields. The formula obtained is consistent with the properties that physicists had previously hypothesized it should possess.
Effective Human-Robot Interaction (HRI) is crucial for future service robots in aging societies. Existing solutions are biased toward only well-trained objects, creating a gap when dealing with new objects. Currently, HRI systems using predefined gestures or language tokens for pretrained objects pose challenges for all individuals, especially elderly ones. These challenges include difficulties in recalling commands, memorizing hand gestures, and learning new names. This paper introduces NVP-HRI, an intuitive multi-modal HRI paradigm that combines voice commands and deictic posture. NVP-HRI utilizes the Segment Anything Model (SAM) to analyze visual cues and depth data, enabling precise structural object representation. Through a pre-trained SAM network, NVP-HRI allows interaction with new objects via zero-shot prediction, even without prior knowledge. NVP-HRI also integrates with a large language model (LLM) for multimodal commands, coordinating them with object selection and scene distribution in real time for collision-free trajectory solutions. We also regulate the action sequence with the essential control syntax to reduce LLM hallucination risks. The evaluation of diverse real-world tasks using a Universal Robot showcased up to 59.2\% efficiency improvement over traditional gesture control, as illustrated in the video https://youtu.be/EbC7al2wiAc. Our code and design will be openly available at https://github.com/laiyuzhi/NVP-HRI.git.
Integrating audio and visual data for training multimodal foundational models remains challenging. We present Audio-Video Vector Alignment (AVVA), which aligns audiovisual (AV) scene content beyond mere temporal synchronization via a Large Language Model (LLM)-based data curation pipeline. Specifically, AVVA scores and selects high-quality training clips using Whisper (speech-based audio foundation model) for audio and DINOv2 for video within a dual-encoder contrastive learning framework. Evaluations on AudioCaps, VALOR, and VGGSound demonstrate that this approach can achieve significant accuracy gains with substantially less curated data. For instance, AVVA yields a 7.6% improvement in top-1 accuracy for audio-to-video retrieval on VGGSound compared to ImageBind, despite training on only 192 hours of carefully filtered data (vs. 5800+ hours). Moreover, an ablation study highlights that trading data quantity for data quality improves performance, yielding respective top-3 accuracy increases of 47.8, 48.4, and 58.0 percentage points on AudioCaps, VALOR, and VGGSound over uncurated baselines. While these results underscore AVVA's data efficiency, we also discuss the overhead of LLM-driven curation and how it may be scaled or approximated in larger domains. Overall, AVVA provides a viable path toward more robust, text-free audiovisual learning with improved retrieval accuracy.
The next generation of active safety features in autonomous vehicles should be capable of safely executing evasive hazard-avoidance maneuvers akin to those performed by professional stunt drivers to achieve high-agility motion at the limits of vehicle handling. This paper presents a novel framework, ManeuverGPT, for generating and executing high-dynamic stunt maneuvers in autonomous vehicles using large language model (LLM)-based agents as controllers. We target aggressive maneuvers, such as J-turns, within the CARLA simulation environment and demonstrate an iterative, prompt-based approach to refine vehicle control parameters, starting tabula rasa without retraining model weights. We propose an agentic architecture comprised of three specialized agents (1) a Query Enricher Agent for contextualizing user commands, (2) a Driver Agent for generating maneuver parameters, and (3) a Parameter Validator Agent that enforces physics-based and safety constraints. Experimental results demonstrate successful J-turn execution across multiple vehicle models through textual prompts that adapt to differing vehicle dynamics. We evaluate performance via established success criteria and discuss limitations regarding numeric precision and scenario complexity. Our findings underscore the potential of LLM-driven control for flexible, high-dynamic maneuvers, while highlighting the importance of hybrid approaches that combine language-based reasoning with algorithmic validation.
Index recommendation is essential for improving query performance in database management systems (DBMSs) through creating an optimal set of indexes under specific constraints. Traditional methods, such as heuristic and learning-based approaches, are effective but face challenges like lengthy recommendation time, resource-intensive training, and poor generalization across different workloads and database schemas. To address these issues, we propose LLMIdxAdvis, a resource-efficient index advisor that uses large language models (LLMs) without extensive fine-tuning. LLMIdxAdvis frames index recommendation as a sequence-to-sequence task, taking target workload, storage constraint, and corresponding database environment as input, and directly outputting recommended indexes. It constructs a high-quality demonstration pool offline, using GPT-4-Turbo to synthesize diverse SQL queries and applying integrated heuristic methods to collect both default and refined labels. During recommendation, these demonstrations are ranked to inject database expertise via in-context learning. Additionally, LLMIdxAdvis extracts workload features involving specific column statistical information to strengthen LLM's understanding, and introduces a novel inference scaling strategy combining vertical scaling (via ''Index-Guided Major Voting'' and Best-of-N) and horizontal scaling (through iterative ''self-optimization'' with database feedback) to enhance reliability. Experiments on 3 OLAP and 2 real-world benchmarks reveal that LLMIdxAdvis delivers competitive index recommendation with reduced runtime, and generalizes effectively across different workloads and database schemas.
Deep Learning (DL) has emerged as a powerful tool for vulnerability detection, often outperforming traditional solutions. However, developing effective DL models requires large amounts of real-world data, which can be difficult to obtain in sufficient quantities. To address this challenge, DiverseVul dataset has been curated as the largest dataset of vulnerable and non-vulnerable C/C++ functions extracted exclusively from real-world projects. Its goal is to provide high-quality, large-scale samples for training DL models. However, during our study several inconsistencies were identified in the raw dataset while applying pre-processing techniques, highlighting the need for a refined version. In this work, we present a refined version of DiverseVul dataset, which is used to fine-tune a large language model, LLaMA 3.2, for vulnerability detection. Experimental results show that the use of pre-processing techniques led to an improvement in performance, with the model achieving an F1-Score of 66%, a competitive result when compared to our baseline, which achieved a 47% F1-Score in software vulnerability detection.
Existing benchmarks are becoming saturated and struggle to separate model performances due to factors like data contamination and advancing LLM capabilities. This paper introduces EMDM (Enhanced Model Differentiation Metric), a novel weighted metric that revitalizes benchmarks by enhancing model separation. EMDM integrates final answer and Chain-of-Thought (CoT) reasoning correctness, assigning weights based on the complexity and reasoning depth required to solve a given sample in the evaluation data. Using a baseline LLM in two setups-Unguided, where the model has no prior exposure to test samples, and Guided, where the model has prior knowledge of the desired answer-EMDM distinguishes instances of varying difficulty. The CoT and answer correctness from these setups inform an optimization objective for weight assignment, resulting in a more nuanced evaluation of model performance. Compared to the exact match (EM) metric, which achieves 17% separation on ARC-Challenge, EMDM achieves 46%, demonstrating its effectiveness in differentiating models based on reasoning and knowledge requirements.
Large Language Model (LLM) services often face challenges in achieving low inference latency and meeting Service Level Objectives (SLOs) under dynamic request patterns. Speculative decoding, which exploits lightweight models for drafting and LLMs for verification, has emerged as a compelling technique to accelerate LLM inference. However, existing speculative decoding solutions often fail to adapt to varying workloads and system environments, resulting in performance variability and SLO violations. In this paper, we introduce SpecServe, an efficient LLM inference system that dynamically adjusts speculative strategies according to real-time request loads and system configurations. SpecServe proposes a theoretical model to understand and predict the efficiency of speculative decoding across diverse scenarios. Additionally, it implements intelligent drafting and verification algorithms to guarantee optimal performance while achieving high SLO attainment. Experimental results on real-world LLM traces demonstrate that SpecServe consistently meets SLOs and achieves substantial performance improvements, yielding 1.14$\times$-14.3$\times$ speedups over state-of-the-art speculative inference systems.
Information technology has profoundly altered the way humans interact with information. The vast amount of content created, shared, and disseminated online has made it increasingly difficult to access relevant information. Over the past two decades, recommender systems and search (collectively referred to as information retrieval systems) have evolved significantly to address these challenges. Recent advances in large language models (LLMs) have demonstrated capabilities that surpass human performance in various language-related tasks and exhibit general understanding, reasoning, and decision-making abilities. This paper explores the transformative potential of LLM agents in enhancing recommender and search systems. We discuss the motivations and roles of LLM agents, and establish a classification framework to elaborate on the existing research. We highlight the immense potential of LLM agents in addressing current challenges in recommendation and search, providing insights into future research directions. This paper is the first to systematically review and classify the research on LLM agents in these domains, offering a novel perspective on leveraging this advanced AI technology for information retrieval. To help understand the existing works, we list the existing papers on LLM agent based recommendation and search at this link: https://github.com/tsinghua-fib-lab/LLM-Agent-for-Recommendation-and-Search.
Large Language Model based multi-agent systems are revolutionizing autonomous communication and collaboration, yet they remain vulnerable to security threats like unauthorized access and data breaches. To address this, we introduce AgentSafe, a novel framework that enhances MAS security through hierarchical information management and memory protection. AgentSafe classifies information by security levels, restricting sensitive data access to authorized agents. AgentSafe incorporates two components: ThreatSieve, which secures communication by verifying information authority and preventing impersonation, and HierarCache, an adaptive memory management system that defends against unauthorized access and malicious poisoning, representing the first systematic defense for agent memory. Experiments across various LLMs show that AgentSafe significantly boosts system resilience, achieving defense success rates above 80% under adversarial conditions. Additionally, AgentSafe demonstrates scalability, maintaining robust performance as agent numbers and information complexity grow. Results underscore effectiveness of AgentSafe in securing MAS and its potential for real-world application.
Temporal progression is an integral part of knowledge accumulation and update. Web search is frequently adopted as grounding for agent knowledge, yet an improper configuration affects the quality of the agent's responses. Here, we assess the agent behavior using distinct date-controlled tools (DCTs) as stress test to measure the knowledge variability of large language model (LLM) agents. We demonstrate the temporal effects of an LLM agent as a writing assistant, which uses web search to complete scientific publication abstracts. We show that the temporality of search engine translates into tool-dependent agent performance but can be alleviated with base model choice and explicit reasoning instructions such as chain-of-thought prompting. Our results indicate that agent design and evaluations should take a dynamical view and implement measures to account for the temporal influence of external resources to ensure reliability.