论文检索

Deep Learning · Large Language Models

Akhiad Bercovich, Tomer Ronen, Talor Abramovich, Nir Ailon, Nave Assaf, Mohammed Dabbah, Ido Galil, Amnon Geifman, Yonatan Geifman, Izhak Golan 等

Large language models (LLMs) offer remarkable capabilities, yet their high inference costs restrict wider adoption.While increasing parameter counts improves accuracy, it also broadens the gap between state-of-the-art capabilities and practical deployability. We present **Puzzle**, a hardware-aware framework that accelerates the inference of LLMs while preserving their capabilities.Using neural architecture search (NAS) at a large-scale, Puzzle optimizes models with tens of billions of parameters.Our approach utilizes blockwise local knowledge distillation (BLD) for parallel architecture exploration and employs mixed-integer programming for precise constraint optimization.We showcase our framework’s impact via Llama-3.1-Nemotron-51B-Instruct (Nemotron-51B) and Llama-3.3-Nemotron-49B, two publicly available models derived from Llama-70B-Instruct. Both models achieve a 2.17x inference throughput speedup, fitting on a single NVIDIA H100 GPU while retaining 98.4% of the original model's benchmark accuracies. These are the most accurate models supporting single H100 GPU inference with large batch sizes, despite training on 45B tokens at most, far fewer than the 15T used to train Llama-70B.Lastly, we show that lightweight alignment on these derived models allows them to surpass the parent model in specific capabilities.Our work establishes that powerful LLM models can be optimized for efficient deployment with only negligible loss in quality, underscoring that inference performance, not parameter count alone, should guide model selection.

Deep Learning · Large Language Models

Dujian Ding, Ankur Mallick, Shaokun Zhang, Chi Wang, Daniel Madrigal, Mirian Hipolito Garcia, Menglin Xia, Laks Lakshmanan, Qingyun Wu, Victor Ruehle

Large language models (LLMs) are powerful tools but are often expensive to deploy at scale. LLM query routing mitigates this by dynamically assigning queries to models of varying cost and quality to obtain a desired tradeoff. Prior query routing approaches generate only one response from the selected model and a single response from a small (inexpensive) model was often not good enough to beat a response from a large (expensive) model due to which they end up overusing the large model and missing out on potential cost savings. However, it is well known that for small models, generating multiple responses and selecting the best can enhance quality while remaining cheaper than a single large-model response. We leverage this idea to propose BEST-Route, a novel routing framework that chooses a model and the number of responses to sample from it based on query difficulty and the quality thresholds. Experiments on real-world datasets demonstrate that our method reduces costs by up to 60% with less than 1% performance drop.

Deep Learning · Large Language Models

Brian Mak, Jeffrey Flanigan

The residual stream acts as a memory bus where transformer layers both store and access features (Elhage et al., 2021). We consider changing the mechanism for retrieving and storing information in the residual stream, and replace the residual stream of the transformer with an outer product memory matrix (Kohonen, 1972, Anderson, 1972). We call this model the Residual Matrix Transformer (RMT). We find that the RMT enjoys a number of attractive properties: 1) the size of the residual stream can be scaled independently of compute and model size, improving performance, 2) the RMT can achieve the same loss as the transformer with 58% fewer FLOPS, 25% fewer parameters, and 41% fewer training tokens tokens, and 3) the RMT outperforms the transformer on downstream evaluations. We theoretically analyze the transformer and the RMT, and show that the RMT allows for more efficient scaling of the residual stream, as well as improved variance propagation properties.

Deep Learning · Large Language Models

Yi Xie, Zhanke Zhou, Chentao Cao, Qiyu Niu, Tongliang Liu, Bo Han

Multi-agent frameworks can substantially boost the reasoning power of large language models (LLMs), but they typically incur heavy computational costs and lack convergence guarantees. To overcome these challenges, we recast multi-LLM coordination as an incomplete-information game and seek a Bayesian Nash equilibrium (BNE), in which each agent optimally responds to its probabilistic beliefs about the strategies of others. We introduce Efficient Coordination via Nash Equilibrium (ECON), a hierarchical reinforcement-learning paradigm that marries distributed reasoning with centralized final output. Under ECON, each LLM independently selects responses that maximize its expected reward, conditioned on its beliefs about co-agents, without requiring costly inter-agent exchanges.We mathematically prove that ECON attains a markedly tighter regret bound than non-equilibrium multi-agent schemes. Empirically, ECON outperforms existing multi-LLM approaches by 11.2% on average across six benchmarks spanning complex reasoning and planning tasks. Further experiments demonstrate ECON’s ability to flexibly incorporate additional models, confirming its scalability and paving the way toward larger, more powerful multi-LLM ensembles. The code is publicly available at: https://github.com/tmlr-group/ECON.

Theory · Game Theory

Ohad Einav, Nir Rosenfeld

Machine learning models play a key role for service providers looking to gain market share in consumer markets. However, traditional learning approaches do not take into account the existence of additional providers, who compete with each other for consumers. Our work aims to study learning in this market setting, as it affects providers, consumers, and the market itself. We begin by analyzing such markets through the lens of the learning objective, and show that accuracy cannot be the only consideration. We then propose a method for classification under competition, so that a learner can maximize market share in the presence of competitors. We show that our approach benefits the providers as well as the consumers, and find that the timing of market entry and model updates can be crucial. We display the effectiveness of our approach across a range of domains, from simple distributions to noisy datasets, and show that the market as a whole remains stable by converging quickly to an equilibrium.

General Machine Learning · Evaluation

Renze Lou, Hanzi Xu, Sijia Wang, Jiangshu Du, Ryo Kamoi, Xiaoxin Lu, Jian Xie, Yuxuan Sun, Yusen Zhang, Jihyun Ahn 等

Numerous studies have assessed the proficiency of AI systems, particularly large language models (LLMs), in facilitating everyday tasks such as email writing, question answering, and creative content generation. However, researchers face unique challenges and opportunities in leveraging LLMs for their own work, such as brainstorming research ideas, designing experiments, and writing or reviewing papers. In this study, we introduce AAAR-1.0, a benchmark dataset designed to evaluate LLM performance in three fundamental, expertise-intensive research tasks: (i) EquationInference, assessing the correctness of equations based on the contextual information in paper submissions; (ii) ExperimentDesign, designing experiments to validate research ideas and solutions; and (iii) PaperWeakness, identifying weaknesses in paper submissions. AAAR-1.0 differs from prior benchmarks in two key ways: first, it is explicitly research-oriented, with tasks requiring deep domain expertise; second, it is researcher-oriented, mirroring the primary activities that researchers engage in on a daily basis. An evaluation of both open-source and proprietary LLMs reveals their potential as well as limitations in conducting sophisticated research tasks. We will release the AAAR-1.0 and keep iterating it to new versions.

Applications · Computer Vision

Chenyu Li, Oscar Michel, Xichen Pan, Sainan Liu, Mike Roberts, Saining Xie

Large-scale pre-trained video generation models excel in content creation but are not reliable as physically accurate world simulators out of the box. This work studies the process of post-training these models for accurate world modeling through the lens of the simple, yet fundamental, physics task of modeling object freefall. We show state-of-the-art video generation models struggle with this basic task, despite their visually impressive outputs. To remedy this problem, we find that fine-tuning on a relatively small amount of simulated videos is effective in inducing the dropping behavior in the model, and we can further improve results through a novel reward modeling procedure we introduce. Our study also reveals key limitations of post-training in generalization and distribution modeling. Additionally, we release a benchmark for this task that may serve as a useful diagnostic tool for tracking physical accuracy in large-scale video generative model development. Code is available at this repository: https://github.com/vision-x-nyu/pisa-experiments.

Deep Learning · Graph Neural Networks

Yangyi Shen, Jincheng Zhou, Beatrice Bevilacqua, Joshua Robinson, Charilaos Kanatsoulis, Jure Leskovec, Bruno Ribeiro

Traditional Graph Neural Networks (GNNs) cannot generalize to new graphs with node attributes different from the training ones, making zero-shot generalization across different node attribute domains an open challenge in graph machine learning. In this paper, we propose STAGE, which encodes *statistical dependencies* between attributes rather than individual attribute values, which may differ in test graphs. By assuming these dependencies remain invariant under changes in node attributes, STAGE achieves provable generalization guarantees for a family of domain shifts. Empirically, STAGE demonstrates strong zero-shot performance on medium-sized datasets: when trained on multiple graph datasets with different attribute spaces (varying in types and number) and evaluated on graphs with entirely new attributes, STAGE achieves a relative improvement in Hits@1 between 40% to 103% in link prediction and a 10% improvement in node classification compared to state-of-the-art baselines.

Social Aspects · Privacy

Haoqi Wu, Wei Dai, Wang Li, Qiang Yan

Large Language Models (LLMs) have gained significant popularity due to their remarkable capabilities in text understanding and generation. However, despite their widespread deployment in inference services such as ChatGPT, concerns about the potential leakage of sensitive user data have arisen. Existing solutions primarily rely on privacy-enhancing technologies to mitigate such risks, facing the trade-off among efficiency, privacy, and utility. To narrow this gap, we propose Cape, a context-aware prompt perturbation mechanism based on differential privacy, to enable efficient inference with an improved privacy-utility trade-off. Concretely, we introduce a hybrid utility function that better captures the token similarity. Additionally, we propose a bucketized sampling mechanism to handle large sampling space, which might lead to long-tail phenomenons. Extensive experiments across multiple datasets, along with ablation studies, demonstrate that Cape achieves a better privacy-utility trade-off compared to prior state-of-the-art works.

Applications · Computer Vision

Xue Zhao, Qinying Gu, Xinbing Wang, Chenghu Zhou, Nanyang Ye

Improving the generalization of multi-camera 3D object detection is essential for safe autonomous driving in the real world. In this paper, we consider a realistic yet more challenging scenario, which aims to improve the generalization when only single source data available for training, as gathering diverse domains of data and collecting annotations is time-consuming and labor-intensive. To this end, we propose the Fourier Cross-View Learning (FCVL) framework including Fourier Hierarchical Augmentation (FHiAug), an augmentation strategy in the frequency domain to boost domain diversity, and Fourier Cross-View Semantic Consistency Loss to facilitate the model to learn more domain-invariant features from adjacent perspectives. Furthermore, we provide theoretical guarantees via augmentation graph theory. To the best of our knowledge, this is the first study to explore generalizable multi-camera 3D object detection with a single source. Extensive experiments on various testing domains have demonstrated that our approach achieves the best performance across various domain generalization methods.

Optimization · Large Scale, Parallel and Distributed

Ganyu Wang, Jinjie Fang, Maxwell (Juncheng) Yin, Bin Gu, Xi Chen, Boyu Wang, Yi Chang, Charles X. Ling

Black-Box Discrete Prompt Learning (BDPL) is a prompt-tuning method that optimizes discrete prompts without accessing model parameters or gradients, making the prompt tuning on a cloud-based Large Language Model (LLM) feasible.Adapting Federated Learning (FL) to BDPL could further enhance prompt tuning performance by leveraging data from diverse sources. However, all previous research on federated black-box prompt tuning had neglected the substantial query cost associated with the cloud-based LLM service. To address this gap, we conducted a theoretical analysis of query efficiency within the context of federated black-box prompt tuning. Our findings revealed that degrading FedAvg to activate only one client per round, a strategy we called \textit{FedOne}, enabled optimal query efficiency in federated black-box prompt learning. Building on this insight, we proposed the FedOne framework, a federated black-box discrete prompt learning method designed to maximize query efficiency when interacting with cloud-based LLMs.We conducted numerical experiments on various aspects of our framework, demonstrating a significant improvement in query efficiency, which aligns with our theoretical results.

Applications · Language, Speech and Dialog

Haoran Luo, Haihong E, Yikai Guo, Qika Lin, Xiaobao Wu, Xinyu Mu, Wenhao Liu, Meina Song, Yifan Zhu, Anh Tuan Luu

Knowledge Base Question Answering (KBQA) aims to answer natural language questions with a large-scale structured knowledge base (KB). Despite advancements with large language models (LLMs), KBQA still faces challenges in weak KB awareness, imbalance between effectiveness and efficiency, and high reliance on annotated data. To address these challenges, we propose KBQA-o1, a novel agentic KBQA method with Monte Carlo Tree Search (MCTS). It introduces a ReAct-based agent process for stepwise logical form generation with KB environment exploration. Moreover, it employs MCTS, a heuristic search method driven by policy and reward models, to balance agentic exploration's performance and search space. With heuristic exploration, KBQA-o1 generates high-quality annotations for further improvement by incremental fine-tuning. Experimental results show that KBQA-o1 outperforms previous low-resource KBQA methods with limited annotated data, boosting Llama-3.1-8B model's GrailQA F1 performance to 78.5% compared to 48.5% of the previous sota method with GPT-3.5-turbo. Our code is publicly available.

Probabilistic Methods · Monte Carlo and Sampling Methods

Michael Albergo, Eric Vanden-Eijnden

We introduce the Non-Equilibrium Transport Sampler (NETS), an algorithm for sampling from unnormalized probability distributions. NETS builds on non-equilibrium sampling strategies that transport a simple base distribution into the target distribution in finite time, as pioneered in Neal's annealed importance sampling (AIS). In the continuous-time setting, this transport is accomplished by evolving walkers using Langevin dynamics with a time-dependent potential, while simultaneously evolving importance weights to debias their solutions following Jarzynski's equality. The key innovation of NETS is to add to the dynamics a learned drift term that offsets the need for these corrective weights by minimizing their variance through an objective that can be estimated without backpropagation and provably bounds the Kullback-Leibler divergence between the estimated and target distributions. NETS provides unbiased samples and features a tunable diffusion coefficient that can be adjusted after training to maximize the effective sample size. In experiments on standard benchmarks, high-dimensional Gaussian mixtures, and statistical lattice field theory models, NETS shows compelling performances.

Theory · Learning Theory

Shira Vansover-Hager, Tomer Koren, Roi Livni

We study the out-of-sample performance of multi-pass stochastic gradient descent (SGD) in the fundamental stochastic convex optimization (SCO) model. While one-pass SGD is known to achieve an optimal $\Theta(1/\sqrt{n})$ excess population loss given a sample of size $n$, much less is understood about the multi-pass version of the algorithm which is widely used in practice. Somewhat surprisingly, we show that in the general non-smooth case of SCO, just a few epochs of SGD can already hurt its out-of-sample performance significantly and lead to overfitting. In particular, using a step size $\eta = \Theta(1/\sqrt{n})$, which gives the optimal rate after one pass, can lead to population loss as large as $\Omega(1)$ after just one additional pass. More generally, we show that the population loss from the second pass onward is of the order $\Theta(1/(\eta T) + \eta \sqrt{T})$, where $T$ is the total number of steps. These results reveal a certain phase-transition in the out-of-sample behavior of SGD after the first epoch, as well as a sharp separation between the rates of overfitting in the smooth and non-smooth cases of SCO. Additionally, we extend our results to with-replacement SGD, proving that the same asymptotic bounds hold after $O(n \log n)$ steps. Finally, we also prove a lower bound of $\Omega(\eta \sqrt{n})$ on the generalization gap of one-pass SGD in dimension $d = {\widetilde O}(n)$, improving on recent results of Koren et al. (2022) and Schliserman et al. (2024).

General Machine Learning · Causality

Carlota Parés Morlans, Michelle Yi, Claire Chen, Sarah A Wu, Rika Antonova, Tobias Gerstenberg, Jeannette Bohg

Tasks that involve complex interactions between objects with unknown dynamics make planning before execution difficult. These tasks require agents to iteratively improve their actions after actively exploring causes and effects in the environment. For these type of tasks, we propose Causal-PIK, a method that leverages Bayesian optimization to reason about causal interactions via a Physics-Informed Kernel to help guide efficient search for the best next action. Experimental results on Virtual Tools and PHYRE physical reasoning benchmarks show that Causal-PIK outperforms state-of-the-art results, requiring fewer actions to reach the goal. We also compare Causal-PIK to human studies, including results from a new user study we conducted on the PHYRE benchmark. We find that Causal-PIK remains competitive on tasks that are very challenging, even for human problem-solvers.

Deep Learning · Large Language Models

Rahul Thomas, Louai Zahran, Erica Choi, Akilesh Potti, Micah Goldblum, Arka Pal

Recent advances in Large Language Models (LLMs) have led to widespread adoption of third-party inference services, raising critical privacy concerns. In this work, we introduce a novel reconstruction technique that can recover original prompts from hidden states with nearly perfect accuracy across multiple state-of-the-art LLMs in the increasingly important open-weights setting. Although the attack is conceptually simple, it has not -- to the best of our knowledge -- previously been described nor shown to work practically. Furthermore, our attack remains effective against various permutation and noise-based defenses, challenging assumptions about the security of previously proposed schemes. To address these vulnerabilities, we propose Cascade, a multi-party inference scheme that leverages sharding in the sequence dimension to retain privacy of the user input. Through theoretical analysis and empirical evaluation, we demonstrate that Cascade is secure against both our attack as well as previous methods, while maintaining computational and communication efficiency. Our findings highlight the importance of rigorous security analysis in privacy-preserving LLM inference and offer practical solutions for secure deployment.

Optimization · Discrete and Combinatorial Optimization

Yuhang Li, Ruokai Yin, Donghyun Lee, Shiting Xiao, Priyadarshini Panda

We introduce GPTAQ, a novel finetuning-free quantization method for compressing large-scale transformer architectures.Unlike the previous GPTQ method, which independently calibrates each layer, we always match the quantized layer's output to the exact output in the full-precision model, resulting in a scheme that we call *asymmetric calibration*. Such a scheme can effectively reduce the quantization error accumulated in previous layers. We analyze this problem using optimal brain compression to derive a close-formed solution. The new solution explicitly minimizes the quantization error as well as the accumulated asymmetry error. Furthermore, we utilize various techniques to parallelize the solution calculation, including channel parallelization, neuron decomposition, and Cholesky reformulation for matrix fusion. As a result, GPTAQ is easy to implement, simply using 20 more lines of code than GPTQ but improving its performance under low-bit quantization. Remarkably, on a single GPU, we quantize a 405B language transformer as well as EVA-02—the rank first vision transformer that achieves 90% pretraining Imagenet accuracy. Code is available at [Github](https://github.com/Intelligent-Computing-Lab-Yale/GPTAQ).

Deep Learning · Attention Mechanisms

Shantanu Acharya, Fei Jia, Boris Ginsburg

Inference with Transformer-based Large Language Models (LLMs) on long sequences is both costly and slow due to the quadratic complexity of the self-attention mechanism. We introduce Star Attention, a two-phase block-sparse approximation that improves computational efficiency by sharding attention across multiple hosts while minimizing communication overhead. In the first phase, the context is processed using blockwise-local attention across hosts, in parallel. In the second phase, query and response tokens attend to all prior cached tokens through sequence-global attention. Star Attention integrates seamlessly with most Transformer-based LLMs trained with global attention, reducing memory requirements and inference time by up to 11x while preserving 97-100% of accuracy.

Deep Learning · Large Language Models

Ruhan Wang, Zhiyong Wang, Chengkai Huang, Rui Wang, Tong Yu, Lina Yao, John C. S. Lui, Dongruo Zhou

For question-answering (QA) tasks, in-context learning (ICL) enables language models (LMs) to generate responses without modifying their parameters by leveraging examples provided in the input. However, the effectiveness of ICL heavily depends on the availability of high-quality examples, which are often scarce due to data privacy constraints, annotation costs, and distribution disparities. A natural solution is to utilize examples stored on client devices, but existing approaches either require transmitting model parameters—incurring significant communication overhead—or fail to fully exploit local datasets, limiting their effectiveness. To address these challenges, we propose Federated In-Context Learning (Fed-ICL), a general framework that enhances ICL through an iterative, collaborative process. Fed-ICL progressively refines responses by leveraging multi-round interactions between clients and a central server, improving answer quality without the need to transmit model parameters. We establish theoretical guarantees for the convergence of Fed-ICL and conduct extensive experiments on standard QA benchmarks, demonstrating that our proposed approach achieves strong performance while maintaining low communication costs.

General Machine Learning

Chao Yang, Shuting Cui, Yang Yang, Shuang Li

Understanding human mental states—such as intentions and desires—is crucial for natural AI-human collaboration. However, this is challenging because human actions occur irregularly over time, and the underlying mental states that drive these actions are unobserved. To tackle this, we propose a novel framework that combines a logic-informed temporal point process (TPP) with amortized variational Expectation-Maximization (EM). Our key innovation is integrating logic rules as priors to guide the TPP’s intensity function, allowing the model to capture the interplay between actions and mental events while reducing dependence on large datasets. To handle the intractability of mental state inference, we introduce a discrete-time renewal process to approximate the posterior. By jointly optimizing model parameters, logic rules, and inference networks, our approach infers entire mental event sequences and adaptively predicts future actions. Experiments on both synthetic and real-world datasets show that our method outperforms existing approaches in accurately inferring mental states and predicting actions, demonstrating its effectiveness in modeling human cognitive processes.