While Retrieval Augmented Generation (RAG) has emerged as a popular technique for improving Large Language Model (LLM) systems, it introduces a large number of choices, parameters and hyperparameters that must be made or tuned. This includes the LLM, embedding, and ranker models themselves, as well as hyperparameters governing individual RAG components. Yet, collectively optimizing the entire configuration in a RAG or LLM system remains under-explored - especially in multi-objective settings - due to intractably large solution spaces, noisy objective evaluations, and the high cost of evaluations. In this work, we introduce the first approach for multi-objective parameter optimization of cost, latency, safety and alignment over entire LLM and RAG systems. We find that Bayesian optimization methods significantly outperform baseline approaches, obtaining a superior Pareto front on two new RAG benchmark tasks. We conclude our work with important considerations for practitioners who are designing multi-objective RAG systems, highlighting nuances such as how optimal configurations may not generalize across tasks and objectives.
State space models (SSMs) have emerged as an efficient alternative to Transformer models for language modeling, offering linear computational complexity and constant memory usage as context length increases. However, despite their efficiency in handling long contexts, recent studies have shown that SSMs, such as Mamba models, generally underperform compared to Transformers in long-context understanding tasks. To address this significant shortfall and achieve both efficient and accurate long-context understanding, we propose LongMamba, a training-free technique that significantly enhances the long-context capabilities of Mamba models. LongMamba builds on our discovery that the hidden channels in Mamba can be categorized into local and global channels based on their receptive field lengths, with global channels primarily responsible for long-context capability. These global channels can become the key bottleneck as the input context lengthens. Specifically, when input lengths largely exceed the training sequence length, global channels exhibit limitations in adaptively extend their receptive fields, leading to Mamba's poor long-context performance. The key idea of LongMamba is to mitigate the hidden state memory decay in these global channels by preventing the accumulation of unimportant tokens in their memory. This is achieved by first identifying critical tokens in the global channels and then applying token filtering to accumulate only those critical tokens. Through extensive benchmarking across synthetic and real-world long-context scenarios, LongMamba sets a new standard for Mamba's long-context performance, significantly extending its operational range without requiring additional training. Our code is available at https://github.com/GATECH-EIC/LongMamba.
Generating a synthetic population that is both feasible and diverse is crucial for ensuring the validity of downstream activity schedule simulation in activity-based models (ABMs). While deep generative models (DGMs), such as variational autoencoders and generative adversarial networks, have been applied to this task, they often struggle to balance the inclusion of rare but plausible combinations (i.e., sampling zeros) with the exclusion of implausible ones (i.e., structural zeros). To improve feasibility while maintaining diversity, we propose a fine-tuning method for large language models (LLMs) that explicitly controls the autoregressive generation process through topological orderings derived from a Bayesian Network (BN). Experimental results show that our hybrid LLM-BN approach outperforms both traditional DGMs and proprietary LLMs (e.g., ChatGPT-4o) with few-shot learning. Specifically, our approach achieves approximately 95% feasibility, significantly higher than the ~80% observed in DGMs, while maintaining comparable diversity, making it well-suited for practical applications. Importantly, the method is based on a lightweight open-source LLM, enabling fine-tuning and inference on standard personal computing environments. This makes the approach cost-effective and scalable for large-scale applications, such as synthesizing populations in megacities, without relying on expensive infrastructure. By initiating the ABM pipeline with high-quality synthetic populations, our method improves overall simulation reliability and reduces downstream error propagation. The source code for these methods is available for research and practical application.
Roaming in Wireless LAN (Wi-Fi) is a critical yet challenging task for maintaining seamless connectivity in dynamic mobile environments. Conventional threshold-based or heuristic schemes often fail, leading to either sticky or excessive handovers. We introduce the first cross-layer use of an on-device large language model (LLM): high-level reasoning in the application layer that issues real-time actions executed in the PHY/MAC stack. The LLM addresses two tasks: (i) context-aware AP selection, where structured prompts fuse environmental cues (e.g., location, time) to choose the best BSSID; and (ii) dynamic threshold adjustment, where the model adaptively decides when to roam. To satisfy the tight latency and resource budgets of edge hardware, we apply a suite of optimizations-chain-of-thought prompting, parameter-efficient fine-tuning, and quantization. Experiments on indoor and outdoor datasets show that our approach surpasses legacy heuristics and DRL baselines, achieving a strong balance between roaming stability and signal quality. These findings underscore the promise of application-layer LLM reasoning for lower-layer wireless control in future edge systems.
Access to legal information is fundamental to access to justice. Yet accessibility refers not only to making legal documents available to the public, but also rendering legal information comprehensible to them. A vexing problem in bringing legal information to the public is how to turn formal legal documents such as legislation and judgments, which are often highly technical, to easily navigable and comprehensible knowledge to those without legal education. In this study, we formulate a three-step approach for bringing legal knowledge to laypersons, tackling the issues of navigability and comprehensibility. First, we translate selected sections of the law into snippets (called CLIC-pages), each being a small piece of article that focuses on explaining certain technical legal concept in layperson's terms. Second, we construct a Legal Question Bank (LQB), which is a collection of legal questions whose answers can be found in the CLIC-pages. Third, we design an interactive CLIC Recommender (CRec). Given a user's verbal description of a legal situation that requires a legal solution, CRec interprets the user's input and shortlists questions from the question bank that are most likely relevant to the given legal situation and recommends their corresponding CLIC pages where relevant legal knowledge can be found. In this paper we focus on the technical aspects of creating an LQB. We show how large-scale pre-trained language models, such as GPT-3, can be used to generate legal questions. We compare machine-generated questions (MGQs) against human-composed questions (HCQs) and find that MGQs are more scalable, cost-effective, and more diversified, while HCQs are more precise. We also show a prototype of CRec and illustrate through an example how our 3-step approach effectively brings relevant legal knowledge to the public.
Memes often merge visuals with brief text to share humor or opinions, yet some memes contain harmful messages such as hate speech. In this paper, we introduces MemeBLIP2, a light weight multimodal system that detects harmful memes by combining image and text features effectively. We build on previous studies by adding modules that align image and text representations into a shared space and fuse them for better classification. Using BLIP-2 as the core vision-language model, our system is evaluated on the PrideMM datasets. The results show that MemeBLIP2 can capture subtle cues in both modalities, even in cases with ironic or culturally specific content, thereby improving the detection of harmful material.
Recent advances in large vision-language models (LVLMs) have revealed an \textit{overthinking} phenomenon, where models generate verbose reasoning across all tasks regardless of questions. To address this issue, we present \textbf{FAST}, a novel \textbf{Fa}st-\textbf{S}low \textbf{T}hinking framework that dynamically adapts reasoning depth based on question characteristics. Through empirical analysis, we establish the feasibility of fast-slow thinking in LVLMs by investigating how response length and data distribution affect performance. We develop FAST-GRPO with three components: model-based metrics for question characterization, an adaptive thinking reward mechanism, and difficulty-aware KL regularization. Experiments across seven reasoning benchmarks demonstrate that FAST achieves state-of-the-art accuracy with over 10\% relative improvement compared to the base model, while reducing token usage by 32.7-67.3\% compared to previous slow-thinking approaches, effectively balancing reasoning length and accuracy.
Reasoning in large language models (LLMs) tends to produce substantially longer token generation sequences than simpler language modeling tasks. This extended generation length reflects the multi-step, compositional nature of reasoning and is often correlated with higher solution accuracy. From an efficiency perspective, longer token generation exacerbates the inherently sequential and memory-bound decoding phase of LLMs. However, not all parts of this expensive reasoning process are equally difficult to generate. We leverage this observation by offloading only the most challenging parts of the reasoning process to a larger, more capable model, while performing most of the generation with a smaller, more efficient model; furthermore, we teach the smaller model to identify these difficult segments and independently trigger offloading when needed. To enable this behavior, we annotate difficult segments across 18k reasoning traces from the OpenR1-Math-220k chain-of-thought (CoT) dataset. We then apply supervised fine-tuning (SFT) and reinforcement learning fine-tuning (RLFT) to a 1.5B-parameter reasoning model, training it to learn to offload the most challenging parts of its own reasoning process to a larger model. This approach improves AIME24 reasoning accuracy by 24% and 28.3% while offloading 1.35% and 5% of the generated tokens respectively. We open-source our SplitReason model, data, code and logs.
Recent advances in multimodal large language models (MLLMs) have demonstrated strong capabilities in understanding general visual content. However, these general-domain MLLMs perform poorly in face perception tasks, often producing inaccurate or misleading responses to face-specific queries. To address this gap, we propose FaceInsight, the versatile face perception MLLM that provides fine-grained facial information. Our approach introduces visual-textual alignment of facial knowledge to model both uncertain dependencies and deterministic relationships among facial information, mitigating the limitations of language-driven reasoning. Additionally, we incorporate face segmentation maps as an auxiliary perceptual modality, enriching the visual input with localized structural cues to enhance semantic understanding. Comprehensive experiments and analyses across three face perception tasks demonstrate that FaceInsight consistently outperforms nine compared MLLMs under both training-free and fine-tuned settings.
Accurate prediction of enzymatic activity from amino acid sequences could drastically accelerate enzyme engineering for applications such as bioremediation and therapeutics development. In recent years, Protein Language Model (PLM) embeddings have been increasingly leveraged as the input into sequence-to-function models. Here, we use consistently collected catalytic turnover observations for 175 orthologs of the enzyme Adenylate Kinase (ADK) as a test case to assess the use of PLMs and their embeddings in enzyme kinetic prediction tasks. In this study, we show that nonlinear probing of PLM embeddings outperforms baseline embeddings (one-hot-encoding) and the specialized $k_{cat}$ (catalytic turnover number) prediction models DLKcat and CatPred. We also compared fixed and learnable aggregation of PLM embeddings for $k_{cat}$ prediction and found that transformer-based learnable aggregation of amino-acid PLM embeddings is generally the most performant. Additionally, we found that ESMC 600M embeddings marginally outperform other PLM embeddings for $k_{cat}$ prediction. We explored Low-Rank Adaptation (LoRA) masked language model fine-tuning and direct fine-tuning for sequence-to-$k_{cat}$ mapping, where we found no difference or a drop in performance compared to zero-shot embeddings, respectively. And we investigated the distinct hidden representations in PLM encoders and found that earlier layer embeddings perform comparable to or worse than the final layer. Overall, this study assesses the state of the field for leveraging PLMs for sequence-to-$k_{cat}$ prediction on a set of diverse ADK orthologs.
Understanding the binding specificity between T-cell receptors (TCRs) and peptide-major histocompatibility complexes (pMHCs) is central to immunotherapy and vaccine development. However, current predictive models struggle with generalization, especially in data-scarce settings and when faced with novel epitopes. We present LANTERN (Large lAnguage model-powered TCR-Enhanced Recognition Network), a deep learning framework that combines large-scale protein language models with chemical representations of peptides. By encoding TCR \b{eta}-chain sequences using ESM-1b and transforming peptide sequences into SMILES strings processed by MolFormer, LANTERN captures rich biological and chemical features critical for TCR-peptide recognition. Through extensive benchmarking against existing models such as ChemBERTa, TITAN, and NetTCR, LANTERN demonstrates superior performance, particularly in zero-shot and few-shot learning scenarios. Our model also benefits from a robust negative sampling strategy and shows significant clustering improvements via embedding analysis. These results highlight the potential of LANTERN to advance TCR-pMHC binding prediction and support the development of personalized immunotherapies.
Objective: A number of machine learning models have utilized semantic features, deep features, or both to assess lung nodule malignancy. However, their reliance on manual annotation during inference, limited interpretability, and sensitivity to imaging variations hinder their application in real-world clinical settings. Thus, this research aims to integrate semantic features derived from radiologists' assessments of nodules, allowing the model to learn clinically relevant, robust, and explainable features for predicting lung cancer. Methods: We obtained 938 low-dose CT scans from the National Lung Screening Trial with 1,246 nodules and semantic features. The Lung Image Database Consortium dataset contains 1,018 CT scans, with 2,625 lesions annotated for nodule characteristics. Three external datasets were obtained from UCLA Health, the LUNGx Challenge, and the Duke Lung Cancer Screening. We finetuned a pretrained Contrastive Language-Image Pretraining model with a parameter-efficient fine-tuning approach to align imaging and semantic features and predict the one-year lung cancer diagnosis. Results: We evaluated the performance of the one-year diagnosis of lung cancer with AUROC and AUPRC and compared it to three state-of-the-art models. Our model demonstrated an AUROC of 0.90 and AUPRC of 0.78, outperforming baseline state-of-the-art models on external datasets. Using CLIP, we also obtained predictions on semantic features, such as nodule margin (AUROC: 0.81), nodule consistency (0.81), and pleural attachment (0.84), that can be used to explain model predictions. Conclusion: Our approach accurately classifies lung nodules as benign or malignant, providing explainable outputs, aiding clinicians in comprehending the underlying meaning of model predictions. This approach also prevents the model from learning shortcuts and generalizes across clinical settings.
First-order optimization methods remain the standard for training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by preconditioning the stochastic gradient with a diagonal matrix. Despite the widespread adoption of first-order methods, second-order optimization algorithms often exhibit superior convergence compared to methods like Adam and SGD. However, their practicality in training DNNs is still limited by a significantly higher per-iteration computational cost compared to first-order methods. In this thesis, we present AdaFisher, a novel adaptive second-order optimizer that leverages a diagonal block-Kronecker approximation of the Fisher information matrix to adaptively precondition gradients. AdaFisher aims to bridge the gap between the improved convergence and generalization of second-order methods and the computational efficiency needed for training DNNs. Despite the traditionally slower speed of second-order optimizers, AdaFisher is effective for tasks such as image classification and language modeling, exhibiting remarkable stability and robustness during hyperparameter tuning. We demonstrate that AdaFisher outperforms state-of-the-art optimizers in both accuracy and convergence speed. The code is available from https://github.com/AtlasAnalyticsLab/AdaFisher.
Language models have emerged as powerful predictors of the viability of biological sequences. During training these models learn the rules of the grammar obeyed by sequences of amino acids or nucleotides. Once trained, these models can take a sequence as input and produce a likelihood score as an output; a higher likelihood implies adherence to the learned grammar and correlates with experimental fitness measurements. Here we show that in-context learning can distort the relationship between fitness and likelihood scores of sequences. This phenomenon most prominently manifests as anomalously high likelihood scores for sequences that contain repeated motifs. We use protein language models with different architectures trained on the masked language modeling objective for our experiments, and find transformer-based models to be particularly vulnerable to this effect. This behavior is mediated by a look-up operation where the model seeks the identity of the masked position by using the other copy of the repeated motif as a reference. This retrieval behavior can override the model's learned priors. This phenomenon persists for imperfectly repeated sequences, and extends to other kinds of biologically relevant features such as reversed complement motifs in RNA sequences that fold into hairpin structures.
The rapid evolution of wireless networks presents unprecedented challenges in managing complex and dynamic systems. Existing methods are increasingly facing fundamental limitations in addressing these challenges. In this paper, we introduce WirelessAgent, a novel framework that harnesses large language models (LLMs) to create autonomous AI agents for diverse wireless network tasks. This framework integrates four core modules that mirror human cognitive processes: perception, memory, planning, and action. To implement it, we provide a basic usage based on agentic workflows and the LangGraph architecture. We demonstrate the effectiveness of WirelessAgent through a comprehensive case study on network slicing. The numerical results show that WirelessAgent achieves $44.4\%$ higher bandwidth utilization than the \emph{Prompt-based} method, while performing only $4.3\%$ below the \emph{Rule-based optimality}. Notably, WirelessAgent delivers near-optimal network throughput across diverse network scenarios. These underscore the framework's potential for intelligent and autonomous resource management in future wireless networks. The code is available at \url{https://github.com/jwentong/WirelessAgent_R1}.
We propose Fuzzy Group Relative Policy Reward (FGRPR), a novel framework that integrates Group Relative Policy Optimization (GRPO) with a fuzzy reward function to enhance learning efficiency. Unlike the conventional binary 0/1 accuracy reward, our fuzzy reward model provides nuanced incentives, encouraging more precise outputs. Experimental results demonstrate that GRPO with a standard 0/1 accuracy reward underperforms compared to supervised fine-tuning (SFT). In contrast, FGRPR, applied to Qwen2.5-VL(3B and 7B), surpasses all baseline models, including GPT4o, LLaMA2(90B), and SFT, across five in-domain datasets. On an out-of-domain dataset, FGRPR achieves performance comparable to SFT but excels when target values are larger, as its fuzzy reward function assigns higher rewards to closer approximations. This approach is broadly applicable to tasks where the precision of the answer is critical. Code and data: https://github.com/yeyimilk/CrowdVLM-R1
Clinical trials are crucial for assessing new treatments; however, recruitment challenges - such as limited awareness, complex eligibility criteria, and referral barriers - hinder their success. With the growth of online platforms, patients increasingly turn to social media and health communities for support, research, and advocacy, expanding recruitment pools and established enrollment pathways. Recognizing this potential, we utilized TrialGPT, a framework that leverages a large language model (LLM) as its backbone, to match 50 online patient cases (collected from published case reports and a social media website) to clinical trials and evaluate performance against traditional keyword-based searches. Our results show that TrialGPT outperforms traditional methods by 46% in identifying eligible trials, with each patient, on average, being eligible for around 7 trials. Additionally, our outreach efforts to case authors and trial organizers regarding these patient-trial matches yielded highly positive feedback, which we present from both perspectives.
Accurate wave height prediction is critical for maritime safety and coastal resilience, yet conventional physics-based models and traditional machine learning methods face challenges in computational efficiency and nonlinear dynamics modeling. This study introduces Chronos, the first implementation of a large language model (LLM)-powered temporal architecture (Chronos) optimized for wave forecasting. Through advanced temporal pattern recognition applied to historical wave data from three strategically chosen marine zones in the Northwest Pacific basin, our framework achieves multimodal improvements: (1) 14.3% reduction in training time with 2.5x faster inference speed compared to PatchTST baselines, achieving 0.575 mean absolute scaled error (MASE) units; (2) superior short-term forecasting (1-24h) across comprehensive metrics; (3) sustained predictive leadership in extended-range forecasts (1-120h); and (4) demonstrated zero-shot capability maintaining median performance (rank 4/12) against specialized operational models. This LLM-enhanced temporal modeling paradigm establishes a new standard in wave prediction, offering both computationally efficient solutions and a transferable framework for complex geophysical systems modeling.
LLMs are increasingly explored for bundle generation, thanks to their reasoning capabilities and knowledge. However, deploying large-scale LLMs introduces significant efficiency challenges, primarily high computational costs during fine-tuning and inference due to their massive parameterization. Knowledge distillation (KD) offers a promising solution, transferring expertise from large teacher models to compact student models. This study systematically investigates knowledge distillation approaches for bundle generation, aiming to minimize computational demands while preserving performance. We explore three critical research questions: (1) how does the format of KD impact bundle generation performance? (2) to what extent does the quantity of distilled knowledge influence performance? and (3) how do different ways of utilizing the distilled knowledge affect performance? We propose a comprehensive KD framework that (i) progressively extracts knowledge (patterns, rules, deep thoughts); (ii) captures varying quantities of distilled knowledge through different strategies; and (iii) exploits complementary LLM adaptation techniques (in-context learning, supervised fine-tuning, combination) to leverage distilled knowledge in small student models for domain-specific adaptation and enhanced efficiency. Extensive experiments provide valuable insights into how knowledge format, quantity, and utilization methodologies collectively shape LLM-based bundle generation performance, exhibiting KD's significant potential for more efficient yet effective LLM-based bundle generation.
We introduce Large Language Model-Assisted Preference Prediction (LAPP), a novel framework for robot learning that enables efficient, customizable, and expressive behavior acquisition with minimum human effort. Unlike prior approaches that rely heavily on reward engineering, human demonstrations, motion capture, or expensive pairwise preference labels, LAPP leverages large language models (LLMs) to automatically generate preference labels from raw state-action trajectories collected during reinforcement learning (RL). These labels are used to train an online preference predictor, which in turn guides the policy optimization process toward satisfying high-level behavioral specifications provided by humans. Our key technical contribution is the integration of LLMs into the RL feedback loop through trajectory-level preference prediction, enabling robots to acquire complex skills including subtle control over gait patterns and rhythmic timing. We evaluate LAPP on a diverse set of quadruped locomotion and dexterous manipulation tasks and show that it achieves efficient learning, higher final performance, faster adaptation, and precise control of high-level behaviors. Notably, LAPP enables robots to master highly dynamic and expressive tasks such as quadruped backflips, which remain out of reach for standard LLM-generated or handcrafted rewards. Our results highlight LAPP as a promising direction for scalable preference-driven robot learning.